Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.5
2.7
Journals
Applied Sciences
Special Issues
Applications of Deep Learning and Artificial Intelligence Methods
share announcement

Applications of Deep Learning and Artificial Intelligence Methods

A special issue of Applied Sciences (ISSN 2076-3417). This special issue belongs to the section "Computing and Artificial Intelligence".

Deadline for manuscript submissions: closed (20 November 2023) | Viewed by 93368

Special Issue Editors

Prof. Dr. Yujin Lim

E-Mail Website
Guest Editor
Department of IT Engineering, Sookmyung Women’s University, Seoul 04310, Republic of Korea
Interests: multi-agent system; artificial intelligence
Special Issues, Collections and Topics in MDPI journals
Prof. Dr. Hideyuki Takahashi

E-Mail Website
Guest Editor
Department of Data Science, Faculty of Informatics, Tohoku Gakuin University, Miyagi 984-8588, Japan
Interests: Internet of Things; ubiquitous computing; multi-agent system
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Deep Learning and Artificial Intelligence have attracted great attention in almost every field in recent years. Applications of deep learning and artificial intelligence methods is now pervasive into many various fields beyond the conventional computer engineering areas. Therefore, the goal of this special issue is intended for discussing new ideas and recent experimental results in the field of applications of deep learning and artificial intelligence methods.

Topics of interest include, but are not limited to, the following:

-Artificial Intelligence Tools & Applications

-Automatic Control

-Natural Language Processing

-Computer Vision and Speech Understanding

-Data Mining and Analysis

-Heuristic and AI Planning Strategies

-Intelligent System

-Robotics

Prof. Dr. Yujin Lim
Prof. Dr. Hideyuki Takahashi
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Applied Sciences is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2400 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • machine learning
  • deep learning
  • artificial intelligence
  • natural language processing
  • computer vision
  • data mining
  • robotics

Related Special Issue

Published Papers (48 papers)

Download All Papers
Order results
Result details
Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:

Research

Jump to: Review

13 pages, 3262 KiB  
Article
Country-Based COVID-19 DNA Sequence Classification in Relation with International Travel Policy
by Elis Khatizah and Hyun-Seok Park
Appl. Sci. 2024, 14(5), 1916; https://doi.org/10.3390/app14051916 - 26 Feb 2024
Viewed by 411
Abstract
As viruses evolve rapidly, variations in their DNA may arise due to environmental factors. This study examines the classification of COVID-19 DNA sequences based on their country of origin and analyzes their primary correlation with the country’s international travel policy. Focusing on DNA [...] Read more.
As viruses evolve rapidly, variations in their DNA may arise due to environmental factors. This study examines the classification of COVID-19 DNA sequences based on their country of origin and analyzes their primary correlation with the country’s international travel policy. Focusing on DNA sequences from nine ASEAN countries, we conducted a two-class classification to distinguish sequences from individual countries and mixed sequences from others. The sequences were initially dissected into 200 base pair units, and a deep-learning method was employed to construct a model. Our results showcase the capacity to differentiate DNA sequences with varying accuracy for each country. Additionally, the index of international travel policy, which reflects how countries implemented varying levels of restrictions regarding inbound travel, several months before the sequence collection date, moderately correlated with the classification accuracy within each country. This finding suggests a preliminary insight that a country’s pandemic management might influence the variation in the DNA virus, determining whether these sequences will evolve distinctly from those of other countries or exhibit similarities. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

21 pages, 9191 KiB  
Article
Multi-Defect Detection Network for High-Voltage Insulators Based on Adaptive Multi-Attention Fusion
by Yiming Hu, Bin Wen, Yongsheng Ye and Chao Yang
Appl. Sci. 2023, 13(24), 13351; https://doi.org/10.3390/app132413351 - 18 Dec 2023
Cited by 2 | Viewed by 912
Abstract
Insulators find extensive use across diverse facets of power systems, playing a pivotal role in ensuring the security and stability of electrical transmission. Detecting insulators is a fundamental measure to secure the safety and stability of power transmission, with precise insulator positioning being [...] Read more.
Insulators find extensive use across diverse facets of power systems, playing a pivotal role in ensuring the security and stability of electrical transmission. Detecting insulators is a fundamental measure to secure the safety and stability of power transmission, with precise insulator positioning being a prerequisite for successful detection. To overcome challenges such as intricate insulator backgrounds, small defect scales, and notable differences in target scales that reduce detection accuracy, we propose the AC-YOLO insulator multi-defect detection network based on adaptive attention fusion. To elaborate, we introduce an adaptive weight distribution multi-head self-attention module designed to concentrate on intricacies in the features, effectively discerning between insulators and various defects. Additionally, an adaptive memory fusion detection head is incorporated to amalgamate multi-scale target features, augmenting the network’s capability to extract insulator defect characteristics. Furthermore, a CBAM attention mechanism is integrated into the backbone network to enhance the detection performance for smaller target defects. Lastly, improvements to the loss function expedite model convergence. This study involved training and evaluation using publicly available datasets for insulator defects. The experimental results reveal that the AC-YOLO model achieves a notable 5.1% enhancement in detection accuracy compared to the baseline. This approach significantly boosts detection precision, diminishes false positive rates, and fulfills real-time insulator localization requirements in power system inspections. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

20 pages, 497 KiB  
Article
Leveraging Ensemble Learning with Generative Adversarial Networks for Imbalanced Software Defects Prediction
by Amani Alqarni and Hamoud Aljamaan
Appl. Sci. 2023, 13(24), 13319; https://doi.org/10.3390/app132413319 - 17 Dec 2023
Viewed by 793
Abstract
Software defect prediction is an active research area. Researchers have proposed many approaches to overcome the imbalanced defect problem and build highly effective machine learning models that are not biased towards the majority class. Generative adversarial networks (GAN) are one of the state-of-the-art [...] Read more.
Software defect prediction is an active research area. Researchers have proposed many approaches to overcome the imbalanced defect problem and build highly effective machine learning models that are not biased towards the majority class. Generative adversarial networks (GAN) are one of the state-of-the-art techniques that can be used to generate synthetic samples of the minority class and produce a balanced dataset. However, it was not investigated thoroughly in the area of imbalanced defect prediction. In this paper, we proposed to combine GAN-based methods with boosting ensembles to yield robust defect prediction models. GAN-based methods were used to balance the defect datasets, and the AdaBoost ensemble was employed to classify the modules into defective and non-defective modules. Our proposed approach was investigated within the context of 10 software defect datasets with different imbalance ratios. Wilcoxon effect size and Scott–Knott effect size difference tests were used as statistical tests to quantify the model’s performance differences statistically. Empirical results indicated that GAN-based methods need hyperparameter optimization when used for imbalanced software defect prediction. In comparison to the traditional sampling techniques, GAN methods outperformed all traditional techniques when used for imbalanced defect prediction. Lastly, results demonstrated that GAN-based methods should not be combined with undersampling to handle imbalance problems. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

28 pages, 9876 KiB  
Article
Deep Q Network Based on a Fractional Political–Smart Flower Optimization Algorithm for Real-World Object Recognition in Federated Learning
by Pir Dino Soomro, Xianping Fu, Muhammad Aslam, Dani Elias Mfungo and Arsalan Ali
Appl. Sci. 2023, 13(24), 13286; https://doi.org/10.3390/app132413286 - 15 Dec 2023
Cited by 1 | Viewed by 793
Abstract
An imperative application of artificial intelligence (AI) techniques is visual object detection, and the methods of visual object detection available currently need highly equipped datasets preserved in a centralized unit. This usually results in high transmission and large storage overheads. Federated learning (FL) [...] Read more.
An imperative application of artificial intelligence (AI) techniques is visual object detection, and the methods of visual object detection available currently need highly equipped datasets preserved in a centralized unit. This usually results in high transmission and large storage overheads. Federated learning (FL) is an eminent machine learning technique to overcome such limitations, and this enables users to train a model together by processing the data in the local devices. In each round, each local device performs processing independently and updates the weights to the global model, which is the server. After that, the weights are aggregated and updated to the local model. In this research, an innovative framework is designed for real-world object recognition in FL using a proposed Deep Q Network (DQN) based on a Fractional Political–Smart Flower Optimization Algorithm (FP-SFOA). In the training model, object detection is performed by employing SegNet, and this classifier is effectively tuned based on the Political–Smart Flower Optimization Algorithm (PSFOA). Moreover, object recognition is performed based on the DQN, and the biases of the classifier are finely optimized based on the FP-SFOA, which is a hybridization of the Fractional Calculus (FC) concept with a Political Optimizer (PO) and a Smart Flower Optimization Algorithm (SFOA). Finally, the aggregation at the global model is accomplished using the Conditional Autoregressive Value at Risk by Regression Quantiles (CAViaRs) model. The designed FP-SFOA obtained a maximum accuracy of 0.950, minimum loss function of 0.104, minimum MSE of 0.122, minimum RMSE of 0.035, minimum FPR of 0.140, maximum average precision of 0.909, and minimum communication cost of 0.078. The proposed model obtained the highest accuracy of 0.950, which is a 14.11%, 6.42%, 7.37%, and 5.68% improvement compared to the existing methods. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

15 pages, 697 KiB  
Article
Generative LLMs in Organic Chemistry: Transforming Esterification Reactions into Natural Language Procedures
by Mantas Vaškevičius, Jurgita Kapočiūtė-Dzikienė and Liudas Šlepikas
Appl. Sci. 2023, 13(24), 13140; https://doi.org/10.3390/app132413140 - 11 Dec 2023
Viewed by 1481
Abstract
This paper presents a novel approach to predicting esterification procedures in organic chemistry by employing generative large language models (LLMs) to interpret and translate SMILES molecular notation into detailed procedural texts of synthesis reactions. Esterification reaction is important in producing various industrial intermediates, [...] Read more.
This paper presents a novel approach to predicting esterification procedures in organic chemistry by employing generative large language models (LLMs) to interpret and translate SMILES molecular notation into detailed procedural texts of synthesis reactions. Esterification reaction is important in producing various industrial intermediates, fragrances, and flavors. Recognizing the challenges of accurate prediction in complex chemical landscapes, we have compiled and made publicly available a curated dataset of esterification reactions to enhance research collaboration. We systematically compare machine learning algorithms, ranging from the conventional k-nearest neighbors (kNN) to advanced sequence-to-sequence transformer models, including FLAN-T5 and ChatGPT-based variants. Our analysis highlights the FLAN-T5 model as the standout performer with a BLEU score of 51.82, suggesting that the model has significant potential in enhancing reaction planning and chemical synthesis. Our findings contribute to the growing field of AI in chemistry, offering a promising direction for enhancing the efficiency of reaction planning and chemical synthesis. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

16 pages, 5704 KiB  
Article
The Effect of Grouping Output Parameters by Quality Characteristics on the Predictive Performance of Artificial Neural Networks in Injection Molding Process
by Junhan Lee, Jongsun Kim and Jongsu Kim
Appl. Sci. 2023, 13(23), 12876; https://doi.org/10.3390/app132312876 - 30 Nov 2023
Viewed by 485
Abstract
In this study, a multi-input, multi-output-based artificial neural network (ANN) was constructed by classifying output parameters into different groups, considering the physical meanings and characteristics of product quality factors in the injection molding process. Injection molding experiments were conducted for bowl products, and [...] Read more.
In this study, a multi-input, multi-output-based artificial neural network (ANN) was constructed by classifying output parameters into different groups, considering the physical meanings and characteristics of product quality factors in the injection molding process. Injection molding experiments were conducted for bowl products, and a dataset was established. Based on this dataset, an ANN model was developed to predict the quality of molded products. The input parameters included melt temperature, mold temperature, packing pressure, packing time, and cooling time. The output parameters included mass, diameter, and height of the molded product. The output parameters were divided into two cases. In one case, diameter, and height, representing length, were grouped together, while mass was organized into a separate group. In the other case, mass, diameter and height were separated individually and applied to the ANN. A multi-task learning method was used to group the output parameters. The performance of the two constructed multi-task learning-based ANNs was compared with that of the conventional ANN where the output parameters were not separated and applied to a single layer. The comparative results showed that the multi-task learning architecture, which grouped the output parameters considering the physical meaning and characteristics of the quality of molded products, exhibited an improved prediction performance of about 32.8% based on the RMSE values. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

22 pages, 1382 KiB  
Article
Proactive Service Caching in a MEC System by Using Spatio-Temporal Correlation among MEC Servers
by Hongseob Bae and Jaesung Park
Appl. Sci. 2023, 13(22), 12509; https://doi.org/10.3390/app132212509 - 20 Nov 2023
Cited by 1 | Viewed by 710
Abstract
Optimizingthe cache hit rate in a multi-access edge computing (MEC) system is essential in increasing the utility of a system. A pivotal challenge within this context lies in predicting the popularity of a service. However, accurately predicting popular services for each MEC server [...] Read more.
Optimizingthe cache hit rate in a multi-access edge computing (MEC) system is essential in increasing the utility of a system. A pivotal challenge within this context lies in predicting the popularity of a service. However, accurately predicting popular services for each MEC server (MECS) is hindered by the dynamic nature of user preferences in both time and space, coupled with the necessity for real-time adaptability. In this paper, we address this challenge by employing the Convolutional Long Short-Term Memory (ConvLSTM) model, which can capture both temporal and spatial correlations inherent in service request patterns. Our proposed methodology leverages ConvLSTM for service popularity prediction by modeling the distribution of service popularity in a MEC system as a heatmap image. Additionally, we propose a procedure that predicts service popularity in each MECS through a sequence of heatmap images. Through simulation studies using real-world datasets, we compare the performance of our method with that of the LSTM-based method. In the LSTM-based method, each MECS predicts the service popularity independently. On the contrary, our method takes a holistic approach by considering spatio-temporal correlations among MECSs during prediction. As a result, our method increases the average cache hit rate by more than 6.97% compared to the LSTM-based method. From an implementation standpoint, our method requires only one ConvLSTM model while the LSTM-based method requires at least one LSTM model for each MECS. Thus, compared to the LSTM-based method, our method reduces the deep learning model parameters by 32.15%. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

13 pages, 4443 KiB  
Article
A Real-Time Nut-Type Classifier Application Using Transfer Learning
by Yusuf Özçevik
Appl. Sci. 2023, 13(21), 11644; https://doi.org/10.3390/app132111644 - 24 Oct 2023
Viewed by 778
Abstract
Smart environments need artificial intelligence (AI) at the moment and will likely utilize AI in the foreseeable future. Shopping has recently been seen as an environment needing to be digitized, especially for payment processes of both packaged and unpackaged products. In particular, for [...] Read more.
Smart environments need artificial intelligence (AI) at the moment and will likely utilize AI in the foreseeable future. Shopping has recently been seen as an environment needing to be digitized, especially for payment processes of both packaged and unpackaged products. In particular, for unpackaged nuts, machine learning models are applied to newly collected dataset to identify the type. Furthermore, transfer learning (TL) has been identified as a promising method to diminish the time and effort for obtaining learning models for different classification problems. There are common TL architectures that can be used to transfer learned knowledge between different problem domains. In this study, TL architectures including ResNet, EfficientNet, Inception, and MobileNet were used to obtain a practical nut-type identifier application to satisfy the challenges of implementing a classifier for unpackaged products. In addition to the TL models, we trained a convolutional neural network (CNN) model on a dataset including 1250 images of 5 different nut types prepared from online-available and manually captured images. The models are evaluated according to a set of parameters including validation loss, validation accuracy, and F1-score. According to the evaluation results, TL models show a promising performance with 96% validation accuracy. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

15 pages, 2205 KiB  
Article
Abnormality Detection of Blast Furnace Tuyere Based on Knowledge Distillation and a Vision Transformer
by Chuanwang Song, Hao Zhang, Yuanjun Wang, Yuhui Wang and Keyong Hu
Appl. Sci. 2023, 13(18), 10398; https://doi.org/10.3390/app131810398 - 17 Sep 2023
Viewed by 779
Abstract
The blast furnace tuyere is a key position in hot metal production and is primarily observed to assess the internal state of the furnace. However, detecting abnormal tuyere conditions has relied heavily on manual judgment, leading to certain limitations. We proposed a tuyere [...] Read more.
The blast furnace tuyere is a key position in hot metal production and is primarily observed to assess the internal state of the furnace. However, detecting abnormal tuyere conditions has relied heavily on manual judgment, leading to certain limitations. We proposed a tuyere abnormality detection model based on knowledge distillation and a vision transformer (ViT) to address this issue. In this approach, ResNet50 is employed as the Teacher model to distill knowledge into the Student model, ViT. Firstly, we introduced spatial attention modules to enhance the model’s perception and feature-extraction capabilities for different image regions. Furthermore, we simplified the depth of the ViT and improved its self-attention mechanism to alleviate training losses. In addition, we employed the knowledge distillation strategy to achieve model lightweighting and enhance the model’s generalization capability. Finally, we evaluate the model’s performance in tuyere abnormality detection and compare it with other classification methods such as VGG-19, ResNet-101, and ResNet-50. Experimental results showed that our model achieved a classification accuracy of 97.86% on a tuyere image dataset from a company, surpassing the original ViT model by 1.12% and the improved ViT model without knowledge distillation by 0.34%. Meanwhile, the model achieved a competitive classification accuracy of 90.31% and 77.65% on the classical fine-grained image datasets, Stanford Dogs and CUB-200-2011, respectively, comparable to other classification models. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

17 pages, 888 KiB  
Article
Arabic Text Clustering Using Self-Organizing Maps and Grey Wolf Optimization
by Souad Larabi-Marie-Sainte, Mashael Bin Alamir and Abdulmajeed Alameer
Appl. Sci. 2023, 13(18), 10168; https://doi.org/10.3390/app131810168 - 10 Sep 2023
Viewed by 1159
Abstract
Arabic text clustering is an essential topic in Arabic Natural Language Processing (ANLP). Its significance resides in various applications, such as document indexing, categorization, user review analysis, and others. After inspecting the current work on clustering Arabic text, it is observed that most [...] Read more.
Arabic text clustering is an essential topic in Arabic Natural Language Processing (ANLP). Its significance resides in various applications, such as document indexing, categorization, user review analysis, and others. After inspecting the current work on clustering Arabic text, it is observed that most researchers focus on applying K-Means clustering while hindering other clustering techniques. Our evaluation shows that K-Means has a weakness of inconsistent clustering results and weak clustering performance when the data dimensionality increases. Unlike K-Means clustering, Artificial Neural Networks (ANN) models such as Self-Organizing Maps (SOM) demonstrated higher accuracy and efficiency in clustering even with high dimensional datasets. In this paper, we introduce a new clustering model based on an optimization technique called Grey Wolf Optimization (GWO) used conjointly with SOM clustering to enhance its clustering performance and accuracy. The evaluation results of our proposed technique show an improvement in the effectiveness and efficiency in comparison with state-of-the-art approaches. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

22 pages, 914 KiB  
Article
Arabic News Classification Based on the Country of Origin Using Machine Learning and Deep Learning Techniques
by Nuha Zamzami, Hanen Himdi and Sahar F. Sabbeh
Appl. Sci. 2023, 13(12), 7074; https://doi.org/10.3390/app13127074 - 13 Jun 2023
Cited by 2 | Viewed by 1171
Abstract
With the rise of Arabic news articles published daily, people are becoming increasingly concerned about following the news from reliable sources, especially regarding events that impact their country. To assess a news article’s significance to the user, it is essential to identify the [...] Read more.
With the rise of Arabic news articles published daily, people are becoming increasingly concerned about following the news from reliable sources, especially regarding events that impact their country. To assess a news article’s significance to the user, it is essential to identify the article’s country of origin. This paper proposes several classification models that categorize Arabic news articles based on their country of origin. The models were developed using comprehensive machine learning and deep learning techniques with several feature training methods. The results show the ability of our model to classify news articles based on their country of origin, with close accuracy between machine learning and deep learning techniques of up to 94%. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

13 pages, 6941 KiB  
Article
Portrait Reification with Generative Diffusion Models
by Andrea Asperti, Gabriele Colasuonno and Antonio Guerra
Appl. Sci. 2023, 13(11), 6487; https://doi.org/10.3390/app13116487 - 25 May 2023
Cited by 2 | Viewed by 1561
Abstract
An application of Generative Diffusion Techniques for the reification of human portraits in artistic paintings is presented. By reification we intend the transformation of the painter’s figurative abstraction into a real human face. The application exploits a recent embedding technique for Denoising Diffusion [...] Read more.
An application of Generative Diffusion Techniques for the reification of human portraits in artistic paintings is presented. By reification we intend the transformation of the painter’s figurative abstraction into a real human face. The application exploits a recent embedding technique for Denoising Diffusion Implicit Models (DDIM), inverting the generative process and mapping the visible image into its latent representation. In this way, we can first embed the portrait into the latent space, and then use the reverse diffusion model, trained to generate real human faces, to produce the most likely real approximation of the portrait. The actual deployment of the application involves several additional techniques, mostly aimed to automatically identify, align, and crop the relevant portion of the face, and to postprocess the generated reification in order to enhance its quality and to allow a smooth reinsertion in the original painting. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

13 pages, 5837 KiB  
Article
HFD: Hierarchical Feature Detector for Stem End of Pomelo with Transformers
by Bowen Hou and Gongyan Li
Appl. Sci. 2023, 13(8), 4976; https://doi.org/10.3390/app13084976 - 15 Apr 2023
Viewed by 1148
Abstract
Transformers have become increasingly prevalent in computer vision research, especially for object detection. To accurately and efficiently distinguish the stem end of pomelo from its black spots, we propose a hierarchical feature detector, which reconfigures the self-attention model, with high detection accuracy. We [...] Read more.
Transformers have become increasingly prevalent in computer vision research, especially for object detection. To accurately and efficiently distinguish the stem end of pomelo from its black spots, we propose a hierarchical feature detector, which reconfigures the self-attention model, with high detection accuracy. We designed the combination attention module and the hierarchical feature fusion module that utilize multi-scale features to improve detection performance. We created a dataset in COCO format and annotated two types of detection targets: the stem end and the black spot. Experimental results on our pomelo dataset confirm that HFD’s results are comparable to those of state-of-the-art one-stage detectors such as YOLO v4 and YOLO v5 and transformer-based detectors such as DETR, Deformable DETR, and YOLOS. It achieves 89.65% mAP at 70.92 FPS with 100.34 M parameters. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

17 pages, 1803 KiB  
Article
Method for Training and White Boxing DL, BDT, Random Forest and Mind Maps Based on GNN
by Kohei Arai
Appl. Sci. 2023, 13(8), 4743; https://doi.org/10.3390/app13084743 - 10 Apr 2023
Cited by 3 | Viewed by 1168
Abstract
A method for training and white boxing of deep learning (DL) binary decision trees (BDT), random forest (RF) as well as mind maps (MM) based on graph neural networks (GNN) is proposed. By representing DL, BDT, RF, and MM as graphs, these can [...] Read more.
A method for training and white boxing of deep learning (DL) binary decision trees (BDT), random forest (RF) as well as mind maps (MM) based on graph neural networks (GNN) is proposed. By representing DL, BDT, RF, and MM as graphs, these can be trained by GNN. These learning architectures can be optimized through the proposed method. The proposed method allows representation of the architectures with matrices because the learning architecture can be expressed with graphs. These matrices and graphs are visible, which makes the learning processes visible, and therefore, more accountable. Some examples are shown here to highlight the usefulness of the proposed method, in particular, for learning processes and for ensuring the accountability of DL together with improvement in network architecture. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

14 pages, 2363 KiB  
Article
Small-Scale Zero-Shot Collision Localization for Robots Using RL-CNN
by Haoyu Lin, Ya’nan Lou, Pengkun Quan, Zhuo Liang, Dongbo Wei and Shichun Di
Appl. Sci. 2023, 13(7), 4079; https://doi.org/10.3390/app13074079 - 23 Mar 2023
Cited by 1 | Viewed by 858
Abstract
For safety reasons, in order to ensure that a robot can make a reasonable response after a collision, it is often necessary to localize the collision. The traditional model-based collision localization methods, which are highly dependent on the designed observer, are often only [...] Read more.
For safety reasons, in order to ensure that a robot can make a reasonable response after a collision, it is often necessary to localize the collision. The traditional model-based collision localization methods, which are highly dependent on the designed observer, are often only useful for rough localization due to the bias between simulation and real-world application. In contrast, for fine collision localization of small-scale regions, data-driven methods can achieve better results. In order to obtain high localization accuracy, the data required by data-driven methods need to be as comprehensive as possible, and this will greatly increase the cost of data collection. To address this problem, this article is dedicated to developing a data-driven method for zero-shot collision localization based on local region data. In previous work, global region data were used to construct the collision localization model without considering the similarity of the data used for analysis caused by the assembly method of the contact parts. However, when using local region data to build collision localization models, the process is easily affected by similarity, resulting in a decrease in the accuracy of collision localization. To alleviate this situation, a two-stage scheme is implemented in our method to simultaneously isolate the similarity and realize collision localization. Compared with the classical methods, the proposed method achieves significantly improved collision localization accuracy. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

17 pages, 5392 KiB  
Article
Pressure Sensitivity Prediction and Pressure Measurement of Fast Response Pressure-Sensitive Paint Based on Artificial Neural Network
by Xianhui Liao, Chunhua Wei, Chenglin Zuo, Zhisheng Gao, Hailin Jiang, Lei Liang and Zhaoyan Li
Appl. Sci. 2023, 13(6), 3504; https://doi.org/10.3390/app13063504 - 09 Mar 2023
Viewed by 1062
Abstract
The characterization of pressure-sensitive paint (PSP) is affected by many physical and chemical factors, making it is difficult to analyze the relationship between characterization and influencing factors. An artificial neural network (ANN)-based method for predicting pressure sensitivity using paint thickness and roughness was [...] Read more.
The characterization of pressure-sensitive paint (PSP) is affected by many physical and chemical factors, making it is difficult to analyze the relationship between characterization and influencing factors. An artificial neural network (ANN)-based method for predicting pressure sensitivity using paint thickness and roughness was proposed in this paper. The mean absolute percentage error (MAPE) for predicting pressure sensitivity is 6.5088%. The difference of paint thickness and roughness between sample and model surface may be a source of experimental error in PSP pressure measurement tests. The Stern-Volmer coefficients A and B are strongly linked. Pressure sensitivity is approximately equal to coefficient B, so coefficient A is predicted using pressure sensitivity based on the same ANN, and the MAPE of predicting A is 2.1315%. Then, we try to calculate the pressure by using the thickness and roughness on a model to predict pressure sensitivity and Stern-Volmer coefficient A. The PSP pressure measurement test was carried out at the China Aerodynamic Research and Development Center. Using the Stern-Volmer coefficient calculated by the in situ method, the method in this paper, and the sample calibration experiment, the root mean square errors (RMSE) of the pressure are 47.4431 Pa, 63.4736 Pa, and 73.0223 Pa, respectively. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

19 pages, 2903 KiB  
Article
Non-Autoregressive Sparse Transformer Networks for Pedestrian Trajectory Prediction
by Di Liu, Qiang Li, Sen Li, Jun Kong and Miao Qi
Appl. Sci. 2023, 13(5), 3296; https://doi.org/10.3390/app13053296 - 04 Mar 2023
Cited by 3 | Viewed by 1426
Abstract
Pedestrian trajectory prediction is an important task in practical applications such as automatic driving and surveillance systems. It is challenging to effectively model social interactions among pedestrians and capture temporal dependencies. Previous methods typically emphasized social interactions among pedestrians but ignored the temporal [...] Read more.
Pedestrian trajectory prediction is an important task in practical applications such as automatic driving and surveillance systems. It is challenging to effectively model social interactions among pedestrians and capture temporal dependencies. Previous methods typically emphasized social interactions among pedestrians but ignored the temporal consistency of predictions and suffered from superfluous interactions by dense undirected graphs, resulting in a considerable deviance from reality. In addition, autoregressive approaches predicted future locations conditioning on previous predictions one by one, which would lead to error accumulation and time consuming. To address these issues, we present Non-autoregressive Sparse Transformer (NaST) networks for pedestrian trajectory prediction. Specifically, NaST models sparse spatial interactions and sparse temporal dependency via a sparse spatial transformer and a sparse temporal transformer separately. Different from previous predictions such as RNN-based approaches, the transformer decoder works in non-autoregressive pattern and predicts all the future locations at one time from a query sequence, which could avoid the error accumulation and be less computationally intensive. We evaluate our proposed method on the ETH and UCY datasets, and the experimental results show our method outperforms comparative state-of-the-art methods. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

20 pages, 17927 KiB  
Article
AAL-Net: A Lightweight Detection Method for Road Surface Defects Based on Attention and Data Augmentation
by Cheng Zhang, Gang Li, Zekai Zhang, Rui Shao, Min Li, Delong Han and Mingle Zhou
Appl. Sci. 2023, 13(3), 1435; https://doi.org/10.3390/app13031435 - 21 Jan 2023
Cited by 2 | Viewed by 1522
Abstract
The pothole is a common road defect that seriously affects traffic efficiency and personal safety. Road evaluation and maintenance and automatic driving take pothole detection as their main research part. In the above scenarios, accuracy and real-time pothole detection are the most important. [...] Read more.
The pothole is a common road defect that seriously affects traffic efficiency and personal safety. Road evaluation and maintenance and automatic driving take pothole detection as their main research part. In the above scenarios, accuracy and real-time pothole detection are the most important. However, the current pothole detection methods can not meet the accuracy and real-time requirements of pothole detection due to their multiple parameters and volume. To solve these problems, we first propose a lightweight one-stage object detection network, the AAL-Net. In the network, we design an LF (lightweight feature extraction) module and use the NAM (Normalization-based Attention Module) attention module to ensure the accuracy and real time of the pothole detection process. Secondly, we make our own pothole dataset for pothole detection. Finally, in order to simulate the real road scene, we design a data augmentation method to further improve the detection accuracy and robustness of the AAL-Net. The metrics F1 and GFLOPs show that our method is better than other deep learning models in the self-made dataset and the pothole600 dataset and can well meet the accuracy and real-time requirements of pothole detection. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

13 pages, 2591 KiB  
Article
Research on Blast Furnace Tuyere Image Anomaly Detection, Based on the Local Channel Attention Residual Mechanism
by Chuanwang Song, Ziyu Li, Yuming Li, Hao Zhang, Mingjian Jiang, Keyong Hu and Rihong Wang
Appl. Sci. 2023, 13(2), 802; https://doi.org/10.3390/app13020802 - 06 Jan 2023
Cited by 4 | Viewed by 1320
Abstract
The channel attention mechanism is widely used in deep learning. However, the existing channel attention mechanism directly performs the global average pooling and then full connection for all channels, which causes the local information to be ignored and the feature information cannot be [...] Read more.
The channel attention mechanism is widely used in deep learning. However, the existing channel attention mechanism directly performs the global average pooling and then full connection for all channels, which causes the local information to be ignored and the feature information cannot be reasonably assigned with the proper weights. This paper proposed a local channel attention module, based on the channel attention. This module focuses on the local information of the feature image, obtains the weight of each regional channel through convolution, and then integrates the information, so that the regional information can be fully utilized. Moreover, the local channel attention module is combined with the residual module, and the local channel attention residual network LSERNet is constructed to detect the abnormal state of the blast furnace tuyere image. With sufficient experiments on the collected datasets of the blast furnace tuyere, the results show that the proposed method can efficiently extract the feature information, and the recognition accuracy of the LSERNet model reached 98.59%. Further, our model achieved the highest accuracy, compared with SE-ResNet50, ResNet50, LSE-ResNeXt, SE-ResNeXt, and ResNeXt models. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

25 pages, 10741 KiB  
Article
Deep Learning-Based Method for Accurate Real-Time Seed Detection in Glass Bottle Manufacturing
by Arantza Bereciartua-Perez, Gorka Duro, Jone Echazarra, Francico Javier González, Alberto Serrano and Liher Irizar
Appl. Sci. 2022, 12(21), 11192; https://doi.org/10.3390/app122111192 - 04 Nov 2022
Cited by 2 | Viewed by 2622
Abstract
Glass bottle-manufacturing companies produce bottles of different colors, shapes and sizes. One identified problem is that seeds appear in the bottle mainly due to the temperature and parameters of the oven. This paper presents a new system capable of detecting seeds of 0.1 [...] Read more.
Glass bottle-manufacturing companies produce bottles of different colors, shapes and sizes. One identified problem is that seeds appear in the bottle mainly due to the temperature and parameters of the oven. This paper presents a new system capable of detecting seeds of 0.1 mm2 in size in glass bottles as they are being manufactured, 24 h per day and 7 days per week. The bottles move along the conveyor belt at 50 m/min, at a production rate of 250 bottles/min. This new proposed method includes deep learning-based artificial intelligence techniques and classical image processing on images acquired with a high-speed line camera. The algorithm comprises three stages. First, the bottle is identified in the input image. Next, an algorithm based in thresholding and morphological operations is applied on this bottle region to locate potential candidates for seeds. Finally, a deep learning-based model can classify whether the proposed candidates are real seeds or not. This method manages to filter out most of false positives due to stains in the glass surface, while no real seeds are lost. The F1 achieved is 0.97. This method reveals the advantages of deep learning techniques for problems where classical image processing algorithms are not sufficient. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

14 pages, 2529 KiB  
Article
Deep Learning Based Improvement in Overseas Manufacturer Address Quality Using Administrative District Data
by Saravit Soeng, Jin-Hyun Bae, Kyung-Hee Lee and Wan-Sup Cho
Appl. Sci. 2022, 12(21), 11129; https://doi.org/10.3390/app122111129 - 02 Nov 2022
Cited by 3 | Viewed by 1933
Abstract
Validating and improving the quality of global address data are important tasks in a modern society where exchanges between countries are due to active Free Trade Agreements (FTAs) and e-commerce. Addresses may be constructed with different systems for each country; therefore, to verify [...] Read more.
Validating and improving the quality of global address data are important tasks in a modern society where exchanges between countries are due to active Free Trade Agreements (FTAs) and e-commerce. Addresses may be constructed with different systems for each country; therefore, to verify and improve the quality of the address data, it is necessary to understand the address system of each country in advance. In the event of food risk, it is important to identify the administrative district from the address in order to take safety measures, such as predicting the contaminated area by tracking the distribution of food in the area. In this study, we propose a method that applies a deep learning approach to verify and improve the quality of the global address data required for imported food-safety management. The address entered by the user is classified to the administrative division levels of the relevant country and the quality of the address data is verified and improved by converting them into a standardized address. Finally, the results show that the accuracy of the model is found to be approximately 90% and the proposed method is able to verify and evaluate the overseas address data quality significantly. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

11 pages, 2034 KiB  
Article
Ultra-Short-Term Continuous Time Series Prediction of Blockchain-Based Cryptocurrency Using LSTM in the Big Data Era
by Yongjun Kim and Yung-Cheol Byun
Appl. Sci. 2022, 12(21), 11080; https://doi.org/10.3390/app122111080 - 01 Nov 2022
Cited by 6 | Viewed by 2710
Abstract
This study uses the API of Upbit, one of Korea’s cryptocurrency exchanges, to predict continuous time series for a limited period and cryptocurrencies using LSTM, a machine learning technique. The trading (buying and selling) point algorithm presented in this study was used to [...] Read more.
This study uses the API of Upbit, one of Korea’s cryptocurrency exchanges, to predict continuous time series for a limited period and cryptocurrencies using LSTM, a machine learning technique. The trading (buying and selling) point algorithm presented in this study was used to conduct experimental research on efficient profit creation for cryptocurrency investment. Several related studies have shown the results of time series prediction for long-term forecasts, such as a week or several months. Still, they have not attempted to make an ultra-short-term prediction in units of one minute. This paper attempts such a 1 min prediction. This is an experiment to create efficient profits by setting efficient trading (buying and selling) points using machine learning techniques and repeating these operations by an algorithm. Applying it to cryptocurrency shows the possibility of time series prediction. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

16 pages, 2205 KiB  
Article
A Dynamic Heterogeneous Information Network Embedding Method Based on Meta-Path and Improved Rotate Model
by Hualong Bu, Jing Xia, Qilin Wu and Liping Chen
Appl. Sci. 2022, 12(21), 10898; https://doi.org/10.3390/app122110898 - 27 Oct 2022
Viewed by 1386
Abstract
Aiming at the current situation of network embedding research focusing on dynamic homogeneous network embedding and static heterogeneous information network embedding but lack of dynamic information utilization, this paper proposes a dynamic heterogeneous information network embedding method based on the meta-path and improved [...] Read more.
Aiming at the current situation of network embedding research focusing on dynamic homogeneous network embedding and static heterogeneous information network embedding but lack of dynamic information utilization, this paper proposes a dynamic heterogeneous information network embedding method based on the meta-path and improved Rotate model; this method first uses meta-paths to model the semantic relationships involved in the heterogeneous information network, then uses GCNs to get local node embedding, and finally uses meta-path-level aggression mechanisms to aggregate local representations of nodes, which can solve the heterogeneous information utilization issues. In addition, a temporal processing component based on a time decay function is designed, which can effectively handle temporal information. The experimental results on two real datasets show that the method has good performance in networks with different characteristics. Compared to current mainstream methods, the accuracy of downstream clustering and node classification tasks can be improved by 0.5~41.8%, which significantly improves the quality of embedding, and it also has a shorter running time than most comparison algorithms. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

23 pages, 3761 KiB  
Article
A Hybrid Framework Using PCA, EMD and LSTM Methods for Stock Market Price Prediction with Sentiment Analysis
by Krittakom Srijiranon, Yoskorn Lertratanakham and Tanatorn Tanantong
Appl. Sci. 2022, 12(21), 10823; https://doi.org/10.3390/app122110823 - 25 Oct 2022
Cited by 11 | Viewed by 3260
Abstract
The aim of investors is to obtain the maximum return when buying or selling stocks in the market. However, stock price shows non-linearity and non-stationarity and is difficult to accurately predict. To address this issue, a hybrid prediction model was formulated combining principal [...] Read more.
The aim of investors is to obtain the maximum return when buying or selling stocks in the market. However, stock price shows non-linearity and non-stationarity and is difficult to accurately predict. To address this issue, a hybrid prediction model was formulated combining principal component analysis (PCA), empirical mode decomposition (EMD) and long short-term memory (LSTM) called PCA-EMD-LSTM to predict one step ahead of the closing price of the stock market in Thailand. In this research, news sentiment analysis was also applied to improve the performance of the proposed framework, based on financial and economic news using FinBERT. Experiments with stock market price in Thailand collected from 2018–2022 were examined and various statistical indicators were used as evaluation criteria. The obtained results showed that the proposed framework yielded the best performance compared to baseline methods for predicting stock market price. In addition, an adoption of news sentiment analysis can help to enhance performance of the original LSTM model. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

19 pages, 4684 KiB  
Article
COVID-19 CXR Classification: Applying Domain Extension Transfer Learning and Deep Learning
by KwangJin Park, YoungJin Choi and HongChul Lee
Appl. Sci. 2022, 12(21), 10715; https://doi.org/10.3390/app122110715 - 22 Oct 2022
Cited by 1 | Viewed by 1770
Abstract
The infectious coronavirus disease-19 (COVID-19) is a viral disease that affects the lungs, which caused great havoc when the epidemic rapidly spread around the world. Polymerase chain reaction (PCR) tests are conducted to screen for COVID-19 and respond to quarantine measures. However, PCR [...] Read more.
The infectious coronavirus disease-19 (COVID-19) is a viral disease that affects the lungs, which caused great havoc when the epidemic rapidly spread around the world. Polymerase chain reaction (PCR) tests are conducted to screen for COVID-19 and respond to quarantine measures. However, PCR tests take a considerable amount of time to confirm the test results. Therefore, to supplement the accuracy and quickness of a COVID-19 diagnosis, we proposed an effective deep learning methodology as a quarantine response through COVID-19 chest X-ray image classification based on domain extension transfer learning. As part of the data preprocessing, contrast limited adaptive histogram equalization was applied to chest X-ray images using Medical Information Mart for Intensive Care (MIMIC)-IV obtained from the Beth Israel Deaconess Medical Center. The classification of the COVID-19 X-ray images was conducted using a pretrained ResNet-50. We also visualized and interpreted the classification performance of the model through explainable artificial intelligence and performed statistical tests to validate the reliability of the model. The proposed method correctly classified images with 96.7% accuracy, an improvement of about 9.9% over the reference model. This study is expected to help medical staff make an integrated decision in selecting the first confirmed case and contribute to suppressing the spread of the virus in the community. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

12 pages, 900 KiB  
Article
Automatic Fact Checking Using an Interpretable Bert-Based Architecture on COVID-19 Claims
by Ramón Casillas, Helena Gómez-Adorno, Victor Lomas-Barrie and Orlando Ramos-Flores
Appl. Sci. 2022, 12(20), 10644; https://doi.org/10.3390/app122010644 - 21 Oct 2022
Cited by 1 | Viewed by 1979
Abstract
We present a neural network architecture focused on verifying facts against evidence found in a knowledge base. The architecture can perform relevance evaluation and claim verification, parts of a well-known three-stage method of fact-checking. We fine-tuned BERT to codify claims and pieces of [...] Read more.
We present a neural network architecture focused on verifying facts against evidence found in a knowledge base. The architecture can perform relevance evaluation and claim verification, parts of a well-known three-stage method of fact-checking. We fine-tuned BERT to codify claims and pieces of evidence separately. An attention layer between the claim and evidence representation computes alignment scores to identify relevant terms between both. Finally, a classification layer receives the vector representation of claims and evidence and performs the relevance and verification classification. Our model allows a more straightforward interpretation of the predictions than other state-of-the-art models. We use the scores computed within the attention layer to show which evidence spans are more relevant to classify a claim as supported or refuted. Our classification models achieve results compared to the state-of-the-art models in terms of classification of relevance evaluation and claim verification accuracy on the FEVER dataset. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

19 pages, 3322 KiB  
Article
MobiRes-Net: A Hybrid Deep Learning Model for Detecting and Classifying Olive Leaf Diseases
by Amel Ksibi, Manel Ayadi, Ben Othman Soufiene, Mona M. Jamjoom and Zahid Ullah
Appl. Sci. 2022, 12(20), 10278; https://doi.org/10.3390/app122010278 - 12 Oct 2022
Cited by 20 | Viewed by 2519
Abstract
The Kingdom of Saudi Arabia is considered to be one of the world leaders in olive production accounting for about 6% of the global olive production. Given the fact that 94% of the olive groves are mainly rain-fed using traditional methods of production, [...] Read more.
The Kingdom of Saudi Arabia is considered to be one of the world leaders in olive production accounting for about 6% of the global olive production. Given the fact that 94% of the olive groves are mainly rain-fed using traditional methods of production, the annual olive production is witnessing a noticeable fluctuation which is worse due to infectious diseases and climate change. Thus, early and effective detection of plant diseases is both required and urgent. Most farmers use traditional methods, for example, visual inspection or laboratory examination, to identify plant diseases. Currently, deep learning (DL) techniques have been shown to be useful methods for diagnosing olive leaf diseases and many other fields. In this work, we use a deep feature concatenation (DFC) mechanism to combine features extracted from input images using the two modern pretrained CNN models, i.e., ResNet50 and MobileNet. Hence, we propose MobiRes-Net: A neural network that is a concatenation of the ResNet50 and MobileNet models for overall improvement of prediction capability. To build the dataset used in the study, 5400 olive leaf images were collected from an olive grove using a remote-controlled agricultural unmanned aerial vehicle (UAV) equipped with a camera. The overall performance of the MobiRes-Net model achieved a classification accuracy of 97.08% which showed its superiority over ResNet50 and MobileNet that achieved classification accuracies of 94.86% and 95.63%, respectively. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

15 pages, 3135 KiB  
Article
An Intelligent Real-Time Object Detection System on Drones
by Chao Chen, Hongrui Min, Yi Peng, Yongkui Yang and Zheng Wang
Appl. Sci. 2022, 12(20), 10227; https://doi.org/10.3390/app122010227 - 11 Oct 2022
Cited by 3 | Viewed by 2821
Abstract
Drones have been widely used in everyday life and they can help deal with various tasks, including photography, searching, and surveillance. Nonetheless, it is difficult for drones to perform customized online real-time object detection. In this study, we propose an intelligent real-time object [...] Read more.
Drones have been widely used in everyday life and they can help deal with various tasks, including photography, searching, and surveillance. Nonetheless, it is difficult for drones to perform customized online real-time object detection. In this study, we propose an intelligent real-time object detection system for drones. It is composed of an FPGA and a drone. A neural-network (NN) engine is designed on the FPGA for NN model acceleration. The FPGA receives activation data from an NN model, which are assembled into the data stream. Multiple fetch and jump pointers catch required activation values from the data stream, which are then filtered and sent to each thread independently. To accelerate processing speed, multiple processing elements (PEs) deal with tasks in parallel by using multiple weights and threads. The image data are transferred from the drone host to the FPGA, which are tackled with high speed by the NN engine. The NN engine results are returned to the host, which is used to adjust the flying route accordingly. Experimental results reveal that our proposed FPGA design well utilizes FPGA computing resources with 81.56% DSP and 72.80% LUT utilization rates, respectively. By using the Yolov3-tiny model for fast object detection, our system can detect objects at the speed of 8 frames per second and achieves a much lower power consumption compared to state-of-the-art methods. More importantly, the intelligent object detection techniques provide more pixels for the target of interest and they can increase the detection confidence score from 0.74 to 0.90 and from 0.70 to 0.84 for persons and cars, respectively. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

11 pages, 884 KiB  
Article
Comparison of Monkeypox and Wart DNA Sequences with Deep Learning Model
by Talha Burak Alakus and Muhammet Baykara
Appl. Sci. 2022, 12(20), 10216; https://doi.org/10.3390/app122010216 - 11 Oct 2022
Cited by 15 | Viewed by 1929
Abstract
After the COVID-19 disease, monkeypox disease has emerged today and has started to be seen almost everywhere in the world in a short time. Monkeypox causes symptoms such as fever, chills, and headache in people. In addition, rashes are seen on the skin [...] Read more.
After the COVID-19 disease, monkeypox disease has emerged today and has started to be seen almost everywhere in the world in a short time. Monkeypox causes symptoms such as fever, chills, and headache in people. In addition, rashes are seen on the skin and lumps are formed. Early diagnosis and treatment of monkeypox, which is a contagious disease, are of great importance. An expert interpretation and clinical examination are usually needed to detect monkeypox. This may cause the treatment process to be slow. Furthermore, monkeypox is sometimes confused with warts. This leads to incorrect diagnosis and treatment. Because of these disadvantages, in this study, the DNA sequences of HPV causing warts and MPV causing monkeypox were analyzed and the classification of these sequences was performed with a deep learning algorithm. The study consisted of four stages. In the first stage, DNA sequences of viruses that cause warts and monkeypox were obtained. In the second stage, these sequences were mapped using various DNA-mapping methods. In the third stage, the mapped sequences were classified using a deep learning algorithm. At the last stage, the performances of DNA-mapping methods were compared by calculating accuracy and F1-score. At the end of the study, an average accuracy of 96.08% and an F1-score of 99.83% were obtained. These results showed that these two diseases can be effectively classified according to their DNA sequences. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

20 pages, 4097 KiB  
Article
Path Planning for Multi-Arm Manipulators Using Soft Actor-Critic Algorithm with Position Prediction of Moving Obstacles via LSTM
by Kwan-Woo Park, MyeongSeop Kim, Jung-Su Kim and Jae-Han Park
Appl. Sci. 2022, 12(19), 9837; https://doi.org/10.3390/app12199837 - 29 Sep 2022
Cited by 6 | Viewed by 2494
Abstract
This paper presents a deep reinforcement learning-based path planning algorithm for the multi-arm robot manipulator when there are both fixed and moving obstacles in the workspace. Considering the problem properties such as high dimensionality and continuous action, the proposed algorithm employs the SAC [...] Read more.
This paper presents a deep reinforcement learning-based path planning algorithm for the multi-arm robot manipulator when there are both fixed and moving obstacles in the workspace. Considering the problem properties such as high dimensionality and continuous action, the proposed algorithm employs the SAC (soft actor-critic). Moreover, in order to predict explicitly the future position of the moving obstacle, LSTM (long short-term memory) is used. The SAC-based path planning algorithm is developed using the LSTM. In order to show the performance of the proposed algorithm, simulation results using GAZEBO and experimental results using real manipulators are presented. The simulation and experiment results show that the success ratio of path generation for arbitrary starting and goal points converges to 100%. It is also confirmed that the LSTM successfully predicts the future position of the obstacle. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

15 pages, 3595 KiB  
Article
A Novel Approach to Detect COVID-19: Enhanced Deep Learning Models with Convolutional Neural Networks
by Awf A. Ramadhan and Muhammet Baykara
Appl. Sci. 2022, 12(18), 9325; https://doi.org/10.3390/app12189325 - 17 Sep 2022
Cited by 17 | Viewed by 2020
Abstract
The novel coronavirus (COVID-19) is a contagious viral disease that has rapidly spread worldwide since December 2019, causing the disruption of life and heavy economic losses. Since the beginning of the virus outbreak, a polymerase chain reaction has been used to detect the [...] Read more.
The novel coronavirus (COVID-19) is a contagious viral disease that has rapidly spread worldwide since December 2019, causing the disruption of life and heavy economic losses. Since the beginning of the virus outbreak, a polymerase chain reaction has been used to detect the virus. However, since it is an expensive and slow method, artificial intelligence researchers have attempted to develop quick, inexpensive alternative methods of diagnosis to help doctors identify positive cases. Therefore, researchers are starting to incorporate chest X-ray scans (CXRs), an easy and inexpensive examination method. This study used an approach that uses image cropping methods and a deep learning technique (updated VGG16 model) to classify three public datasets. This study had four main steps. First, the data were split into training and testing sets (70% and 30%, respectively). Second, in the image processing step, each image was cropped to show only the chest area. The images were then resized to 150 × 150. The third step was to build an updated VGG16 convolutional neural network (VGG16-CNN) model using multiple classifications (three classes: COVID-19, normal, and pneumonia) and binary classification (COVID-19 and normal). The fourth step was to evaluate the model’s performance using accuracy, sensitivity, and specificity. This study obtained 97.50% accuracy for multiple classifications and 99.76% for binary classification. The study also got the best COVID-19 classification accuracy (99%) for both models. It can be considered that the scientific contribution of this research is summarized as: the VGG16 model was reduced from approximately 138 million parameters to around 40 million parameters. Further, it was tested on three different datasets and proved highly efficient in performance. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

24 pages, 8705 KiB  
Article
A Semi-Supervised Learning Approach for Automatic Detection and Fashion Product Category Prediction with Small Training Dataset Using FC-YOLOv4
by Yamin Thwe, Nipat Jongsawat and Anucha Tungkasthan
Appl. Sci. 2022, 12(16), 8068; https://doi.org/10.3390/app12168068 - 12 Aug 2022
Cited by 3 | Viewed by 2068
Abstract
Over the past few decades, research on object detection has developed rapidly, one of which can be seen in the fashion industry. Fast and accurate detection of an E-commerce fashion product is crucial to choosing the appropriate category. Nowadays, both new and second-hand [...] Read more.
Over the past few decades, research on object detection has developed rapidly, one of which can be seen in the fashion industry. Fast and accurate detection of an E-commerce fashion product is crucial to choosing the appropriate category. Nowadays, both new and second-hand clothing is provided by E-commerce sites for purchase. Therefore, when categorizing fashion clothing, it is essential to categorize it precisely, regardless of the cluttered background. We present recently acquired tiny product images with various resolutions, sizes, and positions datasets from the Shopee E-commerce (Thailand) website. This paper also proposes the Fashion Category—You Only Look Once version 4 model called FC-YOLOv4 for detecting multiclass fashion products. We used the semi-supervised learning approach to reduce image labeling time, and the number of resulting images is then increased through image augmentation. This approach results in reasonable Average Precision (AP), Mean Average Precision (mAP), True or False Positive (TP/FP), Recall, Intersection over Union (IoU), and reliable object detection. According to experimental findings, our model increases the mAP by 0.07 percent and 40.2 percent increment compared to the original YOLOv4 and YOLOv3. Experimental findings from our FC-YOLOv4 model demonstrate that it can effectively provide accurate fashion category detection for properly captured and clutter images compared to the YOLOv4 and YOLOv3 models. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

27 pages, 8918 KiB  
Article
Particle Swarm Optimisation in Practice: Multiple Applications in a Digital Microscope System
by Louis Ryan, Stefan Kuhn, Simon Colreavy-Donnely and Fabio Caraffini
Appl. Sci. 2022, 12(15), 7827; https://doi.org/10.3390/app12157827 - 04 Aug 2022
Cited by 3 | Viewed by 1400
Abstract
We demonstrate that particle swarm optimisation (PSO) can be used to solve a variety of problems arising during operation of a digital inspection microscope. This is a use case for the feasibility of heuristics in a real-world product. We show solutions to four [...] Read more.
We demonstrate that particle swarm optimisation (PSO) can be used to solve a variety of problems arising during operation of a digital inspection microscope. This is a use case for the feasibility of heuristics in a real-world product. We show solutions to four measurement problems, all based on PSO. This allows for a compact software implementation solving different problems. We have found that PSO can solve a variety of problems with small software footprints and good results in a real-world embedded system. Notably, in the microscope application, this eliminates the need to return the device to the factory for calibration. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

13 pages, 2868 KiB  
Article
Application of Efficient Channel Attention Residual Mechanism in Blast Furnace Tuyere Image Anomaly Detection
by Rihong Wang, Ziyu Li, Lingzhi Yang, Yuming Li, Hao Zhang, Chuanwang Song, Mingjian Jiang, Xiaoyun Ye and Keyong Hu
Appl. Sci. 2022, 12(15), 7823; https://doi.org/10.3390/app12157823 - 04 Aug 2022
Cited by 3 | Viewed by 1822
Abstract
In the steelmaking industry, the state of the blast furnace tuyere is an important basis for obtaining the internal information of the blast furnace. Traditional detections mainly rely on manual experience judgment, which is a time-consuming and tiring procedure for a human. In [...] Read more.
In the steelmaking industry, the state of the blast furnace tuyere is an important basis for obtaining the internal information of the blast furnace. Traditional detections mainly rely on manual experience judgment, which is a time-consuming and tiring procedure for a human. In order to improve the efficiency of the detection, this paper is devoted to applying artificial intelligence methods to blast furnace anomaly detection. However, because of the low imaging degree of the abnormal state monitoring of the furnace mouth, the difference in the abnormal category is inconspicuous, and it is difficulty to extract the features with the existing intelligent models. To solve these problems, a novel and stable method is proposed in this paper to classify the image recognition of the abnormal state of the tuyere into one category; this is a new architecture that combines multiple technologies. For the fine-grained image classification task, an improved abnormal state recognition algorithm of the blast furnace tuyere based on the channel attention residual mechanism is proposed. In the model, the dataset is augmented by rotating it at random angles to balance the amount of data in each category; then, the residual module is used to integrate high- and low-order feature information and optimize the network; then, the multi-layer channel attention module is added based on the channel attention residual mechanism, and it obtains the optimal parameter combination of the model through k-fold cross-validation. Moreover, the number of channels was reduced by half after channel fusion, which could effectively reduce the model parameters and model complexity. It is shown in our experiments that the proposed method has an accuracy rate of 97.10% in identifying the abnormal state of the tuyere in our collection of blast furnace tuyere datasets. In order to test the performance of the proposed method, some existing models, such as SERNet, ResNeXt, and repVGG, are involved for comparison, and the proposed method has a better classification effect in comparison to them. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

25 pages, 2466 KiB  
Article
IIoT Malware Detection Using Edge Computing and Deep Learning for Cybersecurity in Smart Factories
by Ho-myung Kim and Kyung-ho Lee
Appl. Sci. 2022, 12(15), 7679; https://doi.org/10.3390/app12157679 - 30 Jul 2022
Cited by 13 | Viewed by 4680
Abstract
The smart factory environment has been transformed into an Industrial Internet of Things (IIoT) environment, which is an interconnected and open approach. This has made smart manufacturing plants vulnerable to cyberattacks that can directly lead to physical damage. Most cyberattacks targeting smart factories [...] Read more.
The smart factory environment has been transformed into an Industrial Internet of Things (IIoT) environment, which is an interconnected and open approach. This has made smart manufacturing plants vulnerable to cyberattacks that can directly lead to physical damage. Most cyberattacks targeting smart factories are carried out using malware. Thus, a solution that efficiently detects malware by monitoring and analyzing network traffic for malware attacks in smart factory IIoT environments is critical. However, achieving accurate real-time malware detection in such environments is difficult. To solve this problem, this study proposes an edge computing-based malware detection system that efficiently detects various cyberattacks (malware) by distributing vast amounts of smart factory IIoT traffic information to edge servers for deep learning processing. The proposed malware detection system consists of three layers (edge device, edge, and cloud layers) and utilizes four meaningful functions (model training and testing, model deployment, model inference, and training data transmission) for edge-based deep learning. In experiments conducted on the Malimg dataset, the proposed malware detection system incorporating a convolutional neural network with image visualization technology achieved an overall classification accuracy of 98.93%, precision of 98.93%, recall of 98.93%, and F1-score of 98.92%. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

16 pages, 4377 KiB  
Article
Human Activity Recognition Based on Non-Contact Radar Data and Improved PCA Method
by Yixin Zhao, Haiyang Zhou, Sichao Lu, Yanzhong Liu, Xiang An and Qiang Liu
Appl. Sci. 2022, 12(14), 7124; https://doi.org/10.3390/app12147124 - 14 Jul 2022
Cited by 9 | Viewed by 1912
Abstract
Human activity recognition (HAR) can effectively improve the safety of the elderly at home. However, non-contact millimeter-wave radar data on the activities of the elderly is often challenging to collect, making it difficult to effectively improve the accuracy of neural networks for HAR. [...] Read more.
Human activity recognition (HAR) can effectively improve the safety of the elderly at home. However, non-contact millimeter-wave radar data on the activities of the elderly is often challenging to collect, making it difficult to effectively improve the accuracy of neural networks for HAR. We addressed this problem by proposing a method that combines the improved principal component analysis (PCA) and the improved VGG16 model (a pre-trained 16-layer neural network model) to enhance the accuracy of HAR under small-scale datasets. This method used the improved PCA to enhance features of the extracted components and reduce the dimensionality of the data. The VGG16 model was improved by deleting the complex Fully-Connected layers and adding a Dropout layer between them to prevent the loss of useful information. The experimental results show that the accuracy of our proposed method on HAR is 96.34%, which is 4.27% higher after improvement, and the training time of each round is 10.88 s, which is 12.8% shorter than before. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

17 pages, 5104 KiB  
Article
A Deep Convolutional Generative Adversarial Networks-Based Method for Defect Detection in Small Sample Industrial Parts Images
by Hongbin Gao, Ya Zhang, Wenkai Lv, Jiawei Yin, Tehreem Qasim and Dongyun Wang
Appl. Sci. 2022, 12(13), 6569; https://doi.org/10.3390/app12136569 - 29 Jun 2022
Cited by 17 | Viewed by 3177
Abstract
Online defect detection in small industrial parts is of paramount importance for building closed loop intelligent manufacturing systems. However, high-efficiency and high-precision detection of surface defects in these manufacturing systems is a difficult task and poses a major research challenge. The small sample [...] Read more.
Online defect detection in small industrial parts is of paramount importance for building closed loop intelligent manufacturing systems. However, high-efficiency and high-precision detection of surface defects in these manufacturing systems is a difficult task and poses a major research challenge. The small sample size of industrial parts available for training machine learning algorithms and the low accuracy of computer vision-based inspection algorithms are the bottlenecks that restrict the development of efficient online defect detection technology. To address these issues, we propose a small sample gear face defect detection method based on a Deep Convolutional Generative Adversarial Network (DCGAN) and a lightweight Convolutional Neural Network (CNN) in this paper. Initially, we perform data augmentation by using DCGAN and traditional data enhancement methods which effectively increase the size of the training data. In the next stage, we perform defect classification by using a lightweight CNN model which is based on the state-of-the-art Vgg11 network. We introduce the Leaky ReLU activation function and a dropout layer in the proposed CNN. In the experimental evaluation, the proposed framework achieves a high score of 98.40%, which is better than that of the classic Vgg11 network model. The method proposed in this paper is helpful for the detection of defects in industrial parts when the available sample size for training is small. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

18 pages, 858 KiB  
Article
Sequence Planner: A Framework for Control of Intelligent Automation Systems
by Martin Dahl, Endre Erős, Kristofer Bengtsson, Martin Fabian and Petter Falkman
Appl. Sci. 2022, 12(11), 5433; https://doi.org/10.3390/app12115433 - 27 May 2022
Cited by 4 | Viewed by 1332
Abstract
This paper presents a framework that tackles the challenges met in the development of automation systems featuring collaborative robotics and other machines that have some degree of autonomy. These machines rely on online algorithms for both sensing and acting in order to achieve [...] Read more.
This paper presents a framework that tackles the challenges met in the development of automation systems featuring collaborative robotics and other machines that have some degree of autonomy. These machines rely on online algorithms for both sensing and acting in order to achieve a very high level of flexibility. To take advantage of these new machines and algorithms, control systems must also be increasingly flexible. In this paper, we present a framework for control of this new class of intelligent automation systems called Sequence Planner (SP), which helps with control of both traditional automation equipment and machines with autonomy. To aid the complex task of developing automation control solutions, SP relies on supporting algorithms for control logic synthesis and online planning. SP has been implemented with plug-in support for the Robot Operating System (ROS) and applied to an industrial demonstrator. We present our findings on how SP performed as a control system for this demonstrator, where we show that it is an adequate approach to implement automation for a highly flexible single station system. As a standardized way of automating such systems is missing, we hope that our contribution will provide a foundation for how to develop intelligent automation systems. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

20 pages, 9074 KiB  
Article
MARL-Based Dual Reward Model on Segmented Actions for Multiple Mobile Robots in Automated Warehouse Environment
by Hyeoksoo Lee, Jiwoo Hong and Jongpil Jeong
Appl. Sci. 2022, 12(9), 4703; https://doi.org/10.3390/app12094703 - 07 May 2022
Cited by 6 | Viewed by 2529
Abstract
The simple and labor-intensive tasks of workers on the job site are rapidly becoming digital. In the work environment of logistics warehouses and manufacturing plants, moving goods to a designated place is a typical labor-intensive task for workers. These tasks are rapidly undergoing [...] Read more.
The simple and labor-intensive tasks of workers on the job site are rapidly becoming digital. In the work environment of logistics warehouses and manufacturing plants, moving goods to a designated place is a typical labor-intensive task for workers. These tasks are rapidly undergoing digital transformation by leveraging mobile robots in automated warehouses. In this paper, we studied and tested realistically necessary conditions to operate mobile robots in an automated warehouse. In particular, considering conditions for operating multiple mobile robots in an automated warehouse, we added more complex actions and various routes and proposed a method for improving sparse reward problems when learning paths in a warehouse with reinforcement learning. Multi-Agent Reinforcement Learning (MARL) experiments were conducted with multiple mobile robots in an automated warehouse simulation environment, and it was confirmed that the proposed reward model method makes learning start earlier even there is a sparse reward problem and learning progress was maintained stably. We expect this study to help us understand the actual operation of mobile robots in an automated warehouse further. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

20 pages, 11733 KiB  
Article
Improved U-Net++ with Patch Split for Micro-Defect Inspection in Silk Screen Printing
by Byungguan Yoon, Homin Lee and Jongpil Jeong
Appl. Sci. 2022, 12(9), 4679; https://doi.org/10.3390/app12094679 - 06 May 2022
Viewed by 1953
Abstract
The trend of multi-variety production is leading to a change in the product type of silk screen prints produced at short intervals. The types and locations of defects that usually occur in silk screen prints may vary greatly and thus, it is difficult [...] Read more.
The trend of multi-variety production is leading to a change in the product type of silk screen prints produced at short intervals. The types and locations of defects that usually occur in silk screen prints may vary greatly and thus, it is difficult for operators to conduct quality inspections for minuscule defects. In this paper, an improved U-Net++ is proposed based on patch splits for automated quality inspection of small or tiny defects, hereinafter referred to as ‘fine’ defects. The novelty of the method is that, to better handle defects within an image, patch level inputs are considered instead of using the original image as input. In the existing technique with the original image as input, artificial intelligence (AI) learning is not utilized efficiently, whereas our proposed method learns stably, and the Dice score was 0.728, which is approximately 10% higher than the existing method. The proposed model was applied to an actual silk screen printing process. All of the fine defects in products, such as silk screen prints, could be detected regardless of the product size. In addition, it was shown that quality inspection using the patch-split method-based AI is possible even in situations where there are few prior defective data. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

12 pages, 3188 KiB  
Article
Identification of 3D Lip Shape during Japanese Vowel Pronunciation Using Deep Learning
by Yoshihiro Sato and Yue Bao
Appl. Sci. 2022, 12(9), 4632; https://doi.org/10.3390/app12094632 - 05 May 2022
Viewed by 1808
Abstract
People with speech impediments and hearing impairments, whether congenital or acquired, often encounter difficulty in speaking. Therefore, to acquire conversational communication abilities, it is necessary to practice lipreading and imitation so that correct vocalization can be achieved. In conventional lipreading methods using machine [...] Read more.
People with speech impediments and hearing impairments, whether congenital or acquired, often encounter difficulty in speaking. Therefore, to acquire conversational communication abilities, it is necessary to practice lipreading and imitation so that correct vocalization can be achieved. In conventional lipreading methods using machine learning, model refinement and multimodal processing are the norm to maintain high accuracy. However, since 3D point clouds can now be obtained using smartphones and other devices, it is becoming viable to consider methods that use 3D information. Therefore, given the obvious relation between vowel pronunciation and three-dimensional (3D) lip shape, in this study, we propose a method of extracting and discriminating vowel features via deep learning using 3D point clouds of the lip region. For training, we created two datasets: mixed-gender and male-only datasets. The results of the experiment showed that the average accuracy rate of the k-fold cross-validation exceeded 70% for both the mixed-gender and male-only data. In particular, although the proposed method was ~3.835% less accurate than the machine learning results for 2D images, the training parameters were reduced by 92.834%, and the proposed method succeeded in obtaining vowel features from 3D lip shapes. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

23 pages, 2842 KiB  
Article
Online Service-Time Allocation Strategy for Balancing Energy Consumption and Queuing Delay of a MEC Server
by Jaesung Park and Yujin Lim
Appl. Sci. 2022, 12(9), 4539; https://doi.org/10.3390/app12094539 - 29 Apr 2022
Cited by 2 | Viewed by 1409
Abstract
MEC servers (MESs) support multiple queues to accommodate the delay requirements of tasks offloaded from end devices or transferred from other MESs. The service time assigned to each queue trades off the queue backlog and energy consumption. Because multiple queues share the computational [...] Read more.
MEC servers (MESs) support multiple queues to accommodate the delay requirements of tasks offloaded from end devices or transferred from other MESs. The service time assigned to each queue trades off the queue backlog and energy consumption. Because multiple queues share the computational resources of a MES, optimally scheduling the service time among them is important, reducing the energy consumption of a MES and ensuring the delay requirement of each queue. To achieve a balance between these metrics, we propose an online service-time allocation method that minimizes the average energy consumption and satisfies the average queue backlog constraint. We employ the Lyapunov optimization framework to transform the time-averaged optimization problem into a per-time-slot optimization problem and devise an online service-time allocation method whose time complexity is linear to the number of queues. This method determines the service time for each queue at the beginning of each time slot using the observed queue length and expected workload. We adopt a long short-term memory (LSTM) deep learning model to predict the workload that will be imposed on each queue during a time slot. Using simulation studies, we verify that the proposed method strikes a better balance between energy consumption and queuing delay than conventional methods. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

10 pages, 1922 KiB  
Article
Can AI Automatically Assess Scan Quality of Hip Ultrasound?
by Abhilash Rakkunedeth Hareendrananthan, Myles Mabee, Baljot S. Chahal, Sukhdeep K. Dulai and Jacob L. Jaremko
Appl. Sci. 2022, 12(8), 4072; https://doi.org/10.3390/app12084072 - 18 Apr 2022
Viewed by 2188
Abstract
Ultrasound images can reliably detect Developmental Dysplasia of the Hip (DDH) during early infancy. Accuracy of diagnosis depends on the scan quality, which is subjectively assessed by the sonographer during ultrasound examination. Such assessment is prone to errors and often results in poor-quality [...] Read more.
Ultrasound images can reliably detect Developmental Dysplasia of the Hip (DDH) during early infancy. Accuracy of diagnosis depends on the scan quality, which is subjectively assessed by the sonographer during ultrasound examination. Such assessment is prone to errors and often results in poor-quality scans not being reported, risking misdiagnosis. In this paper, we propose an Artificial Intelligence (AI) technique for automatically determining scan quality. We trained a Convolutional Neural Network (CNN) to categorize 3D Ultrasound (3DUS) hip scans as ‘adequate’ or ‘inadequate’ for diagnosis. We evaluated the performance of this AI technique on two datasets—Dataset 1 (DS1) consisting of 2187 3DUS images in which each image was assessed by one reader for scan quality on a scale of 1 (lowest quality) to 5 (optimal quality) and Dataset 2 (DS2) consisting of 107 3DUS images evaluated semi-quantitatively by four readers using a 10-point scoring system. As a binary classifier (adequate/inadequate), the AI technique gave highly accurate predictions on both datasets (DS1 accuracy = 96% and DS2 accuracy = 91%) and showed high agreement with expert readings in terms of Intraclass Correlation Coefficient (ICC) and Cohen’s kappa coefficient (K). Using our AI-based approach as a screening tool during ultrasound scanning or postprocessing would ensure high scan quality and lead to more reliable ultrasound hip examination in infants. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

20 pages, 2588 KiB  
Article
Detection of Chinese Deceptive Reviews Based on Pre-Trained Language Model
by Chia-Hsien Weng, Kuan-Cheng Lin and Jia-Ching Ying
Appl. Sci. 2022, 12(7), 3338; https://doi.org/10.3390/app12073338 - 25 Mar 2022
Cited by 3 | Viewed by 2173
Abstract
The advancement of the Internet has changed people’s ways of expressing and sharing their views with the world. Moreover, user-generated content has become a primary guide for customer purchasing decisions. Therefore, motivated by commercial interest, some sellers have started manipulating Internet ratings by [...] Read more.
The advancement of the Internet has changed people’s ways of expressing and sharing their views with the world. Moreover, user-generated content has become a primary guide for customer purchasing decisions. Therefore, motivated by commercial interest, some sellers have started manipulating Internet ratings by writing false positive reviews to encourage the sale of their goods and writing false negative reviews to discredit competitors. These reviews are generally referred to as deceptive reviews. Deceptive reviews mislead customers in purchasing goods that are inconsistent with online information and thus obstruct fair competition among businesses. To protect the right of consumers and sellers, an effective method is required to automate the detection of misleading reviews. Previously developed methods of translating text into feature vectors usually fail to interpret polysemous words, which leads to such functions being obstructed. By using dynamic feature vectors, the present study developed several misleading review-detection models for the Chinese language. The developed models were then compared with the standard detection-efficiency models. The deceptive reviews collected from various online forums in Taiwan by previous studies were used to test the models. The results showed that the models proposed in this study can achieve 0.92 in terms of precision, 0.91 in terms of recall, and 0.91 in terms of F1-score. The improvement rate of our proposal is higher than 20%. Accordingly, we prove that our proposal demonstrated improved performance in detecting misleading reviews, and the models based on dynamic feature vectors were capable of more accurately capturing semantic terms than the conventional models based on the static feature vectors, thereby enhancing effectiveness. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

12 pages, 3251 KiB  
Article
Customized Convolutional Neural Networks Technology for Machined Product Inspection
by Yi-Cheng Huang, Kuo-Chun Hung, Chun-Chang Liu, Ting-Hsueh Chuang and Shean-Juinn Chiou
Appl. Sci. 2022, 12(6), 3014; https://doi.org/10.3390/app12063014 - 16 Mar 2022
Cited by 3 | Viewed by 2899
Abstract
Metal workpieces are an indispensable and important part of the manufacturing industry. Surface flaws not only affect the appearance, but also affect the efficiency of the workpiece and reduce the safety of the product. Therefore, the appearance of the product needs to be [...] Read more.
Metal workpieces are an indispensable and important part of the manufacturing industry. Surface flaws not only affect the appearance, but also affect the efficiency of the workpiece and reduce the safety of the product. Therefore, the appearance of the product needs to be inspected to determine if there are surface defects, such as scratches, dirt, chipped objects, etc., after production is completed. The traditional manual comparison inspection method is not only time-consuming and labor-intensive, but human error is also unavoidable when inspecting thousands or tens of thousands of products. Therefore, Automated Optical Inspection (AOI) is often used today. The traditional AOI algorithm does not fully meet the subtle detection requirements and needs to import a Convolutional Neural Network (CNN), but the common deep residual networks are too large, such as ResNet-101, ResNet-152, DarkNet-19, and DarkNet-53. Therefore, this research proposes an improved customized convolutional neural network. We used a self-built convolutional neural network model to detect the defects on the metal’s surface. Grad–CAM was used to display the result of the last layer of convolution as the basis for judging whether it was OK or NG. The self-designed CNN network architecture could be customized and adjusted without using a large network model. The customized network model designed in this study was compared with LeNet, VGG-19, ResNet-34, DarkNet-19, and DarkNet-53 after training five times each. The experimental results show that the self-built customized deep learning model avoiding the use of pooling and fully connected layers can effectively improve the recognition rate of defective samples and unqualified samples, and reduce the training cost. Our custom-designed models have great advantages over other models. The results of this paper contribute to the development of new diagnostic technologies for smart manufacturing. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

16 pages, 2764 KiB  
Article
Hybrid Training Strategies: Improving Performance of Temporal Difference Learning in Board Games
by Jesús Fernández-Conde, Pedro Cuenca-Jiménez and José M. Cañas
Appl. Sci. 2022, 12(6), 2854; https://doi.org/10.3390/app12062854 - 10 Mar 2022
Viewed by 1537
Abstract
Temporal difference (TD) learning is a well-known approach for training automated players in board games with a limited number of potential states through autonomous play. Because of its directness, TD learning has become widespread, but certain critical difficulties must be solved in order [...] Read more.
Temporal difference (TD) learning is a well-known approach for training automated players in board games with a limited number of potential states through autonomous play. Because of its directness, TD learning has become widespread, but certain critical difficulties must be solved in order for it to be effective. It is impractical to train an artificial intelligence (AI) agent against a random player since it takes millions of games for the agent to learn to play intelligently. Training the agent against a methodical player, on the other hand, is not an option owing to a lack of exploration. This article describes and examines a variety of hybrid training procedures for a TD-based automated player that combines randomness with specified plays in a predetermined ratio. We provide simulation results for the famous tic-tac-toe and Connect-4 board games, in which one of the studied training strategies significantly surpasses the other options. On average, it takes fewer than 100,000 games of training for an agent taught using this approach to act as a flawless player in tic-tac-toe. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

14 pages, 1954 KiB  
Article
Trademark Image Similarity Detection Using Convolutional Neural Network
by Hayfa Alshowaish, Yousef Al-Ohali and Abeer Al-Nafjan
Appl. Sci. 2022, 12(3), 1752; https://doi.org/10.3390/app12031752 - 08 Feb 2022
Cited by 10 | Viewed by 4371
Abstract
A trademark is any recognizable sign that identifies products/services and distinguishes them from others. Many regional and international intellectual property offices are dedicated to dealing with trademark registration processes. The registration process involves examining the trademark to ensure there is no confusion or [...] Read more.
A trademark is any recognizable sign that identifies products/services and distinguishes them from others. Many regional and international intellectual property offices are dedicated to dealing with trademark registration processes. The registration process involves examining the trademark to ensure there is no confusion or interference similarity to any other prior registered trademark. Due to the increasing number of registered trademarks annually, the current manual examining approach is becoming insufficient and more susceptible to human error. As such, there is potential for machine learning applications and deep learning, in particular, to enhance the examination process by providing an automated image detection system to be used by the examiners to facilitate and improve the accuracy of the examination process. Therefore, this paper proposed a trademark similarity detection system using deep-learning techniques to extract image features automatically in order to retrieve a trademark based on shape similarity. Two pretrained convolutional neural networks (VGGNet and ResNet) were individually used to extract image features. Then, their performance was compared. Subsequently, the extracted features were used to calculate the similarity between a new trademark and each of those registered using the Euclidean distance. Thereafter, the system retrieved the most similar trademark to the query according to the smallest distances. As a result, the system achieved an average rank of 67,067.788, a normalized average rank of 0.0725, and a mean average precision of 0.774 on the Middle East Technical University dataset, which displays a promising application in detecting trademark similarity. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

Review

Jump to: Research

34 pages, 780 KiB  
Review
A Survey of Applications of Deep Learning in Radio Signal Modulation Recognition
by Tiange Wang, Guangsong Yang, Penghui Chen, Zhenghua Xu, Mengxi Jiang and Qiubo Ye
Appl. Sci. 2022, 12(23), 12052; https://doi.org/10.3390/app122312052 - 25 Nov 2022
Cited by 2 | Viewed by 3030
Abstract
With the continuous development of communication technology, the wireless communication environment becomes more and more complex with various intentional and unintentional signals. Radio signals are modulated in different ways. The traditional radio modulation recognition technology cannot recognize the modulation modes accurately. Consequently, the [...] Read more.
With the continuous development of communication technology, the wireless communication environment becomes more and more complex with various intentional and unintentional signals. Radio signals are modulated in different ways. The traditional radio modulation recognition technology cannot recognize the modulation modes accurately. Consequently, the communication system has embraced Deep Learning (DL) models as they can automatically recognize the modulation modes and have better accuracy. This paper systematically summarizes the related contents of radio Automatic Modulation Recognition (AMR) based on DL over the last seven years. First, we summarize the current research status of modulation recognition and the necessity of AMR research based on DL. Then, we review current radio AMR methods based on DL. In addition, we also propose a network model of AMR based on Convolutional Neural Network (CNN) and prove its effectiveness. Finally, we highlight existing challenges and research directions of radio AMR based on DL. Full article
(This article belongs to the Special Issue Applications of Deep Learning and Artificial Intelligence Methods)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-48
Back to TopTop