Various Deep Learning Algorithms in Computational Intelligence

A special issue of Axioms (ISSN 2075-1680). This special issue belongs to the section "Mathematical Analysis".

Deadline for manuscript submissions: closed (31 January 2023) | Viewed by 37858

Printed Edition Available!
A printed edition of this Special Issue is available here.

Special Issue Editor


E-Mail Website1 Website2
Guest Editor
Centro de Investigación y Desarrollo de Tecnología Digital, Instituto Politécnico Nacional, México City 07738, Mexico
Interests: intelligent systems; quantum computing; quantum intelligent systems; evolutionary computation; fuzzy systems; neural networks; deep learning; computational intelligence
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Dear Colleagues,

Deep learning (Dl) is an essential topic of increasing interest in science, industry, and academia. Unlike traditional and machine learning methods, Dl methods can process large volumes of unstructured data. It is rapidly becoming a tool for modeling and solving complex and difficult problems in different fields of science and technology. For example, in medicine in breast cancer, COVID-19 detection and diabetes detection and prediction; in autonomous vehicles in various tasks such as perception, mapping and localization; in astronomy, for classifying and detecting stars and galaxies; in the design of future wireless networks, and others. Although Dl has been successfully applied in many fields and there are some theoretical developments, there are still many challenging problems in theory and applications that need to be solved for improving these techniques. For instance, it is important to find new methods for training the massive number of parameters required by Dl architectures, solve over-fitting and transfer learning problems, and others. This Special Issue aims to contribute to the state-of-the-art progress on Dl with theoretical, practical, and creative insights that provide vanguard solutions to challenging problems or can demonstrate competitive performance.

Prof. Dr. Oscar Humberto Ross
Guest Editor

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. Axioms is an international peer-reviewed open access monthly 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

  • Autonomous vehicles and robotics
  • Applications in medicine, healthcare, and clinical decision support
  • Future wireless networks
  • Big data in astronomy
  • Complex systems modeling
  • Deep learning in Blockchain and finance
  • Transfer learning and other learning methods
  • Novel deep learning architectures
  • Novel optimization methods for deep learning
  • Deep learning for EEG motor imagery
  • Deep learning for architecture design
  • Computer vision
  • Natural language processing
  • Human activity recognition
  • Any novel theoretical development on deep learning
  • Any novel competitive application with potential industrial impact

Published Papers (15 papers)

Order results
Result details
Select all
Export citation of selected articles as:

Editorial

Jump to: Research

5 pages, 196 KiB  
Editorial
Various Deep Learning Algorithms in Computational Intelligence
by Oscar Humberto Montiel Ross
Axioms 2023, 12(5), 495; https://doi.org/10.3390/axioms12050495 - 19 May 2023
Viewed by 851
Abstract
Deep Learning (DL) is an essential topic of increasing interest in science, industry, and academia [...] Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)

Research

Jump to: Editorial

12 pages, 10168 KiB  
Article
A Unified Learning Approach for Malicious Domain Name Detection
by Atif Ali Wagan, Qianmu Li, Zubair Zaland, Shah Marjan, Dadan Khan Bozdar, Aamir Hussain, Aamir Mehmood Mirza and Mehmood Baryalai
Axioms 2023, 12(5), 458; https://doi.org/10.3390/axioms12050458 - 09 May 2023
Cited by 4 | Viewed by 1383
Abstract
The DNS firewall plays an important role in network security. It is based on a list of known malicious domain names, and, based on these lists, the firewall blocks communication with these domain names. However, DNS firewalls can only block known malicious domain [...] Read more.
The DNS firewall plays an important role in network security. It is based on a list of known malicious domain names, and, based on these lists, the firewall blocks communication with these domain names. However, DNS firewalls can only block known malicious domain names, excluding communication with unknown malicious domain names. Prior research has found that machine learning techniques are effective for detecting unknown malicious domain names. However, those methods have limited capabilities to learn from both textual and numerical data. To solve this issue, we present a novel unified learning approach that uses both numerical and textual features of the domain name to classify whether a domain name pair is malicious or not. The experiments were conducted on a benchmark domain names dataset consisting of 90,000 domain names. The experimental results show that the proposed approach performs significantly better than the six comparative methods in terms of accuracy, precision, recall, and F1-Score. Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)
Show Figures

Figure 1

24 pages, 15344 KiB  
Article
Developing a Deep Learning-Based Defect Detection System for Ski Goggles Lenses
by Dinh-Thuan Dang and Jing-Wein Wang
Axioms 2023, 12(4), 386; https://doi.org/10.3390/axioms12040386 - 17 Apr 2023
Cited by 5 | Viewed by 1583
Abstract
Ski goggles help protect the eyes and enhance eyesight. The most important part of ski goggles is their lenses. The quality of the lenses has leaped with technological advances, but there are still defects on their surface during manufacturing. This study develops a [...] Read more.
Ski goggles help protect the eyes and enhance eyesight. The most important part of ski goggles is their lenses. The quality of the lenses has leaped with technological advances, but there are still defects on their surface during manufacturing. This study develops a deep learning-based defect detection system for ski goggles lenses. The first step is to design the image acquisition model that combines cameras and light sources. This step aims to capture clear and high-resolution images on the entire surface of the lenses. Next, defect categories are identified, including scratches, watermarks, spotlight, stains, dust-line, and dust-spot. They are labeled to create the ski goggles lenses defect dataset. Finally, the defects are automatically detected by fine-tuning the mobile-friendly object detection model. The mentioned defect detection model is the MobileNetV3 backbone used in a feature pyramid network (FPN) along with the Faster-RCNN detector. The fine-tuning includes: replacing the default ResNet50 backbone with a combination of MobileNetV3 and FPN; adjusting the hyper-parameter of the region proposal network (RPN) to suit the tiny defects; and reducing the number of the output channel in FPN to increase computational performance. Our experiments demonstrate the effectiveness of defect detection; additionally, the inference speed is fast. The defect detection accuracy achieves a mean average precision (mAP) of 55%. The work automatically integrates all steps, from capturing images to defect detection. Furthermore, the lens defect dataset is publicly available to the research community on GitHub. The repository address can be found in the Data Availability Statement section. Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)
Show Figures

Figure 1

22 pages, 1406 KiB  
Article
Barrier Options and Greeks: Modeling with Neural Networks
by Nneka Umeorah, Phillip Mashele, Onyecherelam Agbaeze and Jules Clement Mba
Axioms 2023, 12(4), 384; https://doi.org/10.3390/axioms12040384 - 17 Apr 2023
Cited by 2 | Viewed by 2001
Abstract
This paper proposes a non-parametric technique of option valuation and hedging. Here, we replicate the extended Black–Scholes pricing model for the exotic barrier options and their corresponding Greeks using the fully connected feed-forward neural network. Our methodology involves some benchmarking experiments, which result [...] Read more.
This paper proposes a non-parametric technique of option valuation and hedging. Here, we replicate the extended Black–Scholes pricing model for the exotic barrier options and their corresponding Greeks using the fully connected feed-forward neural network. Our methodology involves some benchmarking experiments, which result in an optimal neural network hyperparameter that effectively prices the barrier options and facilitates their option Greeks extraction. We compare the results from the optimal NN model to those produced by other machine learning models, such as the random forest and the polynomial regression; the output highlights the accuracy and the efficiency of our proposed methodology in this option pricing problem. The results equally show that the artificial neural network can effectively and accurately learn the extended Black–Scholes model from a given simulated dataset, and this concept can similarly be applied in the valuation of complex financial derivatives without analytical solutions. Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)
Show Figures

Figure 1

20 pages, 2236 KiB  
Article
Two Novel Models for Traffic Sign Detection Based on YOLOv5s
by Wei Bai, Jingyi Zhao, Chenxu Dai, Haiyang Zhang, Li Zhao, Zhanlin Ji and Ivan Ganchev
Axioms 2023, 12(2), 160; https://doi.org/10.3390/axioms12020160 - 03 Feb 2023
Cited by 18 | Viewed by 2441
Abstract
Object detection and image recognition are some of the most significant and challenging branches in the field of computer vision. The prosperous development of unmanned driving technology has made the detection and recognition of traffic signs crucial. Affected by diverse factors such as [...] Read more.
Object detection and image recognition are some of the most significant and challenging branches in the field of computer vision. The prosperous development of unmanned driving technology has made the detection and recognition of traffic signs crucial. Affected by diverse factors such as light, the presence of small objects, and complicated backgrounds, the results of traditional traffic sign detection technology are not satisfactory. To solve this problem, this paper proposes two novel traffic sign detection models, called YOLOv5-DH and YOLOv5-TDHSA, based on the YOLOv5s model with the following improvements (YOLOv5-DH uses only the second improvement): (1) replacing the last layer of the ‘Conv + Batch Normalization + SiLU’ (CBS) structure in the YOLOv5s backbone with a transformer self-attention module (T in the YOLOv5-TDHSA’s name), and also adding a similar module to the last layer of its neck, so that the image information can be used more comprehensively, (2) replacing the YOLOv5s coupled head with a decoupled head (DH in both models’ names) so as to increase the detection accuracy and speed up the convergence, and (3) adding a small-object detection layer (S in the YOLOv5-TDHSA’s name) and an adaptive anchor (A in the YOLOv5-TDHSA’s name) to the YOLOv5s neck to improve the detection of small objects. Based on experiments conducted on two public datasets, it is demonstrated that both proposed models perform better than the original YOLOv5s model and three other state-of-the-art models (Faster R-CNN, YOLOv4-Tiny, and YOLOv5n) in terms of the mean accuracy (mAP) and F1 score, achieving mAP values of 77.9% and 83.4% and F1 score values of 0.767 and 0.811 on the TT100K dataset, and mAP values of 68.1% and 69.8% and F1 score values of 0.71 and 0.72 on the CCTSDB2021 dataset, respectively, for YOLOv5-DH and YOLOv5-TDHSA. This was achieved, however, at the expense of both proposed models having a bigger size, greater number of parameters, and slower processing speed than YOLOv5s, YOLOv4-Tiny and YOLOv5n, surpassing only Faster R-CNN in this regard. The results also confirmed that the incorporation of the T and SA improvements into YOLOv5s leads to further enhancement, represented by the YOLOv5-TDHSA model, which is superior to the other proposed model, YOLOv5-DH, which avails of only one YOLOv5s improvement (i.e., DH). Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)
Show Figures

Figure 1

20 pages, 4768 KiB  
Article
Improved Method for Oriented Waste Detection
by Weizhi Yang, Yi Xie and Peng Gao
Axioms 2023, 12(1), 18; https://doi.org/10.3390/axioms12010018 - 24 Dec 2022
Cited by 1 | Viewed by 1356
Abstract
Waste detection is one of the main problems preventing the realization of automated waste classification, which is a basic function for robotic arms. In addition to object identification in general image analysis, a waste-sorting robotic arm not only needs to identify a target [...] Read more.
Waste detection is one of the main problems preventing the realization of automated waste classification, which is a basic function for robotic arms. In addition to object identification in general image analysis, a waste-sorting robotic arm not only needs to identify a target object but also needs to accurately judge its placement angle so that it can determine an appropriate angle for grasping. In order to solve the problem of low-accuracy image detection caused by irregular placement angles, in this work, we propose an improved oriented waste detection method based on YOLOv5. By optimizing the detection head of the YOLOv5 model, this method can generate an oriented detection box for a waste object that is placed at any angle. Based on the proposed scheme, we further improved three aspects of the performance of YOLOv5 in the detection of waste objects: the angular loss function was derived based on dynamic smoothing to enhance the model’s angular prediction ability, the backbone network was optimized with enhanced shallow features and attention mechanisms, and the feature aggregation network was improved to enhance the effects of feature multi-scale fusion. The experimental results showed that the detection performance of the proposed method for waste targets was better than other deep learning methods. Its average accuracy and recall were 93.9% and 94.8%, respectively, which were 11.6% and 7.6% higher than those of the original network, respectively. Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)
Show Figures

Figure 1

14 pages, 23696 KiB  
Article
Score-Guided Generative Adversarial Networks
by Minhyeok Lee and Junhee Seok
Axioms 2022, 11(12), 701; https://doi.org/10.3390/axioms11120701 - 07 Dec 2022
Cited by 5 | Viewed by 1525
Abstract
We propose a generative adversarial network (GAN) that introduces an evaluator module using pretrained networks. The proposed model, called a score-guided GAN (ScoreGAN), is trained using an evaluation metric for GANs, i.e., the Inception score, as a rough guide for the training of [...] Read more.
We propose a generative adversarial network (GAN) that introduces an evaluator module using pretrained networks. The proposed model, called a score-guided GAN (ScoreGAN), is trained using an evaluation metric for GANs, i.e., the Inception score, as a rough guide for the training of the generator. Using another pretrained network instead of the Inception network, ScoreGAN circumvents overfitting of the Inception network such that the generated samples do not correspond to adversarial examples of the Inception network. In addition, evaluation metrics are employed only in an auxiliary role to prevent overfitting. When evaluated using the CIFAR-10 dataset, ScoreGAN achieved an Inception score of 10.36 ± 0.15, which corresponds to state-of-the-art performance. To generalize the effectiveness of ScoreGAN, the model was evaluated further using another dataset, CIFAR-100. ScoreGAN outperformed other existing methods, achieving a Fréchet Inception distance (FID) of 13.98. Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)
Show Figures

Figure 1

19 pages, 5009 KiB  
Article
Hybrid Deep Learning Algorithm for Forecasting SARS-CoV-2 Daily Infections and Death Cases
by Fehaid Alqahtani, Mostafa Abotaleb, Ammar Kadi, Tatiana Makarovskikh, Irina Potoroko, Khder Alakkari and Amr Badr
Axioms 2022, 11(11), 620; https://doi.org/10.3390/axioms11110620 - 07 Nov 2022
Cited by 7 | Viewed by 1719
Abstract
The prediction of new cases of infection is crucial for authorities to get ready for early handling of the virus spread. Methodology Analysis and forecasting of epidemic patterns in new SARS-CoV-2 positive patients are presented in this research using a hybrid deep learning [...] Read more.
The prediction of new cases of infection is crucial for authorities to get ready for early handling of the virus spread. Methodology Analysis and forecasting of epidemic patterns in new SARS-CoV-2 positive patients are presented in this research using a hybrid deep learning algorithm. The hybrid deep learning method is employed for improving the parameters of long short-term memory (LSTM). To evaluate the effectiveness of the proposed methodology, a dataset was collected based on the recorded cases in the Russian Federation and Chelyabinsk region between 22 January 2020 and 23 August 2022. In addition, five regression models were included in the conducted experiments to show the effectiveness and superiority of the proposed approach. The achieved results show that the proposed approach could reduce the mean square error (RMSE), relative root mean square error (RRMSE), mean absolute error (MAE), coefficient of determination (R Square), coefficient of correlation (R), and mean bias error (MBE) when compared with the five base models. The achieved results confirm the effectiveness, superiority, and significance of the proposed approach in predicting the infection cases of SARS-CoV-2. Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)
Show Figures

Figure 1

12 pages, 17573 KiB  
Article
A Schelling Extended Model in Networks—Characterization of Ghettos in Washington D.C.
by Diego Ortega and Elka Korutcheva
Axioms 2022, 11(9), 457; https://doi.org/10.3390/axioms11090457 - 06 Sep 2022
Cited by 1 | Viewed by 1372
Abstract
Segregation affects millions of urban dwellers. The main expression of this reality is the creation of ghettos which are city parts characterized by a combination of features: low income, poor cultural level… Segregation models have been usually defined over regular lattices. However, in [...] Read more.
Segregation affects millions of urban dwellers. The main expression of this reality is the creation of ghettos which are city parts characterized by a combination of features: low income, poor cultural level… Segregation models have been usually defined over regular lattices. However, in recent years, the focus has shifted from these unrealistic frameworks to other environments defined via geographic information systems (GIS) or networks. Nevertheless, each one of them has its drawbacks: GIS demands high-resolution data, that are not always available, and networks tend to have limited real-world applications. Our work tries to fill the gap between them. First, we use some basic GIS information to define the network, and then, run an extended Schelling model on it. As a result, we obtain the location of ghettos. After that, we analyze which parts of the city are segregated, via spatial analysis and machine learning and compare our results. For the case study of Washington D.C., we obtain an 80% accuracy. Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)
Show Figures

Figure 1

20 pages, 1935 KiB  
Article
Lexicon-Enhanced Multi-Task Convolutional Neural Network for Emotion Distribution Learning
by Yuchang Dong and Xueqiang Zeng
Axioms 2022, 11(4), 181; https://doi.org/10.3390/axioms11040181 - 17 Apr 2022
Cited by 2 | Viewed by 2010
Abstract
Emotion distribution learning (EDL) handles emotion fuzziness by means of the emotion distribution, which is an emotion vector that quantitatively represents a set of emotion categories with their intensity of a given instance. Despite successful applications of EDL in many practical emotion analysis [...] Read more.
Emotion distribution learning (EDL) handles emotion fuzziness by means of the emotion distribution, which is an emotion vector that quantitatively represents a set of emotion categories with their intensity of a given instance. Despite successful applications of EDL in many practical emotion analysis tasks, existing EDL methods have seldom considered the linguistic prior knowledge of affective words specific to the text mining task. To address the problem, this paper proposes a text emotion distribution learning model based on a lexicon-enhanced multi-task convolutional neural network (LMT-CNN) to jointly solve the tasks of text emotion distribution prediction and emotion label classification. The LMT-CNN model designs an end-to-end multi-module deep neural network to utilize both semantic information and linguistic knowledge. Specifically, the architecture of the LMT-CNN model consists of a semantic information module, an emotion knowledge module based on affective words, and a multi-task prediction module to predict emotion distributions and labels. Extensive comparative experiments on nine commonly used emotional text datasets showed that the proposed LMT-CNN model is superior to the compared EDL methods for both emotion distribution prediction and emotion recognition tasks. Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)
Show Figures

Figure 1

14 pages, 2317 KiB  
Article
Towards Predictive Vietnamese Human Resource Migration by Machine Learning: A Case Study in Northeast Asian Countries
by Nguyen Hong Giang, Tien-Thinh Nguyen, Chac Cau Tay, Le Anh Phuong and Thanh-Tuan Dang
Axioms 2022, 11(4), 151; https://doi.org/10.3390/axioms11040151 - 24 Mar 2022
Cited by 7 | Viewed by 2304
Abstract
Labor exports are currently considered among the most important foreign economic sectors, implying that they contribute to a country’s economic development and serve as a strategic solution for employment creation. Therefore, with the support of data collected between 1992 and 2020, this paper [...] Read more.
Labor exports are currently considered among the most important foreign economic sectors, implying that they contribute to a country’s economic development and serve as a strategic solution for employment creation. Therefore, with the support of data collected between 1992 and 2020, this paper proposes that labor exports contribute significantly to Vietnam’s socio-economic development. This study also aims to employ the Backpropagation Neural Network (BPNN), k-Nearest Neighbor (kNN), and Random Forest Regression (RFR) models to analyze labor migration forecasting in Taiwan, Korea, and Japan. The study results indicate that the BPNN model was able to achieve the highest accuracy regarding the actual labor exports. In terms of these accuracy metrics, this study will aid the Vietnamese government in establishing new legislation for Vietnamese migrant workers in order to improve the nation’s economic development. Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)
Show Figures

Figure 1

23 pages, 10385 KiB  
Article
Cubical Homology-Based Machine Learning: An Application in Image Classification
by Seungho Choe and Sheela Ramanna
Axioms 2022, 11(3), 112; https://doi.org/10.3390/axioms11030112 - 03 Mar 2022
Cited by 9 | Viewed by 3233
Abstract
Persistent homology is a powerful tool in topological data analysis (TDA) to compute, study, and encode efficiently multi-scale topological features and is being increasingly used in digital image classification. The topological features represent a number of connected components, cycles, and voids that describe [...] Read more.
Persistent homology is a powerful tool in topological data analysis (TDA) to compute, study, and encode efficiently multi-scale topological features and is being increasingly used in digital image classification. The topological features represent a number of connected components, cycles, and voids that describe the shape of data. Persistent homology extracts the birth and death of these topological features through a filtration process. The lifespan of these features can be represented using persistent diagrams (topological signatures). Cubical homology is a more efficient method for extracting topological features from a 2D image and uses a collection of cubes to compute the homology, which fits the digital image structure of grids. In this research, we propose a cubical homology-based algorithm for extracting topological features from 2D images to generate their topological signatures. Additionally, we propose a novel score measure, which measures the significance of each of the sub-simplices in terms of persistence. In addition, gray-level co-occurrence matrix (GLCM) and contrast limited adapting histogram equalization (CLAHE) are used as supplementary methods for extracting features. Supervised machine learning models are trained on selected image datasets to study the efficacy of the extracted topological features. Among the eight tested models with six published image datasets of varying pixel sizes, classes, and distributions, our experiments demonstrate that cubical homology-based machine learning with the deep residual network (ResNet 1D) and Light Gradient Boosting Machine (lightGBM) shows promise with the extracted topological features. Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)
Show Figures

Figure 1

14 pages, 2952 KiB  
Article
RainPredRNN: A New Approach for Precipitation Nowcasting with Weather Radar Echo Images Based on Deep Learning
by Do Ngoc Tuyen, Tran Manh Tuan, Xuan-Hien Le, Nguyen Thanh Tung, Tran Kim Chau, Pham Van Hai, Vassilis C. Gerogiannis and Le Hoang Son
Axioms 2022, 11(3), 107; https://doi.org/10.3390/axioms11030107 - 28 Feb 2022
Cited by 15 | Viewed by 4498
Abstract
Precipitation nowcasting is one of the main tasks of weather forecasting that aims to predict rainfall events accurately, even in low-rainfall regions. It has been observed that few studies have been devoted to predicting future radar echo images in a reasonable time using [...] Read more.
Precipitation nowcasting is one of the main tasks of weather forecasting that aims to predict rainfall events accurately, even in low-rainfall regions. It has been observed that few studies have been devoted to predicting future radar echo images in a reasonable time using the deep learning approach. In this paper, we propose a novel approach, RainPredRNN, which is the combination of the UNet segmentation model and the PredRNN_v2 deep learning model for precipitation nowcasting with weather radar echo images. By leveraging the abilities of the contracting-expansive path of the UNet model, the number of calculated operations of the RainPredRNN model is significantly reduced. This result consequently offers the benefit of reducing the processing time of the overall model while maintaining reasonable errors in the predicted images. In order to validate the proposed model, we performed experiments on real reflectivity fields collected from the Phadin weather radar station, located at Dien Bien province in Vietnam. Some credible quality metrics, such as the mean absolute error (MAE), the structural similarity index measure (SSIM), and the critical success index (CSI), were used for analyzing the performance of the model. It has been certified that the proposed model has produced improved performance, about 0.43, 0.95, and 0.94 of MAE, SSIM, and CSI, respectively, with only 30% of training time compared to the other methods. Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)
Show Figures

Figure 1

23 pages, 7025 KiB  
Article
Multicriteria Evaluation of Deep Neural Networks for Semantic Segmentation of Mammographies
by Yoshio Rubio and Oscar Montiel
Axioms 2021, 10(3), 180; https://doi.org/10.3390/axioms10030180 - 05 Aug 2021
Cited by 4 | Viewed by 2624
Abstract
Breast segmentation plays a vital role in the automatic analysis of mammograms. Accurate segmentation of the breast region increments the probability of a correct diagnostic and minimizes computational cost. Traditionally, model-based approaches dominated the landscape for breast segmentation, but recent studies seem to [...] Read more.
Breast segmentation plays a vital role in the automatic analysis of mammograms. Accurate segmentation of the breast region increments the probability of a correct diagnostic and minimizes computational cost. Traditionally, model-based approaches dominated the landscape for breast segmentation, but recent studies seem to benefit from using robust deep learning models for this task. In this work, we present an extensive evaluation of deep learning architectures for semantic segmentation of mammograms, including segmentation metrics, memory requirements, and average inference time. We used several combinations of two-stage segmentation architectures composed of a feature extraction net (VGG16 and ResNet50) and a segmentation net (FCN-8, U-Net, and PSPNet). The training examples were taken from the mini Mammographic Image Analysis Society (MIAS) database. Experimental results using the mini-MIAS database show that the best net scored a Dice similarity coefficient of 99.37% for breast boundary segmentation and 95.45% for pectoral muscle segmentation. Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)
Show Figures

Graphical abstract

24 pages, 3755 KiB  
Article
Optimization of Convolutional Neural Networks Architectures Using PSO for Sign Language Recognition
by Jonathan Fregoso, Claudia I. Gonzalez and Gabriela E. Martinez
Axioms 2021, 10(3), 139; https://doi.org/10.3390/axioms10030139 - 29 Jun 2021
Cited by 28 | Viewed by 4590
Abstract
This paper presents an approach to design convolutional neural network architectures, using the particle swarm optimization algorithm. The adjustment of the hyper-parameters and finding the optimal network architecture of convolutional neural networks represents an important challenge. Network performance and achieving efficient learning models [...] Read more.
This paper presents an approach to design convolutional neural network architectures, using the particle swarm optimization algorithm. The adjustment of the hyper-parameters and finding the optimal network architecture of convolutional neural networks represents an important challenge. Network performance and achieving efficient learning models for a particular problem depends on setting hyper-parameter values and this implies exploring a huge and complex search space. The use of heuristic-based searches supports these types of problems; therefore, the main contribution of this research work is to apply the PSO algorithm to find the optimal parameters of the convolutional neural networks which include the number of convolutional layers, the filter size used in the convolutional process, the number of convolutional filters, and the batch size. This work describes two optimization approaches; the first, the parameters obtained by PSO are kept under the same conditions in each convolutional layer, and the objective function evaluated by PSO is given by the classification rate; in the second, the PSO generates different parameters per layer, and the objective function is composed of the recognition rate in conjunction with the Akaike information criterion, the latter helps to find the best network performance but with the minimum parameters. The optimized architectures are implemented in three study cases of sign language databases, in which are included the Mexican Sign Language alphabet, the American Sign Language MNIST, and the American Sign Language alphabet. According to the results, the proposed methodologies achieved favorable results with a recognition rate higher than 99%, showing competitive results compared to other state-of-the-art approaches. Full article
(This article belongs to the Special Issue Various Deep Learning Algorithms in Computational Intelligence)
Show Figures

Figure 1

Back to TopTop