Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
4.7
2.9
Journals
Electronics
Special Issues
Research Progress of Machine Learning and Pattern Recognition Application
share announcement

Research Progress of Machine Learning and Pattern Recognition Application

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Computer Science & Engineering".

Deadline for manuscript submissions: closed (30 September 2023) | Viewed by 17710

Special Issue Editor

Dr. Qian Yin

E-Mail Website
Guest Editor
School of Artificial Intelligence, Beijing Normal University, Beijing 100875, China
Interests: Artificial Intelligence; image processing; pattern recognition

Special Issue Information

Dear Colleagues,

Pattern recognition and machine learning have been proven effective in many fields, which is reflected in the unprecedented increase in the number of algorithms and models around this discipline. The huge number of different machine learning methods allows for almost any new specific pattern recognition problem to be easily matched with a more appropriate machine learning approach. The accuracy and efficiency of many models are gradually catching up with or even surpassing work done by humans, giving this discipline a bright outlook.

Algorithms and models for machine learning and pattern recognition have a wide range of research possibilities. The real-world environment is usually open and dynamic and requires new robust pattern recognition models to have the ability to reject out-of-distribution and unknown samples. Additionally, there are still many new fields urgently needing more effective machine learning algorithms, ranging from robotic navigation systems, 3D object model reconstruction, interpretable models for NLP, and transformers in vision, to name but a few. A less-explored but promising research direction is using machine learning, including supervised, unsupervised, and reinforcement learning-based algorithms, to enhance system throughput and processing capabilities.

In this Special Issue, we look for new contributions, including theoretical issues and applications of the discipline. Topics of interest include all aspects of algorithms and models for machine learning and pattern recognition, including but not limited to the following detailed list:

  • Machine learning and data mining
  • Open world robust pattern recognition
  • Intelligent systems
  • Document and media analysis
  • Biometrics, human analysis, and behavior understanding
  • Signal processing for pattern recognition solutions
  • 2D/3D object detection and recognition
  • Image and video analysis and understanding
  • Machine learning for systems
  • Efficient model training, inference, and serving

Dr. Qian Yin
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. Electronics 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 and data mining
  • open world robust pattern recognition
  • intelligent systems
  • document and media analysis
  • biometrics, human analysis and behavior understanding
  • signal processing for pattern recognition solutions
  • 2D/3D object detection and recognition
  • image and video analysis and understanding
  • machine learning for systems
  • efficient model training, inference, and serving

Published Papers (10 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

23 pages, 636 KiB  
Article
Forecasting Significant Stock Market Price Changes Using Machine Learning: Extra Trees Classifier Leads
by Antonio Pagliaro
Electronics 2023, 12(21), 4551; https://doi.org/10.3390/electronics12214551 - 06 Nov 2023
Cited by 1 | Viewed by 1968
Abstract
Predicting stock market fluctuations is a difficult task due to its intricate and ever-changing nature. To address this challenge, we propose an approach to minimize forecasting errors by utilizing a classification-based technique, which is a widely used set of algorithms in the field [...] Read more.
Predicting stock market fluctuations is a difficult task due to its intricate and ever-changing nature. To address this challenge, we propose an approach to minimize forecasting errors by utilizing a classification-based technique, which is a widely used set of algorithms in the field of machine learning. Our study focuses on the potential effectiveness of this approach in improving stock market predictions. Specifically, we introduce a new method to predict stock returns using an Extra Trees Classifier. Technical indicators are used as inputs to train our model while the target is the percentage difference between the closing price and the closing price after 10 trading days for 120 companies from various industries. The 10-day time frame strikes a good balance between accuracy and practicality for traders, avoiding the low accuracy of short time frames and the impracticality of longer ones. The Extra Trees Classifier algorithm is ideal for stock market predictions because of its ability to handle large data sets with a high number of input features and improve model robustness by reducing overfitting. Our results show that our Extra Trees Classifier model outperforms the more traditional Random Forest method, achieving an accuracy of 86.1%. These findings suggest that our model can effectively predict significant price changes in the stock market with high precision. Overall, our study provides valuable insights into the potential of classification-based techniques in enhancing stock market predictions. Full article
(This article belongs to the Special Issue Research Progress of Machine Learning and Pattern Recognition Application)
►▼ Show Figures

Figure 1

12 pages, 2291 KiB  
Article
Research on Pattern Recognition Method for φ-OTDR System Based on Dendrite Net
by Xiaojuan Chen, Cheng Yang, Haoyu Yu and Guangwei Hou
Electronics 2023, 12(18), 3757; https://doi.org/10.3390/electronics12183757 - 06 Sep 2023
Viewed by 796
Abstract
The phase-sensitive optical time-domain reflectometer (φ-OTDR) is commonly used in various industries such as oil and gas pipelines, power communication networks, safety maintenance, and perimeter security. However, one challenge faced by the φ-OTDR system is low pattern recognition accuracy. To overcome this issue, [...] Read more.
The phase-sensitive optical time-domain reflectometer (φ-OTDR) is commonly used in various industries such as oil and gas pipelines, power communication networks, safety maintenance, and perimeter security. However, one challenge faced by the φ-OTDR system is low pattern recognition accuracy. To overcome this issue, a Dendrite Net (DD)-based pattern recognition method is proposed to differentiate the vibration signals detected by the φ-OTDR system, and normalize the differential signals with the original signals for feature extraction. These features serve as input for the pattern recognition task. To optimize the DD for the pattern recognition of the feature vectors, the Variable Three-Term Conjugate Gradient (VTTCG) is employed. The experimental results demonstrate the effectiveness of the proposed method. The classification accuracy achieved using this method is 98.6%, which represents a significant improvement compared to other techniques. Specifically, the proposed method outperforms the DD, Support Vector Machine (SVM), and Extreme Learning Machine (ELM) by 7.5%, 8.6%, and 1.5% respectively. The findings of this research paper indicate that the pattern recognition method based on DD and optimized using the VTTCG can greatly enhance the accuracy of the φ-OTDR system. This improvement has important implications for various applications in industries such as pipeline monitoring, power communication networks, safety maintenance, and perimeter security. Full article
(This article belongs to the Special Issue Research Progress of Machine Learning and Pattern Recognition Application)
►▼ Show Figures

Figure 1

23 pages, 5380 KiB  
Article
SoftVein-WELM: A Weighted Extreme Learning Machine Model for Soft Biometrics on Palm Vein Images
by David Zabala-Blanco, Ruber Hernández-García and Ricardo J. Barrientos
Electronics 2023, 12(17), 3608; https://doi.org/10.3390/electronics12173608 - 26 Aug 2023
Viewed by 806
Abstract
Contactless biometric technologies such as palm vein recognition have gained more relevance in the present and immediate future due to the COVID-19 pandemic. Since certain soft biometrics like gender and age can generate variations in the visualization of palm vein patterns, these soft [...] Read more.
Contactless biometric technologies such as palm vein recognition have gained more relevance in the present and immediate future due to the COVID-19 pandemic. Since certain soft biometrics like gender and age can generate variations in the visualization of palm vein patterns, these soft traits can reduce the penetration rate on large-scale databases for mass individual recognition. Due to the limited availability of public databases, few works report on the existing approaches to gender and age classification through vein pattern images. Moreover, soft biometric classification commonly faces the problem of imbalanced data class distributions, representing a limitation of the reported approaches. This paper introduces weighted extreme learning machine (W-ELM) models for gender and age classification based on palm vein images to address imbalanced data problems, improving the classification performance. The highlights of our proposal are that it avoids using a feature extraction process and can incorporate a weight matrix in optimizing the ELM model by exploiting the imbalanced nature of the data, which guarantees its application in realistic scenarios. In addition, we evaluate a new class distribution for soft biometrics on the VERA dataset and a new multi-label scheme identifying gender and age simultaneously. The experimental results demonstrate that both evaluated W-ELM models outperform previous existing approaches and a novel CNN-based method in terms of the accuracy and G-mean metrics, achieving accuracies of 98.91% and 99.53% for gender classification on VERA and PolyU, respectively. In more challenging scenarios for age and gender–age classifications on the VERA dataset, the proposed method reaches accuracies of 97.05% and 96.91%, respectively. The multi-label classification results suggest that further studies can be conducted on multi-task ELM for palm vein recognition. Full article
(This article belongs to the Special Issue Research Progress of Machine Learning and Pattern Recognition Application)
►▼ Show Figures

Figure 1

14 pages, 2945 KiB  
Article
Semi-Supervised Active Learning for Object Detection
by Sijin Chen, Yingyun Yang and Yan Hua
Electronics 2023, 12(2), 375; https://doi.org/10.3390/electronics12020375 - 11 Jan 2023
Cited by 1 | Viewed by 2454
Abstract
Behind the rapid development of deep learning methods, massive data annotations are indispensable yet quite expensive. Many active learning (AL) and semi-supervised learning (SSL) methods have been proposed to address this problem in image classification tasks. However, these methods face a new challenge [...] Read more.
Behind the rapid development of deep learning methods, massive data annotations are indispensable yet quite expensive. Many active learning (AL) and semi-supervised learning (SSL) methods have been proposed to address this problem in image classification tasks. However, these methods face a new challenge in object detection tasks, since object detection requires classification as well as localization information in the labeling process. Therefore, in this paper, an object detection framework combining active learning and semi-supervised learning is presented. Tailored for object detection tasks, the uncertainty of an unlabeled image is measured from two perspectives, namely classification stability and localization stability. The unlabeled images with low uncertainty are manually annotated as the AL part, and those with high uncertainty are pseudo-labeled with the detector’s prediction results as the SSL part. Furthermore, to better filter out the noisy pseudo-boxes brought by SSL, a novel pseudo-label mining strategy is proposed that includes a stability aggregation score (SAS) and dynamic adaptive threshold (DAT). The SAS aggregates the classification and localization stability scores to measure the quality of predicted boxes, while the DAT adaptively adjusts the thresholds for each category to alleviate the class imbalance problem. Extensive experimental results demonstrate that our proposed method significantly outperforms state-of-the-art AL and SSL methods. Full article
(This article belongs to the Special Issue Research Progress of Machine Learning and Pattern Recognition Application)
►▼ Show Figures

Figure 1

12 pages, 2423 KiB  
Article
CSU-Net: A CNN-Transformer Parallel Network for Multimodal Brain Tumour Segmentation
by Yu Chen, Ming Yin, Yu Li and Qian Cai
Electronics 2022, 11(14), 2226; https://doi.org/10.3390/electronics11142226 - 16 Jul 2022
Cited by 11 | Viewed by 2611
Abstract
Medical image segmentation techniques are vital to medical image processing and analysis. Considering the significant clinical applications of brain tumour image segmentation, it represents a focal point of medical image segmentation research. Most of the work in recent times has been centred on [...] Read more.
Medical image segmentation techniques are vital to medical image processing and analysis. Considering the significant clinical applications of brain tumour image segmentation, it represents a focal point of medical image segmentation research. Most of the work in recent times has been centred on Convolutional Neural Networks (CNN) and Transformers. However, CNN has some deficiencies in modelling long-distance information transfer and contextual processing information, while Transformer is relatively weak in acquiring local information. To overcome the above defects, we propose a novel segmentation network with an “encoder–decoder” architecture, namely CSU-Net. The encoder consists of two parallel feature extraction branches based on CNN and Transformer, respectively, in which the features of the same size are fused. The decoder has a dual Swin Transformer decoder block with two learnable parameters for feature upsampling. The features from multiple resolutions in the encoder and decoder are merged via skip connections. On the BraTS 2020, our model achieves 0.8927, 0.8857, and 0.8188 for the Whole Tumour (WT), Tumour Core (TC), and Enhancing Tumour (ET), respectively, in terms of Dice scores. Full article
(This article belongs to the Special Issue Research Progress of Machine Learning and Pattern Recognition Application)
►▼ Show Figures

Figure 1

11 pages, 1579 KiB  
Article
Pulsar Candidate Recognition Using Deep Neural Network Model
by Qian Yin, Yan Wang, Xin Zheng and Jikai Zhang
Electronics 2022, 11(14), 2216; https://doi.org/10.3390/electronics11142216 - 15 Jul 2022
Cited by 1 | Viewed by 1219
Abstract
With an improvement in the performance of radio telescopes, the number of pulsar candidates has increased rapidly, which makes selecting valuable pulsar signals from the candidates challenging. It is imperative to improve the recognition efficiency of pulsars. Therefore, we solved this problem from [...] Read more.
With an improvement in the performance of radio telescopes, the number of pulsar candidates has increased rapidly, which makes selecting valuable pulsar signals from the candidates challenging. It is imperative to improve the recognition efficiency of pulsars. Therefore, we solved this problem from the perspective of intelligent image processing and a deep neural network model AR_Net was proposed in this paper. A single time–phase-subgraph or frequency-phase-subgraph was used as the judgment basis in the recognition model. The convolution blocks can be obtained by combining the attention mechanism module, feature extractor and residual connection. Then, different convolution blocks were superimposed to constitute the AR_Net to screen pulsars. The attention mechanism module was used to calculate the weight through an additional feedforward neural network and the important features in the sample were identified by weight, so the ability of the model to learn pivotal information was improved. The feature extractor was used to gain the high-dimensional features in the samples and the residual connection was introduced to alleviate the problem of network degradation and intensify feature reuse. The experimental results show that AR_Net has higher F1-score, recall and accuracy, and our method produces a competitive result compared with previous methods. Full article
(This article belongs to the Special Issue Research Progress of Machine Learning and Pattern Recognition Application)
►▼ Show Figures

Figure 1

19 pages, 4224 KiB  
Article
Extracting Prominent Aspects of Online Customer Reviews: A Data-Driven Approach to Big Data Analytics
by Noaman M. Ali, Abdullah Alshahrani, Ahmed M. Alghamdi and Boris Novikov
Electronics 2022, 11(13), 2042; https://doi.org/10.3390/electronics11132042 - 29 Jun 2022
Cited by 2 | Viewed by 1452
Abstract
Sentiment analysis on social media and e-markets has become an emerging trend. Extracting aspect terms for structure-free text is the primary task incorporated in the aspect-based sentiment analysis. This significance relies on the dependency of other tasks on the results it provides, which [...] Read more.
Sentiment analysis on social media and e-markets has become an emerging trend. Extracting aspect terms for structure-free text is the primary task incorporated in the aspect-based sentiment analysis. This significance relies on the dependency of other tasks on the results it provides, which directly influences the accuracy of the final results of the sentiment analysis. In this work, we propose an aspect term extraction model to identify the prominent aspects. The model is based on clustering the word vectors generated using the pre-trained word embedding model. Dimensionality reduction was employed to improve the quality of word clusters obtained using the K-Means++ clustering algorithm. The proposed model was tested on the real datasets collected from online retailers’ websites and the SemEval-14 dataset. Results show that our model outperforms the baseline models. Full article
(This article belongs to the Special Issue Research Progress of Machine Learning and Pattern Recognition Application)
►▼ Show Figures

Figure 1

16 pages, 15603 KiB  
Article
Multiple Frequency Inputs and Context-Guided Attention Network for Stereo Disparity Estimation
by Yan Hua, Lin Yang and Yingyun Yang
Electronics 2022, 11(12), 1803; https://doi.org/10.3390/electronics11121803 - 07 Jun 2022
Cited by 1 | Viewed by 1417
Abstract
Deep learning-based methods have made remarkable progress for stereo matching in terms of accuracy. However, two issues still hinder producing a perfect disparity map: (1) blurred boundaries and the discontinuous disparity of a continuous region on disparity estimation maps, and (2) a lack [...] Read more.
Deep learning-based methods have made remarkable progress for stereo matching in terms of accuracy. However, two issues still hinder producing a perfect disparity map: (1) blurred boundaries and the discontinuous disparity of a continuous region on disparity estimation maps, and (2) a lack of effective means to restore resolution precisely. In this paper, we propose to utilize multiple frequency inputs and an attention mechanism to construct the deep stereo matching model. Specifically, high-frequency and low-frequency information of the input image together with the RGB image are fed into a feature extraction network with 2D convolutions. It is conducive to produce a distinct boundary and continuous disparity of the smooth region on disparity maps. To regularize the 4D cost volume for disparity regression, we propose a 3D context-guided attention module for stacked hourglass networks, where high-level cost volumes as context guide low-level features to obtain high-resolution yet precise feature maps. The proposed approach achieves competitive performance on SceneFlow and KITTI 2015 datasets. Full article
(This article belongs to the Special Issue Research Progress of Machine Learning and Pattern Recognition Application)
►▼ Show Figures

Figure 1

12 pages, 1529 KiB  
Article
A Novel Un-Supervised GAN for Fundus Image Enhancement with Classification Prior Loss
by Shizhao Chen, Qian Zhou and Hua Zou
Electronics 2022, 11(7), 1000; https://doi.org/10.3390/electronics11071000 - 24 Mar 2022
Cited by 2 | Viewed by 2041
Abstract
Fundus images captured for clinical diagnosis usually suffer from degradation factors due to variation in equipment, operators, or environment. These degraded fundus images need to be enhanced to achieve better diagnosis and improve the results of downstream tasks. As there is no paired [...] Read more.
Fundus images captured for clinical diagnosis usually suffer from degradation factors due to variation in equipment, operators, or environment. These degraded fundus images need to be enhanced to achieve better diagnosis and improve the results of downstream tasks. As there is no paired low- and high-quality fundus image, existing methods mainly focus on supervised or semi-supervised learning methods for color fundus image enhancement (CFIE) tasks by utilizing synthetic image pairs. Consequently, domain gaps between real images and synthetic images arise. With respect to existing unsupervised methods, the most important low scale pathological features and structural information in degraded fundus images are prone to be erased after enhancement. To solve these problems, an unsupervised GAN is proposed for CFIE tasks utilizing adversarial training to enhance low quality fundus images. Synthetic image pairs are no longer required during the training. A specially designed U-Net with skip connection in our enhancement network can effectively remove degradation factors while preserving pathological features and structural information. Global and local discriminators adopted in the GAN lead to better illumination uniformity in the enhanced fundus image. To better improve the visual quality of enhanced fundus images, a novel non-reference loss function based on a pretrained fundus image quality classification network was designed to guide the enhancement network to produce high quality images. Experiments demonstrated that our method could effectively remove degradation factors in low-quality fundus images and produce a competitive result compared with previous methods in both quantitative and qualitative metrics. Full article
(This article belongs to the Special Issue Research Progress of Machine Learning and Pattern Recognition Application)
►▼ Show Figures

Figure 1

16 pages, 5779 KiB  
Article
Tobacco Spatial Data Intelligent Visual Analysis
by Bo Yang, Dong Tian and Guihua Shan
Electronics 2022, 11(7), 995; https://doi.org/10.3390/electronics11070995 - 23 Mar 2022
Cited by 1 | Viewed by 1606
Abstract
A multi-module visualization framework is designed and a visual analysis system called TobaccoGeoVis is implemented to analyze tobacco spatial data efficiently. The proposed system provides a visualization technology for overlaying multiple graphics on a map to enrich the form of tobacco spatial data [...] Read more.
A multi-module visualization framework is designed and a visual analysis system called TobaccoGeoVis is implemented to analyze tobacco spatial data efficiently. The proposed system provides a visualization technology for overlaying multiple graphics on a map to enrich the form of tobacco spatial data visualization. The system also adopts artificial intelligence algorithms and multi-view linkage interactive methods and provides flexible data-attribute field mapping and graphical parameter configuration to analyze tobacco spatial data. We demonstrated that the system is user-friendly and the applied visualization methods are effective using cases selected from the three sets of data. Full article
(This article belongs to the Special Issue Research Progress of Machine Learning and Pattern Recognition Application)
►▼ Show Figures

Figure 1

Show export options expand_more Show export options expand_less
Select all
Export citation of selected articles as:
 
Displaying articles 1-10
Back to TopTop