Applications of Artificial Intelligence, Machine Learning, Deep Learning, and Explainable AI (XAI)

A special issue of Electronics (ISSN 2079-9292). This special issue belongs to the section "Artificial Intelligence".

Deadline for manuscript submissions: closed (15 January 2025) | Viewed by 32351

Special Issue Editors


E-Mail Website
Guest Editor
School of Computing, Engineering & Intelligent Systems, Ulster University, Coleraine BT52 1SA, UK
Interests: computer vision; machine learning; deep learning; medical imaging; explainable AI (XAI)

E-Mail Website
Guest Editor
School of Information and Data Sciences, Nagasaki University, Nagasaki City 852-8521, Japan
Interests: image processing; machine learning; neural network algorithms

E-Mail Website
Guest Editor
Faculty of Engineering, Misr International University, Cairo 11828, Egypt
Interests: medical image & signal processing; affective computing; machine & deep learning; explainable AI (XAI)

E-Mail Website
Guest Editor
School of Computer Science and Engineering, Vellore Institute of Technology, Chennai 632014, India
Interests: deep learning; computer vision; image processing; Artificial Intelligence

Special Issue Information

Dear Colleagues,

Artificial intelligence (AI) with machine learning and deep learning models has been widely applied in numerous domains, including medical imaging, healthcare, industrial manufacturing, sports, and many more. In recent years, many efforts have been made to improve the interpretability of the decisions of machine learning and deep learning algorithms. Explainable Artificial Intelligence (XAI) has been established as a new research area, which aims to provide new methodologies and algorithms to enhance transparency and reliability to both the decisions made by predictive algorithms and the contributions and importance of individual features to the outcome.

The purpose of this Special Issue is to report on the advances in state-of-the-art research on artificial intelligence machine learning, deep learning, and explainable AI applications. The advances in the state-of-the-art for addressing real-world AI applications are of great interest.

The research domains may involve (but are not limited to):

  • Medical Image and Signal Processing
  • Uncertainty detection, Synthesis, and registration of Images
  • Detection from noisy labels and limited data
  • Semi-supervised/Self-supervised detection
  • Affective Computing
  • Computer vision based Intelligent applications
  • Intelligent Applications using Augmented and Virtual Reality
  • Healthcare Intelligence
  • Advanced security using AI
  • AI-enabled decision support systems
  • Image processing applications
  • XAI methods for Deep Learning (e.g., medical domain, industrial applications, security, surveillance)
  • Multimodal XAI approaches

Dr. Pratheepan Yogarajah
Dr. Muthu Subash Kavitha
Dr. Lamiaa Abdel-Hamid
Dr. Ananthakrishnan Balasundaram
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. 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

  • medical Image and Signal Processing
  • uncertainty detection, Synthesis, and registration of Images
  • detection from noisy labels and limited data
  • semi-supervised/Self-supervised detection
  • affective Computing
  • computer vision based Intelligent applications
  • intelligent Applications using Augmented and Virtual Reality
  • healthcare Intelligence
  • advanced security using AI
  • AI-enabled decision support systems
  • image processing applications
  • XAI methods for Deep Learning (e.g., medical domain, industrial applications, security, surveillance)
  • multimodal XAI approaches

Benefits of Publishing in a Special Issue

  • Ease of navigation: Grouping papers by topic helps scholars navigate broad scope journals more efficiently.
  • Greater discoverability: Special Issues support the reach and impact of scientific research. Articles in Special Issues are more discoverable and cited more frequently.
  • Expansion of research network: Special Issues facilitate connections among authors, fostering scientific collaborations.
  • External promotion: Articles in Special Issues are often promoted through the journal's social media, increasing their visibility.
  • e-Book format: Special Issues with more than 10 articles can be published as dedicated e-books, ensuring wide and rapid dissemination.

Further information on MDPI's Special Issue policies can be found here.

Published Papers (15 papers)

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

Research

Jump to: Review

25 pages, 11090 KiB  
Article
Analysis of Molding Defection in IC Packaging and Testing Process
by Bao Rong Chang, Hsiu-Fen Tsai and Chen-Chia Chen
Electronics 2024, 13(22), 4356; https://doi.org/10.3390/electronics13224356 - 6 Nov 2024
Viewed by 1026
Abstract
Molding injects a molding compound into a mold to form a protective shell around the wafer. During the injection process, overflow may occur, leading to mold flash, which reduces yield and causes significant manufacturing cost losses. This paper proposes a deep-learning-based method for [...] Read more.
Molding injects a molding compound into a mold to form a protective shell around the wafer. During the injection process, overflow may occur, leading to mold flash, which reduces yield and causes significant manufacturing cost losses. This paper proposes a deep-learning-based method for detecting and predicting the occurrence of mold flash probability to address this issue. First, the paper conducts random forest importance analysis and correlation analysis to identify the key parameters that significantly impact mold flash. This paper uses these key parameters as input signals for the prediction model. The paper introduces an HLGA Transformer to construct an ensemble meta-learning model that predicts the probability of molding defects, achieving a prediction accuracy of 98.16%. The ensemble meta-learning approach proposed in this paper outperforms other methods in terms of performance. The model predictions can be communicated to the system in real time, allowing it to promptly adjust critical machine operation parameters, thereby significantly improving the molding process yield and reducing substantial manufacturing cost losses. Full article
Show Figures

Figure 1

26 pages, 10202 KiB  
Article
Detection and Prediction of Probe Mark Damage in Wafer Testing
by Bao Rong Chang, Hsiu-Fen Tsai and Yi-Ru Wu
Electronics 2024, 13(20), 4075; https://doi.org/10.3390/electronics13204075 - 16 Oct 2024
Viewed by 997
Abstract
In wafer testing, the test probe needs to contact the surface of the semiconductor wafer to measure electrical parameters such as resistance, capacitance, and current. The probe mark damage frequently occurs on the machine during wafer testing. This phenomenon causes inaccuracies in electrical [...] Read more.
In wafer testing, the test probe needs to contact the surface of the semiconductor wafer to measure electrical parameters such as resistance, capacitance, and current. The probe mark damage frequently occurs on the machine during wafer testing. This phenomenon causes inaccuracies in electrical parameter testing, significantly reducing the yield in IC packaging processes and resulting in substantial manufacturing cost losses. Therefore, this study proposed an effective probe mark damage detection and prediction method to prevent significant yield reduction due to inaccurate testing. This study uses importance analysis from random forests and correlation analysis to identify the critical parameters influencing probe mark damage. Introducing these parameters into a Sparse Transformer with hybrid normalization can successfully train an intelligent model for predicting the occurrence of probe mark damage. The model accurately predicts the probability of probe mark damage and promptly adjusts machine parameters to avoid inaccuracies in electrical parameter settings. The proposed approach can outperform other methods, achieving two very high accuracies of 95.1% (at room temperature) and 93.5% (at high temperature) and significantly reducing the occurrence of large-area probe mark damage. Full article
Show Figures

Figure 1

22 pages, 3493 KiB  
Article
Few-Shot Learning Based on Dimensionally Enhanced Attention and Logit Standardization Self-Distillation
by Yuhong Tang, Guang Li, Ming Zhang and Jianjun Li
Electronics 2024, 13(15), 2928; https://doi.org/10.3390/electronics13152928 - 24 Jul 2024
Viewed by 992
Abstract
Few-shot learning (FSL) is a challenging problem. Transfer learning methods offer a straightforward and effective solution to FSL by leveraging pre-trained models and generalizing them to new tasks. However, pre-trained models often lack the ability to highlight and emphasize salient features, a gap [...] Read more.
Few-shot learning (FSL) is a challenging problem. Transfer learning methods offer a straightforward and effective solution to FSL by leveraging pre-trained models and generalizing them to new tasks. However, pre-trained models often lack the ability to highlight and emphasize salient features, a gap that attention mechanisms can fill. Unfortunately, existing attention mechanisms encounter issues such as high complexity and incomplete attention information. To address these issues, we propose a dimensionally enhanced attention (DEA) module for FSL. This DEA module introduces minimal additional computational overhead while fully attending to both channel and spatial information. Specifically, the feature map is first decomposed into 1D tensors of varying dimensions using strip pooling. Next, a multi-dimensional collaborative learning strategy is introduced, enabling cross-dimensional information interactions through 1D convolutions with adaptive kernel sizes. Finally, the feature representation is enhanced by calculating attention weights for each dimension using a sigmoid function and weighting the original input accordingly. This approach ensures comprehensive attention to different dimensions of information, effectively characterizing data in various directions. Additionally, we have found that knowledge distillation significantly improves FSL performance. To this end, we implement a logit standardization self-distillation method tailored for FSL. This method addresses the issue of exact logit matching, which arises from the shared temperature in the self-distillation process, by employing logit standardization. We present experimental results on several benchmark datasets where the proposed method yields significant performance improvements. Full article
Show Figures

Graphical abstract

22 pages, 9100 KiB  
Article
Benchmarking Time-Frequency Representations of Phonocardiogram Signals for Classification of Valvular Heart Diseases Using Deep Features and Machine Learning
by Edwin M. Chambi, Jefry Cuela, Milagros Zegarra, Erasmo Sulla and Jorge Rendulich
Electronics 2024, 13(15), 2912; https://doi.org/10.3390/electronics13152912 - 24 Jul 2024
Cited by 1 | Viewed by 1428
Abstract
Heart sounds and murmur provide crucial diagnosis information for valvular heart diseases (VHD). A phonocardiogram (PCG) combined with modern digital processing techniques provides a complementary tool for clinicians. This article proposes a benchmark different time–frequency representations, which are spectograms, mel-spectograms and cochleagrams for [...] Read more.
Heart sounds and murmur provide crucial diagnosis information for valvular heart diseases (VHD). A phonocardiogram (PCG) combined with modern digital processing techniques provides a complementary tool for clinicians. This article proposes a benchmark different time–frequency representations, which are spectograms, mel-spectograms and cochleagrams for obtaining images, in addition to the use of two interpolation techniques to improve the quality of the images, which are bicubic and Lanczos. Deep features are extracted from a pretrained model called VGG16, and for feature reduction, the Boruta algorithm is applied. To evaluate the models and obtain more precise results, nested cross-validation is used. The best results achieved in this study were for the cochleagram with 99.2% accuracy and mel-spectogram representation with the bicubic interpolation technique, which reached 99.4% accuracy, both having a support vector machine (SVM) as a classifier algorithm. Overall, this study highlights the potential of time–frequency representations of PCG signals combined with modern digital processing techniques and machine learning algorithms for accurate diagnosis of VHD. Full article
Show Figures

Figure 1

21 pages, 1914 KiB  
Article
An Approach to Deepfake Video Detection Based on ACO-PSO Features and Deep Learning
by Hanan Saleh Alhaji, Yuksel Celik and Sanjay Goel
Electronics 2024, 13(12), 2398; https://doi.org/10.3390/electronics13122398 - 19 Jun 2024
Cited by 6 | Viewed by 2737
Abstract
The rapid advancement of deepfake technology presents significant challenges in detecting highly convincing fake videos, posing risks such as misinformation, identity theft, and privacy violations. In response, this paper proposes an innovative approach to deepfake video detection by integrating features derived from ant [...] Read more.
The rapid advancement of deepfake technology presents significant challenges in detecting highly convincing fake videos, posing risks such as misinformation, identity theft, and privacy violations. In response, this paper proposes an innovative approach to deepfake video detection by integrating features derived from ant colony optimization–particle swarm optimization (ACO-PSO) and deep learning techniques. The proposed methodology leverages ACO-PSO features and deep learning models to enhance detection accuracy and robustness. Features from ACO-PSO are extracted from the spatial and temporal characteristics of video frames, capturing subtle patterns indicative of deepfake manipulation. These features are then used to train a deep learning classifier to automatically distinguish between authentic and deepfake videos. Extensive experiments using comparative datasets demonstrate the superiority of the proposed method in terms of detection accuracy, robustness to manipulation techniques, and generalization to unseen data. The computational efficiency of the approach is also analyzed, highlighting its practical feasibility for real-time applications. The findings revealed that the proposed method achieved an accuracy of 98.91% and an F1 score of 99.12%, indicating remarkable success in deepfake detection. The integration of ACO-PSO features and deep learning enables comprehensive analysis, bolstering precision and resilience in detecting deepfake content. This approach addresses the challenges involved in facial forgery detection and contributes to safeguarding digital media integrity amid misinformation and manipulation. Full article
Show Figures

Figure 1

14 pages, 4239 KiB  
Article
Design and Evaluation of CPU-, GPU-, and FPGA-Based Deployment of a CNN for Motor Imagery Classification in Brain-Computer Interfaces
by Federico Pacini, Tommaso Pacini, Giuseppe Lai, Alessandro Michele Zocco and Luca Fanucci
Electronics 2024, 13(9), 1646; https://doi.org/10.3390/electronics13091646 - 25 Apr 2024
Cited by 3 | Viewed by 2149
Abstract
Brain–computer interfaces (BCIs) have gained popularity in recent years. Among noninvasive BCIs, EEG-based systems stand out as the primary approach, utilizing the motor imagery (MI) paradigm to discern movement intentions. Initially, BCIs were predominantly focused on nonembedded systems. However, there is now a [...] Read more.
Brain–computer interfaces (BCIs) have gained popularity in recent years. Among noninvasive BCIs, EEG-based systems stand out as the primary approach, utilizing the motor imagery (MI) paradigm to discern movement intentions. Initially, BCIs were predominantly focused on nonembedded systems. However, there is now a growing momentum towards shifting computation to the edge, offering advantages such as enhanced privacy, reduced transmission bandwidth, and real-time responsiveness. Despite this trend, achieving the desired target remains a work in progress. To illustrate the feasibility of this shift and quantify the potential benefits, this paper presents a comparison of deploying a CNN for MI classification across different computing platforms, namely, CPU-, embedded GPU-, and FPGA-based. For our case study, we utilized data from 29 participants included in a dataset acquired using an EEG cap for training the models. The FPGA solution emerged as the most efficient in terms of the power consumption–inference time product. Specifically, it delivers an impressive reduction of up to 89% in power consumption compared to the CPU and 71% compared to the GPU and up to a 98% reduction in memory footprint for model inference, albeit at the cost of a 39% increase in inference time compared to the GPU. Both the embedded GPU and FPGA outperform the CPU in terms of inference time. Full article
Show Figures

Figure 1

30 pages, 17457 KiB  
Article
Melanoma Skin Cancer Identification with Explainability Utilizing Mask Guided Technique
by Lahiru Gamage, Uditha Isuranga, Dulani Meedeniya, Senuri De Silva and Pratheepan Yogarajah
Electronics 2024, 13(4), 680; https://doi.org/10.3390/electronics13040680 - 6 Feb 2024
Cited by 15 | Viewed by 3092
Abstract
Melanoma is a highly prevalent and lethal form of skin cancer, which has a significant impact globally. The chances of recovery for melanoma patients substantially improve with early detection. Currently, deep learning (DL) methods are gaining popularity in assisting with the identification of [...] Read more.
Melanoma is a highly prevalent and lethal form of skin cancer, which has a significant impact globally. The chances of recovery for melanoma patients substantially improve with early detection. Currently, deep learning (DL) methods are gaining popularity in assisting with the identification of diseases using medical imaging. The paper introduces a computational model for classifying melanoma skin cancer images using convolutional neural networks (CNNs) and vision transformers (ViT) with the HAM10000 dataset. Both approaches utilize mask-guided techniques, employing a specialized U2-Net segmentation module to generate masks. The CNN-based approach utilizes ResNet50, VGG16, and Xception with transfer learning. The training process is enhanced using a Bayesian hyperparameter tuner. Moreover, this study applies gradient-weighted class activation mapping (Grad-CAM) and Grad-CAM++ to generate heatmaps to explain the classification models. These visual heatmaps elucidate the contribution of each input region to the classification outcome. The CNN-based model approach achieved the highest accuracy at 98.37% in the Xception model with a sensitivity and specificity of 95.92% and 99.01%, respectively. The ViT-based model approach achieved high values for accuracy, sensitivity, and specificity, such as 92.79%, 91.09%, and 93.54%, respectively. Furthermore, the performance of the model was assessed through intersection over union (IOU) and other qualitative evaluations. Finally, we developed the proposed model as a web application that can be used as a support tool for medical practitioners in real-time. The system usability study score of 86.87% is reported, which shows the usefulness of the proposed solution. Full article
Show Figures

Figure 1

20 pages, 1873 KiB  
Article
Entity Matching by Pool-Based Active Learning
by Youfang Han and Chunping Li
Electronics 2024, 13(3), 559; https://doi.org/10.3390/electronics13030559 - 30 Jan 2024
Cited by 2 | Viewed by 1236
Abstract
The goal of entity matching is to find the corresponding records representing the same entity from different data sources. At present, in the mainstream methods, rule-based entity matching methods need tremendous domain knowledge. Machine-learning-based or deep-learning-based entity matching methods need a large number [...] Read more.
The goal of entity matching is to find the corresponding records representing the same entity from different data sources. At present, in the mainstream methods, rule-based entity matching methods need tremendous domain knowledge. Machine-learning-based or deep-learning-based entity matching methods need a large number of labeled samples to build the model, which is difficult to achieve in some applications. In addition, learning-based methods are more likely to overfit, so the quality requirements of training samples are very high. In this paper, we present an active learning method for entity matching tasks. This method needs to manually label only a small number of valuable samples, and use these labeled samples to build a model with high quality. This paper proposes hybrid uncertainty as a query strategy to find those valuable samples for labeling, which can minimize the number of labeled training samples and at the same time meet the requirements of entity matching tasks. The proposed method is validated on seven data sets in different fields. The experiments show that the proposed method uses only a small number of labeled samples and achieves better effects compared to current existing approaches. Full article
Show Figures

Figure 1

16 pages, 2408 KiB  
Article
Random Convolutional Kernels for Space-Detector Based Gravitational Wave Signals
by Ruben Poghosyan and Yuan Luo
Electronics 2023, 12(20), 4360; https://doi.org/10.3390/electronics12204360 - 20 Oct 2023
Viewed by 1985
Abstract
Neural network models have entered the realm of gravitational wave detection, proving their effectiveness in identifying synthetic gravitational waves. However, these models rely on learned parameters, which necessitates time-consuming computations and expensive hardware resources. To address this challenge, we propose a gravitational wave [...] Read more.
Neural network models have entered the realm of gravitational wave detection, proving their effectiveness in identifying synthetic gravitational waves. However, these models rely on learned parameters, which necessitates time-consuming computations and expensive hardware resources. To address this challenge, we propose a gravitational wave detection model tailored specifically for binary black hole mergers, inspired by the Random Convolutional Kernel Transform (ROCKET) family of models. We conduct a rigorous analysis by factoring in realistic signal-to-noise ratios in our datasets, demonstrating that conventional techniques lose predictive accuracy when applied to ground-based detector signals. In contrast, for space-based detectors with high signal-to-noise ratios, our method not only detects signals effectively but also enhances inference speed due to its streamlined complexity—a notable achievement. Compared to previous gravitational wave models, we observe a significant acceleration in training time while maintaining acceptable performance metrics for ground-based detector signals and achieving equal or even superior metrics for space-based detector signals. Our experiments on synthetic data yield impressive results, with the model achieving an AUC score of 96.1% and a perfect recall rate of 100% on a dataset with a 1:3 class imbalance for ground-based detectors. For high signal-to-noise ratio signals, we achieve flawless precision and recall of 100% without losing precision on datasets with low-class ratios. Additionally, our approach reduces inference time by a factor of 1.88. Full article
Show Figures

Figure 1

22 pages, 5485 KiB  
Article
A Hierarchical Resource Scheduling Method for Satellite Control System Based on Deep Reinforcement Learning
by Yang Li, Xiye Guo, Zhijun Meng, Junxiang Qin, Xuan Li, Xiaotian Ma, Sichuang Ren and Jun Yang
Electronics 2023, 12(19), 3991; https://doi.org/10.3390/electronics12193991 - 22 Sep 2023
Cited by 4 | Viewed by 1971
Abstract
Space-based systems providing remote sensing, communication, and navigation services are essential to the economy and national defense. Users’ demand for satellites has increased sharply in recent years, but resources such as storage, energy, and computation are limited. Therefore, an efficient resource scheduling strategy [...] Read more.
Space-based systems providing remote sensing, communication, and navigation services are essential to the economy and national defense. Users’ demand for satellites has increased sharply in recent years, but resources such as storage, energy, and computation are limited. Therefore, an efficient resource scheduling strategy is urgently needed to satisfy users’ demands maximally and get high task execution benefits. A hierarchical scheduling method is proposed in this work, which combines improved ant colony optimization and an improved deep Q network. The proposed method considers the quality of current task execution and resource load balance. The entire resource scheduling process contains two steps, task allocation and resource scheduling in the timeline. The former mainly implements load balance by improved ant colony optimization, while the latter mainly accomplishes the high task completion rate by an improved deep Q network. Compared with several other heuristic algorithms, the proposed approach is proven to have advantages in terms of CPU runtime, task completion rate, and resource variance between satellites. In the simulation scenarios, the proposed method can achieve up to 97.3% task completion rate, with almost 50% of the CPU runtime required by HAW and HADRT. Furthermore, this method has successfully implemented load balance. Full article
Show Figures

Figure 1

12 pages, 9865 KiB  
Article
Evo-MAML: Meta-Learning with Evolving Gradient
by Jiaxing Chen, Weilin Yuan, Shaofei Chen, Zhenzhen Hu and Peng Li
Electronics 2023, 12(18), 3865; https://doi.org/10.3390/electronics12183865 - 13 Sep 2023
Cited by 7 | Viewed by 2408
Abstract
How to rapidly adapt to new tasks and improve model generalization through few-shot learning remains a significant challenge in meta-learning. Model-Agnostic Meta-Learning (MAML) has become a powerful approach, with offers a simple framework with excellent generality. However, the requirement to compute second-order derivatives [...] Read more.
How to rapidly adapt to new tasks and improve model generalization through few-shot learning remains a significant challenge in meta-learning. Model-Agnostic Meta-Learning (MAML) has become a powerful approach, with offers a simple framework with excellent generality. However, the requirement to compute second-order derivatives and retain a lengthy calculation graph poses considerable computational and memory burdens, limiting the practicality of MAML. To address this issue, we propose Evolving MAML (Evo-MAML), an optimization-based meta-learning method that incorporates evolving gradient within the inner loop. Evo-MAML avoids the second-order information, resulting in reduced computational complexity. Experimental results show that Evo-MAML exhibits higher generality and competitive performance when compared to existing first-order approximation approaches, making it suitable for both few-shot learning and meta-reinforcement learning settings. Full article
Show Figures

Graphical abstract

19 pages, 8208 KiB  
Article
A Bi-Directional Two-Dimensional Deep Subspace Learning Network with Sparse Representation for Object Recognition
by Xiaoxue Li, Weijia Feng, Xiaofeng Wang, Jia Guo, Yuanxu Chen, Yumeng Yang, Chao Wang, Xinyu Zuo and Manlu Xu
Electronics 2023, 12(18), 3745; https://doi.org/10.3390/electronics12183745 - 5 Sep 2023
Viewed by 1396
Abstract
A principal component analysis network (PCANet), as one of the representative deep subspace learning networks, utilizes principal component analysis (PCA) to learn filters that represent the dominant structural features of objects. However, the filters used in PCANet are linear combinations of all the [...] Read more.
A principal component analysis network (PCANet), as one of the representative deep subspace learning networks, utilizes principal component analysis (PCA) to learn filters that represent the dominant structural features of objects. However, the filters used in PCANet are linear combinations of all the original variables and contain complex and redundant principal components, which hinders the interpretability of the results. To address this problem, we introduce sparse constraints into a subspace learning network and propose three sparse bi-directional two-dimensional PCANet algorithms, including sparse row 2D2PCANet (SR2D2PCANet), sparse column 2D2PCANet (SC2D2PCANet), and sparse row–column 2D2PCANet (SRC2D2PCANet). These algorithms perform sparse operations on the projection matrices in the row, column, and row–column direction, respectively. Sparsity is achieved by utilizing the elastic net to shrink the loads of the non-primary elements in the principal components to zero and to reduce the redundancy in the projection matrices, thus improving the learning efficiency of the networks. Finally, a variety of experimental results on ORL, COIL-100, NEC, and AR datasets demonstrate that the proposed algorithms learn filters with more discriminative information and outperform other subspace learning networks and traditional deep learning networks in terms of classification and run-time performance, especially for less sample learning. Full article
Show Figures

Figure 1

16 pages, 7047 KiB  
Article
BoT2L-Net: Appearance-Based Gaze Estimation Using Bottleneck Transformer Block and Two Identical Losses in Unconstrained Environments
by Xiaohan Wang, Jian Zhou, Lin Wang, Yong Yin, Yu Wang and Zhongjun Ding
Electronics 2023, 12(7), 1704; https://doi.org/10.3390/electronics12071704 - 4 Apr 2023
Cited by 3 | Viewed by 2218
Abstract
As a nonverbal cue, gaze plays a critical role in communication, expressing emotions and reflecting mental activity. It has widespread applications in various fields. Recently, the appearance-based gaze estimation method, which utilizes CNN (convolutional neural networks), has rapidly improved the accuracy and robustness [...] Read more.
As a nonverbal cue, gaze plays a critical role in communication, expressing emotions and reflecting mental activity. It has widespread applications in various fields. Recently, the appearance-based gaze estimation method, which utilizes CNN (convolutional neural networks), has rapidly improved the accuracy and robustness of gaze estimation algorithms. Due to their insufficient ability to capture global relationships, the present accuracy of gaze estimation methods in unconstrained environments, has the potential for improvement. To address this challenge, the focus of this paper is to enhance the accuracy of gaze estimation, which is typically measured by mean angular error. In light of Transformer’s breakthrough in image classification and target detection tasks, and the need for an efficient network, the Transformer-enhanced-CNN method is a suitable choice. This paper proposed a novel model for 3D gaze estimation in unconstrained environments, based on the Bottleneck Transformer block and multi-loss methods. Our designed network (BoT2L-Net), incorporates self-attention through the BoT block, utilizing two identical loss functions to predict the two gaze angles. Additionally, the back-propagation network was combined with classification and regression losses, to improve the network’s accuracy and robustness. Our model was evaluated on two commonly used gaze datasets: Gaze360 and MPIIGaze, achieving mean angular errors of 11.53° and 9.59° for front 180° and front-facing gaze angles, respectively, on the Gaze360 testing set, and a mean angular error of 3.97° on the MPIIGaze testing set, outperforming the CNN-based gaze estimation method. The BoT2L-Net model proposed in this paper performs well on two publicly available datasets, demonstrating the effectiveness of our approach. Full article
Show Figures

Figure 1

Review

Jump to: Research

21 pages, 2428 KiB  
Review
Coral Reef Surveillance with Machine Learning: A Review of Datasets, Techniques, and Challenges
by Abdullahi Chowdhury, Musfera Jahan, Shahriar Kaisar, Mahbub E. Khoda, S M Ataul Karim Rajin and Ranesh Naha
Electronics 2024, 13(24), 5027; https://doi.org/10.3390/electronics13245027 - 20 Dec 2024
Cited by 1 | Viewed by 1898
Abstract
Climate change poses a significant threat to our planet, particularly affecting intricate marine ecosystems like coral reefs. These ecosystems are crucial for biodiversity and serve as indicators of the overall health of our oceans. To better understand and predict these changes, this paper [...] Read more.
Climate change poses a significant threat to our planet, particularly affecting intricate marine ecosystems like coral reefs. These ecosystems are crucial for biodiversity and serve as indicators of the overall health of our oceans. To better understand and predict these changes, this paper discusses a multidisciplinary technical approach incorporating machine learning, artificial intelligence (AI), geographic information systems (GIS), and remote sensing techniques. We focus primarily on the changes that occur in coral reefs over time, taking into account biological components, geographical considerations, and challenges stemming from climate change. We investigate the application of GIS technology in coral reef studies, analyze publicly available datasets from various organisations such as the National Oceanic and Atmospheric Administration (NOAA), the Monterey Bay Aquarium Research Institute, and the Hawaii Undersea Research Laboratory, and present the use of machine and deep learning models in coral reef surveillance. This article examines the application of GIS in coral reef studies across various contexts, identifying key research gaps, particularly the lack of a comprehensive catalogue of publicly available datasets. Additionally, it reviews the existing literature on machine and deep learning techniques for coral reef surveillance, critically evaluating their contributions and limitations. The insights provided in this work aim to guide future research, fostering advancements in coral reef monitoring and conservation. Full article
Show Figures

Figure 1

30 pages, 2631 KiB  
Review
A Systematic Literature Review on Using Natural Language Processing in Software Requirements Engineering
by Sabina-Cristiana Necula, Florin Dumitriu and Valerică Greavu-Șerban
Electronics 2024, 13(11), 2055; https://doi.org/10.3390/electronics13112055 - 24 May 2024
Cited by 6 | Viewed by 4986
Abstract
This systematic literature review examines the integration of natural language processing (NLP) in software requirements engineering (SRE) from 1991 to 2023. Focusing on the enhancement of software requirement processes through technological innovation, this study spans an extensive array of scholarly articles, conference papers, [...] Read more.
This systematic literature review examines the integration of natural language processing (NLP) in software requirements engineering (SRE) from 1991 to 2023. Focusing on the enhancement of software requirement processes through technological innovation, this study spans an extensive array of scholarly articles, conference papers, and key journal and conference reports, including data from Scopus, IEEE Xplore, ACM Digital Library, and Clarivate. Our methodology employs both quantitative bibliometric tools, like keyword trend analysis and thematic mapping, and qualitative content analysis to provide a robust synthesis of current trends and future directions. Reported findings underscore the essential roles of advanced computational techniques like machine learning, deep learning, and large language models in refining and automating SRE tasks. This review highlights the progressive adoption of these technologies in response to the increasing complexity of software systems, emphasizing their significant potential to enhance the accuracy and efficiency of requirement engineering practices while also pointing to the challenges of integrating artificial intelligence (AI) and NLP into existing SRE workflows. The systematic exploration of both historical contributions and emerging trends offers new insights into the dynamic interplay between technological advances and their practical applications in SRE. Full article
Show Figures

Figure 1

Back to TopTop