Electronics

Research

Jump to: Review

14 pages, 6802 KiB

Open AccessArticle

Contamination Detection Using a Deep Convolutional Neural Network with Safe Machine—Environment Interaction

by Syed Ali Hassan, Muhammad Adnan Khalil, Fabrizia Auletta, Mariangela Filosa, Domenico Camboni, Arianna Menciassi and Calogero Maria Oddo

Electronics 2023, 12(20), 4260; https://doi.org/10.3390/electronics12204260 - 15 Oct 2023

Cited by 2 | Viewed by 1804

Abstract

In the food and medical packaging industries, clean packaging is crucial to both customer satisfaction and hygiene. An operational Quality Assurance Department (QAD) is necessary for detecting contaminated packages. Manual examination becomes tedious and may lead to instances of contamination being missed along [...] Read more.

In the food and medical packaging industries, clean packaging is crucial to both customer satisfaction and hygiene. An operational Quality Assurance Department (QAD) is necessary for detecting contaminated packages. Manual examination becomes tedious and may lead to instances of contamination being missed along the production line. To address this issue, a system for contamination detection is proposed using an enhanced deep convolutional neural network (CNN) in a human–robot collaboration framework. The proposed system utilizes a CNN to identify and classify the presence of contaminants on product surfaces. A dataset is generated, and augmentation methods are applied to the dataset for nine classes such as coffee, spot, chocolate, tomato paste, jam, cream, conditioner, shaving cream, and toothpaste contaminants. The experiment was conducted using a mechatronic platform with a camera for contamination detection and a time-of-flight sensor for safe machine–environment interaction. The results of the experiment indicate that the reported system can accurately identify contamination with 99.74% mean average precision (mAP). Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

17 pages, 2745 KiB

Open AccessArticle

MDBF: Meta-Path-Based Depth and Breadth Feature Fusion for Recommendation in Heterogeneous Network

by Hongjuan Liu and Huairui Zhang

Electronics 2023, 12(19), 4017; https://doi.org/10.3390/electronics12194017 - 24 Sep 2023

Viewed by 1364

Abstract

The main challenge of recommendation in a heterogeneous information network comes from the diversity of nodes and links and the problem of semantic expression ambiguity caused by diversity. Therefore, we propose a movie recommendation algorithm for a heterogeneous network called Meta-Path-Based Depth and [...] Read more.

The main challenge of recommendation in a heterogeneous information network comes from the diversity of nodes and links and the problem of semantic expression ambiguity caused by diversity. Therefore, we propose a movie recommendation algorithm for a heterogeneous network called Meta-Path-Based Depth and Breadth Feature Fusion(MDBF). Using a random walk for depth feature learning, we can extract a depth feature meta-path that reflects the overall structure of the network. In addition, using random walks in adjacent nodes, we can extract a breadth feature meta-path, preserving the neighborhood information of a node. If there is some auxiliary information, it will be learned by its own meta-paths. Then, all of the feature sequences can be fused and learned by the Skip-gram algorithm to obtain the final feature vector. In the recommendation process, based on traditional collaborative filtering, we propose a secondary filtering recommendation. The experimental results show that, without external auxiliary information, compared to the existing state-of-the-art models, the algorithm improves each index by an average of 12% on MovieLens and 22% on MovieTweetings. The algorithm not only improves the effect of movie recommendation, but also provides application scenarios for accurate recommendation services through auxiliary information. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

20 pages, 1969 KiB

Open AccessArticle

Multi-Phase Focused PID Adaptive Tuning with Reinforcement Learning

by Ye Ding, Xiaoguang Ren, Xiaochuan Zhang, Xin Liu and Xu Wang

Electronics 2023, 12(18), 3925; https://doi.org/10.3390/electronics12183925 - 18 Sep 2023

Cited by 4 | Viewed by 1692

Abstract

The Proportional-Integral-Derivative (PID) controller, a fundamental element in industrial control systems, plays a pivotal role in regulating an extensive array of controlled objects. Accurate and rapid adaptive tuning of PID controllers holds significant practical value in fields such as mechatronics, robotics, and automatic [...] Read more.

The Proportional-Integral-Derivative (PID) controller, a fundamental element in industrial control systems, plays a pivotal role in regulating an extensive array of controlled objects. Accurate and rapid adaptive tuning of PID controllers holds significant practical value in fields such as mechatronics, robotics, and automatic control. The three parameters of the PID controller exert a substantial influence on control performance, rendering the tuning of these parameters an area of significant interest within related research fields. Numerous tuning techniques are widely employed to optimize its functionality. Nonetheless, their adaptability and control stability may be constrained in situations where prior knowledge is inadequate. In this paper, a multi-phase focused PID adaptive tuning method is introduced, leveraging the deep deterministic policy gradient (DDPG) algorithm to automatically establish reference values for PID tuning. This method constrains agent actions in multiple phases based on the reward thresholds, allowing the output PID parameters to focus within the stable region, which provides enhanced adaptability and maintains the stability of the PID controller even with limited prior knowledge. To counteract the potential issue of a vanishing gradient following action constraints, a residual structure is incorporated into the actor network. The results of experiments conducted on both first-order and second-order systems demonstrate that the proposed method can reduce the tracking error of a PID controller by 16–30% compared with the baseline methods without a loss in stability. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

39 pages, 10826 KiB

Open AccessArticle

An Integrated Support System for People with Intellectual Disability

by Maria Papadogiorgaki, Nikos Grammalidis, Athina Grammatikopoulou, Konstantinos Apostolidis, Ekaterini S. Bei, Kostas Grigoriadis, Stylianos Zafeiris, George Livanos, Vasileios Mezaris and Michalis E. Zervakis

Electronics 2023, 12(18), 3803; https://doi.org/10.3390/electronics12183803 - 8 Sep 2023

Cited by 2 | Viewed by 2120

Abstract

People with Intellectual Disability (ID) encounter several problems in their daily living regarding their needs, activities, interrelationships, and communication. In this paper, an interactive platform is proposed, aiming to provide personalized recommendations for information and entertainment, including creative and educational activities, tailored to [...] Read more.

People with Intellectual Disability (ID) encounter several problems in their daily living regarding their needs, activities, interrelationships, and communication. In this paper, an interactive platform is proposed, aiming to provide personalized recommendations for information and entertainment, including creative and educational activities, tailored to the special user needs of this population. Furthermore, the proposed platform integrates capabilities for the automatic recognition of health-related emergencies, such as fever, oxygen saturation decline, and tachycardia, as well as location tracking and detection of wandering behavior based on smartwatch/smartphone sensors, while providing appropriate notifications to caregivers and automated assistance to people with ID through voice instructions and interaction with a virtual assistant. A short-scale pilot study has been carried out, where a group of end-users participated in the testing of the integrated platform, verifying its effectiveness concerning the recommended services. The experimental results indicate the potential value of the proposed system in providing routine health measurements, identifying and managing emergency cases, and supporting a creative and qualitative daily life for people with disabilities. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

16 pages, 14139 KiB

Open AccessArticle

The Application of ResNet-34 Model Integrating Transfer Learning in the Recognition and Classification of Overseas Chinese Frescoes

by Le Gao, Xin Zhang, Tian Yang, Baocang Wang and Juntao Li

Electronics 2023, 12(17), 3677; https://doi.org/10.3390/electronics12173677 - 31 Aug 2023

Cited by 4 | Viewed by 2824

Abstract

The unique characteristics of frescoes on overseas Chinese buildings can attest to the integration and historical background of Chinese and Western cultures. Reasonable analysis and preservation of overseas Chinese frescoes can provide sustainable development for culture and history. This research adopts image analysis [...] Read more.

The unique characteristics of frescoes on overseas Chinese buildings can attest to the integration and historical background of Chinese and Western cultures. Reasonable analysis and preservation of overseas Chinese frescoes can provide sustainable development for culture and history. This research adopts image analysis technology based on artificial intelligence and proposes a ResNet-34 model and method integrating transfer learning. This deep learning model can identify and classify the source of the frescoes of the emigrants, and effectively deal with problems such as the small number of fresco images on the emigrants’ buildings, poor quality, difficulty in feature extraction, and similar pattern text and style. The experimental results show that the training process of the model proposed in this article is stable. On the constructed Jiangmen and Haikou fresco JHD datasets, the final accuracy is 98.41%, and the recall rate is 98.53%. The above evaluation indicators are superior to classic models such as AlexNet, GoogLeNet, and VGGNet. It can be seen that the model in this article has strong generalization ability and is not prone to overfitting. It can effectively identify and classify the cultural connotations and regions of frescoes. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Graphical abstract

18 pages, 513 KiB

Open AccessEditor’s ChoiceArticle

Cascading and Ensemble Techniques in Deep Learning

by I. de Zarzà, J. de Curtò, Enrique Hernández-Orallo and Carlos T. Calafate

Electronics 2023, 12(15), 3354; https://doi.org/10.3390/electronics12153354 - 5 Aug 2023

Cited by 7 | Viewed by 4648

Abstract

In this study, we explore the integration of cascading and ensemble techniques in Deep Learning (DL) to improve prediction accuracy on diabetes data. The primary approach involves creating multiple Neural Networks (NNs), each predicting the outcome independently, and then feeding these initial predictions [...] Read more.

In this study, we explore the integration of cascading and ensemble techniques in Deep Learning (DL) to improve prediction accuracy on diabetes data. The primary approach involves creating multiple Neural Networks (NNs), each predicting the outcome independently, and then feeding these initial predictions into another set of NN. Our exploration starts from an initial preliminary study and extends to various ensemble techniques including bagging, stacking, and finally cascading. The cascading ensemble involves training a second layer of models on the predictions of the first. This cascading structure, combined with ensemble voting for the final prediction, aims to exploit the strengths of multiple models while mitigating their individual weaknesses. Our results demonstrate significant improvement in prediction accuracy, providing a compelling case for the potential utility of these techniques in healthcare applications, specifically for prediction of diabetes where we achieve compelling model accuracy of 91.5% on the test set on a particular challenging dataset, where we compare thoroughly against many other methodologies. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

15 pages, 1476 KiB

Open AccessArticle

Enhanced-Deep-Residual-Shrinkage-Network-Based Voiceprint Recognition in the Electric Industry

by Qingrui Zhang, Hongting Zhai, Yuanyuan Ma, Lili Sun, Yantong Zhang, Weihong Quan, Qi Zhai, Bangwei He and Zhiquan Bai

Electronics 2023, 12(14), 3017; https://doi.org/10.3390/electronics12143017 - 10 Jul 2023

Cited by 5 | Viewed by 1759

Abstract

Voiceprint recognition can extract voice features and identity the speaker through the voice information, which has great application prospects in personnel identity verification and voice dispatching in the electric industry. The traditional voiceprint recognition algorithms work well in a quiet environment. However, noise [...] Read more.

Voiceprint recognition can extract voice features and identity the speaker through the voice information, which has great application prospects in personnel identity verification and voice dispatching in the electric industry. The traditional voiceprint recognition algorithms work well in a quiet environment. However, noise interference inevitably exists in the electric industry, degrading the accuracy of traditional voiceprint recognition algorithms. In this paper, we propose an enhanced deep residual shrinkage network (EDRSN)-based voiceprint recognition by combining the traditional voiceprint recognition algorithms with deep learning (DL) in the context of the noisy electric industry environment, where a dual-path convolution recurrent network (DPCRN) is employed to reduce the noise, and its structure is also improved based on the deep residual shrinkage network (DRSN). Moreover, we further use a convolutional block attention mechanism (CBAM) module and a hybrid dilated convolution (HDC) in the proposed EDRSN. Simulation results show that the proposed network can enhance the speaker’s vocal features and further distinguish and eliminate the noise features, thus reducing the noise influence and achieving better recognition performance in a noisy electric environment. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

18 pages, 8941 KiB

Open AccessArticle

Underwater Image Enhancement Method Based on Improved GAN and Physical Model

by Shuangshuang Chang, Farong Gao and Qizhong Zhang

Electronics 2023, 12(13), 2882; https://doi.org/10.3390/electronics12132882 - 29 Jun 2023

Cited by 5 | Viewed by 2281

Abstract

Underwater vision technology is of great significance in marine investigation. However, the complex underwater environment leads to some problems, such as color deviation and high noise. Therefore, underwater image enhancement has been a focus of the research community. In this paper, a new [...] Read more.

Underwater vision technology is of great significance in marine investigation. However, the complex underwater environment leads to some problems, such as color deviation and high noise. Therefore, underwater image enhancement has been a focus of the research community. In this paper, a new underwater image enhancement method is proposed based on a generative adversarial network (GAN). We embedded the channel attention mechanism into U-Net to improve the feature utilization performance of the network and used the generator to estimate the parameters of the simplified underwater physical model. At the same time, the adversarial loss, the perceptual loss, and the global loss were fused to train the model. The effectiveness of the proposed method was verified by using four image evaluation metrics on two publicly available underwater image datasets. In addition, we compared the proposed method with some advanced underwater image enhancement algorithms under the same experimental conditions. The experimental results showed that the proposed method demonstrated superiority in terms of image color correction and image noise suppression. In addition, the proposed method was competitive in real-time processing speed. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

25 pages, 8807 KiB

Open AccessArticle

3D Pose Recognition of Small Special-Shaped Sheet Metal with Multi-Objective Overlapping

by Yaohua Deng, Guanhao Chen, Xiali Liu, Cheng Sun, Zhihai Huang and Shengyu Lin

Electronics 2023, 12(12), 2613; https://doi.org/10.3390/electronics12122613 - 9 Jun 2023

Cited by 3 | Viewed by 1140

Abstract

This paper addresses the challenging task of determining the position and posture of small-scale thin metal parts with multi-objective overlapping. To tackle this problem, we propose a method that utilizes instance segmentation and a three-dimensional (3D) point cloud for recognizing the posture of [...] Read more.

This paper addresses the challenging task of determining the position and posture of small-scale thin metal parts with multi-objective overlapping. To tackle this problem, we propose a method that utilizes instance segmentation and a three-dimensional (3D) point cloud for recognizing the posture of thin special-shaped metal parts. We investigate the process of obtaining a single target point cloud by aligning the target mask with the depth map. Additionally, we explore a pose estimation method that involves registering the target point cloud with the model point cloud, designing a registration algorithm that combines the sample consensus initial alignment algorithm (SAC-IA) for coarse registration and the iterative closest point (ICP) algorithm for fine registration. The experimental results demonstrate the effectiveness of our approach. The average accuracy of the instance segmentation models, utilizing ResNet50 + FPN and ResNet101 + FPN as backbone networks, exceeds 97%. The time consumption of the ResNet50 + FPN model is reduced by 50%. Furthermore, the registration algorithm, which combines the SAC-IA and ICP, achieves a lower average consumption time while satisfying the requirements for the manufacturing of new energy batteries. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

16 pages, 1792 KiB

Open AccessArticle

Support Vector Machine Chains with a Novel Tournament Voting

by Ceren Atik, Recep Alp Kut, Reyat Yilmaz and Derya Birant

Electronics 2023, 12(11), 2485; https://doi.org/10.3390/electronics12112485 - 31 May 2023

Cited by 3 | Viewed by 1633

Abstract

Support vector machine (SVM) algorithms have been widely used for classification in many different areas. However, the use of a single SVM classifier is limited by the advantages and disadvantages of the algorithm. This paper proposes a novel method, called support vector machine [...] Read more.

Support vector machine (SVM) algorithms have been widely used for classification in many different areas. However, the use of a single SVM classifier is limited by the advantages and disadvantages of the algorithm. This paper proposes a novel method, called support vector machine chains (SVMC), which involves chaining together multiple SVM classifiers in a special structure, such that each learner is constructed by decrementing one feature at each stage. This paper also proposes a new voting mechanism, called tournament voting, in which the outputs of classifiers compete in groups, the common result in each group gradually moves to the next round, and, at the last round, the winning class label is assigned as the final prediction. Experiments were conducted on 14 real-world benchmark datasets. The experimental results showed that SVMC (88.11%) achieved higher accuracy than SVM (86.71%) on average thanks to the feature selection, sampling, and chain structure combined with multiple models. Furthermore, the proposed tournament voting demonstrated higher performance than the standard majority voting in terms of accuracy. The results also showed that the proposed SVMC method outperformed the state-of-the-art methods with a 6.88% improvement in average accuracy. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

26 pages, 6100 KiB

Open AccessArticle

Imperfect-Information Game AI Agent Based on Reinforcement Learning Using Tree Search and a Deep Neural Network

by Xin Ouyang and Ting Zhou

Electronics 2023, 12(11), 2453; https://doi.org/10.3390/electronics12112453 - 29 May 2023

Cited by 2 | Viewed by 3293

Abstract

In the field of computer intelligence, it has always been a challenge to construct an agent model that can be adapted to various complex tasks. In recent years, based on the planning algorithm of Monte Carlo tree search (MCTS), a new idea has [...] Read more.

In the field of computer intelligence, it has always been a challenge to construct an agent model that can be adapted to various complex tasks. In recent years, based on the planning algorithm of Monte Carlo tree search (MCTS), a new idea has been proposed to solve the AI problems of two-player zero-sum games such as chess and Go. However, most of the games in the real environment rely on imperfect information, so it is impossible to directly use the normal tree search planning algorithm to construct a decision-making model. Mahjong, which is a popular multiplayer game with a long history in China, attracts great attention from AI researchers because it contains a large game state space and a lot of hidden information. In this paper, we utilize an agent learning approach that leverages deep learning, reinforcement learning, and dropout learning techniques to implement a Mahjong AI game agent. First, we improve the state transition of the tree search based on the learned MDP model, the player position variable and transition information are introduced into the tree search algorithm to construct a multiplayer search tree. Then, the model training based on a deep reinforcement learning method ensures the stable and sustainable training process of the learned MDP model. Finally, we utilize the strategy data generated by the tree search and use the dropout learning method to train the normal decision-making agent. The experimental results demonstrate the efficiency and stability performance of the agent trained by our proposed method compared with existing agents in terms of test data accuracy, tournament ranking performance, and online match performance. The agent plays against human players and acts like real humans. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

24 pages, 5323 KiB

Open AccessArticle

MRLBot: Multi-Dimensional Representation Learning for Social Media Bot Detection

by Fanrui Zeng, Yingjie Sun and Yizhou Li

Electronics 2023, 12(10), 2298; https://doi.org/10.3390/electronics12102298 - 19 May 2023

Cited by 2 | Viewed by 1718

Abstract

Social media bots pose potential threats to the online environment, and the continuously evolving anti-detection technologies require bot detection methods to be more reliable and general. Current detection methods encounter challenges, including limited generalization ability, susceptibility to evasion in traditional feature engineering, and [...] Read more.

Social media bots pose potential threats to the online environment, and the continuously evolving anti-detection technologies require bot detection methods to be more reliable and general. Current detection methods encounter challenges, including limited generalization ability, susceptibility to evasion in traditional feature engineering, and insufficient exploration of user relationships. To tackle these challenges, this paper proposes MRLBot, a social media bot detection framework based on unsupervised representation learning. We design a behavior representation learning model that utilizes Transformer and a CNN encoder–decoder to simultaneously extract global and local features from behavioral information. Furthermore, a network representation learning model is proposed that introduces intra- and outer-community-oriented random walks to learn structural features and community connections from the relationship graph. Finally, the behavioral representation and relationship representation learning models are combined to generate fused representations for bot detection. The experimental results of four publicly available social network datasets demonstrate that the proposed method has certain advantages over state-of-the-art detection methods in this field. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

23 pages, 3201 KiB

Open AccessArticle

Novel Design of Industrial Real-Time CT System Based on Sparse-View Reconstruction and Deep-Learning Image Enhancement

by Zheng Fang and Tingjun Wang

Electronics 2023, 12(8), 1815; https://doi.org/10.3390/electronics12081815 - 11 Apr 2023

Cited by 2 | Viewed by 2519

Abstract

Industrial CT is useful for defect detection, dimensional inspection and geometric analysis, while it does not meet the needs of industrial mass production because of its time-consuming imaging procedure. This article proposes a novel stationary real-time CT system, which is able to refresh [...] Read more.

Industrial CT is useful for defect detection, dimensional inspection and geometric analysis, while it does not meet the needs of industrial mass production because of its time-consuming imaging procedure. This article proposes a novel stationary real-time CT system, which is able to refresh the CT-reconstructed slices to the detector frame frequency. This structure avoids the movement of the X-ray sources and detectors. Projections from different angles can be acquired with the objects’ translation, making it easier to be integrated into production line. All the detectors are arranged along the conveyor and observe the objects in different angles of view. With the translation of objects, their X-ray projections are obtained for CT reconstruction. To decrease the mechanical size and reduce the number of X-ray sources and detectors, the FBP reconstruction algorithm was combined with deep-learning image enhancement. Medical CT images were applied to train the deep-learning network for its quantity advantage in comparison with industrial ones. It is the first time this source-detector layout strategy has been adopted. Data augmentation and regularization were used to elevate the generalization of the network. Time consumption of the CT imaging process was also calculated to prove its high efficiency. Our experiment shows that the reconstruction resulting in undersampled projections is highly enhanced using a deep-learning neural network which meets the demand of non-destructive testing. Meanwhile, our proposed system structure can perform quick scans and reconstructions on larger objects. It solves the pain points of limited scan size and slow scanning speed of existing industrial CT scans. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

15 pages, 2961 KiB

Open AccessArticle

High-Embedded Low-Distortion Multihistogram Shift Video Reversible Data Hiding Based on DCT Coefficient

by Yuhang Yang, Xuyu Xiang, Jiaohua Qin, Yun Tan, Zhangdong Wang and Yajie Liu

Electronics 2023, 12(7), 1652; https://doi.org/10.3390/electronics12071652 - 31 Mar 2023

Cited by 1 | Viewed by 1383

Abstract

Video reversible data hiding technology can be applied to copyright protection, medical images, the military, and other fields, but it cannot guarantee high visual quality with an effective embedded capacity. In this paper, a high-embedding and low-distortion reversible data hiding scheme based on [...] Read more.

Video reversible data hiding technology can be applied to copyright protection, medical images, the military, and other fields, but it cannot guarantee high visual quality with an effective embedded capacity. In this paper, a high-embedding and low-distortion reversible data hiding scheme based on a discrete cosine transform (DCT) coefficients method is proposed. The scheme first decodes the original video stream with entropy, obtains all the DCT blocks, and selects the embeddable DCT blocks according to the capacity of the zero factor. Then, it divides the coefficients in the DCT blocks into the shift and embedding coefficients. The shift coefficients directly generate a one-dimensional histogram; the embedding coefficients generate a two-dimensional histogram according to paired strategies. Finally, the secret data can be successfully embedded according to the proposed two-dimensional histogram shift reversible data hiding scheme. This scheme performed more effectively than existing schemes in terms of the embedded capacity, peak signal-to-noise ratio (PSNR), and structural similarity index measure (SSIM). Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

19 pages, 1359 KiB

Open AccessArticle

Improving Sentiment Prediction of Textual Tweets Using Feature Fusion and Deep Machine Ensemble Model

by Hamza Ahmad Madni, Muhammad Umer, Nihal Abuzinadah, Yu-Chen Hu, Oumaima Saidani, Shtwai Alsubai, Monia Hamdi and Imran Ashraf

Electronics 2023, 12(6), 1302; https://doi.org/10.3390/electronics12061302 - 9 Mar 2023

Cited by 8 | Viewed by 2855

Abstract

Widespread fear and panic has emerged about COVID-19 on social media platforms which are often supported by falsified and altered content. This mass hysteria creates public anxiety due to misinformation, misunderstandings, and ignorance of the impact of COVID-19. To assist health professionals in [...] Read more.

Widespread fear and panic has emerged about COVID-19 on social media platforms which are often supported by falsified and altered content. This mass hysteria creates public anxiety due to misinformation, misunderstandings, and ignorance of the impact of COVID-19. To assist health professionals in addressing this epidemic more appropriately at the onset, sentiment analysis can potentially help the authorities for devising appropriate strategies. This study analyzes tweets related to COVID-19 using a machine learning approach and offers a high-accuracy solution. Experiments are performed involving different machine and deep learning models along with various features such as Word2vec, term-frequency, term-frequency document frequency, and feature fusion of both feature-generating approaches. The proposed approach combines the extra tree classifier and convolutional neural network and uses feature fusion to achieve the highest accuracy score of 99%. The proposed approach obtains far better results than existing sentiment analysis approaches. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

26 pages, 2453 KiB

Open AccessArticle

AQSA: Aspect-Based Quality Sentiment Analysis for Multi-Labeling with Improved ResNet Hybrid Algorithm

by Muhammad Irfan, Nasir Ayub, Qazi Arbab Ahmed, Saifur Rahman, Muhammad Salman Bashir, Grzegorz Nowakowski, Samar M. Alqhtani and Marek Sieja

Electronics 2023, 12(6), 1298; https://doi.org/10.3390/electronics12061298 - 8 Mar 2023

Cited by 4 | Viewed by 2585

Abstract

Sentiment analysis (SA) is an area of study currently being investigated in text mining. SA is the computational handling of a text’s views, emotions, subjectivity, and subjective nature. The researchers realized that generating generic sentiment from textual material was inadequate, so they developed [...] Read more.

Sentiment analysis (SA) is an area of study currently being investigated in text mining. SA is the computational handling of a text’s views, emotions, subjectivity, and subjective nature. The researchers realized that generating generic sentiment from textual material was inadequate, so they developed SA to extract expressions from textual information. The problem of removing emotional aspects through multi-labeling based on data from certain aspects may be resolved. This article proposes the swarm-based hybrid model residual networks with sand cat swarm optimization (ResNet-SCSO), a novel method for increasing the precision and variation of learning the text with the multi-labeling method. Contrary to existing multi-label training approaches, ResNet-SCSO highlights the diversity and accuracy of methodologies based on multi-labeling. Five distinct datasets were analyzed (movies, research articles, medical, birds, and proteins). To achieve accurate and improved data, we initially used preprocessing. Secondly, we used the GloVe and TF-IDF to extract features. Thirdly, a word association is created using the word2vec method. Additionally, the enhanced data are utilized for training and validating the ResNet model (tuned with SCSO). We tested the accuracy of ResNet-SCSO on research article, medical, birds, movie, and protein images using the aspect-based multi-labeling method. The accuracy was 95%, 96%, 97%, 92%, and 96%, respectively. With multi-label datasets of varying dimensions, our proposed model shows that ResNet-SCSO is significantly better than other commonly used techniques. Experimental findings confirm the implemented strategy’s success compared to existing benchmark methods. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

14 pages, 3179 KiB

Open AccessArticle

DBoTPM: A Deep Neural Network-Based Botnet Prediction Model

by Mohd Anul Haq

Electronics 2023, 12(5), 1159; https://doi.org/10.3390/electronics12051159 - 27 Feb 2023

Cited by 22 | Viewed by 2521

Abstract

Internet of things (IoT) devices’ evolution and growth have boosted system efficiency, reduced human labour, and improved operational efficiency; however, IoT devices pose substantial security and privacy risks, making them highly vulnerable to botnet attacks. Botnet attacks are capable of degrading the performance [...] Read more.

Internet of things (IoT) devices’ evolution and growth have boosted system efficiency, reduced human labour, and improved operational efficiency; however, IoT devices pose substantial security and privacy risks, making them highly vulnerable to botnet attacks. Botnet attacks are capable of degrading the performance of an IoT system in a way that makes it difficult for IoT network users to identify them. Earlier studies mainly focused on the detection of IoT botnets, and there was a gap in predicting the botnet attack due to their complex behaviour, repetitive nature, uncertainty, and almost invisible presence in the compromised system. Based on the gaps, it is highly required to develop efficient and stable AI models that can reliably predict botnet attacks. The current study developed and implemented DBoTPM, a novel deep-neural-network-based model for botnet prediction. The DBoTPM was optimized for performance and less computational overhead by utilizing rigorous hyperparameter tuning. The consequences of overfitting and underfitting were mitigated through dropouts. The evaluation of the DBoTPM demonstrated that it is one of the most accurate and efficient models for botnet prediction. This investigation is unique in that it makes use of two real datasets to detect and predict botnet attacks with efficient performance and faster response. The results achieved through the DBoTPM model were assessed against prior research and found to be highly effective at predicting botnet attacks with a real dataset. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

13 pages, 3161 KiB

Open AccessArticle

Music Emotion Recognition Based on a Neural Network with an Inception-GRU Residual Structure

by Xiao Han, Fuyang Chen and Junrong Ban

Electronics 2023, 12(4), 978; https://doi.org/10.3390/electronics12040978 - 15 Feb 2023

Cited by 8 | Viewed by 4902

Abstract

As a key field in music information retrieval, music emotion recognition is indeed a challenging task. To enhance the accuracy of music emotion classification and recognition, this paper uses the idea of inception structure to use different receptive fields to extract features of [...] Read more.

As a key field in music information retrieval, music emotion recognition is indeed a challenging task. To enhance the accuracy of music emotion classification and recognition, this paper uses the idea of inception structure to use different receptive fields to extract features of different dimensions and perform compression, expansion, and recompression operations to mine more effective features and connect the timing signals in the residual network to the GRU module to extract timing features. A one-dimensional (1D) residual Convolutional Neural Network (CNN) with an improved Inception module and Gate Recurrent Unit (GRU) was presented and tested on the Soundtrack dataset. Fast Fourier Transform (FFT) was used to process the samples experimentally and determine their spectral characteristics. Compared with the shallow learning methods such as support vector machine and random forest and the deep learning method based on Visual Geometry Group (VGG) CNN proposed by Sarkar et al., the proposed deep learning method of the 1D CNN with the Inception-GRU residual structure demonstrated better performance in music emotion recognition and classification tasks, achieving an accuracy of 84%. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

17 pages, 3458 KiB

Open AccessArticle

Physical Activity Recognition Based on Deep Learning Using Photoplethysmography and Wearable Inertial Sensors

by Narit Hnoohom, Sakorn Mekruksavanich and Anuchit Jitpattanakul

Electronics 2023, 12(3), 693; https://doi.org/10.3390/electronics12030693 - 30 Jan 2023

Cited by 16 | Viewed by 3176

Abstract

Human activity recognition (HAR) extensively uses wearable inertial sensors since this data source provides the most information for non-visual datasets’ time series. HAR research has advanced significantly in recent years due to the proliferation of wearable devices with sensors. To improve recognition performance, [...] Read more.

Human activity recognition (HAR) extensively uses wearable inertial sensors since this data source provides the most information for non-visual datasets’ time series. HAR research has advanced significantly in recent years due to the proliferation of wearable devices with sensors. To improve recognition performance, HAR researchers have extensively investigated other sources of biosignals, such as a photoplethysmograph (PPG), for this task. PPG sensors measure the rate at which blood flows through the body, and this rate is regulated by the heart’s pumping action, which constantly occurs throughout the body. Even though detecting body movement and gestures was not initially the primary purpose of PPG signals, we propose an innovative method for extracting relevant features from the PPG signal and use deep learning (DL) to predict physical activities. To accomplish the purpose of our study, we developed a deep residual network referred to as PPG-NeXt, designed based on convolutional operation, shortcut connections, and aggregated multi-branch transformation to efficiently identify different types of daily life activities from the raw PPG signal. The proposed model achieved more than 90% prediction F1-score from experimental results using only PPG data on the three benchmark datasets. Moreover, our results indicate that combining PPG and acceleration signals can enhance activity recognition. Although, both biosignals—electrocardiography (ECG) and PPG—can differentiate between stationary activities (such as sitting) and non-stationary activities (such as cycling and walking) with a level of success that is considered sufficient. Overall, our results propose that combining features from the ECG signal can be helpful in situations where pure tri-axial acceleration (3D-ACC) models have trouble differentiating between activities with relative motion (e.g., walking, stair climbing) but significant differences in their heart rate signatures. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

17 pages, 827 KiB

Open AccessArticle

An Approach for Classification of Alzheimer’s Disease Using Deep Neural Network and Brain Magnetic Resonance Imaging (MRI)

by Ruhul Amin Hazarika, Arnab Kumar Maji, Debdatta Kandar, Elzbieta Jasinska, Petr Krejci, Zbigniew Leonowicz and Michal Jasinski

Electronics 2023, 12(3), 676; https://doi.org/10.3390/electronics12030676 - 29 Jan 2023

Cited by 26 | Viewed by 4756

Abstract

Alzheimer’s disease (AD) is a deadly cognitive condition in which people develop severe dementia symptoms. Neurologists commonly use a series of physical and mental tests to diagnose AD that may not always be effective. Damage to brain cells is the most significant physical [...] Read more.

Alzheimer’s disease (AD) is a deadly cognitive condition in which people develop severe dementia symptoms. Neurologists commonly use a series of physical and mental tests to diagnose AD that may not always be effective. Damage to brain cells is the most significant physical change in AD. Proper analysis of brain images may assist in the identification of crucial bio-markers for the disease. Because the development of brain cells is so intricate, traditional image processing algorithms sometimes fail to perceive important bio-markers. The deep neural network (DNN) is a machine learning technique that helps specialists in making appropriate decisions. In this work, we used brain magnetic resonance scans to implement some commonly used DNN models for AD classification. According to the classification results, where the average of multiple metrics is observed, which includes accuracy, precision, recall, and an F1 score, it is found that the DenseNet-121 model achieved the best performance (86.55%). Since DenseNet-121 is a computationally expensive model, we proposed a hybrid technique incorporating LeNet and AlexNet that is light weight and also capable of outperforming DenseNet. To extract important features, we replaced the traditional convolution Layers with three parallel small filters (

1 \times 1, 3 \times 3

, and

5 \times 5

). The model functions effectively, with an overall performance rate of 93.58%. Mathematically, it is observed that the proposed model generates significantly fewer convolutional parameters, resulting in a lightweight model that is computationally effective. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

16 pages, 3889 KiB

Open AccessArticle

Table Structure Recognition Method Based on Lightweight Network and Channel Attention

by Tao Zhang, Yi Sui, Shunyao Wu, Fengjing Shao and Rencheng Sun

Electronics 2023, 12(3), 673; https://doi.org/10.3390/electronics12030673 - 29 Jan 2023

Cited by 2 | Viewed by 2511

Abstract

The table recognition model rows and columns aggregated network (RCANet) uses a semantic segmentation approach to recognize table structure, and achieves better performance in table row and column segmentation. However, this model uses ResNet18 as the backbone network, and the model has 11.35 [...] Read more.

The table recognition model rows and columns aggregated network (RCANet) uses a semantic segmentation approach to recognize table structure, and achieves better performance in table row and column segmentation. However, this model uses ResNet18 as the backbone network, and the model has 11.35 million parameters and a volume of 45.5 M, which is inconvenient to deploy to lightweight servers or mobile terminals. Therefore, from the perspective of model compression, this paper proposes the lightweight rows and columns attention aggregated network (LRCAANet), which uses the lightweight network ShuffleNetv2 to replace the original RCANet backbone network ResNet18 to simplify the model size. Considering that the lightweight network reduces the number of feature channels, it has a certain impact on the performance of the model. In order to strengthen the learning between feature channels, the rows attention aggregated (RAA) module and the columns attention aggregated (CAA) module are proposed. The RAA module and the CAA module add the squeeze and excitation (SE) module to the original row and column aggregated modules, respectively. Adding the SE module means the model can learn the correlation between channels and improve the prediction effect of the lightweight model. The experimental results show that our method greatly reduces the model parameters and model volume while ensuring low-performance loss. In the end, the average F1 score of our model is only 1.77% lower than the original model, the parameters are only 0.17 million, and the volume is only 0.8 M. Compared with the original model, the parameter amount and volume are reduced by more than 95%. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

21 pages, 4359 KiB

Open AccessArticle

Filter-Based Ensemble Feature Selection and Deep Learning Model for Intrusion Detection in Cloud Computing

by C. Kavitha, Saravanan M., Thippa Reddy Gadekallu, Nimala K., Balasubramanian Prabhu Kavin and Wen-Cheng Lai

Electronics 2023, 12(3), 556; https://doi.org/10.3390/electronics12030556 - 21 Jan 2023

Cited by 16 | Viewed by 2787

Abstract

In recent years, the high improvement in communication, Internet of Things (IoT) and cloud computing have begun complex questioning in security. Based on the development, cyberattacks can be increased since the present security techniques do not give optimal solutions. As a result, the [...] Read more.

In recent years, the high improvement in communication, Internet of Things (IoT) and cloud computing have begun complex questioning in security. Based on the development, cyberattacks can be increased since the present security techniques do not give optimal solutions. As a result, the authors of this paper created filter-based ensemble feature selection (FEFS) and employed a deep learning model (DLM) for cloud computing intrusion detection. Initially, the intrusion data were collected from the global datasets of KDDCup-99 and NSL-KDD. The data were utilized for validation of the proposed methodology. The collected database was utilized for feature selection to empower the intrusion prediction. The FEFS is a combination of three feature extraction processes: filter, wrapper and embedded algorithms. Based on the above feature extraction process, the essential features were selected for enabling the training process in the DLM. Finally, the classifier received the chosen features. The DLM is a combination of a recurrent neural network (RNN) and Tasmanian devil optimization (TDO). In the RNN, the optimal weighting parameter is selected with the assistance of the TDO. The proposed technique was implemented in MATLAB, and its effectiveness was assessed using performance metrics including sensitivity, F measure, precision, sensitivity, recall and accuracy. The proposed method was compared with the conventional techniques such as an RNN and deep neural network (DNN) and RNN–genetic algorithm (RNN-GA), respectively. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

23 pages, 948 KiB

Open AccessEditor’s ChoiceArticle

A Truthful and Reliable Incentive Mechanism for Federated Learning Based on Reputation Mechanism and Reverse Auction

by Ao Xiong, Yu Chen, Hao Chen, Jiewei Chen, Shaojie Yang, Jianping Huang, Zhongxu Li and Shaoyong Guo

Electronics 2023, 12(3), 517; https://doi.org/10.3390/electronics12030517 - 19 Jan 2023

Cited by 5 | Viewed by 3407

Abstract

As a distributed machine learning paradigm, federated learning (FL) enables participating clients to share only model gradients instead of local data and achieves the secure sharing of private data. However, the lack of clients’ willingness to participate in FL and the malicious influence [...] Read more.

As a distributed machine learning paradigm, federated learning (FL) enables participating clients to share only model gradients instead of local data and achieves the secure sharing of private data. However, the lack of clients’ willingness to participate in FL and the malicious influence of unreliable clients both seriously degrade the performance of FL. The current research on the incentive mechanism of FL lacks the accurate assessment of clients’ truthfulness and reliability, and the incentive mechanism based on untruthful and unreliable clients is unreliable and inefficient. To solve this problem, we propose an incentive mechanism based on the reputation mechanism and reverse auction to achieve a more truthful, more reliable, and more efficient FL. First, we introduce the reputation mechanism to measure clients’ truthfulness and reliability through multiple reputation evaluations and design a reliable client selection scheme. Then the reverse auction is introduced to select the optimal clients that maximize the social surplus while satisfying individual rationality, incentive compatibility, and weak budget balance. Extensive experimental results demonstrate that this incentive mechanism can motivate more clients with high-quality data and high reputations to participate in FL with less cost, which increases the FL tasks’ economic benefit by 31% and improves the accuracy from 0.9356 to 0.9813, and then promote the efficient and stable development of the FL service trading market. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

16 pages, 64628 KiB

Open AccessArticle

Single-Image Dehazing Based on Improved Bright Channel Prior and Dark Channel Prior

by Chuan Li, Changjiu Yuan, Hongbo Pan, Yue Yang, Ziyan Wang, Hao Zhou and Hailing Xiong

Electronics 2023, 12(2), 299; https://doi.org/10.3390/electronics12020299 - 6 Jan 2023

Cited by 11 | Viewed by 3823

Abstract

Single-image dehazing plays a significant preprocessing role in machine vision tasks. As the dark-channel-prior method will fail in the sky region of the image, resulting in inaccurately estimated parameters, and given the failure of many methods to address a large band of haze, [...] Read more.

Single-image dehazing plays a significant preprocessing role in machine vision tasks. As the dark-channel-prior method will fail in the sky region of the image, resulting in inaccurately estimated parameters, and given the failure of many methods to address a large band of haze, we propose a simple yet effective method for single-image dehazing based on an improved bright prior and dark channel prior. First, we use the Otsu method by particle swarm optimization to divide the hazy image into sky regions and non-sky regions. Then, we use the improved bright channel prior and dark channel prior to estimate the parameters in the physical model. Second, we propose a weighted fusion function to efficiently fuse the parameters estimated by two priors. Finally, the clear image is restored through the physical model. Experiments illustrate that our method can solve the problem of the invalidation of the dark channel prior in the sky region well and achieve high-quality image restoration, especially for images with limited haze. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

19 pages, 4990 KiB

Open AccessArticle

Modified Ring Routing Protocol for Mobile Sinks in a Dynamic Sensor Network in Smart Monitoring Applications

by Seli Mohapatra, Prafulla Kumar Behera, Prabodh Kumar Sahoo, Manoj Kumar Ojha, Chetan Swarup, Kamred Udham Singh, Saroj Kumar Pandey, Ankit Kumar and Anjali Goswami

Electronics 2023, 12(2), 281; https://doi.org/10.3390/electronics12020281 - 5 Jan 2023

Cited by 7 | Viewed by 2135

Abstract

The stationary hierarchical network faces considerable challenges from hotspots and faster network breakdowns, especially in smart monitoring applications. As a solution to this issue, mobile sinks were recommended since they are associated with huge and balanced ways to transfer data and energy across [...] Read more.

The stationary hierarchical network faces considerable challenges from hotspots and faster network breakdowns, especially in smart monitoring applications. As a solution to this issue, mobile sinks were recommended since they are associated with huge and balanced ways to transfer data and energy across the network. Again, due to the mobile sink node advertisement around the network latency and the energy utilization overheads introduced across the network, ring routing reduces the control overhead while preserving the benefits of the mobile sink, thereby optimizing the energy and improving the network life span. Consequently, we suggested a novel, distributed advanced ring routing strategy, in this work, for the mobile wireless sensor network. Extensive simulations and performance evaluation, in comparison to previous distributed mobile approaches, reveal a 37% and 40% boost in the network throughput and end-to end delay, respectively. Additionally, the lifespan of a network is determined by the control overhead and energy demand. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

11 pages, 2516 KiB

Open AccessArticle

A Substation Fire Early Warning Scheme Based on Multi-Information Fusion

by Junjie Miao, Bingyu Li, Xuhao Du and Haobin Wang

Electronics 2022, 11(24), 4222; https://doi.org/10.3390/electronics11244222 - 18 Dec 2022

Cited by 6 | Viewed by 2219

Abstract

In view of the substation fire early warning using a single information sensor monitoring, it is easy to make mistakes and omissions. Taking the cable in substation as the research object, a multi-information fusion fire prediction model based on back propagation neural network [...] Read more.

In view of the substation fire early warning using a single information sensor monitoring, it is easy to make mistakes and omissions. Taking the cable in substation as the research object, a multi-information fusion fire prediction model based on back propagation neural network (BPNN) and fuzzy set theory is proposed. Firstly, the BPNN model is trained by using the existing data. Secondly, the artificial fish swarm algorithm (AFSA) is used to optimize the BPNN, which speeds up convergence speed of the model and improves the accuracy of prediction. The fuzzy set theory is applied to fuse the predicted fire probability to obtain the optimal fire prevention and control decision. Finally, the fire protection measures are taken according to the fire decision. The experimental show that the average absolute errors of no fire, smoldering and open fire decreased by 26.06%, 38.5% and 43.13% respectively. The model has higher prediction accuracy, can reasonably output different levels of fire alarm signals, establish substation fire warning and prevention and control system, and provide reference for future substation fire and other disasters warning and prevention and control. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

19 pages, 4119 KiB

Open AccessArticle

Real-Time 3D Object Detection and Classification in Autonomous Driving Environment Using 3D LiDAR and Camera Sensors

by K. S. Arikumar, A. Deepak Kumar, Thippa Reddy Gadekallu, Sahaya Beni Prathiba and K. Tamilarasi

Electronics 2022, 11(24), 4203; https://doi.org/10.3390/electronics11244203 - 16 Dec 2022

Cited by 25 | Viewed by 4966

Abstract

The rapid development of Autonomous Vehicles (AVs) increases the requirement for the accurate prediction of objects in the vicinity to guarantee safer journeys. For effectively predicting objects, sensors such as Three-Dimensional Light Detection and Ranging (3D LiDAR) and cameras can be used. The [...] Read more.

The rapid development of Autonomous Vehicles (AVs) increases the requirement for the accurate prediction of objects in the vicinity to guarantee safer journeys. For effectively predicting objects, sensors such as Three-Dimensional Light Detection and Ranging (3D LiDAR) and cameras can be used. The 3D LiDAR sensor captures the 3D shape of the object and produces point cloud data that describes the geometrical structure of the object. The LiDAR-only detectors may be subject to false detection or even non-detection over objects located at high distances. The camera sensor captures RGB images with sufficient attributes that describe the distinct identification of the object. The high-resolution images produced by the camera sensor benefit the precise classification of the objects. However, hindrances such as the absence of depth information from the images, unstructured point clouds, and cross modalities affect assertion and boil down the environmental perception. To this end, this paper proposes an object detection mechanism that fuses the data received from the camera sensor and the 3D LiDAR sensor (OD-C3DL). The 3D LiDAR sensor obtains point clouds of the object such as distance, position, and geometric shape. The OD-C3DL employs Convolutional Neural Networks (CNN) for further processing point clouds obtained from the 3D LiDAR sensor and the camera sensor to recognize the objects effectively. The point cloud of the LiDAR is enhanced and fused with the image space on the Regions of Interest (ROI) for easy recognition of the objects. The evaluation results show that the OD-C3DL can provide an average of 89 real-time objects for a frame and reduces the extraction time by a recall rate of 94%. The average processing time is 65ms, which makes the OD-C3DL model incredibly suitable for the AVs perception. Furthermore, OD-C3DL provides mean accuracy for identifying automobiles and pedestrians at a moderate degree of difficulty is higher than that of the previous models at 79.13% and 88.76%. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

15 pages, 4063 KiB

Open AccessArticle

An End-to-End Robust Video Steganography Model Based on a Multi-Scale Neural Network

by Shutong Xu, Zhaohong Li, Zhenzhen Zhang and Junhui Liu

Electronics 2022, 11(24), 4102; https://doi.org/10.3390/electronics11244102 - 9 Dec 2022

Cited by 3 | Viewed by 2688

Abstract

The purpose of video steganography is to hide messages in the video file and prevent them from being detected, and finally the secret message can be extracted completely at the receiver. In this paper, an end-to-end video steganography based on GAN and multi-scale [...] Read more.

The purpose of video steganography is to hide messages in the video file and prevent them from being detected, and finally the secret message can be extracted completely at the receiver. In this paper, an end-to-end video steganography based on GAN and multi-scale deep learning network is proposed, which consists of the encoder, decoder and discriminator. However, in the transmission process, videos will inevitably be encoded. Thus, a noise layer is introduced between the encoder and the decoder, which makes the model able to resist popular video compressions. Experimental results show that the proposed end-to-end steganography has achieved high visual quality, large embedding capacity, and strong robustness. Moreover, the proposed method performances better compared to the latest end-to-end video steganography. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

19 pages, 2766 KiB

Open AccessArticle

A Novel Approach for Emotion Detection and Sentiment Analysis for Low Resource Urdu Language Based on CNN-LSTM

by Farhat Ullah, Xin Chen, Syed Bilal Hussain Shah, Saoucene Mahfoudh, Muhammad Abul Hassan and Nagham Saeed

Electronics 2022, 11(24), 4096; https://doi.org/10.3390/electronics11244096 - 8 Dec 2022

Cited by 13 | Viewed by 3236

Abstract

Emotion detection (ED) and sentiment analysis (SA) play a vital role in identifying an individual’s level of interest in any given field. Humans use facial expressions, voice pitch, gestures, and words to convey their emotions. Emotion detection and sentiment analysis in English and [...] Read more.

Emotion detection (ED) and sentiment analysis (SA) play a vital role in identifying an individual’s level of interest in any given field. Humans use facial expressions, voice pitch, gestures, and words to convey their emotions. Emotion detection and sentiment analysis in English and Chinese have received much attention in the last decade. Still, poor-resource languages such as Urdu have been mostly disregarded, which is the primary focus of this research. Roman Urdu should also be investigated like other languages because social media platforms are frequently used for communication. Roman Urdu faces a significant challenge in the absence of corpus for emotion detection and sentiment analysis because linguistic resources are vital for natural language processing. In this study, we create a corpus of 1021 sentences for emotion detection and 20,251 sentences for sentiment analysis, both obtained from various areas, and annotate it with the aid of human annotators from six and three classes, respectively. In order to train large-scale unlabeled data, the bag-of-word, term frequency-inverse document frequency, and Skip-gram models are employed, and the learned word vector is then fed into the CNN-LSTM model. In addition to our proposed approach, we also use other fundamental algorithms, including a convolutional neural network, long short-term memory, artificial neural networks, and recurrent neural networks for comparison. The result indicates that the CNN-LSTM proposed method paired with Word2Vec is more effective than other approaches regarding emotion detection and evaluating sentiment analysis in Roman Urdu. Furthermore, we compare our based model with some previous work. Both emotion detection and sentiment analysis have seen significant improvements, jumping from an accuracy of 85% to 95% and from 89% to 93.3%, respectively. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

16 pages, 2390 KiB

Open AccessArticle

Study on Price Bubbles of China’s Agricultural Commodity against the Background of Big Data

by Jiayue Wang, Kun Ma, Ling Zhang and Jianzhong Wang

Electronics 2022, 11(24), 4067; https://doi.org/10.3390/electronics11244067 - 7 Dec 2022

Cited by 2 | Viewed by 2514

Abstract

Agriculture provides a basis for social and economic development. It is therefore crucial for society and the economy to stabilize agricultural prices. Recent large increases and decreases in Chinese agricultural commodity prices have increased production risks, heightened fluctuations in the domestic agricultural supply, [...] Read more.

Agriculture provides a basis for social and economic development. It is therefore crucial for society and the economy to stabilize agricultural prices. Recent large increases and decreases in Chinese agricultural commodity prices have increased production risks, heightened fluctuations in the domestic agricultural supply, and impacted the stability of the global agricultural market. Meanwhile, big data technology has advanced quickly and now serves as a foundation for the investigation of time series bubbles. Identifying agricultural price bubbles is important for determining agricultural production decisions and policies that control agricultural prices. Using weekly agricultural price data from 2009 to 2021, this paper identifies agricultural price bubbles, pinpoints their time points, and examines their causes. According to our research, prices for corn, hog, green onions, pork, and ginger all have bubbles, but garlic do not. The quantity, length, time distribution, and type of bubbles differ significantly among corn, ginger, green onion, hog, and pork. The main causes for ginger and green onion price bubbles are speculation and natural disasters. Price bubbles for hog and pork are influenced by animal disease and rising costs. Conflicts between supply and demand and changes in price policy cause corn price bubbles to form. This paper advises that the government adopt various regulatory actions to stabilize agricultural prices depending on the characteristics and causes of the various types of agricultural price bubbles, it should also improve the early warning system and response mechanism for agricultural price bubbles and focus on how policies and market processes work together. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

28 pages, 20127 KiB

Open AccessFeature PaperArticle

High-Frequency Forecasting of Stock Volatility Based on Model Fusion and a Feature Reconstruction Neural Network

by Zhiwei Shi, Zhifeng Wu, Shuaiwei Shi, Chengzhi Mao, Yingqiao Wang and Laiqi Zhao

Electronics 2022, 11(23), 4057; https://doi.org/10.3390/electronics11234057 - 6 Dec 2022

Cited by 2 | Viewed by 2266

Abstract

Stock volatility is an important measure of financial risk. Due to the complexity and variability of financial markets, time series forecasting in the financial field is extremely challenging. This paper proposes a “model fusion learning algorithm” and a “feature reconstruction neural network” to [...] Read more.

Stock volatility is an important measure of financial risk. Due to the complexity and variability of financial markets, time series forecasting in the financial field is extremely challenging. This paper proposes a “model fusion learning algorithm” and a “feature reconstruction neural network” to forecast the future 10 min volatility of 112 stocks from different industries over the past three years. The results show that the model in this paper has higher fitting accuracy and generalization ability than the traditional model (CART, MLR, LightGBM, etc.). This study found that the “model fusion learning algorithm” can be well applied to financial data modeling; the “feature reconstruction neural network” can well-model data sets with fewer features. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

15 pages, 3529 KiB

Open AccessArticle

Design and Evaluation of a Personal Robot Playing a Self-Management for Children with Obesity

by Tareq Alhmiedat and Mohammed Alotaibi

Electronics 2022, 11(23), 4000; https://doi.org/10.3390/electronics11234000 - 2 Dec 2022

Cited by 6 | Viewed by 2125

Abstract

The preponderance of obesity and being overweight among children has increased significantly during the last two decades in Saudi Arabia and United Arab Emirates (UAE) with overwhelming consequences to public health. Most recommended approaches have paid attention to a healthier diet and physical [...] Read more.

The preponderance of obesity and being overweight among children has increased significantly during the last two decades in Saudi Arabia and United Arab Emirates (UAE) with overwhelming consequences to public health. Most recommended approaches have paid attention to a healthier diet and physical activity (PA) to reduce obesity. Recent research shows that the use of social robots could play a vital role in encouraging children to improve their skills in self-management. As children need to be surprised and feel a sense of enjoyment when involved in any activity where they can spend time and actively engage in activities, social robots could be an effective intervention for this purpose. In this context, the current project aimed to build an innovation social robot system to offer a set of activities to help obese children improve their capabilities to manage their selves properly and increase their obesity knowledge. This study aimed to determine the perceptions of obese children towards the NAO robot, a new medical technology, and analyze their responses to the robot’s advice and education-related activities. A proposed model of the intervention using the NAO robot is discussed in this study, and a pilot study was conducted to assess the performance of the proposed system. The obtained results showed an average acceptability of 89.37% for social robots to be involved in obesity management. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

17 pages, 3303 KiB

Open AccessArticle

Research on Short-Term Load Forecasting Based on Optimized GRU Neural Network

by Chao Li, Quanjie Guo, Lei Shao, Ji Li and Han Wu

Electronics 2022, 11(22), 3834; https://doi.org/10.3390/electronics11223834 - 21 Nov 2022

Cited by 11 | Viewed by 2233

Abstract

Accurate short-term load forecasting can ensure the safe and stable operation of power grids, but the nonlinear load increases the complexity of forecasting. In order to solve the problem of modal aliasing in historical data, and fully explore the relationship between time series [...] Read more.

Accurate short-term load forecasting can ensure the safe and stable operation of power grids, but the nonlinear load increases the complexity of forecasting. In order to solve the problem of modal aliasing in historical data, and fully explore the relationship between time series characteristics in load data, this paper proposes a gated cyclic network model (SSA–GRU) based on sparrow algorithm optimization. Firstly, the complementary sets and empirical mode decomposition (EMD) are used to decompose the original data to obtain the characteristic components. The SSA–GRU combined model is used to predict the characteristic components, and finally obtain the prediction results, and complete the short-term load forecasting. Taking the real data of a company as an example, this paper compares the combined model CEEMD–SSA–GRU with EMD–SSA–GRU, SSA–GRU, and GRU models. Experimental results show that this model has better prediction effect than other models. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

16 pages, 2386 KiB

Open AccessArticle

Artificial Intelligence Model for the Identification of the Personality of Twitter Users through the Analysis of Their Behavior in the Social Network

by William Villegas-Ch., Daniel Mauricio Erazo, Iván Ortiz-Garces, Walter Gaibor-Naranjo and Xavier Palacios-Pacheco

Electronics 2022, 11(22), 3811; https://doi.org/10.3390/electronics11223811 - 19 Nov 2022

Cited by 4 | Viewed by 4511

Abstract

Currently, social networks have become one of the most used channels by society to share their ideas, their status, generate trends, etc. By applying artificial intelligence techniques and sentiment analysis to the large volume of data found in social networks, it is possible [...] Read more.

Currently, social networks have become one of the most used channels by society to share their ideas, their status, generate trends, etc. By applying artificial intelligence techniques and sentiment analysis to the large volume of data found in social networks, it is possible to predict the personality of people. In this work, the development of a data analysis model with machine learning algorithms with the ability to predict the personality of a user based on their activity on Twitter is proposed. To do this, a data collection and transformation process is carried out to be analyzed with sentiment analysis techniques and the linguistic analysis of tweets. Very successful results were obtained by developing a training process for the machine learning algorithm. By generating comparisons of this model, with the related literature, it is shown that social networks today house a large volume of data that contains significant value if your approach is appropriate. Through the analysis of tweets, retweets, and other factors, there is the possibility of creating a virtual profile on the Internet for each person; the uses can vary, from creating marketing campaigns to optimizing recruitment processes. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

21 pages, 2507 KiB

Open AccessArticle

A Hybrid Model to Predict Stock Closing Price Using Novel Features and a Fully Modified Hodrick–Prescott Filter

by Qazi Mudassar Ilyas, Khalid Iqbal, Sidra Ijaz, Abid Mehmood and Surbhi Bhatia

Electronics 2022, 11(21), 3588; https://doi.org/10.3390/electronics11213588 - 3 Nov 2022

Cited by 10 | Viewed by 4621

Abstract

Forecasting stock market prices is an exciting knowledge area for investors and traders. Successful predictions lead to high financial revenues and prevent investors from market risks. This paper proposes a novel hybrid stock prediction model that improves prediction accuracy. The proposed method consists [...] Read more.

Forecasting stock market prices is an exciting knowledge area for investors and traders. Successful predictions lead to high financial revenues and prevent investors from market risks. This paper proposes a novel hybrid stock prediction model that improves prediction accuracy. The proposed method consists of three main components, a noise-filtering technique, novel features, and machine learning-based prediction. We used a fully modified Hodrick–Prescott filter to smooth the historical stock price data by removing the cyclic component from the time series. We propose several new features for stock price prediction, including the return of firm, return open price, return close price, change in return open price, change in return close price, and volume per total. We investigate traditional and deep machine learning approaches for prediction. Support vector regression, auto-regressive integrated moving averages, and random forests are used for conventional machine learning. Deep learning techniques comprise long short-term memory and gated recurrent units. We performed several experiments with these machine learning algorithms. Our best model achieved a prediction accuracy of 70.88%, a root-mean-square error of 0.04, and an error rate of 0.1. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

20 pages, 979 KiB

Open AccessArticle

Malware Analysis in IoT & Android Systems with Defensive Mechanism

by Chandra Shekhar Yadav, Jagendra Singh, Aruna Yadav, Himansu Sekhar Pattanayak, Ravindra Kumar, Arfat Ahmad Khan, Mohd Anul Haq, Ahmed Alhussen and Sultan Alharby

Electronics 2022, 11(15), 2354; https://doi.org/10.3390/electronics11152354 - 28 Jul 2022

Cited by 65 | Viewed by 6404

Abstract

The Internet of Things (IoT) and the Android operating system have made cutting-edge technology accessible to the general public. These are affordable, easy-to-use, and open-source technology. Android devices connect to different IoT devices such as IoT-enabled cameras, Alexa powered by Amazon, and various [...] Read more.

The Internet of Things (IoT) and the Android operating system have made cutting-edge technology accessible to the general public. These are affordable, easy-to-use, and open-source technology. Android devices connect to different IoT devices such as IoT-enabled cameras, Alexa powered by Amazon, and various other sensors. Due to the escalated growth of Android devices, users are facing cybercrime through their Android devices. This article aims to provide a comprehensive study of the IoT and Android systems. This article classifies different attacks on IoT and Android devices and mitigation strategies proposed by different researchers. The article emphasizes the role of the developer in secure application design. This article attempts to provide a relative analysis of several malware detection methods in the different environments of attacks. This study expands the awareness of certain application-hardening strategies applicable to IoT devices and Android applications and devices. This study will help domain experts and researchers to gain knowledge of IoT systems and Android systems from a security point of view and provide insight into how to design more efficient, robust, and comprehensive solutions. This article discusses different attack vectors and mitigation strategies available to both developers and in the open domain. Certain guidelines are also suggested for application and platform developers, as well as application databases (Google play store), to limit the risk of attack, and users can form their own defense with knowledge regarding keeping hardware and software updated and securing their system with a strong password. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

14 pages, 3092 KiB

Open AccessArticle

Defect Detection Scheme for Key Equipment of Transmission Line for Complex Environment

by Jian Wang, Fangming Deng and Baoquan Wei

Electronics 2022, 11(15), 2332; https://doi.org/10.3390/electronics11152332 - 27 Jul 2022

Cited by 9 | Viewed by 1962

Abstract

Aiming at the difficulty in detecting defects of key equipment of transmission lines in small samples and complex environments, and the problems of low accuracy and unreliability in one-time detection using traditional deep learning-based methods, an image detection scheme combining optimized deep convolutional [...] Read more.

Aiming at the difficulty in detecting defects of key equipment of transmission lines in small samples and complex environments, and the problems of low accuracy and unreliability in one-time detection using traditional deep learning-based methods, an image detection scheme combining optimized deep convolutional neural networks and Kalman filtering is proposed. The convolutional neural network architecture is based on Faster Region-based Convolutional Neural Networks (R-CNNs). First, the model backbone network is constructed by MobileNet, which effectively reduces the computational cost. Secondly, a soft nonmaximum suppression algorithm is integrated to solve the occlusion problem of target parts, and the context-aware ROI pooling layer replaces the original pooling layer, maintaining the original structure of small-sized components. Finally, the detection results are corrected twice by Kalman filtering to further improve the detection accuracy and reliability. The experimental results show that this method can realize the accurate detection of components in complex transmission line equipment, the mean Average Precision (mAP) reaches 91.10%, which is 11.05% higher than the original model, and the detection time of each picture is only 0.05 s. Compared with other detection algorithms under the same conditions, the comprehensive performance of the proposed method can be improved by 20%. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

19 pages, 7102 KiB

Open AccessArticle

A Radical Safety Measure for Identifying Environmental Changes Using Machine Learning Algorithms

by Pravin R. Kshirsagar, Hariprasath Manoharan, Shitharth Selvarajan, Sara A. Althubiti, Fayadh Alenezi, Gautam Srivastava and Jerry Chun-Wei Lin

Electronics 2022, 11(13), 1950; https://doi.org/10.3390/electronics11131950 - 22 Jun 2022

Cited by 17 | Viewed by 2377

Abstract

Due to air pollution, pollutants that harm humans and other species, as well as the environment and natural resources, can be detected in the atmosphere. In real-world applications, the following impurities that are caused due to smog, nicotine, bacteria, yeast, biogas, and carbon [...] Read more.

Due to air pollution, pollutants that harm humans and other species, as well as the environment and natural resources, can be detected in the atmosphere. In real-world applications, the following impurities that are caused due to smog, nicotine, bacteria, yeast, biogas, and carbon dioxide occur uninterruptedly and give rise to unavoidable pollutants. Weather, transportation, and the combustion of fossil fuels are all factors that contribute to air pollution. Uncontrolled fire in parts of grasslands and unmanaged construction projects are two factors that contribute to air pollution. The challenge of assessing contaminated air is critical. Machine learning algorithms are used to forecast the surroundings if any pollution level exceeds the corresponding limit. As a result, in the proposed method air pollution levels are predicted using a machine learning technique where a computer-aided procedure is employed in the process of developing technological aspects to estimate harmful element levels with 99.99% accuracy. Some of the models used to enhance forecasts are Mean Square Error (MSE), Coefficient of Determination Error (CDE), and R Square Error (RSE). Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

Review

Jump to: Research

46 pages, 12779 KiB

Open AccessReview

From Beginning to BEGANing: Role of Adversarial Learning in Reshaping Generative Models

by Aradhita Bhandari, Balakrushna Tripathy, Amit Adate, Rishabh Saxena and Thippa Reddy Gadekallu

Electronics 2023, 12(1), 155; https://doi.org/10.3390/electronics12010155 - 29 Dec 2022

Cited by 5 | Viewed by 3539

Abstract

Deep generative models, such as deep Boltzmann machines, focused on models that provided parametric specification of probability distribution functions. Such models are trained by maximizing intractable likelihood functions, and therefore require numerous approximations to the likelihood gradient. This underlying difficulty led to the [...] Read more.

Deep generative models, such as deep Boltzmann machines, focused on models that provided parametric specification of probability distribution functions. Such models are trained by maximizing intractable likelihood functions, and therefore require numerous approximations to the likelihood gradient. This underlying difficulty led to the development of generative machines such as generative stochastic networks, which do not represent the likelihood functions explicitly, like the earlier models, but are trained with exact backpropagation rather than the numerous approximations. These models use piecewise linear units that are having well behaved gradients. Generative machines were further extended with the introduction of an associative adversarial network leading to the generative adversarial nets (GANs) model by Goodfellow in 2014. The estimations in GANs process two multilayer perceptrons, called the generative model and the discriminative model. These are learned jointly by alternating the training of the two models, using game theory principles. However, GAN has many difficulties, including: the difficulty of training the models; criticality in the selection of hyper-parameters; difficulty in the control of generated samples; balancing the convergence of the discriminator and generator; and the problem of modal collapse. Since its inception, efforts have been made to tackle these issues one at a time or in multiples at several stages by many researchers. However, most of these have been handled efficiently in the boundary equilibrium generative adversarial networks (BEGAN) model introduced by Berthelot et al. in 2017. In this work we presented the advent of adversarial networks, starting with the history behind the models and c developments done on GANs until the BEGAN model was introduced. Since some time has elapsed since the proposal of BEGAN, we provided an up-to-date study, as well as future directions for various aspects of adversarial learning. Full article

(This article belongs to the Special Issue Artificial Intelligence Technologies and Applications)

► Show Figures

Figure 1

Journal Menu

Journal Browser

Artificial Intelligence Technologies and Applications

Share This Special Issue

Special Issue Editors

Special Issue Information

Keywords

Benefits of Publishing in a Special Issue

Published Papers (39 papers)

Research

Review

Further Information

Guidelines

MDPI Initiatives

Follow MDPI