Search

To ensure structural safety and integrity, a novel framework is developed for detecting the loosening of multi-bolt connections using wavelet entropy of vibro-acoustic modulation (VAM) signals. Wavelet entropy is employed as the dynamic index to capture the intricate time-frequency characteristics that are indicative of the connection status. Taking the wavelet entropy vectors as input, the proposed framework distinguishes itself by integrating a Transformer model for high-dimensional feature extraction with the recursive feature elimination (RFE) for essential feature selection, followed by a support vector machine (SVM) model for classification. Specifically, the Transformer model with innovative positional encoding capability helps to extract the time-dependent transient features that are sensitive to the bolt loosening. The RFE process reduces the data dimensionality while discerning the diagnostic information for more accurate classification. Through the experiment on a four-bolt joint, the identification results with cross-validation showed high accuracy and robustness of the proposed framework across various loosening cases. It outperformed the traditional SVM, long short-term memory network (LSTM), convolutional neural network (CNN)-SVM models without and with RFE, as well as the Transformer-SVM model without RFE, achieving an accuracy increase of 15.72%, 11.74%, 9.47%, 5.49%, and 5.06%, respectively. The proposed framework was demonstrated to be able to learn the damage-sensitive features more effectively from wavelet entropy data, marking a significant advancement in the health monitoring of engineering structures with high-strength bolt connections. [ABSTRACT FROM AUTHOR]

Research on developing deep learning techniques for autonomous spacecraft relative navigation challenges is continuously growing in recent years. Adopting those techniques offers enhanced performance. However, such approaches also introduce heightened apprehensions regarding the trustability and security of such deep learning methods through their susceptibility to adversarial attacks. In this work, we propose a novel approach for adversarial attack detection for deep neural network-based relative pose estimation schemes based on the explainability concept. We develop for an orbital rendezvous scenario an innovative relative pose estimation technique adopting our proposed Convolutional Neural Network (CNN), which takes an image from the chaser's onboard camera and outputs accurately the target's relative position and rotation. We perturb seamlessly the input images using adversarial attacks that are generated by the Fast Gradient Sign Method (FGSM). The adversarial attack detector is then built based on a Long Short Term Memory (LSTM) network which takes the explainability measure namely SHapley Value from the CNN-based pose estimator and flags the detection of adversarial attacks when acting. Simulation results show that the proposed adversarial attack detector achieves a detection accuracy of 99.21%. Both the deep relative pose estimator and adversarial attack detector are then tested on real data captured from our laboratory-designed setup. The experimental results from our laboratory-designed setup demonstrate that the proposed adversarial attack detector achieves an average detection accuracy of 96.29%. [ABSTRACT FROM AUTHOR]

Enabling diabetic patients to predict their Blood Glucose Levels (BGL) is a crucial aspect of managing their metabolic condition, as it allows them to take appropriate measures to avoid hypo or hyperglycemia. Machine Learning (ML) and Deep Learning (DL) techniques have made this possible, and this paper evaluates and compares the performance of five distinct ML/DL models including: Convolutional Neural Network (CNN), Long Short Term Memory (LSTM), Support Vector Regression (SVR), Gated Reccurent Unit (GRU) and Deep Belief Network (DBN) for forecasting BGL, by applying two different forecasting methods, namely One Step Ahead (OSF) and Multi‐Step Ahead (MSF) comprising five different variants. The performance is evaluated based on four metrics: Mean Absolute Error (MAE), Mean Magnitude Relative Error (MMRE), Root Mean Square Error (RMSE) and Predictive Level (PRED). Additionally, the statistical significance of the regressors was evaluated using the Scott‐Knott (SK) test, while the Borda Count (BC) voting system was employed to rank them. The results indicate that the best performance was achieved with OSF using GRU. Furthermore, the effectiveness of an MSF strategy depends on the ML/DL technique used, and the best combinations were DBN with DirRec, DBN with Recursive, SVR with Recursive and SVR with DirRec. Additionally, DirRec was found to be the best strategy, as it consistently ranked first regardless of the ML/DL technique used. [ABSTRACT FROM AUTHOR]

Autism spectrum disorder (ASD) is considered a spectrum disorder. The availability of technology to identify the characteristics of ASD will have major implications for clinicians. In this article, we present a new autism diagnosis method based on attention mechanisms for behavior modelingbased feature embedding along with aspect-based analysis for a better classification of ASD. The hybrid model comprises a convolutional neural network (CNN) architecture that integrates two bidirectional long short-term memory (BiLSTM) blocks, together with additional propagation techniques, for the purpose of classification the origins of Autism Tweet dataset; the proposed work takes Autism Tweet dataset and preprocesses them to employ n-gram to extract features of which the features of the ASD behavior are fed to generate the significant behavior for classification. The model takes into account both behavior-guided features across every aspect of the Class/ASD to provide higher accuracy using Adam optimizer. The experimental values inferred that the n-BiLSTM technique reaches maximum accuracy with 98%. [ABSTRACT FROM AUTHOR]

This research paper monitors the patient's health using sensor data, cloud, and big data Hadoop tools and used to predict heart attack and related results were discussed in detail. The integration of big data, and wearable sensors in pervasive computing has significantly enhanced healthcare services. This proposal focuses on developing an advanced healthcare monitoring system tailored for tracking the activities of elderly individuals. The wearable sensors are placed on humans at a right angle, left arm, right arm, and chest to collect the data. The large data are split into smaller segments using the map and reduce process of big data Hadoop tools. The intensity-modulated radiation therapy (IMRT) approach is used for the mapping phase and deep convolutional neural network (DCNN), deep belief network (DBN), and long short-term memory (LSTM) and proposed deep learning heart rate prediction (DLHRP) algorithms are used for the combiner/reduce phase. The reduction process combines similar segments of data to predict identical classes to predict the severity of human conditions. The proposed IMRTDLHRP system has improved performance of 96.34% accuracy compared with 84.25%, 89.47%, and 91.58% compared to DCNN, DBN, and LSTM respectively, therefore proposed framework has significant improvement over existing approaches. [ABSTRACT FROM AUTHOR]

Email types sorting is one of the most important tasks in current information systems with the purpose to improve the security of messages, allowing for their sorting into different types. This paper aims at studying the Convolution Neural Network and Long Short-Term Memory (CNN-LSTM), Convolution Neural Network and Gated Recurrent Unit (CNN-GRU) and Long Short-Term Memory (LSTM) deep learning models for the classification of emails into categories such as "Normal", "Fraudulent", "Harassment" and "Suspicious". The architecture of each model is discussed and the results of the models' performance by testing on labelled emails are presented. Evaluation outcomes show substantial gains in precision and throughput to conventional approaches hence inferring to the efficiency of these proposed models for automated email filtration and content evaluation. Last but not the least, the performance of the classification algorithms is evaluated with the help of parameters like Accuracy, precision, recall and F1-Score. From the experiment, the models found out that CNN-LSTM, together with the Term Frequency and Inverse Document Frequency (TF-IDF) feature extraction yielded the highest accuracy. The accuracy, precision, recall and f1-score values are 99. 348%, 99. 5%, 99. 3%, and 99. 2%, respectively. [ABSTRACT FROM AUTHOR]

Spreading fake news on social media is regarded as a cybercrime that greatly affects society, government and people. Identifying this fake news by manual analysis is a complex task. Hence, various researchers carried out an analysis on exploiting intelligent approaches to detect fake news. This work aims to propose a hybrid deep learning model for fake news detection. In these works, the news is verified in a unidirectional manner. Hence, there is a demand to change the present scenario and a new model is required for increasing the accuracy of the fake news detection. In this work, the deep learning (DL) model Long Short Term Memory (LSTM) with 3 Parallel-concatenated Convolutional Neural Networks (PCCNN) is utilised for fake news detection. For the feature extraction process, the methods like Term Frequency- Inverse Document Frequency (TF-IDF) and Latent Semantic Analysis (LSA) are utilised. Finally, for optimising the weights of the neural network, the metaheuristic optimisation Enhanced Sun Flower Optimisation (ESFO) algorithm is used. The robustness of LSTM-PCCNN is compared with other deep learning models to verify its robustness. The experimentation is carried out on the two benchmark datasets and obtained better accuracies of 0.994 on the fake news and 0.997 on the Real and fake news datasets respectively. [ABSTRACT FROM AUTHOR]

Recently, social demands for a good quality of life have increased among the elderly and disabled people. So, biomedical engineers and robotic researchers aimed to fuse these techniques in a novel rehabilitation system. Moreover, these models utilized the biomedical signals acquired from the human body's particular organ, cells, or tissues. The human motion intention prediction mechanism plays an essential role in various applications, such as assistive and rehabilitation robots, that execute specific tasks among elders and physically impaired individuals. However, more complications are increased in the human–machine-based interaction techniques, creating more scope for personalized assistance for the human motion intention prediction system. Therefore, in this paper, an Adaptive Hybrid Network (AHN) is implemented for effective human motion intention prediction. Initially, multimodal data like electroencephalogram (EEG)/Electromyography (EMG) signals and sensor measures data are collected from the available data resource. The gathered EEG/EMG signals are then converted into spectrogram images and sent to AH-CNN-LSTM, which is the integration of an Adaptive Hybrid Convolution Neural Network (AH-CNN) with a Long Short-Term Memory (LSTM) network. Similarly, the data details of sensor measures are directly subjected to AH-CNN-Res-LSTM, which is the combination of Adaptive Hybrid CNN with Residual Network and LSTM (Res-LSTM) to get the predictive result. Further, to enhance the prediction, the parameters in both the AH-CNN-LSTM and AH-CNN-Res-LSTM techniques are optimized using the Improved Yellow Saddle Goatfish Algorithm (IYSGA). The efficiency of the implemented model is computed by conducting the comparison experiment of the proposed technique with other standard models. The performance outcome of the developed method outperformed the other traditional methods. [ABSTRACT FROM AUTHOR]

The emergence of small-drone technology has revolutionized the way we use drones. Small drones leverage the Internet of Things (IoT) to deliver location-based navigation services, making them versatile tools for various applications. Unmanned aerial vehicle (UAV) communication networks and smart grid communication protocols share several similarities, particularly in terms of their architecture, the nature of the data they handle, and the security challenges they face. To ensure the safe, secure, and reliable operation of both, it is imperative to establish a secure and dependable network infrastructure and to develop and implement robust security and privacy mechanisms tailored to the specific needs of this domain. The research evaluates the performance of deep learning models, including convolutional neural networks (CNN), long short-term memory (LSTM), CNN-LSTM, and convolutional long short-term memory (ConvLSTM), in detecting intrusions within UAV communication networks. The study utilizes five diverse and realistic datasets, namely, KDD Cup-99, NSL-KDD, WSN-DS, CICIDS 2017, and Drone, to simulate real-world intrusion scenarios. Notably, the ConvLSTM model consistently achieves an accuracy of 99.99%, showcasing its potential in securing UAVs from cyber threats. By demonstrating its superior performance, this work highlights the importance of tailored security mechanisms in safeguarding UAV technology against evolving cyber threats. Ultimately, this research contributes to the growing body of knowledge on UAV security, emphasizing the necessity of high-quality datasets and advanced models in ensuring the safe, secure, and reliable operation of UAV systems across various industries. [ABSTRACT FROM AUTHOR]

This study proposes an AI-based framework to predict the quality of results from the deep drawing process without requiring considerable amounts of actual data. A few-shot learning method with a Siamese network was employed for training with limited experimental data and virtual simulation data. As the base of the Siamese network, three network architectures, fully connected network (FCN), convolutional neural network (CNN), and long short-term memory (LSTM), were considered. By increasing the ratio of the experimental data, the best accuracy for each network was determined. Finally, the K-nearest neighbor algorithm was trained to predict the drawing quality using the embedding vector from the Siamese network. In all networks, it was confirmed that the accuracy of the classification algorithm improved as more experimental data were added. At this time, the classification accuracy of the CNN was 100%, which was significantly superior to the 77.8% of the FCN and 88.9% of the LSTM. Finally, the AI-based framework proposed in this paper can be effectively applied to various press forming processes as a method for predicting the quality of deep drawing molded products. [ABSTRACT FROM AUTHOR]

Electric shock protection is critical for ensuring power safety in low-voltage grids, and robust fault diagnosis methods provide an essential foundation for the accurate operation of such protection devices. However, current low-voltage electric shock protection devices often suffer from limitations in operational precision and in their ability to effectively recognize electric shock types. To address these challenges, this paper proposes a fault diagnosis method for low-voltage electric shocks based on an attention-enhanced parallel CNN-BiLSTM model. The method first utilizes CNN to extract local spatial features of the electric shock signal and BiLSTM to capture temporal features. An attention mechanism is then introduced to fuse the local spatial and temporal features with weighted emphasis. Finally, a fully connected layer maps the fused features to the output layer, generating diagnostic results. Visualization through T-SNE analysis validates the improvement in model performance due to the attention mechanism. Comparative experiments show that the proposed model outperforms single models and other combined models in terms of accuracy, precision, recall, F1 score, and convergence speed. The results demonstrate that the proposed model achieves a fault diagnosis accuracy of 99.55%. [ABSTRACT FROM AUTHOR]

Financial time series prediction is a fundamental problem in investment and risk management. Deep learning models, such as multilayer perceptrons, Convolutional Neural Networks (CNNs), and Long Short-Term Memory (LSTM), have been widely used in modeling time series data by incorporating historical information. Among them, LSTM has shown excellent performance in capturing long-term temporal dependencies in time-series data, owing to its enhanced internal memory mechanism. In spite of the success of these models, it is observed that in the presence of sharp changing points, these models fail to perform. To address this problem, we propose, in this article, an innovative financial time series prediction method inspired by the Deep Operator Network (DeepONet) architecture, which uses a combination of transformer architecture and a one-dimensional CNN network for processing feature-based information, followed by an LSTM based network for processing temporal information. It is therefore named the CNN–LSTM–Transformer (CLT) model. It not only incorporates external information to identify latent patterns within the financial data but also excels in capturing their temporal dynamics. The CLT model adapts to evolving market conditions by leveraging diverse deep-learning techniques. This dynamic adaptation of the CLT model plays a pivotal role in navigating abrupt changes in the financial markets. Furthermore, the CLT model improves the long-term prediction accuracy and stability compared with state-of-the-art existing deep learning models and also mitigates adverse effects of market volatility. The experimental results show the feasibility and superiority of the proposed CLT model in terms of prediction accuracy and robustness as compared to existing prediction models. Moreover, we posit that the innovation encapsulated in the proposed DeepONet-inspired CLT model also holds promise for applications beyond the confines of finance, such as remote sensing, data mining, natural language processing, and so on. [ABSTRACT FROM AUTHOR]

Satellite SAR (synthetic aperture radar) imagery offers global coverage and all-weather recording capabilities, making it valuable for applications like remote sensing and maritime surveillance. However, its use in machine learning-based automatic target classification faces challenges, including the limited availability of SAR target training samples and the inherent constraints of SAR images, which provide less detailed features compared to natural images. These issues hinder the effective training of convolutional neural networks (CNNs) and complicate the transfer learning process due to the distinct imaging mechanisms of SAR and natural images. To address these challenges, we propose a shallow CNN architecture specifically designed to optimize performance on SAR datasets. Evaluations were performed on three datasets: FUSAR-Ship, OpenSARShip, and MSTAR. While the FUSAR-Ship and OpenSARShip datasets present difficulties due to their limited and imbalanced class distributions, MSTAR serves as a benchmark with balanced classes. To compare and optimize the proposed shallow architecture, we examine various properties of CNN components, such as the filter numbers and sizes in the convolution layers, to reduce redundancy, improve discrimination capability, and decrease network size and learning time. In the second phase of this paper, we combine the CNN with Long short-term memory (LSTM) networks to enhance SAR image classification. Comparative experiments with six state-of-the-art CNN architectures (VGG16, ResNet50, Xception, DenseNet121, EfficientNetB0, and MobileNetV2) demonstrate the superiority of the proposed approach, achieving competitive accuracy while significantly reducing training times and network complexity. This study underscores the potential of customized architectures to address SAR-specific challenges and enhance the efficiency of target classification. [ABSTRACT FROM AUTHOR]

This paper examines Connected Smart Green Buildings (CSGBs) in Burnaby, BC, Canada, with a focus on townhouses with one to four bedrooms. The proposed model integrates sustainable materials and smart components such as recycled insulation, Photovoltaic (PV) solar panels, smart meters, and high-efficiency systems. These elements improve energy efficiency and promote sustainability. Operating in island mode, CSGBs can function independently of the grid, providing resilience during power outages and reducing reliance on external energy sources. Real data on electricity, gas, and water consumption are used to optimize load management under isolated conditions. Electric Vehicles (EVs) are also considered in the system. They serve as energy storage devices and, through Vehicle-to-Grid (V2G) technology, can supply power when needed. A hybrid Machine Learning (ML) model combining Long Short-Term Memory (LSTM) and a Convolutional Neural Network (CNN) is proposed to improve the performance. The metrics considered include accuracy, efficiency, emissions, and cost. The performance was compared with several well-known models including Linear Regression (LR), CNN, LSTM, Random Forest (RF), Gradient Boosting (GB), and hybrid LSTM–CNN, and the results show that the proposed model provides the best results. For a four-bedroom Connected Smart Green Townhouse (CSGT), the Mean Absolute Percentage Error (MAPE) is 4.43%, the Root Mean Square Error (RMSE) is 3.49 kWh, the Mean Absolute Error (MAE) is 3.06 kWh, and R 2 is 0.81. These results indicate that the proposed model provides robust load optimization, particularly in island mode, and highlight the potential of CSGBs for sustainable urban living. [ABSTRACT FROM AUTHOR]

Solar radiation forecasting is the basis of building a robust solar power system. Most ground-based forecasting methods are unable to consider the impact of cloud changes on future solar radiation. To alleviate this limitation, this study develops a hybrid network which relies on a convolutional neural network to extract cloud motion patterns from time series of satellite observations and a long short-term memory neural network to establish the relationship between future solar radiation and cloud information, as well as antecedent measurements. We carefully select the optimal scales to consider the spatial and temporal correlations of solar radiation and design test experiments at ten stations to check the model performance in various climate zones. The results demonstrate that the solar radiation forecasting accuracy is considerably improved, particularly in cloudy conditions, compared with purely ground-based models. The maximum magnitude of improvements reaches up to 50 W/m2 (15%) in terms of the (relative) root mean squared error (RMSE) for 1 h ahead forecasts. The network achieves superior forecasts with correlation coefficients varying from 0.96 at 1 h ahead to 0.85 at 6 h ahead. Forecast errors are related to cloud regimes, of which the cloud amount leads to a maximum relative RMSE difference of about 50% with an additional 5% from cloud variability. This study ascertains that multi-source data fusion contributes to a better simulation of cloud impacts and a combination of different deep learning techniques enables more reliable forecasts of solar radiation. In addition, multi-step forecasts with a low latency make the advance planning and management of solar energy possible in practical applications. [ABSTRACT FROM AUTHOR]

The widespread fake news challenges the management of low-quality information, making effective detection strategies necessary. This study addresses this critical issue by advancing fake news detection in Arabic and overcoming limitations in existing approaches. Deep learning models, Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM), EfficientNetB4, Inception, Xception, ResNet, ConvLSTM and a novel voting ensemble framework combining CNN and LSTM are employed for text classification. The proposed framework integrates the ELMO word embedding technique having contextual representation capabilities, which is compared with GloVe, BERT, FastText and FastText subwords. Comprehensive experiments demonstrate that the proposed voting ensemble, combined with ELMo word embeddings, consistently outperforms previous approaches. It achieves an accuracy of 98.42%, precision of 98.54%, recall of 99.5%, and an F1 score of 98.93%, offering an efficient and highly effective solution for text classification tasks.The proposed framework benchmark against state-of-the-art transformer architectures, including BERT and RoBERTa, demonstrates competitive performance with significantly reduced inference time and enhanced interpretability accompanied by a 5-fold cross-validation technique. Furthermore, this research utilizes the LIME XAI technique to provide deeper insights into the contribution of each feature in predicting a specific target class. These findings show the proposed framework's effectiveness in dealing with the issues of detecting false news, particularly in Arabic text. By generating higher performance metrics and displaying comparable results, this work opens the way for more reliable and interpretable text classification solutions. [ABSTRACT FROM AUTHOR]

The rapid growth of Internet of Things (IoT) devices has significantly increased reliance on sensor-generated data, which are essential to a wide range of systems and services. Wireless sensor networks (WSNs), crucial to this ecosystem, are often deployed in diverse and challenging environments, making them susceptible to faults such as software bugs, communication breakdowns, and hardware malfunctions. These issues can compromise data accuracy, stability, and reliability, ultimately jeopardizing system security. While advanced sensor fault detection methods in WSNs leverage a machine learning approach to achieve high accuracy, they typically rely on centralized learning, and face scalability and privacy challenges, especially when transferring large volumes of data. In our experimental setup, we employ a decentralized approach using federated learning with long short-term memory (FedLSTM) for sensor fault detection in WSNs, thereby preserving client privacy. This study utilizes temperature data enhanced with synthetic sensor data to simulate various common sensor faults: bias, drift, spike, erratic, stuck, and data-loss. We evaluate the performance of FedLSTM against the centralized approach based on accuracy, precision, sensitivity, and F1-score. Additionally, we analyze the impacts of varying the client participation rates and the number of local training epochs. In federated learning environments, comparative analysis with established models like the one-dimensional convolutional neural network and multilayer perceptron demonstrate the promising results of FedLSTM in maintaining client privacy while reducing communication overheads and the server load. [ABSTRACT FROM AUTHOR]

This study addresses the limitations of traditional sports rehabilitation, emphasizing the need for improved accuracy and response speed in real-time action detection and recognition in complex rehabilitation scenarios. We propose the STA-C3DL model, a deep learning framework that integrates 3D Convolutional Neural Networks (C3D), Long Short-Term Memory (LSTM) networks, and spatiotemporal attention mechanisms to capture nuanced action dynamics more precisely. Experimental results on multiple datasets, including NTU RGB + D, Smarthome Rehabilitation, UCF101, and HMDB51, show that the STA-C3DL model significantly outperforms existing methods, achieving up to 96.42% accuracy and an F1 score of 95.83% on UCF101, with robust performance across other datasets. The model demonstrates particular strength in handling real-time feedback requirements, highlighting its practical application in enhancing rehabilitation processes. This work provides a powerful, accurate tool for action recognition, advancing the application of deep learning in rehabilitation therapy and offering valuable support to therapists and researchers. Future research will focus on expanding the model's adaptability to unconventional and extreme actions, as well as its integration into a wider range of rehabilitation settings to further support individualized patient recovery. [ABSTRACT FROM AUTHOR]

The study introduces a groundbreaking two-stage deep hybrid learning architecture, Robust Autonomous Driving Control (RADC), designed to address the formidable challenge of ensuring safe and efficient autonomous driving in adverse weather conditions, including heavy rain and snow, in complex scenarios. In the first stage, our proposal utilizes an encoder as a variational autoencoder (VAE) model. This encoder leverages the VAE to extract feature information from the perceptual data surrounding the environment. Moving on to the second stage, we build a decoder as an Inception-Bidirectional Long Short-Term Memory (IBL) model. This decoder combines the VAE latent features obtained in stage one with additional control vehicle information tasks, including steering, speed, etc. Our approach involves predicting driving behavior along a predetermined route, allowing autonomous vehicles to stay centered on the road, simulating diverse driving scenarios, and achieving significant reductions in route-following time. This framework utilizes deep hybrid learning methods and harnesses Nvidia GPU capabilities to evaluate the effectiveness of InceptionNet, ResNet-50, MobileNet, DenseNet, and VGG16 convolutional neural networks. It enhances vehicle route following with improved metrics such as reduced inference time, heightened accuracy, and minimized lane changes in training. The RADC demonstrates exceptional performance, notably achieving a mean square error of 0.0464, 0.0346, and a 6-millisecond inference time in challenging weather like hard rain and snow. The proposed model is validated through comprehensive experiments in the Airsim environment, showcasing notable interpretability, generalization, and robustness capabilities. [ABSTRACT FROM AUTHOR]

Accurate identification of coal and gangue is a crucial guarantee for efficient and safe mining of top coal caving face. This article proposes a coal-gangue recognition method based on an improved beluga whale optimization algorithm (IBWO), convolutional neural network, and long short-term memory network (CNN-LSTM) multi-modal fusion model. First, the mutation and memory library mechanisms are introduced into the beluga whale optimization to explore the solution space fully, prevent falling into local optimum, and accelerate the convergence process. Subsequently, the image mapping of the audio signal and vibration signal is performed to extract Mel-Frequency Cepstral Coefficients (MFCC) features, generating rich sample data for CNN-LSTM. Then the multi-head attention mechanism is introduced into CNN-LSTM to speed up the training speed and improve the classification accuracy. Finally, the IBWO-CNN-LSTM coal-gangue recognition model is constructed by the optimal hyperparameter combination obtained by IBWO to realize the automatic recognition of coal-gangue. The benchmark function proves that IBWO is superior to other optimization algorithms. By building an experimental platform for the impact of coal and gangue falling on the tail beam of hydraulic support, multiple experimental data collection is carried out. The experimental results show that the proposed coal-gangue recognition model has better performance than other recognition models, and the accuracy rate reaches 95.238%. The multi-modal fusion strategy helps to improve the accuracy and robustness of coal-gangue recognition. [ABSTRACT FROM AUTHOR]

This study proposes a new hybrid machine learning (ML) model for the early and accurate diagnosis of heart disease. The proposed model is a combination of two powerful ensemble ML models, namely ExtraTreeClassifier (ETC) and XGBoost (XGB), resulting in a hybrid model named ETCXGB. At first, all the features of the utilized heart disease dataset were given as input to the ETC model, which processed it by extracting the predicted probabilities and produced an output. The output of the ETC model was then added to the original feature space by producing an enriched feature matrix, which is then used as input for the XGB model. The new feature matrix is used for training the XGB model, which produces the final result that whether a person has cardiac disease or not, resulting in a high diagnosis accuracy for cardiac disease. In addition to the proposed model, three other hybrid DL models, such as convolutional neural network + recurrent neural network (CNN-RNN), convolutional neural network + long short-term memory (CNN-LSTM), and convolutional neural network + bidirectional long short-term memory (CNN-BLSTM), were also investigated. The proposed ETCXGB model improved the prediction accuracy by 3.91%, while CNN-RNN, CNN-LSTM, and CNN-BLSTM enhanced the prediction accuracy by 1.95%, 2.44%, and 2.45%, respectively, for the diagnosis of cardiac disease. The simulation outcomes illustrate that the proposed ETCXGB hybrid ML outperformed the classical ML and DL models in terms of all performance measures. Therefore, using the proposed hybrid ML model for the diagnosis of cardiac disease will help the medical practitioner make an accurate diagnosis of the disease and will help the healthcare society decrease the mortality rate caused by cardiac disease. [ABSTRACT FROM AUTHOR]

Background: Emotions play a crucial role in people's lives, profoundly affecting their cognition, decision-making, and interpersonal communication. Emotion recognition based on brain signals has become a significant challenge in the fields of affective computing and human-computer interaction. Methods: Addressing the issue of inaccurate feature extraction and low accuracy of existing deep learning models in emotion recognition, this paper proposes a multi-channel automatic classification model for emotion EEG signals named DACB, which is based on dual attention mechanisms, convolutional neural networks, and bidirectional long short-term memory networks. DACB extracts features in both temporal and spatial dimensions, incorporating not only convolutional neural networks but also SE attention mechanism modules for learning the importance of different channel features, thereby enhancing the network's performance. DACB also introduces dot product attention mechanisms to learn the importance of spatial and temporal features, effectively improving the model's accuracy. Results: The accuracy of this method in single-shot validation tests on the SEED-IV and DREAMER (Valence-Arousal-Dominance three-classification) datasets is 99.96% and 87.52%, 90.06%, and 89.05%, respectively. In 10-fold cross-validation tests, the accuracy is 99.73% and 84.26%, 85.40%, and 85.02%, outperforming other models. Conclusions: This demonstrates that the DACB model achieves high accuracy in emotion classification tasks, demonstrating outstanding performance and generalization ability and providing new directions for future research in EEG signal recognition. [ABSTRACT FROM AUTHOR]

Current research on futures price prediction focuses on the autocorrelation of historical prices, yet the resulting predictions often suffer from issues of inaccuracy and lag. This paper uses Chinese corn futures as the subject of study. First, we identify key influencing factors, such as Chinese soybean futures, U.S. soybean futures, and the U.S.-China exchange rate, that exhibit 'predictive causality' with corn futures prices through the Granger causality test. We then apply the sample convolution and interaction network (SCINet) to perform both single-step and multi-step predictions of futures prices. The experimental results show that incorporating key influencing factors significantly improves prediction accuracy. For instance, in the single-step prediction, combining historical prices with Chinese soybean futures prices reduces the MAE and RMSE values by 5.12% and 3.45%, respectively, compared to using historical prices alone. Furthermore, the SCINet model outperforms traditional models such as temporal convolutional networks (TCN), gated recurrent units (GRU), and long short-term memory (LSTM) networks when based solely on historical prices. This study validates the effectiveness of key influencing factors in forecasting Chinese corn futures prices and demonstrates the advantages of the SCINet model in futures price prediction. The findings provide valuable insights for optimising the agricultural futures market and enhancing the ability to predict price risks. [ABSTRACT FROM AUTHOR]

Author Gender Identification (AGI) is an extensively studied subject owing to its significance in several domains, such as security and marketing. Recognizing an author's gender may assist marketers in segmenting consumers more effectively and crafting tailored content that aligns with a gender's preferences. Also, in cybersecurity, identifying an author's gender might aid in detecting phishing attempts where hackers could imitate individuals of a specific gender. Although studies in Arabic have mostly concentrated on written dialects, such as tweets, there is a paucity of studies addressing Modern Standard Arabic (MSA) in journalistic genres. To address the AGI issue, this work combines the beneficial properties of natural language processing with cutting-edge deep learning methods. Firstly, we propose a large 8k MSA article dataset composed of various columns sourced from news platforms, labeled with each author's gender. Moreover, we extract and analyze textual features that may be beneficial in identifying gender-related cues through their writings, focusing on semantics and syntax linguistics. Furthermore, we probe several innovative deep learning models, namely, Convolutional Neural Networks (CNNs), LSTM, Bidirectional LSTM (BiLSTM), and Bidirectional Encoder Representations from Transformers (BERT). Beyond that, a novel enhanced BERT model is proposed by incorporating gender-specific textual features. Through various experiments, the results underscore the potential of both BERT and the textual features, resulting in a 91% accuracy for the enhanced BERT model and a range of accuracy from 80% to 90% accuracy for deep learning models. We also employ these features for AGI in informal, dialectal text, with the enhanced BERT model reaching 68.7% accuracy. This demonstrates that these gender-specific textual features are conducive to AGI across MSA and dialectal texts. [ABSTRACT FROM AUTHOR]

Ambient air pollution affects human health, vegetative growth and sustainable socio-economic development. Therefore, air pollution data in Dezhou City in China are collected from January 2014 to December 2023, and multiple deep learning models are used to forecast air pollution PM2.5 concentrations. The ability of the multiple models is evaluated and compared with observed data using various statistical parameters. Although all eight deep learning models can accomplish PM2.5 forecasting assignments, the precision accuracy of the CNN-GRU-LSTM forecasting method is 34.28% higher than that of the ANN forecasting method. The result shows that CNN-GRU-LSTM has the best forecasting performance compared to the other seven models, achieving an R (correlation coefficient) of 0.9686 and an RMSE (root mean square error) of 4.6491 μg/m3. The RMSE values of CNN, GRU and LSTM models are 57.00%, 35.98% and 32.78% higher than that of the CNN-GRU-LSTM method, respectively. The forecasting results reveal that the CNN-GRU-LSTM predictor remarkably improves the performances of benchmark CNN, GRU and LSTM models in overall forecasting. This research method provides a new perspective for predictive forecasting of ambient air pollution PM2.5 concentrations. The research results of the predictive model provide a scientific basis for air pollution prevention and control. [ABSTRACT FROM AUTHOR]

Predicting streamflow is essential for managing water resources, especially in basins and watersheds where snowmelt plays a major role in river discharge. This study evaluates the advanced deep learning models for accurate monthly and peak streamflow forecasting in the Gilgit River Basin. The models utilized were LSTM, BiLSTM, GRU, CNN, and their hybrid combinations (CNN-LSTM, CNN-BiLSTM, CNN-GRU, and CNN-BiGRU). Our research measured the model's accuracy through root mean square error (RMSE), mean absolute error (MAE), Nash–Sutcliffe efficiency (NSE), and the coefficient of determination (R2). The findings indicated that the hybrid models, especially CNN-BiGRU and CNN-BiLSTM, achieved much better performance than traditional models like LSTM and GRU. For instance, CNN-BiGRU achieved the lowest RMSE (71.6 in training and 95.7 in testing) and the highest R2 (0.962 in training and 0.929 in testing). A novel aspect of this research was the integration of MODIS-derived snow-covered area (SCA) data, which enhanced model accuracy substantially. When SCA data were included, the CNN-BiLSTM model's RMSE improved from 83.6 to 71.6 during training and from 108.6 to 95.7 during testing. In peak streamflow prediction, CNN-BiGRU outperformed other models with the lowest absolute error (108.4), followed by CNN-BiLSTM (144.1). This study's results reinforce the notion that combining CNN's spatial feature extraction capabilities with the temporal dependencies captured by LSTM or GRU significantly enhances model accuracy. The demonstrated improvements in prediction accuracy, especially for extreme events, highlight the potential for these models to support more informed decision-making in flood risk management and water allocation. [ABSTRACT FROM AUTHOR]

In an intelligent driving environment, monitoring the physiological state of drivers is crucial for ensuring driving safety. This paper proposes a method for monitoring and analyzing driver physiological characteristics by combining electronic vehicle identification (EVI) with multimodal biometric recognition. The method aims to efficiently monitor the driver's heart rate, breathing frequency, emotional state, and fatigue level, providing real-time feedback to intelligent driving systems to enhance driving safety. First, considering the precision, adaptability, and real-time capabilities of current physiological signal monitoring devices, an intelligent cushion integrating MEMSs (Micro-Electro-Mechanical Systems) and optical sensors is designed. This cushion collects heart rate and breathing frequency data in real time without disrupting the driver, while an electrodermal activity monitoring system captures electromyography data. The sensor layout is optimized to accommodate various driving postures, ensuring accurate data collection. The EVI system assigns a unique identifier to each vehicle, linking it to the physiological data of different drivers. By combining the driver physiological data with the vehicle's operational environment data, a comprehensive multi-source data fusion system is established for a driving state evaluation. Secondly, a deep learning model is employed to analyze physiological signals, specifically combining Convolutional Neural Networks (CNNs) and Long Short-Term Memory (LSTM) networks. The CNN extracts spatial features from the input signals, while the LSTM processes time-series data to capture the temporal characteristics. This combined model effectively identifies and analyzes the driver's physiological state, enabling timely anomaly detection. The method was validated through real-vehicle tests involving multiple drivers, where extensive physiological and driving behavior data were collected. Experimental results show that the proposed method significantly enhances the accuracy and real-time performance of physiological state monitoring. These findings highlight the effectiveness of combining EVI with multimodal biometric recognition, offering a reliable means for assessing driver states in intelligent driving systems. Furthermore, the results emphasize the importance of personalizing adjustments based on individual driver differences for more effective monitoring. [ABSTRACT FROM AUTHOR]

Modern vehicles rely on electronic control units (ECUs) communicating through the controller area network (CAN) bus protocol. However, increased connectivity through Wi-Fi, Bluetooth, and onboard diagnostics (OBD) ports has heightened cybersecurity risks due to the CAN bus protocol's inherent security vulnerabilities. Addressing this challenge requires an in-vehicle intrusion detection system (IDS) with high accuracy and minimal false alarms. Existing IDSs for in-vehicle networks often fall short due to inadequate extraction of network traffic features' dependencies in a time-series context.To overcome this limitation, this study presents ACL-IDS, a hybrid intrusion detection system for in-vehicle network traffic. Leveraging deep learning techniques like CNN, LSTM, and attention mechanisms, ACL-IDS effectively captures short-term and long-term dependencies within network traffic, enhancing intrusion detection accuracy. Extensive experiments on a real benchmark dataset demonstrate ACL-IDS's superior performance compared to individual, ensemble, and state-of-the-art methods. With detection accuracy reaching up to 99%, ACL-IDS emerges as a robust solution for analyzing and detecting intrusions in in-vehicle network traffic. [ABSTRACT FROM AUTHOR]

Waves that remain at sea or come from other sea areas after the wind weakens, stops, or turns are called swells. Swell has a lower wave level than the wind wave, but the period is larger. Swell is easy to resonate with floating structures such as ships, which affects the normal operation. In order to avoid the damage caused by swells, it is necessary to have a method that can predict swells efficiently and accurately. A neural network was built based on the Convolutional LSTM (ConvLSTM) model to process the wave height distribution of swells was a two-dimensional image. The network combines the image feature capture ability of convolution operation and the time series prediction ability of Long Short Term Memory (LSTM) model, and considers both the spatial propagation characteristics of swell and the temporal variation characteristics in the network learning process. The ERAS reanalysis dataset was used to train the network, and the significant wave height of the swell in the East China Sea (21°N-34°N, 114°E-131°E) was predicted, and the prediction results were in good agreement with the dataset, with a maximum correlation of 0.997. At the same time, compared with the model that does not consider the spatial propagation characteristics of swells, the prediction effect is improved. The method used in this paper provides a new idea for the research on swell forecasting. [ABSTRACT FROM AUTHOR]

We investigate the performance of intelligent systems such as various Long Short-Term Memory (LSTM) and hybrid models to forecast the electricity spot prices considering univariate and multivariate models. Six models are created to handle the Electricity Price Forecast (EPF). Furthermore, an EPF methodology that consists of a LSTM univariate model, namely Single in–out (Sio) model is proposed. It builds on the Day-Ahead electricity Market (DAM) specificity and, as a novelty, it inserts the predicted value back into the sliding input vector to predict the next values until the entire vector of 24 prices is predicted. The proposed model is further enhanced by the convolutional reading of input data that is embedded into the LSTM cell or by a hybrid combination of LSTM and Convolutional Neural Networks (CNN) that interprets sub-sequences of input data and extracts features that are provided as a sequence to the LSTM model. The methodology is validated using data sets from the Romanian Market Operator (OPCOM) and other market operators from Serbia (SEEPEX), Hungary (HUPX) and Bulgaria (IBEX). Our models improve the results for the day-ahead forecast in comparison with other models by 21.02% in terms of Mean Absolute Error (MAE). [ABSTRACT FROM AUTHOR]

Understanding metaphorical language is essential for AI to interpret and communicate with humans accurately. However, current methods often struggle with the complexity of metaphors, making it difficult for AI systems to understand human language fully. Recognizing metaphors is challenging because they are frequently ambiguous and depend on context. In this study, we propose a new approach using a combination of Bi-directional Long Short-Term Memory (Bi-LSTM) networks, Convolutional Neural Networks (CNN), and uni-directional LSTM components to create a multi-level model for recognizing metaphors. Our model uses various features, including dependency, semantics, and part-of-speech, to improve its learning ability. Additionally, we introduce a new method for recognizing the emotional context of metaphors using a random walk model to determine the emotional tone of words. Our results show that this model improves performance in recognizing metaphors, enhancing AI's ability to understand them. [ABSTRACT FROM AUTHOR]

Spectrum sensing is pivotal in cognitive radio (CR), a burgeoning technology for optimizing radio spectrum utilization. Traditional spectrum sensing techniques like energy detection, matching filter, and cyclic stationary detection have been proposed, which rely on prior knowledge and models. These techniques suffer from challenging issues such as missed detection and false alarms, which impede the effective utilization of the spectrum. Inaccurate assumptions or limited knowledge can hinder detection. To tackle these challenging issues, we propose a novel deep learning-oriented spectrum sensing (DLoSS) technique and highlight the use of deep neural networks (DNNs) for cooperative spectrum sensing (CSS) model. Specifically, we propose a "DLSpectSenNet," a DLoSS-based model, utilizes structural information from incoming modulated signals for spectrum sensing. Particularly, we combine convolutional neural network (CNN) and long-short-term memory (LSTM) network in series, extracting hidden spatial information and temporal data, respectively. The simulation results using the RadioML2016.10b dataset, show the proposed DLSpectSenNet's improved detection performance, especially under low SNR conditions, surpassing traditional cooperative algorithms. It outperforms previous models, enabling improved spectrum detection. [ABSTRACT FROM AUTHOR]

Consumer reviews play a pivotal role in shaping purchasing decisions and influencing the reputation of businesses in today's digital economy. This paper presents a novel hybrid deep learning model, WDE-CNN-LSTM, designed to enhance the sentiment classification of consumer reviews. The model leverages the strengths of Word Embeddings (WDE), Long Short-Term Memory (LSTM) networks, and Convolutional Neural Networks (CNNs) to capture temporal and local text data features. Extensive experiments were conducted across binary, three-class, and five-class classification tasks, with the proposed model achieving an accuracy of 98% for binary classification, 98% for three-class classification, and 95.21% for five-class classifications. The WDE-CNN-LSTM model consistently outperformed standalone CNN, LSTM, and WDE-LSTM models regarding precision, recall, and F 1 -score, achieving up to 98.26% in F 1 -score for three-class classification. The consistency analysis also revealed a high alignment between the predicted sentiment and customer ratings, with a consistency rate of 96.00%. These results demonstrate the efficacy of this hybrid architecture in handling complex sentiment classification tasks (SCTs), offering significant improvements in accuracy, classification metrics, and sentiment consistency. The findings have important implications for improving sentiment analysis in customer review systems, contributing to more reliable and accurate sentiment classification. [ABSTRACT FROM AUTHOR]

Deep learning, a foundational technology in artificial intelligence, facilitates the identification of complex associations between stock prices and various influential factors through comprehensive data analysis. Stock price data exhibits unique time-series characteristics; models emphasizing long-term data may miss short-term fluctuations, while those focusing solely on short-term data may not capture cyclical trends. Existing models that integrate long short-term memory (LSTM) and convolutional neural networks (CNNs) face limitations in capturing both long- and short-term dependencies due to LSTM's gated transmission mechanism and CNNs' limited receptive field. This study introduces an innovative deep learning model, CNN-CBAM-LSTM, which integrates the convolutional block attention module (CBAM) to enhance the extraction of both long- and short-term features. The model's performance is assessed using the Australian Standard & Poor's 200 Index (AS51), showing improvement over traditional models across metrics such as RMSE, MAE, R2, and RETURN. To further confirm its robustness and generalizability, Diebold–Mariano (DM) tests and model confidence set experiments are conducted, with results indicating the consistently high performance of the CNN-CBAM-LSTM model. Additional tests on six globally recognized stock indices reinforce the model's predictive strength and adaptability, establishing it as a reliable tool for forecasting in the stock market. [ABSTRACT FROM AUTHOR]

Summary: Glaucoma is a major cause of blindness and vision impairment worldwide, and visual field (VF) tests are essential for monitoring the conversion of glaucoma. While previous studies have primarily focused on using VF data at a single time point for glaucoma prediction, there has been limited exploration of longitudinal trajectories. Additionally, many deep learning techniques treat the time‐to‐glaucoma prediction as a binary classification problem (glaucoma Yes/No), resulting in the misclassification of some censored subjects into the nonglaucoma category and decreased power. To tackle these challenges, we propose and implement several deep‐learning approaches that naturally incorporate temporal and spatial information from longitudinal VF data to predict time‐to‐glaucoma. When evaluated on the Ocular Hypertension Treatment Study (OHTS) dataset, our proposed convolutional neural network (CNN)‐long short‐term memory (LSTM) emerged as the top‐performing model among all those examined. The implementation code can be found online (https://github.com/rivenzhou/VF_prediction). [ABSTRACT FROM AUTHOR]

Efficient BCIs (Brain-Computer Interfaces) harnessing EEG (Electroencephalography) have shown potential in controlling mobile robots, also presenting new possibilities for assistive technologies. This study explores the integration of advanced deep learning models—ASTGCN, EEGNetv4, and a combined CNN-LSTM architecture—with ROS (Robot Operating System) to control a two-wheeled mobile robot. The models were trained using a published EEG dataset, which includes signals from subjects performing thought-based tasks. Each model was evaluated based on its accuracy, F1-score, and latency. The CNN-LSTM architecture model exhibited the best performance on the cross-subject strategy with an accuracy of 88.5%, demonstrating significant potential for real-time applications. Integration with ROS was facilitated through a custom middleware, enabling seamless translation of neural commands into robot movements. The findings indicate that the CNN-LSTM model not only outperforms existing EEG-based systems in terms of accuracy but also underscores the practical feasibility of implementing such systems in real-world scenarios. Considering its efficacy, CNN-LSTM shows a great potential for assistive technology in the future. This research contributes to the development of a more intuitive and accessible robotic control system, potentially enhancing the quality of life for individuals with mobility impairments. [ABSTRACT FROM AUTHOR]

Once the rolling bearing fails, it will threaten the normal operation of the whole rotating machinery. Therefore, it is very necessary to conduct research on rolling bearing fault diagnosis. This paper proposes a rolling bearing fault diagnosis method combining MSSSA-VMD (variational mode decomposition optimized by the improved salp swarm algorithm based on mixed strategy) with the parallel network of GASF-CNN (convolutional neural network based on Gramian angular summation field) and bi-directional long short-term memory (BiLSTM) to solve the problem of poor diagnostic performance for the rolling bearing faults caused by the respective limitations of existing fault diagnosis methods based on signal processing and deep learning. Firstly, MSSSA-VMD is proposed to solve the problem where the decomposition effect of VMD is not ideal due to improper parameter selection. Then, MSSSA-VMD is employed to preprocess and extract characteristics. Finally, the extracted characteristics are input into the parallel network of GASF-CNN and BiLSTM for diagnosis. In one channel of the parallel network, GASF is used to convert the characteristic vectors into a two-dimensional image, which is then fed into CNN for spatial characteristic extraction. In the other channel of the parallel network, the characteristic vectors are directly input into BiLSTM for temporal characteristic extraction. Experimental results demonstrate that the proposed method has good performance in terms of fault diagnosis performance under constant operating conditions, generalization ability under variable operating conditions and noise resistance. [ABSTRACT FROM AUTHOR]

In view of the problem of the insufficient performance of deep learning models in time series prediction and poor comprehensive space–time feature extraction, this paper proposes a diagnostic method (CNN-LSTM-GRU) that integrates convolutional neural network (CNN), long short-term memory (LSTM) network, and gated recurrent unit (GRU) models. In this study, a convolutional neural network (CNN) model is used to process two-dimensional image data in both time and frequency domains, and a convolutional core attention mechanism is introduced to extract spatial features, such as peaks, cliffs, and waveforms, from the samples. A long short-term memory (LSTM) network is embedded in the output processing of the convolutional neural network (CNN) to analyze the long-sequence variation characteristics of rolling bearing vibration signals and enable long-term time series prediction by capturing long-term dependencies in the sequence. In addition, a gated recurrent unit (GRU) is used to refine long-term time series predictions, providing local fine-tuning and improving the accuracy of fault diagnosis. Using a dataset obtained from Case Western Reserve University (CWRU), the average accuracy of CNN-LSTM-GRU fault vibration is greater than 99%, and its superior performance in a noisy environment is demonstrated. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Hebei University of Science & Technology is the property of Hebei University of Science & Technology, Journal of Hebei University of Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This research presents a comparative analysis of various deep learning models—including Recurrent Neural Networks (RNN), Long Short-Term Memory (LSTM), Convolutional Neural Networks (CNN), Gated Recurrent Units (GRU), and Attention LSTM—in predicting stock prices of major companies in the Indian stock market, specifically HDFC, TCS, ICICI, Reliance, and Nifty. The study evaluates model performance using key regression metrics such as Mean Absolute Error (MAE), Mean Squared Error (MSE), and R-Squared (R²). The results indicate that CNN and GRU models generally outperform the others, depending on the specific stock, and demonstrate superior capabilities in forecasting stock price movements. This investigation provides insights into the strengths and limitations of each model while highlighting potential avenues for improvement through feature engineering and hyperparameter optimization. [ABSTRACT FROM AUTHOR]

Gait analysis plays a pivotal role in clinical diagnostics and aids in the detection and evaluation of various disorders and disabilities. Traditional methods often rely on intricate video systems or pressure mats to assess gait. Previous studies have demonstrated the potential of artificial intelligence (AI) in gait analysis using techniques, such as convolutional neural networks (CNN) and long short-term memory (LSTM) networks. However, these methods often encounter challenges related to high dimensionality, temporal dependencies, and variability in gait patterns, making accurate and efficient classification difficult. To address these challenges, this study introduces a simple one-dimensional (1D) CNN model designed to analyze ground reaction force (GRF) patterns and classify individuals as healthy or suffering from gait disorders. The model achieved a remarkable classification accuracy of 98.65% in distinguishing healthy individuals from those with gait disorders, demonstrating significant improvements over the existing models. This performance is bolstered by the attention mechanism and standardization techniques that enhance robustness and accuracy [ABSTRACT FROM AUTHOR]

The proliferation of Internet of Things (IoT) technology has exponentially increased the number of devices interconnected over networks, thereby escalating the potential vectors for cybersecurity threats. In response, this study rigorously applies and evaluates deep learning models—namely Convolutional Neural Networks (CNN), Autoencoders, and Long Short-Term Memory (LSTM) networks—to engineer an advanced Intrusion Detection System (IDS) specifically designed for IoT environments. Utilizing the comprehensive UNSW-NB15 dataset, which encompasses 49 distinct features representing varied network traffic characteristics, our methodology focused on meticulous data preprocessing including cleaning, normalization, and strategic feature selection to enhance model performance. A robust comparative analysis highlights the CNN model's outstanding performance, achieving an accuracy of 99.89%, precision of 99.90%, recall of 99.88%, and an F1 score of 99.89% in binary classification tasks, outperforming other evaluated models significantly. These results not only confirm the superior detection capabilities of CNNs in distinguishing between benign and malicious network activities but also illustrate the model's effectiveness in multiclass classification tasks, addressing various attack vectors prevalent in IoT setups. The empirical findings from this research demonstrate deep learning's transformative potential in fortifying network security infrastructures against sophisticated cyber threats, providing a scalable, high-performance solution that enhances security measures across increasingly complex IoT ecosystems. This study's outcomes are critical for security practitioners and researchers focusing on the next generation of cyber defense mechanisms, offering a data-driven foundation for future advancements in IoT security strategies. [ABSTRACT FROM AUTHOR]

Spear Phishing Attacks (SPAs) pose a significant threat to the healthcare sector, resulting in data breaches, financial losses, and compromised patient confidentiality. Traditional defenses, such as firewalls and antivirus software, often fail to counter these sophisticated attacks, which target human vulnerabilities. To strengthen defenses, healthcare organizations are increasingly adopting Machine Learning (ML) techniques. ML-based SPA defenses use advanced algorithms to analyze various features, including email content, sender behavior, and attachments, to detect potential threats. This capability enables proactive security measures that address risks in real-time. The interpretability of ML models fosters trust and allows security teams to continuously refine these algorithms as new attack methods emerge. Implementing ML techniques requires integrating diverse data sources, such as electronic health records, email logs, and incident reports, which enhance the algorithms' learning environment. Feedback from end-users further improves model performance. Among tested models, the hierarchical models, Convolutional Neural Network (CNN) achieved the highest accuracy at 99.99%, followed closely by the sequential Bidirectional Long Short-Term Memory (BiLSTM) model at 99.94%. In contrast, the traditional Multi-Layer Perceptron (MLP) model showed an accuracy of 98.46%. This difference underscores the superior performance of advanced sequential and hierarchical models in detecting SPAs compared to traditional approaches. [ABSTRACT FROM AUTHOR]

Phishing attacks are more than two-decade-old attacks that attackers use to steal passwords related to financial services. After the first reported incident in 1995, its impact keeps on increasing. Also, during COVID-19, due to the increase in digitization, there is an exponential increase in the number of victims of phishing attacks. Many deep learning and machine learning techniques are available to detect phishing attacks. However, most of the techniques did not use efficient optimization techniques. In this context, our proposed model used random forest-based techniques to select the best features, and then the Brown-Bear optimization algorithm (BBOA) was used to fine-tune the hyper-parameters of the convolutional neural network (CNN) model. To test our model, we used a dataset from Kaggle comprising 11,000+ websites. In addition to that, the dataset also consists of the 30 features that are extracted from the website uniform resource locator (URL). The target variable has two classes: "Safe" and "Phishing." Due to the use of BBOA, our proposed model detects malicious URLs with an accuracy of 93% and a precision of 92%. In addition, comparing our model with standard techniques, such as GRU (Gated Recurrent Unit), LSTM (Long Short-Term Memory), RNN (Recurrent Neural Network), ANN (Artificial Neural Network), SVM (Support Vector Machine), and LR (Logistic Regression), presents the effectiveness of our proposed model. Also, the comparison with past literature showcases the contribution and novelty of our proposed model. [ABSTRACT FROM AUTHOR]

This research aims to enhance Clinical Decision Support Systems (CDSS) within Wireless Body Area Networks (WBANs) by leveraging advanced machine learning techniques. Specifically, we target the challenges of accurate diagnosis in medical imaging and sequential data analysis using Recurrent Neural Networks (RNNs) with Long Short-Term Memory (LSTM) layers and echo state cells. These models are tailored to improve diagnostic precision, particularly for conditions like rotator cuff tears in osteoporosis patients and gastrointestinal diseases. Traditional diagnostic methods and existing CDSS frameworks often fall short in managing complex, sequential medical data, struggling with long-term dependencies and data imbalances, resulting in suboptimal accuracy and delayed decisions. Our goal is to develop Artificial Intelligence (AI) models that address these shortcomings, offering robust, real-time diagnostic support. We propose a hybrid RNN model that integrates SimpleRNN, LSTM layers, and echo state cells to manage long-term dependencies effectively. Additionally, we introduce CG-Net, a novel Convolutional Neural Network (CNN) framework for gastrointestinal disease classification, which outperforms traditional CNN models. We further enhance model performance through data augmentation and transfer learning, improving generalization and robustness against data scarcity and imbalance. Comprehensive validation, including 5-fold cross-validation and metrics such as accuracy, precision, recall, F1-score, and Area Under the Curve (AUC), confirms the models' reliability. Moreover, SHapley Additive exPlanations (SHAP) and Local Interpretable Model-agnostic Explanations (LIME) are employed to improve model interpretability. Our findings show that the proposed models significantly enhance diagnostic accuracy and efficiency, offering substantial advancements in WBANs and CDSS. [ABSTRACT FROM AUTHOR]

The short-term power load forecasting provides an essential foundation for the dispatching management of the power system, which is crucial for enhancing economy and ensuring operational stability. To enhance the precision of the short-term power load forecasting, this paper proposes a hybrid prediction algorithm based on sparrow search algorithm (SSA), convolutional neural network (CNN) and long short-term memory (LSTM). First, feature datasets are constructed based on date information, meteorological data, similar days. The CNN performs effective feature extraction on the data and feeds the results into the LSTM for time series data analysis. Second, eight key parameters are optimized by SSA for improving the prediction precision of the CNN-LSTM prediction model. Simulation results show that the R2 of the proposed model exhibits a substantial enhancement in comparison to other models, reaching 0.9919 and presents a remarkable decrease in MAPE resulting in a value of 1.2%. Furthermore, RMSE and MAE have decreased to 1.17MW and 0.97MW respectively. Therefore, the proposed method has the ability to improve the prediction accuracy, due to the advantages in data mining of CNN, good time series data fitting ability of LSTM, and excellent optimization ability of SSA. [ABSTRACT FROM AUTHOR]

In recent years, Human activity recognition (HAR) based on wearable devices has been widely applied in health applications and other fields. Currently, most HAR models are based on the Convolutional Neural Network (CNN), Long Short-Term Memory (LSTM), or their combination. Recently, there have been proposals based on Transformer and its variant models. However, due to the fact that these models have sequential network structures and are unable to simultaneously focus on local and global features, thus, resulting in a reduction in recognition performance. In addition, along with the substantial computational resources required by Transformers, they are not suitable for resource-constrained devices. In this paper, the primary distinction of our proposed model from other hybrid models that combine CNN and Transformer is that our model adopts a completely new parallel network architecture and primarily focuses on lightweight design. Particularly, We proposed the Mobile Human Activity Recognition Conformer (MobileHARC), which adopts the parallel structure with a lightweight Transformer and CNN as the backbone networks. Furthermore, we proposed the Inverted Residual Lightweight Convolution Block and Multiscale Lightweight Multi-Head Self-Attention Mechanism. We systematically evaluate the proposed models on four public datasets. Experimental results show that MobileHARC achieves superior recognition performance, and uses fewer Floating-Point Operations per Second (FLOPs) and parameters compared to current models. [ABSTRACT FROM AUTHOR]

This research article introduces a novel approach to text-independent speaker recognition by integrating Mel-Frequency Cepstral Coefficients (MFCC) and Bidirectional Long Short-Term Memory (Bi-LSTM) networks, with noise removal facilitated by Convolutional Neural Networks (CNNs). The primary objective is to upgrade the robustness and precision of speaker recognition systems in real-world environments where background noise is prevalent. The proposed method begins with the extraction of MFCC features, which effectively capture the timbral characteristics of the speech signal. To enhance these features, we employ a CNN-based noise removal mechanism that reduces background interference, thereby improving the quality of the input signal. The denoised MFCC features are then fed into a Bi-LSTM network, which excels in modeling temporal dependencies and capturing long-range contextual information inherent in speech data. Extensive experiments were conducted on publicly available datasets, demonstrating significant improvements in speaker recognition accuracy under various noise conditions compared to traditional approaches. The integration of CNN for noise removal and Bi-LSTM for temporal feature modeling showcases a synergistic effect, leading to a more robust and reliable speaker recognition system. Our results underscore the effectiveness of combining advanced feature extraction, noise reduction, and deep learning techniques for enhanced speaker recognition in challenging acoustic environments. The accuracy of the proposed method is found to be 98.17% at the Signal to Noise Ratio (SNR) level of 30 dB. [ABSTRACT FROM AUTHOR]