Search

Summary: In this study, we propose an inverse design approach based on a neural network for a novel multiport power divider (MP‐PD) with complex geometry. The inverse design approach is obtaining geometry from the desired physical performance to address the challenge of conventional methods. We develop a hybrid neural network model for this inverse design. The backbone architecture incorporates a bidirectional long short‐term memory module, a multihead self‐attention module, and convolutional modules. This hybrid neural network is employed to capture the feature of physical performance and learn the relationship between the geometric structure of the proposed MP‐PD and its corresponding physical performance. Consider the design of the power divider as an end‐to‐end methodology that directly maps design requirements to optimal geometric parameters. The neural network transfers the designed process into multiple‐input‐multiple‐output. We adopt the network model to successfully predict 20 geometric parameters of MP‐PDs for two distinct operating frequencies. The two operating frequencies are those utilized in real engineering applications, which are 3.5 GHz in the 5G band and 2.45 GHz in the trackside communication band. The predicted MP‐PD improves the return loss and bandwidth by 8.05 dB and 0.25 GHz, respectively, over the desired performance. The experiments and comparisons demonstrate the effectiveness and accuracy of our inverse design approach. The efficiency and flexibility of design are also significantly improved by the hybrid neural network model. [ABSTRACT FROM AUTHOR]

Summary: Ensuring data integrity in wireless sensor networks (WSNs) is crucial for accurate monitoring, yet missing data due to sensor faults present a significant challenge. This research introduces an innovative approach that integrates advanced data recovery techniques with leading‐edge methods to address this issue. The system begins by identifying and isolating fault nodes using a specialized algorithm that analyzes network behavior. By applying fuzzy density‐based spatial clustering of applications with noise (FDBSCAN), potential fault nodes are precisely located based on deviations from expected patterns. Subsequently, an intelligent missing data recovery mechanism powered by bidirectional long short‐term memory (Bi‐LSTM) networks takes action. The Bi‐LSTM model is trained on existing sensor data to capture intricate patterns and dependencies, enabling accurate prediction and reconstruction of missing values caused by identified faults. The synergy between Bi‐LSTM for missing data recovery and FDBSCAN for fault node detection comprehensively addresses the missing data problem in WSNs. In missing data recovery, it demonstrates low mean absolute deviation (MAD) ranging from 0.021 to 0.13 and mean squared deviation (MSD) ranging from 0.0025 to 0.05 across various missing data ratios. Data reliability remains consistently high at 96% to 98%, even with up to 80% missing data. For fault node detection, the approach achieves precision of 95.7%, recall of 96.3%, F1‐score of 96.1%, and accuracy of 97.4%, outperforming existing techniques. The computational cost during training is noted at 5.79 h, presenting a limitation compared to other methods. This research highlights the importance of integrating fault node detection into missing data recovery mechanisms, presenting an innovative solution for the advancement of WSNs. [ABSTRACT FROM AUTHOR]

Predictive maintenance in industrial settings, especially tool wear prediction, remains crucial for operational efficiency and cost reduction. This paper proposes BiLPReS, a novel predictive model leveraging a hybrid architecture integrating bidirectional long short-term memory, Performer encoder, and residual-skip connections. Compared to convolutional and recurrent neural networks, the proposed model achieves long-range dependent global sensing and parallel computing. The Performer encoder reduces the computational complexity by the FAVOR + approach compared to the Transformer encoder. Moreover, the proposed model includes residual-skip connections to enhance information flow efficiency and minimize the risk of information loss during training. The final use of the fully connected layer reduces dimensionality and generates the predicted values. Experiments on the PHM2010 dataset involve the analysis of multichannel sensor signals, including force, acceleration, and acoustic emission. The model undergoes training and validation through k-fold cross-validation. Results unequivocally demonstrate the model's high accuracy. Furthermore, conducting comparative experiments by selectively reducing modules validates the effectiveness of the utilized modules in enhancing the model's performance. This study provides a viable solution for optimizing maintenance schedules, reducing downtime, and real-time monitoring of tool machining. [ABSTRACT FROM AUTHOR]

Pipeline networks are crucial components of modern infrastructure, and ensuring their reliable operation is essential for sustainable development. The percussion-based methods are considered promising for detecting pipeline faults due to their avoidance of constant-contact sensors and ease of implementation. However, the majority of existing percussion-based methods suffer from limitations such as the requirement for manual feature extraction, as well as subpar noise resilience and adaptability. This paper introduces a one-dimensional convolutional bidirectional long short-term memory network with wide first-layer kernels for the classification of percussion-induced acoustic signals, thus achieving automatic identification of pipeline leakage and water deposit conditions. This approach directly extracts features from audio signals using wide first-layer convolutional kernels, eliminating the need for manual feature extraction. Additionally, it employs bidirectional long short-term memory to effectively capture long-term signal dependencies from both past and future contexts. To validate the effectiveness of the method, two case studies were conducted on three groups of pipes. The results show that the proposed method demonstrates superior noise resistance and adaptability compared to other methods, and it also exhibits strong applicability to other percussion signal datasets. Additionally, the impact of different first convolutional kernel sizes on the noise resistance and adaptive performance of the model was investigated, which provides robust guidance for the effective processing of percussion-induced acoustic signals. [ABSTRACT FROM AUTHOR]

Millimeter wave Massive Multiple Input Multiple Output (MIMO) and Orthogonal Frequency Domain Multiplexing (OFDM) utilize a lens antenna array to minimize the count of Radio Frequency (RF) chains. However, MIMO-OFDM faces a significant issue due to having fewer RF chains, as compared to the number of antennas. The estimation of beam space channel in the sparse signal recovery makes it challenging due to the channel exploitation. The traditional approaches-based channel estimation faces significant challenges like degradation of the model training process due to inappropriate adoption of Deep Learning (DL) architectures. In addition, they have complex architecture and require higher training data. So, this research develops a sparse channel estimation approach with the help of DL approach, along with the optimization technique. The Adaptive Deep Neural Network (ADNN) helps in uplink channel estimation and the Bidirectional Long Short-Term Memory (Bi-LSTM) helps to perform hybrid pre-coding. The Hippopotamus Optimization Algorithm (HOA) is introduced to optimize hidden neurons for enhancing accuracy. The experimental outcomes exhibit that the proposed approach achieves a better accuracy of 0.9831 at the learning rate of 35, as opposed to the existing method, Trail-based Red Deer Algorithm (T-RDA). [ABSTRACT FROM AUTHOR]

Social media platforms are widely used around the world for communication, but they are often misused for harmful purposes such as cyberbullying. However, text data input for detecting cyberbullying often includes unwanted text, spelling errors, irrelevant features, and a large number of labels. These factors reduce accuracy and complicate learning from the data. This research proposes the use of Bidirectional Long Short-Term Memory (Bi-LSTM) and Feed Forward Neural Network (FFNN) techniques to process the sequential text data for feature independence and high accuracy in learning complex the text data. Initially, a cyberbullying tweets dataset is obtained from social media and pre-processing techniques such as converting text are applied to the lowercase, while stemming is included to improve data quality in the training process. Term Frequency-Inverse Document Frequency (TF-IDF) techniques using feature extraction is performed using to identify the most compact and Principal Component Analysis (PCA) for feature selection to identify relevant feature sets. The proposed Bi-LSTM with FFNN techniques are evaluated using the cyberbullying tweets dataset, achieving a higher accuracy of 98.94%, precision of 97.62%, recall of 96.02%, and F1-score of 96.82%. The existing techniques, Multi-Layer Perceptron (MLP)and Bi-Directional Long Short-Term Memory Assisted Attention Hierarchical Capsule Network (BiLSTM-AHCNet) are used to evaluate the proposed method. [ABSTRACT FROM AUTHOR]

Methamphetamine (MA) is a neurological drug, which is harmful to the overall brain cognitive function when abused. Based on this property of MA, people can be divided into those with MA abuse and healthy people. However, few studies to date have investigated automatic detection of MA abusers based on the neural activity. For this reason, the purpose of this research was to investigate the difference in the neural activity between MA abusers and healthy persons and accordingly discriminate MA abusers. First, we performed event-related potential (ERP) analysis to determine the time range of P300. Then, the wavelet coefficients of the P300 component were extracted as the main features, along with the time and frequency domain features within the selected P300 range to classify. To optimize the feature set, F_score was used to remove features below the average score. Finally, a Bidirectional Long Short-term Memory (BiLSTM) network was performed for classification. The experimental result showed that the detection accuracy of BiLSTM could reach 83.85%. In conclusion, the P300 component of EEG signals of MA abusers is different from that in normal persons. Based on this difference, this study proposes a novel way for the prevention and diagnosis of MA abuse. [ABSTRACT FROM AUTHOR]

The identification of individuals through ear images is a prominent area of study in the biometric sector. Facial recognition systems have faced challenges during the COVID-19 pandemic due to mask-wearing, prompting the exploration of supplementary biometric measures such as ear biometrics. The research proposes a Deep Learning (DL) framework, termed DeepBio, using ear biometrics for human identification. It employs two DL models and five datasets, including IIT Delhi (IITD-I and IITD-II), annotated web images (AWI), mathematical analysis of images (AMI), and EARVN1. Data augmentation techniques such as flipping, translation, and Gaussian noise are applied to enhance model performance and mitigate overfitting. Feature extraction and human identification are conducted using a hybrid approach combining Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (Bi-LSTM). The DeepBio framework achieves high recognition rates of 97.97%, 99.37%, 98.57%, 94.5%, and 96.87% on the respective datasets. Comparative analysis with existing techniques demonstrates improvements of 0.41%, 0.47%, 12%, and 9.75% on IITD-II, AMI, AWE, and EARVN1 datasets, respectively. [ABSTRACT FROM AUTHOR]

Oral Squamous Cell Carcinoma (OSCC) causes a severe challenge in oncology due to the lack of diagnostic devices, leading to delays in detecting the disorder. The OSCC diagnosis through histopathology demands a pathologist expert because the cellular presentation is variable and highly complex. Existing diagnostic approaches for OSCC have specific efficiency and accuracy restrictions, highlighting the necessity for more reliable techniques. The increase of deep neural networks (DNN) model and their applications in medical imaging have been instrumental in disease diagnosis and detection. Automatic detection systems using deep learning (DL) approaches show tremendous promise in investigating medical imagery with speed, efficiency, and accuracy. In terms of OSCC, this system allows the diagnostic method to be streamlined, facilitating earlier diagnosis and enhancing survival rates. Automatic analysis of histopathological image (HI) can assist in accurately detecting and identifying tumorous tissue, reducing diagnostic turnaround times and increasing the efficacy of pathologists. This study presents a Squeeze-Excitation with Hybrid Deep Learning for Oral Squamous Cell Carcinoma Recognition (SEHDL-OSCCR) on HIs. The presented SEHDL-OSCCR technique mainly focuses on detecting oral cancer (OC) using hybrid DL models. The bilateral filtering (BF) technique is initially used to remove the noise. Next, the SEHDL-OSCCR technique employs the SE-CapsNet model to recognize the feature extractors. An improved crayfish optimization algorithm (ICOA) technique is utilized to improve the performance of the SE-CapsNet model. At last, the classification of the OSCC technique is performed by employing a convolutional neural network with a bidirectional long short-term memory (CNN-BiLSTM) model. The simulation results obtained using the SEHDL-OSCCR technique are investigated using a benchmark medical image dataset. The experimental validation of the SEHDL-OSCCR technique illustrated a greater accuracy outcome of 98.75% compared to recent approaches. [ABSTRACT FROM AUTHOR]

With the ubiquitous deployment of mobile and sensor technologies in modes of transportation, taxis have become a significant component of public transportation. However, vacant taxis represent an important waste of transportation resources. Forecasting taxi demand within a short time achieves a supply–demand balance and reduces oil emissions. Although earlier studies have forwarded highly developed machine learning- and deep learning-based models to forecast taxicab demands, these models often face significant computational expenses and cannot effectively utilize large-scale trajectory sensor data. To address these challenges, in this paper, we propose a hybrid deep learning-based model for taxi demand prediction. In particular, the Variational Mode Decomposition (VMD) algorithm is integrated along with a Bidirectional Long Short-Term Memory (BiLSTM) model to perform the prediction process. The VMD algorithm is applied to decompose time series-aware traffic features into multiple sub-modes of different frequencies. After that, the BiLSTM method is utilized to predict time series data fed with the relevant demand features. To overcome the limitation of high computational expenses, the designed model is performed on the Spark distributed platform. The performance of the proposed model is tested using a real-world dataset, and it surpasses existing state-of-the-art predictive models in terms of accuracy, efficiency, and distributed performance. These findings provide insights for enhancing the efficiency of passenger search and increasing the profit of taxicabs. [ABSTRACT FROM AUTHOR]

The advancement of medical technology has brought about a significant transformation in remote healthcare monitoring, which is crucial for providing customized care and ongoing observation. This is especially important when it comes to controlling long-term illnesses like high blood pressure, which raises the risk of heart disease considerably, especially in older people. This methodology achieves greater accuracy by combining regular medical monitoring and Electronic Clinical Data (ECD) from complete medical records with physical data from patients' routine medical monitoring. This innovative technique enhances the area of cardiac disease prediction. A technique that uses cutting-edge machine learning models and IoT technology to meet this demand. In particular, we use the powerful Extreme Gradient Boosting (XGBoost) algorithm to effectively examine big datasets and extract important characteristics to improve prediction accuracy. The deep learning model Bidirectional Long Short-Term Memory (Bi-LSTM) is used to further enhance prediction skills to extract complex temporal patterns from patient data. It outperformed naive Bayes, decision trees, and random forests with our approach, achieving a greater prediction accuracy of 99.4 %. With the combination of Internet of Things technologies and sophisticated machine learning models, this paper offers a novel approach to remote healthcare monitoring. [ABSTRACT FROM AUTHOR]

Transformer models are widely used in natural language processing (NLP) and time-series data analysis. Applications of these models include prediction systems and hand gesture recognition using electromyogram (EMG) signals. However, in the case of time-series analysis, the models perform similarly to traditional networks, contrary to expectations. This study aimed to compare the performance of the transformer model and its various modified versions in terms of accuracy through a user authentication system using EMG signals, which exhibit significant variability and pose challenges in feature extraction. A Siamese network was employed to distinguish subtle differences in the EMG signals between users, using Euclidean distance. Data from 100 individuals were used to create a challenging scenario while ensuring accuracy. Three scenarios were considered: data preprocessing, integration with existing models, and the modification of the internal structure of the transformer model. The method that achieved the highest accuracy was the bidirectional long short-term memory (BiLSTM)–transformer approach. Based on this, a network was further constructed and optimized, resulting in a user authentication accuracy of 99.7% using EMG data from 100 individuals. [ABSTRACT FROM AUTHOR]

The precise estimation of the operational lifespan of insulated gate bipolar transistors (IGBT) holds paramount significance for ensuring the efficient and uncompromised safety of industrial equipment. However, numerous methodologies and models currently employed for this purpose often fall short of delivering highly accurate predictions. The analytical approach that combines the Pattern Optimization Algorithm (POA) with Successive Variational Mode Decomposition (SVMD) and Bidirectional Long Short-term Memory (BiLSTM) network is introduced. Firstly, SVMD is employed as an unsupervised feature learning method to partition the data into intrinsic modal functions (IMFs), which are used to eliminate noise and preserve the essential signal. Secondly, the BiLSTM network is integrated for supervised learning purposes, enabling the prediction of the decomposed sequence. Additionally, the hyperparameters of BiLSTM and the penalty coefficients of SVMD are optimized utilizing the POA technique. Subsequently, the various modal functions are predicted utilizing the trained prediction model, and the individual mode predictions are subsequently aggregated to yield the model's definitive final life prediction. Through case studies involving IGBT aging datasets, the optimal prediction model was formulated and its lifespan prediction capability was validated. The superiority of the proposed method is demonstrated by comparing it with benchmark models and other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The most significant issue today is electricity theft (ET) which causes much loss to electricity boards. The development of smart grids (SGs) is crucial for ET detection (ETD) because these systems produce enormous amounts of data, including information on customer consumption, which can be used to identify ET using machine learning and deep learning (DL) techniques. However, the existing models majorly suffers with lower prediction accuracy because of over-fitting and dataset imbalancing issues. Therefore, to overcome these shortcomings, this paper proposes a novel DL approach for ETD in the Internet of Things-based SGs using parameter-tuned bidirectional long short-term memory (PTBiLSTM) with pre-trained feature learning model. The proposed system mainly comprises '4' phases: preprocessing, dataset balancing, feature selection, and ETD. Initially, the consumers' electricity consumption data are collected from the theft detection dataset 2022 (TDD2022) dataset. Then, the data balancing is carried out by using Gaussian distribution, including fuzzy C-means approach to handle the imbalance data. Afterward, the meaningful features from the balanced dataset are extracted using the hard swish and dropout layer included residual neural network-50 (ResNet-50) model. Finally, the ETD is done, which utilizes a PTBiLSTM. The proposed models' performance is evaluated using different performance metrics like accuracy, precision, recall, f-measure, the area under the curve, and kappa. The outcomes proved the efficiency of the proposed method over other related schemes in the ETD of SGs. [ABSTRACT FROM AUTHOR]

Existing studies on gait phase estimation generally involve walking experiments using inertial measurement units under limited walking conditions (WCs). In this study, a gait phase estimation algorithm is proposed that uses data from force sensing resistors (FSRs) and a Bi-LSTM model. The proposed algorithm estimates gait phases in real time under various WCs, e.g., walking on paved/unpaved roads, ascending and descending stairs, and ascending or descending on ramps. The performance of the proposed algorithm is evaluated by performing walking experiments on ten healthy adult participants. An average gait estimation accuracy exceeding 90% is observed with a small error (root mean square error = 0.794, R2 score = 0.906) across various WCs. These results demonstrate the wide applicability of the proposed gait phase estimation algorithm using various insole devices, e.g., in walking aid control, gait disturbance diagnosis in daily life, and motor ability analysis. [ABSTRACT FROM AUTHOR]

• We designed an intelligent two-layer deep learning (DL) model that predict the promoter region in the first stage and their functional types in second stage respectively. • We captured the DNA encoded patterns using Word2Vec algorithm and analyzed the visual impact of biological features using t-distributed stochastic neighbor embedding method. • We enhanced the overall prediction performance of promoters and their functional types (as weak and strong prompters) on multiple datasets. Promoters, which are short (50–1500 base-pair) in DNA regions, have emerged to play a critical role in the regulation of gene transcription. Numerous dangerous diseases, likewise cancer, cardiovascular, and inflammatory bowel diseases, are caused by genetic variations in promoters. Consequently, the correct identification and characterization of promoters are significant for the discovery of drugs. However, experimental approaches to recognizing promoters and their strengths are challenging in terms of cost, time, and resources. Therefore, computational techniques are highly desirable for the correct characterization of promoters from unannotated genomic data. Here, we designed a powerful bi-layer deep-learning based predictor named "PROCABLES", which discriminates DNA samples as promoters in the first-phase and strong or weak promoters in the second-phase respectively. The proposed method utilizes five distinct features, such as word2vec, k-spaced nucleotide pairs, trinucleotide propensity-based features, trinucleotide composition, and electron–ion interaction pseudopotentials, to extract the hidden patterns from the DNA sequence. Afterwards, a stacked framework is formed by integrating a convolutional neural network (CNN) with bidirectional long-short-term memory (LSTM) using multi-view attributes to train the proposed model. The PROCABLES model achieved an accuracy of 0.971 and 0.920 and the MCC 0.940 and 0.840 for the first and second-layer using the ten-fold cross-validation test, respectively. The predicted results anticipate that the proposed PROCABLES protocol outperformed the advanced computational predictors targeting promoters and their types. In summary, this research will provide useful hints for the recognition of large-scale promoters in particular and other DNA problems in general. [ABSTRACT FROM AUTHOR]

In the digital age, personalized recommendation systems have become crucial for information dissemination and user experience. While traditional systems focus on accuracy, they often overlook diversity, novelty, and serendipity. This study introduces an innovative recommendation system model, Time-based Outlier Aware Recommender (TOAR), designed to address the challenges of content homogenization and information bubbles in personalized recommendations. TOAR integrates Neural Matrix Factorization (NeuMF), Bidirectional Long Short-Term Memory Networks (Bi-LSTM), and Mean Shift clustering to enhance recommendation accuracy, novelty, and diversity. The model analyzes temporal dynamics of user behavior and facilitates cross-domain knowledge exchange through feature sharing and transfer learning mechanisms. By incorporating an attention mechanism and unsupervised clustering, TOAR effectively captures important time-series information and ensures recommendation diversity. Experimental results on a news recommendation dataset demonstrate TOAR's superior performance across multiple metrics, including AUC, precision, NDCG, and novelty, compared to traditional and deep learning-based recommendation models. This research provides a foundation for developing more intelligent and personalized recommendation services that balance accuracy with content diversity. [ABSTRACT FROM AUTHOR]

The internet of things (IoT) greatly impacts daily life by enabling efficient data exchange between objects and servers. However, cyber-attacks pose a serious threat to IoT devices. Intrusion detection systems (IDS) are vital for safeguarding networks, and machine learning methods are increasingly used to enhance security. Continuous improvement in accuracy and performance is crucial for effective IoT security. Deep learning not only outshines traditional machine learning methods but also holds untapped potential in fortifying IDS systems. This paper introduces an innovative deep learning framework tailored for anomaly detection within IoT networks, leveraging bidirectional long short-term memory (BiLSTM) and gated recurrent unit (GRU) architectures. The hyper parameters of the proposed model are optimized using the JAYA optimization technique. These models are validated using IoT-23 and MQTTset datasets. Several performance metrics including accuracy, precision, recall, F-score, true negative rate (TNR), false positive rate (FPR), and false negative rate (FNR), have been selected to assess the effectiveness of the suggested model. The empirical results are scrutinized and juxtaposed with prevailing approaches in the realm of intrusion detection for IoT. Notably, the proposed method emerges as showcasing superior accuracy when contrasted with existing methods. [ABSTRACT FROM AUTHOR]

Breast cancer is a significant threat to the global population, affecting not only women but also a threat to the entire population. With recent advancements in digital pathology, Eosin and hematoxylin images provide enhanced clarity in examining microscopic features of breast tissues based on their staining properties. Early cancer detection facilitates the quickening of the therapeutic process, thereby increasing survival rates. The analysis made by medical professionals, especially pathologists, is time-consuming and challenging, and there arises a need for automated breast cancer detection systems. The upcoming artificial intelligence platforms, especially deep learning models, play an important role in image diagnosis and prediction. Initially, the histopathology biopsy images are taken from standard data sources. Further, the gathered images are given as input to the Multi-Scale Dilated Vision Transformer, where the essential features are acquired. Subsequently, the features are subjected to the Bidirectional Long Short-Term Memory (Bi-LSTM) for classifying the breast cancer disorder. The efficacy of the model is evaluated using divergent metrics. When compared with other methods, the proposed work reveals that it offers impressive results for detection. [ABSTRACT FROM AUTHOR]

This research presents a uni-regression deep approximate forecasting model for predicting future demand in supply chains, tackling issues like complex patterns, external factors, and nonlinear relationships. It diverges from traditional models by employing a deep learning strategy through recurrent bidirectional long short-term memory (BiLSTM) and nonlinear autoregressive with exogenous inputs (NARX), focusing on regression-based approaches. The model can capture intricate dependencies and patterns that elude conventional approaches. The integration of BiLSTM and NARX provides a robust foundation for accurate demand forecasting. The novel uni-regression technique significantly improves the model's capability to detect intricate patterns and dependencies in supply chain data, offering a new angle for demand forecasting. This approach not only broadens the scope of modeling techniques but also underlines the value of deep learning for enhanced accuracy in the fluctuating supply chain sector. The uni-regression model notably outperforms existing models in accuracy, achieving the lowest errors: mean average error (MAE) at 1.73, mean square error (MSE) at 4.14, root mean square error (RMSE) at 2.03, root mean squared scaled error (RMSSE) at 0.020, and R-squared at 0.94. This underscores its effectiveness in forecasting demand within dynamic supply chains. Practitioners and decision-makers can leverage the uni-regression model to make informed decisions, optimize inventory management, and enhance supply chain resilience. Furthermore, the findings contribute to the ongoing evolution of supply chain demand forecasting methodologies. [ABSTRACT FROM AUTHOR]

With the increasing demand for the refined management of residential loads, the study of the non-invasive load monitoring (NILM) technologies has attracted much attention in recent years. This paper proposes a novel method of residential load identification based on load feature matrix and improved neural networks. Firstly, it constructs a unified scale bitmap format gray image consisted of multiple load feature matrix including: V-I characteristic curve, 1-16 harmonic currents, 1- cycle steady-state current waveform, maximum and minimum current values, active and reactive power. Secondly, it adopts a convolutional layer to extract image features and performs further feature extraction through a convolutional block attention module (CBAM). Thirdly, the feature matrix is converted and input to a bidirectional long short-term memory (BiLSTM) for training and identification. Furthermore, the identification results are optimized with dynamic time warping (DTW). The effectiveness of the proposed method is verified by the commonly used PLAID database. [ABSTRACT FROM AUTHOR]

Error checking of verb forms in English articles is beneficial for learning English and improving the fluency of English texts. In this study, long shortterm memory (LSTM) was used to recognize the types of errors in verb forms. To maximize the utilization of textual context information, a bidirectional LSTM algorithm was employed. Simulation experiments were then conducted, and the algorithm was evaluated against the support vector machine (SVM) algorithm and the grammar rules-based algorithm. The bidirectional LSTM method demonstrated higher accuracy in recognizing the parts of speech of words and the types of verb form errors in the text. Additionally, the accuracy was more stable when faced with different types of verb form errors. [ABSTRACT FROM AUTHOR]

In the realm of precision space applications, improving the accuracy of orbit determination (OD) is a crucial and demanding task, primarily because of the presence of measurement noise. To address this issue, a novel machine learning method based on bidirectional long short-term memory (BiLSTM) is proposed in this research. In particular, the proposed method aims to improve the OD accuracy of Earth–Moon Libration orbits with angle-only measurements. The proposed BiLSTM network is designed to detect inaccurate measurements during an OD process, which is achieved by incorporating the least square method (LSM) as a basic estimation approach. The structure, inputs, and outputs of the modified BiLSTM network are meticulously crafted for the detection of inaccurate measurements. Following the detection of inaccurate measurements, a compensating strategy is devised to modify these detection results and thereby reduce their negative impact on OD accuracy. The modified measurements are then used to obtain a more accurate OD solution. The proposed method is applied to solve the OD problem of a 4:1 synodic resonant near-rectilinear halo orbit around the Earth–Moon L2 point. The training results reveal that the bidirectional network structure outperforms the regular unidirectional structures in terms of detection accuracy. Numerical simulations show that the proposed method can reduce the estimated error by approximately 10%. The proposed method holds significant potential for future missions in cislunar space. [ABSTRACT FROM AUTHOR]

Furnace temperature and oxygen content are important parameters reflecting the combustion inside a circulating fluidized bed (CFB) boiler. Accurately predicting boiler output is a complex task due to the high noise and nonsmoothness of actual boiler input and output data. In this paper, a new hybrid convolutional neural network (CNN), bidirectional long short-term memory (biLSTM) network, and squeezing and excitation (SE) network prediction model is proposed to significantly improve the prediction accuracy of oxygen content and furnace temperature by combining the advantages of multiple deep learning networks. This network can extract spatiotemporal characteristics of input parameters such as coal feed to effectively predict boiler furnace temperature and oxygen content. CNNs can extract complex features such as dynamic and static nonlinearities between multiple variables affecting the furnace temperature and oxygen content, as well as high noise. The biLSTM network layer can efficiently handle the temporal information of irregular trends in modeling time series components; SE can extract the important information between channels through the feature relationships between channels for better overfeature extraction. The CNN-biLSTM-SE model can effectively solve the problem of nonlinear mapping complexity between inputs and outputs. Experiments show that the proposed CNN-biLSTM-SE model outperforms existing methods. The experimental results showed that the average MAPE errors for oxygen content prediction were CNN-biLSTM-SE (0.038), CNN-biLSTM with attention mechanism (AM) (0.043), CNN-biLSTM (0.051), CNN-LSTM (0.051), biLSTM (0.051), RNN (0.051), LSTM(0.0052), and CNN(0.0054). Extensive experiments in CFB boilers with oxygen content and furnace temperature show that the proposed CNN-biLSTM-SE model achieves better results in terms of goodness-of-fit, generalization ability and accuracy. [ABSTRACT FROM AUTHOR]

In response to the escalating demand for robust security solutions in increasingly complex Internet of Things (IoT) networks, this study introduces an advanced Intrusion Detection System (IDS) leveraging both deep learning and active learning techniques. This research addresses the unique challenges posed by IoT environments, such as limited resources and diverse network components, which traditional security measures fail to adequately protect. Employing a BiLSTM model integrated with an active learning strategy, our approach achieved impressive results, including precision, recall, and F1-scores close to 1, and a total accuracy of 0.99. The inclusion of active learning enables the IDS to focus on the most informative data subsets, enhancing processing efficiency and reducing computational demands essential for IoT contexts. This method demonstrates significant promise for detecting sophisticated cyber threats and providing an effective tool for real-world applications. The performance of the proposed model has been rigorously validated on well-established cybersecurity datasets and through simulations in an IoT network environment, confirming its scalability and efficiency. Future work will address potential limitations such as computational demands and adaptability to diverse IoT device architectures, ensuring broader applicability and robustness of the IDS in varied IoT scenarios. [ABSTRACT FROM AUTHOR]

This study primarily investigates advanced object detection and time series prediction methods in image-based visual servoing systems, aiming to capture targets better and predict the motion trajectory of robotic arms in advance, thereby enhancing the system's performance and reliability. The research first implements object detection on the VOC2007 dataset using the Detection Transformer (DETR) and achieves ideal detection scores. The particle swarm optimization algorithm and 3-5-3 polynomial interpolation methods were utilized for trajectory planning, creating a unique dataset through simulation. This dataset contains randomly generated trajectories within the workspace, fully simulating actual working conditions. Significantly, the Bidirectional Long Short-Term Memory (BILSTM) model was improved by substituting its traditional Multilayer Perceptron (MLP) components with Kolmogorov–Arnold Networks (KANs). KANs, inspired by the K-A theorem, improve the network representation ability by placing learnable activation functions on fixed node activation functions. By implementing KANs, the model enhances parameter efficiency and interpretability, thus addressing the typical challenges of MLPs, such as the high parameter count and lack of transparency. The experiments achieved favorable predictive results, indicating that the KAN not only reduces the complexity of the model but also improves learning efficiency and prediction accuracy in dynamic visual servoing environments. Finally, Gazebo software was used in ROS to model and simulate the robotic arm, verify the effectiveness of the algorithm, and achieve visual servoing. [ABSTRACT FROM AUTHOR]

The operation and maintenance of futuristic electric vehicles need accurate estimation of the state of health (SOH) of lithium-ion batteries (LIBs). To address this issue, a robust neural network framework is proposed to estimate the SOH. This article developed a novel approach that combines improved particle swarm optimization (IPSO) with bidirectional long short-term memory (Bi-LSTM) to effectively address the issue of precisely estimating SOH. The proposed IPSO-Bi-LSTM model is more effective than the other models for SOH estimation. This is because Bi-LSTM can capture both past and future appropriate information, making it more suitable for modeling complicated temporal sequences. The IPSO main objective is to optimize the model hyperparameters. To increase the model's accuracy, the IPSO improves the parameters. The PSO-Bi-LSTM model performed better than the other approaches, according to experimental findings based on the NASA-PCOE battery dataset, and all of the SOH estimated outcomes, such as root mean square errors, were less than 0.50%. This result suggests that the proposed PSO-Bi-LSTM model has the ability to robustly estimate the SOH with a high accuracy. [ABSTRACT FROM AUTHOR]

Abstract Oral Squamous Cell Carcinoma (OSCC) causes a severe challenge in oncology due to the lack of diagnostic devices, leading to delays in detecting the disorder. The OSCC diagnosis through histopathology demands a pathologist expert because the cellular presentation is variable and highly complex. Existing diagnostic approaches for OSCC have specific efficiency and accuracy restrictions, highlighting the necessity for more reliable techniques. The increase of deep neural networks (DNN) model and their applications in medical imaging have been instrumental in disease diagnosis and detection. Automatic detection systems using deep learning (DL) approaches show tremendous promise in investigating medical imagery with speed, efficiency, and accuracy. In terms of OSCC, this system allows the diagnostic method to be streamlined, facilitating earlier diagnosis and enhancing survival rates. Automatic analysis of histopathological image (HI) can assist in accurately detecting and identifying tumorous tissue, reducing diagnostic turnaround times and increasing the efficacy of pathologists. This study presents a Squeeze-Excitation with Hybrid Deep Learning for Oral Squamous Cell Carcinoma Recognition (SEHDL-OSCCR) on HIs. The presented SEHDL-OSCCR technique mainly focuses on detecting oral cancer (OC) using hybrid DL models. The bilateral filtering (BF) technique is initially used to remove the noise. Next, the SEHDL-OSCCR technique employs the SE-CapsNet model to recognize the feature extractors. An improved crayfish optimization algorithm (ICOA) technique is utilized to improve the performance of the SE-CapsNet model. At last, the classification of the OSCC technique is performed by employing a convolutional neural network with a bidirectional long short-term memory (CNN-BiLSTM) model. The simulation results obtained using the SEHDL-OSCCR technique are investigated using a benchmark medical image dataset. The experimental validation of the SEHDL-OSCCR technique illustrated a greater accuracy outcome of 98.75% compared to recent approaches.

The advancement of medical technology has brought about a significant transformation in remote healthcare monitoring, which is crucial for providing customized care and ongoing observation. This is especially important when it comes to controlling long-term illnesses like high blood pressure, which raises the risk of heart disease considerably, especially in older people. This methodology achieves greater accuracy by combining regular medical monitoring and Electronic Clinical Data (ECD) from complete medical records with physical data from patients' routine medical monitoring. This innovative technique enhances the area of cardiac disease prediction. A technique that uses cutting-edge machine learning models and IoT technology to meet this demand. In particular, we use the powerful Extreme Gradient Boosting (XGBoost) algorithm to effectively examine big datasets and extract important characteristics to improve prediction accuracy. The deep learning model Bidirectional Long Short-Term Memory (Bi-LSTM) is used to further enhance prediction skills to extract complex temporal patterns from patient data. It outperformed naive Bayes, decision trees, and random forests with our approach, achieving a greater prediction accuracy of 99.4 %. With the combination of Internet of Things technologies and sophisticated machine learning models, this paper offers a novel approach to remote healthcare monitoring.

Crop yield prediction is one of the burgeoning research areas in the agriculture domain. The crop yield forecasting models are developed to enhance productivity with improved decision-making strategies. The highly efficient crop yield forecasting model assists farmers in determining when, what and how much to plant on their cultivable land. The main objective of the proposed research work is to build a high efficacious crop yield prediction model based on the data available for the period of 21 years from 1997 to 2017 using machine learning and hybrid deep learning approaches. Two prediction models have been proposed in this research work to predict the crop yield accurately. The first model is a machine learning-based model which uses the CatBoost regression model and its hyperparameters are tuned which improves the performance of the yield prediction using the Optuna framework. The second model is the hybrid deep learning model which uses spatio-temporal attention-based convolutional neural network (STACNN) for extracting the features and the bidirectional long short-term memory (BiLSTM) model for predicting the crop yield effectively. The proposed models are evaluated using the error metrics and compared with the latest contemporary models. From the evaluation results, it is shown that the proposed models significantly outperform all other existing models and CatBoost regression model slightly performs better than the STACNN-BiLSTM model, with the R-squared value of 0.99. [ABSTRACT FROM AUTHOR]

Structural health monitoring (SHM) data encompasses vital information that provides a comprehensive understanding of the structural health condition. However, data loss may occur due to faults in acquisition equipment or sensors, and it is essential to reconstruct missing data to ensure the integrity of the monitoring information. Although extensive researches have been conducted on the topic of data recovery, a suitable missing data recovery method that can effectively address the missing data for multiple-source monitoring variables has not been identified yet. In this study, we proposed a novel missing data recovery model based on a deep learning framework to recover the missing strain and acceleration data simultaneously for SHM of the quayside container crane (QCC). The framework combines dual-tree complex wave transform (DTCWT) and bidirectional long short-term memory with attention mechanism (Att-BiLSTM). The multiple-source monitoring data are decomposed into several subtime series using the dual-tree complex wavelet, then, the Att-BiLSTM network is used to assign different weights to each subsequence in order to capture valuable information from the complete data. The effectiveness of the proposed model is verified by case studies, and the comparison results of missing data recovery under different miss rates show that the proposed model simultaneously improves the accuracy of missing data recovery for multiple-source monitoring variables. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Shanghai Jiaotong University (Science) is the property of Springer Nature 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.)

Accurate flow forecasting is crucial for effective basin management, regional agricultural policy development, environmental impact analysis, soil and water conservation studies, and flood protection planning. This study proposes a novel approach that integrates particle swarm optimization (PSO) with bidirectional long short-term memory (Bi-LSTM) and bidirectional gated recurrent unit (Bi-GRU) architectures, augmented by feature fusion and attention layers. Our approach consistently outperforms traditional methods across multiple datasets, including Ahmethacı, Büyükincirli, and Ersil, thereby achieving lower RMSE, MAE, and higher KGE and BF scores. Specifically, in Ahmethacı, our method yields an RMSE of 3.448, MAE of 1.224, and an R2 of 0.886. In Büyükincirli, it records an RMSE of 0.085, MAE of 0.040, and an R2 of 0.964. In Ersil, it achieves an RMSE of 1.495, MAE of 0.565, and R2 of 0.883. These results underscore the effectiveness of the proposed approach in flow forecasting. [ABSTRACT FROM AUTHOR]

In artificial intelligence, combating overfitting and enhancing model generalization is crucial. This research explores innovative noise-induced regularization techniques, focusing on natural language processing tasks. Inspired by gradient noise and Dropout, this study investigates the interplay between controlled noise, model complexity, and overfitting prevention. Utilizing long short-term memory and bidirectional long short term memory architectures, this study examines the impact of noise-induced regularization on robustness to noisy input data. Through extensive experimentation, this study shows that introducing controlled noise improves model generalization, especially in language understanding. This contributes to the theoretical understanding of noise-induced regularization, advancing reliable and adaptable artificial intelligence systems for natural language processing. [ABSTRACT FROM AUTHOR]

Abstract Virus‒host protein‒lncRNA interaction (VHPLI) predictions are critical for decoding the molecular mechanisms of viral pathogens and host immune processes. Although VHPLI interactions have been predicted in both plants and animals, they have not been extensively studied in viruses. For the first time, we propose a new deep learning-based approach that consists mainly of a convolutional neural network and bidirectional long and short-term memory network modules in combination with transfer learning named CBIL‒VHPLI to predict viral–host protein‒lncRNA interactions. The models were first trained on large and diverse datasets (including plants, animals, etc.). Protein sequence features were extracted using a k-mer method combined with the one-hot encoding and composition–transition–distribution (CTD) methods, and lncRNA sequence features were extracted using a k-mer method combined with the one-hot encoding and Z curve methods. The results obtained on three independent external validation datasets showed that the pre-trained CBIL‒VHPLI model performed the best with an accuracy of approximately 0.9. Pretraining was followed by conducting transfer learning on a viral protein–human lncRNA dataset, and the fine-tuning results showed that the accuracy of CBIL‒VHPLI was 0.946, which was significantly greater than that of the previous models. The final case study results showed that CBIL‒VHPLI achieved a prediction reproducibility rate of 91.6% for the RIP-Seq experimental screening results. This model was then used to predict the interactions between human lncRNA PIK3CD-AS2 and the nonstructural protein 1 (NS1) of the H5N1 virus, and RNA pull-down experiments were used to prove the prediction readiness of the model in terms of prediction. The source code of CBIL‒VHPLI and the datasets used in this work are available at https://github.com/Liu-Lab-Lnu/CBIL-VHPLI for academic usage.

This study introduces an advanced artificial model, grey wolf optimization (GWO)-nested complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN)-convolutional neural network (CNN)-bidirectional long short-term memory (BiLSTM), for wind speed forecasting. Initially, CEEMDAN with two nested layers decomposes the time series into intrinsic mode functions (IMFs) to enhance forecasting capabilities. Subsequently, CNN extracts features from IMFs, and BiLSTM captures temporal dependencies for precise predictions. GWO further enhances the accurac by selecting optimal hyperparameters based on decomposition results. Test results on diverse wind speed datasets demonstrate the model’s superiority, with a mean absolute percentage error (MAPE) of approximately 3%.

Falls among the elderly are a common and serious health risk that can lead to physical injuries and other complications. To promptly detect and respond to fall events, radar-based fall detection systems have gained widespread attention. In this paper, a deep learning model is proposed based on the frequency spectrum of radar signals, called the convolutional bidirectional long short-term memory (CB-LSTM) model. The introduction of the CB-LSTM model enables the fall detection system to capture both temporal sequential and spatial features simultaneously, thereby enhancing the accuracy and reliability of the detection. Extensive comparison experiments demonstrate that our model achieves an accuracy of 98.83% in detecting falls, surpassing other relevant methods currently available. In summary, this study provides effective technical support using the frequency spectrum and deep learning methods to monitor falls among the elderly through the design and experimental validation of a radar-based fall detection system, which has great potential for improving quality of life for the elderly and providing timely rescue measures. [ABSTRACT FROM AUTHOR]

Tool condition monitoring technology is an indispensable part of intelligent manufacturing. Most current research focuses on complex signal processing techniques or advanced deep learning algorithms to improve prediction performance without fully leveraging the end-to-end advantages of deep learning. The challenge lies in transforming multi-sensor raw data into input data suitable for direct model feeding, all while minimizing data scale and preserving sufficient temporal interpretation of tool wear. However, there is no clear reference standard for this so far. In light of this, this paper innovatively explores the processing methods that transform raw data into input data for deep learning models, a process known as an input paradigm. This paper introduces three new input paradigms: the downsampling paradigm, the periodic paradigm, and the subsequence paradigm. Then an improved hybrid model that combines a convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM) was employed to validate the model's performance. The subsequence paradigm demonstrated considerable superiority in prediction results based on the PHM2010 dataset, as the newly generated time series maintained the integrity of the raw data. Further investigation revealed that, with 120 subsequences and the temporal indicator being the maximum value, the model's mean absolute error (MAE) and root mean square error (RMSE) were the lowest after threefold cross-validation, outperforming several classical and contemporary methods. The methods explored in this paper provide references for designing input data for deep learning models, helping to enhance the end-to-end potential of deep learning models, and promoting the industrial deployment and practical application of tool condition monitoring systems. [ABSTRACT FROM AUTHOR]

Predicting remaining useful life (RUL) is crucial for tool condition monitoring (TCM) systems. Inaccurate predictions can lead to premature tool replacements or excessive usage, resulting in resource wastage and potential equipment failures. This study introduces a novel tool RUL prediction method that integrates the enhanced northern goshawk optimization (MSANGO) algorithm with a bidirectional long short-term memory (BiLSTM) network. Initially, key statistical features are extracted from collected signal data using multivariate variational mode decomposition. This is followed by effective feature reduction, facilitated by the uniform information coefficient and Mann–Kendall trend tests. The RUL predictions are subsequently refined through a BiLSTM network, with the MSANGO algorithm optimizing the network parameters. Comparative evaluations with BiLSTM, BiGRU, and NGO-BiLSTM models, as well as tests on real-world datasets, demonstrate this method's superior accuracy and generalizability in RUL prediction, enhancing the efficacy of tool management systems. [ABSTRACT FROM AUTHOR]

Applications for automatic license plate recognition (ALPR) are evaluated as an important technology for effective traffic control. In particular, the most used application today for license plate recognition is at highways, toll stations, agencies, parking, and schools, with the support of camera equipment that provides high accuracy. In this study, Convolutional Recurrent Neural Networks (CRNNs) are utilized for the license plate recognition task. We are developing an automatic license plate recognition system designed for Vietnamese license plates, intended for use in indoor parking facilities with fixed cameras. In this context, the problem presents three main steps: (1) using the YOLO model to detect vehicles in the given images, (2) using the WPOD-NET model to extract license plates, and (3) introducing a new method based on an improved Convolution Recurrent Neural Network (CRNN) with combination between connectionist temporal classification (CTC) and attention mechanism to recognize characters on license plates. Our CRNN model is jointly trained with both CTC and attention objective functions. Experimental results on a license plate database collected from an indoor parking area achieved a Word Error Rate (WER) of 0.014 in the optical character recognition (OCR) task. The experimental results demonstrate that the proposed model performs well for vehicle number plate recognition and can be applied to real-time applications. [ABSTRACT FROM AUTHOR]

This study addresses the challenges of predicting ship heave motion in real time, which is essential for mitigating sensor–actuator delays in high-performance active compensation control. Traditional methods often fall short due to training on specific sea conditions, and they lack real-time prediction capabilities. To overcome these limitations, this study introduces a multi-step prediction model based on a Seq2Seq framework, training with heave data taken from various sea conditions. The model features a long-term encoder with attention-enhanced Bi-LSTM, a short-term encoder with Gated CNN, and a decoder composed of multiple fully connected layers. The long-term encoder and short-term encoder are designed to maximize the extraction of global characteristics and multi-scale short-term features of heave data, respectively. An optimized Huber loss function is used to improve the fitting performance in peak and valley regions. The experimental results demonstrate that this model outperforms baseline methods across all metrics, providing precise predictions for high-sampling-rate real-time applications. Trained on simulated sea conditions and fine-tuned through transfer learning on actual ship data, the proposed model shows strong generalization with prediction errors smaller than 0.02 m. Based on both results from the regular test and the generalization test, the model's predictive performance is shown to meet the necessary criteria for active heave compensation control. [ABSTRACT FROM AUTHOR]

This paper proposes a deep-learning-based wind speed forecasting model based on CNNs and BLSTM. After CNN layers there are BLSTM layers which take the high-level features from the CNN layer and capture the behaviour of data in time. Finally, the BLSTM layers are followed by a fully connected layer and loss function. The main advantage of the proposed method over previous methods is the two-level structure of the model. In this architecture, the CNN layers extract the high-level features from raw input data and feed them to the BLSTM layers which are very good at capturing the sequential pattern of the data. This feature of the network increases the accuracy and performance of the model significantly. The simulation results illustrate the accurate and reliable performance of the proposed method. Also, it is shown that the performance of the model in forecasting the U characteristics of the wind is relatively better than V characteristics. [ABSTRACT FROM AUTHOR]

Virus‒host protein‒lncRNA interaction (VHPLI) predictions are critical for decoding the molecular mechanisms of viral pathogens and host immune processes. Although VHPLI interactions have been predicted in both plants and animals, they have not been extensively studied in viruses. For the first time, we propose a new deep learning-based approach that consists mainly of a convolutional neural network and bidirectional long and short-term memory network modules in combination with transfer learning named CBIL‒VHPLI to predict viral–host protein‒lncRNA interactions. The models were first trained on large and diverse datasets (including plants, animals, etc.). Protein sequence features were extracted using a k-mer method combined with the one-hot encoding and composition–transition–distribution (CTD) methods, and lncRNA sequence features were extracted using a k-mer method combined with the one-hot encoding and Z curve methods. The results obtained on three independent external validation datasets showed that the pre-trained CBIL‒VHPLI model performed the best with an accuracy of approximately 0.9. Pretraining was followed by conducting transfer learning on a viral protein–human lncRNA dataset, and the fine-tuning results showed that the accuracy of CBIL‒VHPLI was 0.946, which was significantly greater than that of the previous models. The final case study results showed that CBIL‒VHPLI achieved a prediction reproducibility rate of 91.6% for the RIP-Seq experimental screening results. This model was then used to predict the interactions between human lncRNA PIK3CD-AS2 and the nonstructural protein 1 (NS1) of the H5N1 virus, and RNA pull-down experiments were used to prove the prediction readiness of the model in terms of prediction. The source code of CBIL‒VHPLI and the datasets used in this work are available at https://github.com/Liu-Lab-Lnu/CBIL-VHPLI for academic usage. [ABSTRACT FROM AUTHOR]

Gesture recognition, having multitudinous applications in the real world, is one of the core areas of research in the field of human-computer interaction. In this paper, we propose a novel method for isolated and continuous hand gesture recognition utilizing the movement epenthesis detection and removal. For this purpose, the present work detects and removes the movement epenthesis frames from the isolated and continuous hand gesture videos. In this paper, we have also proposed a novel modality based on the temporal difference that extracts hand regions, removes gesture irrelevant factors and provides temporal information contained in the hand gesture videos. Using the proposed modality and other modalities such as the RGB modality, depth modality and segmented hand modality, features are extracted using Googlenet Caffe Model. Next, we derive a set of discriminative features by fusing the acquired features that form a feature vector representing the sign gesture in question. We have designed and used a Bidirectional Long Short-Term Memory Network (Bi-LSTM) for classification purpose. To test the efficacy of our proposed work, we applied our method on various publicly available continuous and isolated hand gesture datasets like ChaLearn LAP IsoGD, ChaLearn LAP ConGD, IPN Hand, and NVGesture. We observe in our experiments that our proposed method performs exceptionally well with several individual modalities as well as combination of modalities of these datasets. The combined effect of the proposed modality and movement epenthesis frames removal led to significant improvement in gesture recognition accuracy and considerable reduction in computational burden. Thus the obtained results advocate our proposed approach to be at par with the existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Partial discharge (PD) fault diagnosis is of great importance for ensuring the safe and stable operation of power transformers. To address the issues of low accuracy in traditional PD fault diagnostic methods, this paper proposes a novel method for the power transformer PD fault diagnosis. It incorporates the approximate entropy (ApEn) of symplectic geometry mode decomposition (SGMD) into the optimized bidirectional long short-term memory (BILSTM) neural network. This method extracts dominant PD features employing SGMD and ApEn. Meanwhile, it improves the diagnostic accuracy with the optimized BILSTM by introducing the golden jackal optimization (GJO). Simulation studies evaluate the performance of FFT, EMD, VMD, and SGMD. The results show that SGMD–ApEn outperforms other methods in extracting dominant PD features. Experimental results verify the effectiveness and superiority of the proposed method by comparing different traditional methods. The proposed method improves PD fault recognition accuracy and provides a diagnostic rate of 98.6%, with lower noise sensitivity. [ABSTRACT FROM AUTHOR]

For malicious purposes, attackers hide malware in the software used by their victims. New malware is continuously being shared on the Internet, which differs both in terms of the type of malware and method of damage. When new malware is discovered, it is possible to check whether there has been similar malware in the past and to use the old malware to counteract the new malware; however, it is difficult to check the maliciousness and similarity of all software. Thus, deep learning technology can be used to efficiently detect and classify malware. This study improves this technology's accuracy by converting static features, which are binary data, into images and by converting time-series data, such as API call sequences, which are dynamic data with different lengths for each datum, into data with fixed lengths. We propose a system that combines AI-based malware detection and classification systems trained on both static and dynamic features. The experimental results showed a detection accuracy of 99.34%, a classification accuracy of 95.1%, and a prediction speed of approximately 0.1 s. [ABSTRACT FROM AUTHOR]

This paper introduces a comprehensive framework for the detection of behaviors indicative of reduced concentration levels among motor vehicle operators, leveraging multimodal image data. By integrating dedicated deep learning models, our approach systematically analyzes RGB images, depth maps, and thermal imagery to identify driver drowsiness and distraction signs. Our novel contribution includes utilizing state-of-the-art convolutional neural networks (CNNs) and bidirectional long short-term memory (Bi-LSTM) networks for effective feature extraction and classification across diverse distraction scenarios. Additionally, we explore various data fusion techniques, demonstrating their impact on improving detection accuracy. The significance of this work lies in its potential to enhance road safety by providing more reliable and efficient tools for the real-time monitoring of driver attentiveness, thereby reducing the risk of accidents caused by distraction and fatigue. The proposed methods are thoroughly evaluated using a multimodal benchmark dataset, with results showing their substantial capabilities leading to the development of safety-enhancing technologies for vehicular environments. The primary challenge addressed in this study is the detection of driver states not relying on the lighting conditions. Our solution employs multimodal data integration, encompassing RGB, thermal, and depth images, to ensure robust and accurate monitoring regardless of external lighting variations [ABSTRACT FROM AUTHOR]

The occurrence of tool chatter can have a detrimental impact on the quality of the workpiece. In order to improve surface quality, machining stability, and reduce tool wear cycles, it is essential to monitor the workpiece machining process in real time during the turning process. This paper presents a tool chatter state recognition model based on a denoising autoencoder (DAE) for feature dimensionality reduction and a bidirectional long short-term memory (BiLSTM) network. This study examines the feature dimensionality reduction method of the DAE, whereby the reduced-dimensional data are concatenated and input into the BiLSTM model for training. This approach reduces the learning difficulty of the network and enhances its anti-interference capability. Turning experiments were conducted on a SK50P lathe to collect the dataset for model performance validation. The experimental results and analysis indicate that the proposed DAE-BiLSTM model outperforms other models in terms of prediction and classification accuracy in distinguishing between stable machining, over-machining, and severe chatter stages in turning chatter state recognition. The overall classification accuracy reached 96.28%. [ABSTRACT FROM AUTHOR]

Electrocardiography (ECG) is the gold standard for monitoring vital signs and for diagnosing, controlling, and preventing cardiovascular diseases (CVDs). However, ECG requires continuous user participation, and cannot be used for continuous cardiac monitoring. In contrast to ECG, photoplethysmography (PPG) devices do not require continued user involvement, and can offer ongoing and long-term detection capabilities. However, from a medical perspective, ECG can provide more information about the heart. Currently, most existing work contains different signals recorded from the same subject in training and test sets. This study proposes a neural network model based on a 1D convolutional neural network (CNN) and a bidirectional long short-term memory (BiLSTM) network. This neural network model can directly reconstruct ECG signals from PPG signals. The learned features are captured from the CNN model and fed into the BiLSTM model. In order to verify the validity of the model, it is evaluated using the MIMIC II dataset in the completely subject-independent model (records are placed in a training set, and a test set appears once, but the test signal belongs to a record that is not in the training set). The Pearson's correlation coefficient between the reconstructed ECG and the reference ECG of the proposed model is 0.963 in the completely subject-independence model. The results of the proposed model are better than those of several cited state-of-the-art models. The results of our trained model indicate that we can obtain reconstructed ECGs that are highly similar to reference ECGs in the completely subject-independent model. [ABSTRACT FROM AUTHOR]

This paper introduces BiLSTM-MLAM, a novel multi-scale time series prediction model. Initially, the approach utilizes bidirectional long short-term memory to capture information from both forward and backward directions in time series data. Subsequently, a multi-scale patch segmentation module generates various long sequences composed of equal-length segments, enabling the model to capture data patterns across multiple time scales by adjusting segment lengths. Finally, the local attention mechanism enhances feature extraction by accurately identifying and weighting important time segments, thereby strengthening the model's understanding of the local features of the time series, followed by feature fusion. The model demonstrates outstanding performance in time series prediction tasks by effectively capturing sequence information across various time scales. Experimental validation illustrates the superior performance of BiLSTM-MLAM compared to six baseline methods across multiple datasets. When predicting the remaining life of aircraft engines, BiLSTM-MLAM outperforms the best baseline model by 6.66% in RMSE and 11.50% in MAE. In the LTE dataset, it achieves RMSE improvements of 12.77% and MAE enhancements of 3.06%, while in the load dataset, it demonstrates RMSE enhancements of 17.96% and MAE improvements of 30.39%. Additionally, ablation experiments confirm the positive impact of each module on prediction accuracy. Through segment length parameter tuning experiments, combining different segment lengths has resulted in lower prediction errors, affirming the effectiveness of the multi-scale fusion strategy in enhancing prediction accuracy by integrating information from multiple time scales. [ABSTRACT FROM AUTHOR]