Search

The rapid growth of malware variants has made malware classification an essential task for ensuring security. Different malware families require tailored techniques to effectively manage unique variants within each family. The existing methods often struggle with high dimensionality of malware images, which negatively impacts classification accuracy. This research proposes Ghost Strategy Northern Goshawk Optimization with Spatial Temporal Graph Convolutional Neural Network (GSNGO-STGCNN) technique for malware classification, which addresses dimensionality issues and significantly improves classification performance. Initially, data is acquired from the BIG15 and Malimg dataset, and pre-processing is carried out to convert binary data into grayscale images, facilitating the visualization of malware patterns. Feature extraction is performed using MobileNetV1, which involves depth-wise separable convolutions to efficiently capture image patterns. The GSNGO-STGCNN technique used for classification involves hyperparameter tuning to optimize the model's parameters, effectively detect malware patterns, and improve classification accuracy. The proposed method achieves a commendable accuracy of 99.12% on BIG15 dataset, and 99.25% on the Malimg dataset, thereby outperforming existing methods namely, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) techniques. [ABSTRACT FROM AUTHOR]

Purpose: The energy efficiency of buildings has been emphasized along with the continual development in the building and construction sector that consumes a significant amount of energy. To this end, the purpose of this research paper is to forecast energy consumption to improve energy resource planning and management. Design/methodology/approach: This study proposes the application of the convolutional neural network (CNN) for estimating the electricity consumption in the Grey Nuns building in Canada. The performance of the proposed model is compared against that of long short-term memory (LSTM) and multilayer perceptron (MLP) neural networks. The models are trained and tested using monthly electricity consumption records (i.e. from May 2009 to December 2021) available from Concordia's facility department. Statistical measures (e.g. determination coefficient [R2], root mean squared error [RMSE], mean absolute error [MAE] and mean absolute percentage error [MAPE]) are used to evaluate the outcomes of models. Findings: The results reveal that the CNN model outperforms the other model predictions for 6 and 12 months ahead. It enhances the performance metrics reported by the LSTM and MLP models concerning the R2, RMSE, MAE and MAPE by more than 4%, 6%, 42% and 46%, respectively. Therefore, the proposed model uses the available data to predict the electricity consumption for 6 and 12 months ahead. In June and December 2022, the overall electricity consumption is estimated to be 195,312 kWh and 254,737 kWh, respectively. Originality/value: This study discusses the development of an effective time-series model that can forecast future electricity consumption in a Canadian heritage building. Deep learning techniques are being used for the first time to anticipate the electricity consumption of the Grey Nuns building in Canada. Additionally, it evaluates the effectiveness of deep learning and machine learning methods for predicting electricity consumption using established performance indicators. Recognizing electricity consumption in buildings is beneficial for utility providers, facility managers and end users by improving energy and environmental efficiency. [ABSTRACT FROM AUTHOR]

Fault location in DC microgrids (DCMGs) is a critical challenge due to the system's inherent complexities and the demand for high reliability in modern power systems. This study proposes an explainable artificial intelligence (XAI)-based quantum deep neural network (QDNN) framework to address fault localization challenges in DCMGs. First, voltage signals from the DCMG are collected and analyzed using high-order synchrosqueezing transform to detect traveling waves (TWs) and extract critical fault parameters such as time of arrival, magnitude, and polarity of the first and second TWs. These features are fed into the proposed QDNN model that integrates advanced learning techniques for accurate fault localization. The cumulative distance from the fault point to the bus connecting the DCMG to the power network is considered the output vector. The model uses a combination of deep learning and quantum computing techniques to extract features and improve accuracy. To ensure transparency, an XAI technique called Shapley additive explanations (SHAP) is applied, enabling system operators to identify critical fault features. The SHAP-based explainability framework plays a critical role in translating the model's predictions into actionable insights, ensuring that the proposed solution is not only accurate but also practically implementable in real-world scenarios. The results demonstrate the QDNN framework's superior accuracy in fault localization even in noisy environments and with high-resistance faults, independent of voltage levels and DCMG configurations, making it a robust solution for modern power systems. [ABSTRACT FROM AUTHOR]

Electrocardiogram (ECG) records a series of heart depolarization and repolarization of the atria and ventricles that manifest in waves. They are systematically deployed as a standard non-invasive tool to monitor the cardiac activity and reliably detect eventual heart diseases or any abnormal heart activity. To relief the medical staff of the burden of diagnosing long ECG records, classification algorithms have been tested and explored to give a new way for heartbeat failure detection. This paper proposes a method based on a convolutional neural network (CNN) to extract time-invariant features and a bidirectional long short-term memory (BiLSTM) network-based sequence-to-sequence (seq2seq) architecture augmented with an attention mechanism (AM) to classify the heartbeats into five classes according to the ANSI/AAMI/ISO EC57, 1998-(R)2008 standard. We also use the adaptive synthetic sampling (ADASYN) which is a data augmentation technique to reduce the bias caused by imbalanced data. Finally, to avoid skewing the classification results, we use the inter-patient paradigm diagnosis. For verification, we used the MIT-BIH arrhythmia database, the experiment achieved an accuracy rate of 99.87%. The evaluation results demonstrate that the proposed method obtains excellent performances for heartbeat classification task. The introduction of an AM improves the efficiency of the encoder–decoder architecture. [ABSTRACT FROM AUTHOR]

Heart diseases are a major cause of death worldwide, highlighting the need for early detection. The electrocardiogram (ECG) records the heart's electrical activity using electrodes. Our research focuses on the ECG data to diagnose heart disorders, particularly arrhythmias. We utilized the MIT-BIH arrhythmia dataset for comparative analysis of various machine learning techniques, including random forest, K-Nearest Neighbor, and Decision Tree, along with deep learning algorithms like Long short-term memory and Convolutional Neural Networks. This required employing various preprocessing methods like filtering and normalization and feature selection techniques such as chi-square and sequential feature selectors to improve the performance of heart disease prediction. Therefore, hybrid machine and deep learning models are proposed, and the results reveal that hybrid models perform better than conventional models. [ABSTRACT FROM AUTHOR]

Rotor motor fault diagnosis in Unmanned Aerial Vehicles (UAVs) presents significant challenges under variable speeds. Recent advances in deep learning offer promising solutions. To address challenges in extracting spatial, temporal, and hierarchical features from raw vibration signals, a hybrid CNN-BiLSTM-MHSA model is developed. This model leverages Convolutional Neural Networks (CNNs) to identify spatial patterns, a Bidirectional Long Short-Term Memory (BiLSTM) network to capture long- and short-term temporal dependencies, and a Multi-Head Self-Attention (MHSA) mechanism to highlight essential diagnostic features. Experiments on raw rotor motor vibration data preprocessed with Butterworth band-stop filters were conducted under laboratory and real-world conditions. The proposed model achieves 99.33% accuracy in identifying faulty bearings, outperforming traditional models like CNN (93.33%) and LSTM (62.00%) and recent advances including CNN-LSTM (98.87%), the Attention Recurrent Autoencoder hybrid Model (ARAE) (66.00%), Lightweight Time-focused Model Network (LTFM-Net) (96.67%), and Wavelet Denoising CNN-LSTM (WDCNN-LSTM) (96.00%). The model's high accuracy and stability under varying conditions underscore its robustness, making it a reliable solution for rolling bearing fault diagnosis in rotor motors, particularly for dynamic UAV applications. [ABSTRACT FROM AUTHOR]

An immense volume of user-generated content exists online due to the exponential growth of internet usage among individuals. However, this abundance presents substantial challenges for recommendation systems and online customer services. The diverse data, encompassing consumer emails, reviews, and comments, contain a broad spectrum of information, making it challenging to decipher the underlying emotions and nuances. In social media analytics, sentiment analysis has emerged as a pivotal tool to unveil the emotional context embedded within textual data, offering deeper insights into user attitudes, opinions, and sentiments. This study introduces a novel strategy to strengthen the performance and precision of sentiment analysis-based book recommendation systems through ensemble learning on hybrid deep learning models. These book recommendation models leverage customer ratings and reviews from a vast Amazon books dataset as input. Initially, we used TextBlob to assess the polarity of customer reviews, categorizing them into neutral, negative, and positive sentiments. Subsequently, the input data underwent preprocessing, tokenization, and word embedding using bidirectional encoder representations from transformers (BERT). To effectively analyze and filter processed review comments and ratings, the proposed ensemble model integrates a diverse array of hybrid deep learning architectures, including long short-term memory (LSTM), bidirectional LSTM (BiLSTM), gated recurrent unit (GRU), and convolutional neural network (CNN). Extensive experimentation validated the superiority of the proposed ensemble model, achieving an impressive accuracy and F1-score of 98.21%. The significance of the approach lies in its ability to provide more accurate and contextually relevant book recommendations by considering the nuanced emotions expressed in customer reviews. This contributes to enhancing user satisfaction and engagement with recommendation systems, ultimately improving the overall quality of personalized book suggestions. Evaluation metrics further validate the efficacy of the proposed model, underscoring its practical utility in real-world applications of sentiment-based book recommendation systems. [ABSTRACT FROM AUTHOR]

Accurately extracting network security situation elements is an important basis for improving the situational awareness of industrial Internet security. This paper proposes an industrial internet security situation element extraction algorithm based on a hybrid neural network. Firstly, the powerful local feature extraction ability of convolutional neural networks (CNNs) was used to extract the features of key situation elements, and the obtained features were flattened and then input into long short-term memory networks (LSTMs) to solve the problem of the poor time feature extraction ability of CNNs. Then, the output features of the fully connected layer were input to the backpropagation (BP) network for classification, and LSTM was used to correct the prediction residual of the BP network to optimize the parameters of each module in the model and improve the classification effect and generalization ability. Comparative experimental results show that the accuracy of the model on the KDD Cup99 dataset and SCADA2014 dataset can reach 98.03% and 98.96%, respectively. Compared with other models, the model has higher classification accuracy and can provide more effective indicator data for security situation assessment. [ABSTRACT FROM AUTHOR]

Lithium-ion (li-ion) batteries have a high energy density and a long cycle life. Lithium-ion batteries have a finite lifespan, and their energy storage capacity diminishes with use. In order to properly plan battery maintenance, the state of health (SoH) of lithium-ion batteries is crucial. This study aims to combine two deep learning techniques (hybrid deep learning), namely convolutional neural network (CNN) and bidirectional long short-term memory (BiLSTM), for SoH estimation in li-ion batteries. This study contrasts hybrid deep learning methods to single deep learning models so that the most suitable model for accurately measuring the SoH in lithium-ion batteries can be determined. In comparison to other methodologies, CNN-BiLSTM yields the best results. The CNN-BiLSTM algorithm yields RMSE, mean square error (MSE), mean absolute error (MAE), and mean absolute percentage error (MAPE) in the following order: 0.00916, 0.000084, 0.0048, and 0.00603. This indicates that CNN-BiLSTM, as a hybrid deep learning model, is able to calculate the approximate capacity of the lithium-ion battery more accurately than other methods. [ABSTRACT FROM AUTHOR]

In response to the typical fault issues encountered during the operation of marine diesel engines, a fault diagnosis method based on a convolutional neural network (CNN), a temporal convolutional network (TCN), and the attention mechanism (ATTENTION) is proposed, referred to as CNN-TCN–ATTENTION. This method successfully addresses the issue of insufficient feature extraction in previous fault diagnosis algorithms. The CNN is employed to capture the local features of diesel engine faults; the TCN is employed to explore the correlations and temporal dependencies in sequential data, further obtaining global features; and the attention mechanism is introduced to assign different weights to the features, ultimately achieving intelligent fault diagnosis for marine diesel engines. The results of the experiments demonstrate that the CNN-TCN–ATTENTION-based model achieves an accuracy of 100%, showing superior performance compared to the individual CNN, TCN, and CNN-TCN methods. Compared with commonly used algorithms such as Transformer, long short-term memory (LSTM), Gated Recurrent Unit (GRU), and Deep Belief Network (DBN), the proposed method demonstrates significantly higher accuracy. Furthermore, the model maintains an accuracy of over 90% in noise environments such as random noise, Gaussian noise, and salt-and-pepper noise, demonstrating strong diagnostic performance, generalization capability, and noise robustness. This provides a theoretical basis for its practical application in the fault diagnosis of marine diesel engines. [ABSTRACT FROM AUTHOR]

Emotions are important for human well-being and social connections. This work focuses on the issue of effectively understanding emotions in human speech, specifically in the context of Industry 5.0. Traditional approaches and machine learning (ML) techniques for identifying emotions in speech are limited, such as the requirement for complicated feature extraction. Traditional methods yield recognition accuracies of no more than 90% because to the restricted extraction of temporal/sequence information. This paper suggests a ground-breaking fusion-based deep learning (DL) method to overcome these limitations. Specifically, one-dimensional (1D) and twodimensional (2D) convolution neural network (CNN) can automatically extract significant characteristics and handle enormous datasets in real time. Furthermore, a fusion-based DL network, speech emotion recognition deep learning fusion network (SER_DLFNet), has been proposed, which combines CNN with long short-term memory (LSTM) to collect sequence information and increase recognition accuracy. The proposed model shows impressive results, with a test accuracy of 95.52% on the ryerson audiovisual database of emotional speech and song (RAVDESS) dataset. This research contributes to the advancement of more precise and efficient emotion identification algorithms for voice analysis, especially within the framework of Industry 5.0. [ABSTRACT FROM AUTHOR]

This research introduces a novel convolutional neural network-bidirectional long short-term memory (CNN-BiLSTM) hybrid network for the automatic classification of heart arrhythmias using 12-lead electrocardiograms (ECGs). By merging the spatial feature extraction capabilities of CNNs with the temporal precision of BiLSTM networks, our approach sets a new standard in cardiac diagnostics. The proposed model was tested against the comprehensive CPSC2018 dataset, demonstrating superior performance with an accuracy of 90.67%, precision of 93.27%, recall of 96.35%, and an Fscore of 94.78%, surpassing existing state-of-the-art methods. These results underscore the effectiveness of integrating spatial and temporal data analysis, offering a robust and reliable tool for medical practitioners. This study represents a significant advancement in automated ECG analysis, paving the way for improved diagnosis and treatment of heart diseases, and contributing to enhanced patient outcomes in cardiac care. [ABSTRACT FROM AUTHOR]

This study attempts to address overfitting, a frequent problem with multimodal emotion identification models. This study proposes model optimization using various hyperparameter approaches, such as dropout layer, l2 kernel regularization, batch normalization, and learning rate schedule, and discovers which approach yields the most impact for optimizing the model from overfitting. For the emotion dataset, this research utilizes the interactive emotional dyadic motion capture (IEMOCAP) dataset and uses the motion capture and speech audio data modality. The models used in this experiment are convolutional neural network (CNN) for the motion capture data and CNN-bidirectional long short-term memory (CNNBiLSTM) for the audio data. This study also applied a smaller model batch size in the experiment to accommodate the limited computing resources. The result of the experiment is that the optimization using hyperparameter tuning raises the validation accuracy to 73.67% and the f1-score to 73% on audio and motion capture data, respectively, from the base model of this research and can competitively compete with another research model result. It is hoped that the optimization experiment results in this study can be useful for future emotion recognition research, especially for those who have encountered overfitting problems. [ABSTRACT FROM AUTHOR]

Predicting the Remaining Useful Life (RUL) is vital for ensuring the reliability and safety of equipment and components. This study introduces a novel method for predicting RUL that utilizes the Convolutional Block Attention Module (CBAM) to address the problem that Convolutional Neural Networks (CNNs) do not effectively leverage data channel features and spatial features in residual life prediction. Firstly, Fast Fourier Transform (FFT) is applied to convert the data into the frequency domain. The resulting frequency domain data is then used as input to the convolutional neural network for feature extraction; Then, the weights of channel features and spatial features are assigned to the extracted features by CBAM, and the weighted features are then input into the Long Short-Term Memory (LSTM) network to learn temporal features. Finally, the effectiveness of the proposed model is verified using the PHM2012 bearing dataset. Compared to several existing RUL prediction methods, the mean squared error, mean absolute error, and root mean squared error of the proposed method in this paper are reduced by 53%, 16.87%, and 31.68%, respectively, which verifies the superiority of the method. Meanwhile, the experimental results demonstrate that the proposed method achieves good RUL prediction accuracy across various failure modes. [ABSTRACT FROM AUTHOR]

Remote photoplethysmography (rPPG) has attracted growing attention due to its non-contact nature. However, existing non-contact heart rate detection methods are often affected by noise from motion artifacts and changes in lighting, which can lead to a decrease in detection accuracy. To solve this problem, this paper initially employs manual extraction to precisely define the facial Region of Interest (ROI), expanding the facial area while avoiding rigid regions such as the eyes and mouth to minimize the impact of motion artifacts. Additionally, during the training phase, illumination normalization is employed on video frames with uneven lighting to mitigate noise caused by lighting fluctuations. Finally, this paper introduces a 3D convolutional neural network (CNN) method incorporating an attention mechanism for heart rate detection from facial videos. We optimize the traditional 3D-CNN to capture global features in spatiotemporal data more effectively. The SimAM attention mechanism is introduced to enable the model to precisely focus on and enhance facial ROI feature representations. Following the extraction of rPPG signals, a heart rate estimation network using a bidirectional long short-term memory (BiLSTM) model is employed to derive the heart rate from the signals. The method introduced here is experimentally validated on two publicly available datasets, UBFC-rPPG and PURE. The mean absolute errors were 0.24 bpm and 0.65 bpm, the root mean square errors were 0.63 bpm and 1.30 bpm, and the Pearson correlation coefficients reached 0.99, confirming the method's reliability. Comparisons of predicted signals with ground truth signals further validated its accuracy. [ABSTRACT FROM AUTHOR]

As the core component of an airplane, the health status of the aviation engine is crucial for the safe operation of the aircraft. Therefore, predicting the remaining service life of the engine is of great significance for ensuring its safety and reliability. In this paper, a multichannel hybrid network is proposed; this network is a combination of the one-dimensional convolutional neural network (1D-CNN), the bidirectional long short-term memory network (BiLSTM), and the self-attention mechanism. For each sensor of the engine, an SA-CNN-BiLSTM network is established. The one-dimensional convolutional neural network and the bidirectional long short-term memory network are used to extract the spatial features and temporal features of the input data, respectively. Moreover, multichannel modeling is utilized to achieve the parallel processing of different sensors. Subsequently, the results are stitched together to establish a mapping relationship with the engine's remaining useful life (RUL). Experimental validation was conducted on the aero-engine C-MAPSS dataset. The prediction results were compared with those of the other seven models to verify the effectiveness of this method in predicting the remaining service life. The results indicate that the proposed method significantly reduces the prediction error compared to other models. Specifically, for the two datasets, their mean absolute errors were only 11.47 and 11.76, the root-mean-square error values were only 12.26 and 12.78, and the scoring function values were only 195 and 227. [ABSTRACT FROM AUTHOR]

Mobile Ad Hoc Networks (MANETs) are increasingly replacing conventional communication systems due to their decentralized and dynamic nature. However, their wireless architecture makes them highly vulnerable to flooding attacks, which can disrupt communication, deplete energy resources, and degrade network performance. This study presents a novel hybrid deep learning approach integrating Convolutional Neural Networks (CNN) with Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) architectures to effectively detect and mitigate flooding attacks in MANETs. To optimize the model's efficiency, a unique DECEHGS algorithm combining Differential Evolution and Evolutionary Population Dynamics techniques is employed, enhancing both convergence and performance. The proposed model demonstrates significant improvements over existing methods, achieving an accuracy of 95%, a 12% increase in packet delivery ratio, and a 20% reduction in routing overhead compared to traditional techniques. These advancements underline the model's superiority in detecting malicious nodes, conserving energy, and ensuring reliable network performance. The comprehensive evaluation using MATLAB R2023a validates the proposed approach as an effective and energy-efficient solution for enhancing MANET security. [ABSTRACT FROM AUTHOR]

Accurately predicting rainfall is still a difficult but crucial task in meteorological forecasting, with significant implications for agriculture, disaster planning, and water resource management. In the past, statistical methods were used to forecast rainfall, however these methods were less accurate due to data dynamics and other problems. To address the data issue in this study, Discrete Wavelet Transform (DWT) was employed, it improves rainfall data preprocessing by decomposing data, eliminating noise, risk of overfitting and concentrating on significant patterns. Overlapping Flexible Sliding Window (OFSW) technique is essential since it dynamically modifies window sizes according to data properties unlike the overlapping sliding windows. Leveraging the advancements in Deep Learning (DL), this paper presents rainfall prediction by employing DL algorithms Convolutional Neural Networks (CNNs), Long Short-Term Memory Networks (LSTMs), and Multilayer Perceptron (MLPs). Furthermore, the standalone models were fused to form a weighted average ensemble. The monthly data from Nigeria and the Kaduna region were gathered and used in forecasting. The Bi-LSTM model has shown better performance compared to other models in predicting rainfall univariate time series data. In this study, these models are integrated into an ensemble structure for prediction purposes. The obtained ensemble learning model harmonizes the advantages of CNNs, Bi-LSTMs, and MLPs. The results of the weighted average ensemble demonstrated the benefits of the ensemble model in rainfall prediction in Kaduna by achieving the least MSE of 0.0018,0.04242, 0.0303 of MSE, RMSE and MAE in the training phase respectively, while in the testing phase, it achieves, 0.0041, 0.0640 and 0.0447 of MSE, RMSE and MAE in the testing phase respectively. MSE, RMSE and MAE of 0.0017, 0.0412, and 0.0301 for Nigeria in the training phase respectively, while in the testing phase, 0.0042, 0.0648 and 0.0457 of MSE, RMSE and MAE were achieved. [ABSTRACT FROM AUTHOR]

Detection of anomalies in video surveillance plays a key role in ensuring the safety and security of public spaces. The number of surveillance cameras is growing, making it harder to monitor them manually. So, automated systems are needed. This change increases the demand for automated systems that detect abnormal events or anomalies, such as road accidents, fighting, snatching, car fires, and explosions in real-time. These systems improve detection accuracy, minimize human error, and make security operations more efficient. In this study, we proposed the Composite Recurrent Bi-Attention (CRBA) model for detecting anomalies in surveillance videos. The CRBA model combines DenseNet201 for robust spatial feature extraction with BiLSTM networks that capture temporal dependencies across video frames. A multi-attention mechanism was also incorporated to direct the model's focus to critical spatiotemporal regions. This improves the system's ability to distinguish between normal and abnormal behaviors. By integrating these methodologies, the CRBA model improves the detection and classification of anomalies in surveillance videos, effectively addressing both spatial and temporal challenges. Experimental assessments demonstrate that the CRBA model achieves high accuracy on both the University of Central Florida (UCF) and the newly developed Road Anomaly Dataset (RAD). This model enhances detection accuracy while also improving resource efficiency and minimizing response times in critical situations. These advantages make it an invaluable tool for public safety and security operations, where rapid and accurate responses are needed for maintaining safety. [ABSTRACT FROM AUTHOR]

With the deepening research on music works, music transcription algorithms have been increasingly studied. This study examined the recognition of piano-playing notes using a music-transcription algorithm. First, the characteristics of MelSpec, LogSpec, and the constant Q-transform (CQT) are briefly introduced. Then, a convolutional recurrent neural network (CRNN) transcription algorithm, which includes four convolutional blocks and one bidirectional long short-term memory (BiLSTM) structure, was designed. The recognition performance of this method was analyzed using the MAPS dataset. LogSpec was found to have the best recognition performance for piano-playing notes when used as an input feature. In the CRNN structure, the recognition performance for piano-playing notes was the best when four convolutional blocks were used. Compared with the convolutional neural network (CNN), BiLSTM, and CNN-hidden Markov model algorithms, the F1-values of the CRNN algorithm were 84.9%, 92.24%, and 79.27% for frames, notes, and offsets, respectively, achieving the best recognition results. The results verify that the CRNN transcription algorithm is effective for the recognition of piano-playing notes and can be applied in practice. [ABSTRACT FROM AUTHOR]

With the development and application of machine learning, significant advances have been made in landslide susceptibility mapping. However, due to challenges in actual field landslide investigations, current landslide susceptibility mapping is usually characterized by insufficient landslide samples (positive samples) and low reliability of non-landslide samples (negative samples). Considering Lianghe County in Yunnan Province, China, as an example, this paper aims to research the effectiveness of three oversampling models in generating positive samples for landslides: Conditional Tabular Generative Adversarial Networks (CTGAN), Generative Adversarial Networks (GAN), and the traditional Synthetic Minority Oversampling Technique (SMOTE) algorithms. Additionally, three machine learning methods, including 1D Convolutional Neural Network-Long Short-Term Memory Neural Network (CNN-LSTM), Random Forest (RF), and Gradient Boosting Decision Tree (GBDT) classifiers, are used for landslide susceptibility assessment. We also devise a non-landslide data (negative samples) screening method utilizing a self-trained support vector machine within a semi-supervised framework. The results show that by training on the dataset after negative sample screening, the AUC values for the 1D-CNN-LSTM, RF, and GBDT models have shown significant improvement, increasing from (0.778, 0.869, 0.849) to (0.837, 0.936, 0.877). Compared with the original training set, the prediction accuracy of the three machine learning models is improved after training on the augmented data by CTGAN, GAN, and SMOTE models. The RF model, augmented with 200 positive samples generated by CTGAN, achieves the highest prediction accuracy in the study (AUC = 0.962). The 1D CNN-LSTM model achieves its highest prediction accuracy (AUC = 0.953) when augmented with 200 positive samples from GAN. Similarly, the GBDT model reaches its highest prediction accuracy (AUC = 0.928) when augmented with 200 positive samples created by SMOTE. In addition, the spatial distribution of data indicates that the data generated by the generative adversarial model exhibits higher diversity, which can be used for landslide susceptibility assessment. [ABSTRACT FROM AUTHOR]

Background: COVID-19 genetic sequence research is crucial despite immunizations and pandemic control. COVID-19-causing SARS-CoV-2 must be understood genomically for several reasons. New viral strains may resist vaccines. Categorizing genetic sequences helps researchers track changes and assess immunization efficacy. Classifying COVID-19 genome sequences with other viruses helps to understand its evolution and interactions with other illnesses. Methods: The proposed study introduces a deep learning-based COVID-19 genomic sequence categorization approach. Attention-based hybrid deep learning (DL) models categorize 1423 COVID-19 and 11,388 other viral genome sequences. An unknown dataset is also used to assess the models. The five models' accuracy, f1-score, area under the curve (AUC), precision, Matthews correlation coefficient (MCC), and recall are evaluated. Results: The results indicate that the Convolutional neural network (CNN) with Bidirectional long short-term memory (BLSTM) with attention layer (CNN-BLSTM-Att) achieved an accuracy of 99.99%, which outperformed the other models. For external validation, the model shows an accuracy of 99.88%. It reveals that DL-based approaches with an attention layer can accurately classify COVID-19 genomic sequences with a high degree of accuracy. This method might assist in identifying and classifying COVID-19 virus strains in clinical situations. Immunizations have lowered COVID-19 danger, but categorizing its genetic sequences is crucial to global health activities to plan for recurrence or future viral threats. [ABSTRACT FROM AUTHOR]

In farmland environments where GNSS signals are obstructed, such as forested areas or in adverse weather conditions, traditional GNSS/INS integrated navigation systems suffer from positioning errors and instability. To address this, a model-assisted integrated navigation system is proposed, combining Convolutional Neural Networks (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) networks. The CNN-BiLSTM model is trained under normal GNSS conditions and used to predict positioning when GNSS signals are interrupted, effectively replacing GNSS to ensure stable and accurate navigation. Experimental validation is conducted using field data from tractor simulations. The results show that, during a 100-s GNSS denial, the CNN-BiLSTM model reduces the average position error by 79.3% compared to pure inertial navigation and by 5.4% compared to traditional LSTM. In a 30-s GNSS denial, the average position error is reduced by 41% compared to inertial navigation and 6.2% compared to LSTM. The model maintains positioning accuracy within 3% of the GNSS/INS output under normal conditions, demonstrating its feasibility and effectiveness. This approach offers a promising solution for autonomous tractor navigation in GNSS-denied agricultural environments, contributing to precision agriculture. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. 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.)