Sliding Window Technique Research Articles

A Novel CNN With Sliding Window Technique for Enhanced Classification of MI-EEG Sensor Data

A Novel CNN With Sliding Window Technique for Enhanced Classification of MI-EEG Sensor Data

Haralick Texture Analysis for Differentiating Suspicious Prostate Lesions from Normal Tissue in Low-Field MRI.

This study evaluates the feasibility of using Haralick texture analysis on low-field, T2-weighted MRI images for detecting prostate cancer, extending current research from high-field MRI to the more accessible and cost-effective low-field MRI. A total of twenty-one patients with biopsy-proven prostate cancer (Gleason score 4+3 or higher) were included. Before transperineal biopsy guided by low-field (58-74mT) MRI, a radiologist annotated suspicious regions of interest (ROIs) on high-field (3T) MRI. Rigid image registration was performed to align corresponding regions on both high- and low-field images, ensuring an accurate propagation of annotations to the co-registered low-field images for texture feature calculations. For each cancerous ROI, a matching ROI of identical size was drawn in a non-suspicious region presumed to be normal tissue. Four Haralick texture features (Energy, Correlation, Contrast, and Homogeneity) were extracted and compared between cancerous and non-suspicious ROIs. Two extraction methods were used: the direct computation of texture measures within the ROIs and a sliding window technique generating texture maps across the prostate from which average values were derived. The results demonstrated statistically significant differences in texture features between cancerous and non-suspicious regions. Specifically, Energy and Homogeneity were elevated (p-values: <0.00001-0.004), while Contrast and Correlation were reduced (p-values: <0.00001-0.03) in cancerous ROIs. These findings suggest that Haralick texture features are both feasible and informative for differentiating abnormalities, offering promise in assisting prostate cancer detection on low-field MRI.

An intelligent retrievable object‐tracking system with real‐time edge inference capability

AbstractAn intelligent retrievable object‐tracking system assists users in quickly and accurately locating lost objects. However, challenges such as real‐time processing on edge devices, low image resolution, and small‐object detection significantly impact the accuracy and efficiency of video‐stream‐based systems, especially in indoor home environments. To overcome these limitations, a novel real‐time intelligent retrievable object‐tracking system is designed. The system incorporates a retrievable object‐tracking algorithm that combines DeepSORT and sliding window techniques to enhance tracking capabilities. Additionally, the YOLOv7‐small‐scale model is proposed for small‐object detection, integrating a specialized detection layer and the convolutional batch normalization LeakyReLU spatial‐depth convolution module to enhance feature capture for small objects. TensorRT and INT8 quantization are used for inference acceleration on edge devices, doubling the frames per second. Experiments on a Jetson Nano (4 GB) using YOLOv7‐small‐scale show an 8.9% improvement in recognition accuracy over YOLOv7‐tiny in video stream processing. This advancement significantly boosts the system's performance in efficiently and accurately locating lost objects in indoor home settings.

Machine Learning Techniques for Egg Production Prediction

Predicting egg production in poultry farming is a complex task due to the multitude of influencing factors such as temperature, nutrition, and environmental conditions. This study aims to evaluate the performance of various machine learning models in forecasting egg production using multivariate time series data. The dataset comprises records of the Hy-Line breed, divided into four batches, with attributes including age, maximum and minimum temperature, feed and water consumption, and daily production percentage. The study employs a sliding window technique to capture temporal patterns and evaluates models including Ridge Regression, Random Forest, XGBoost, and MLP. The models were trained on three batches and tested on the fourth, with performance measured using Mean Squared Error (MSE) and Mean Absolute Percentage Error (MAPE). The results indicate that Ridge Regression, with a window size of 7 days, provided the most accurate predictions, achieving an MSE of 19.74 and a MAPE of 3.81%. This study demonstrates the effectiveness of machine learning techniques and the sliding window approach in improving the accuracy of egg production forecasts, offering valuable insights for poultry farm management and optimization.

A Hybrid Data Preprocessing-Based Hierarchical Attention BiLSTM Network for Remaining Useful Life Prediction of Spacecraft Lithium-Ion Batteries.

As a crucial energy storage for the spacecraft power system, lithium-ion batteries degradation mechanisms are complex and involved with external environmental perturbations. Hence, effective remaining useful life (RUL) prediction and model reliability assessment confronts considerable obstacles. This article develops a new RUL prediction method for spacecraft lithium-ion batteries, where a hybrid data preprocessing-based deep learning model is proposed. First, to improve the correlation between battery capacity and features, the empirically selected high-dimensional features are linearized by using the Box-Cox transformation and then denoised via the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) method. Second, the principal component analysis (PCA) algorithm is employed to perform feature dimensionality reduction, and the output of PCA is further processed by the sliding window technique. Third, a multiscale hierarchical attention bi-directional long short-term memory (MHA-BiLSTM) model is constructed to estimate the capacity in future cycles. Specifically, the MHA-BiLSTM model can predict the RUL of lithium-ion batteries by considering the correlation and significance of each cycle's information during the degradation process on different scales. Finally, the proposed method is validated based on multiple types of experiments under two lithium-ion battery datasets, demonstrating its superior performance in terms of feature extraction and multidimensional time series prediction.

Dynamic Process Fault Detection and Diagnosis Method Based on Factor Analysis: Application on the Three‐Tank System Process

ABSTRACTTo address the issue of underreporting faults in the detection of tiny faults by dynamic factor analysis (DFA), a novel fault detection and diagnosis method based on DFA‐sliding window combined with mean square error (DFA‐SWMSE) is proposed. Firstly, the data matrix is augmented by introducing time lag shifts. Secondly, factor analysis (FA) is applied to the augmented data matrix, achieving dimensionality reduction and feature extraction while retaining most of the original data's information. Then, the sliding window technique is applied to calculate the mean square error of the dimensionally reduced data, allowing for the monitoring of the system's current state and the detection of tiny faults. Finally, effective fault diagnosis is achieved through the analysis of fault factors and variable contributions. The proposed method is validated using a complex dynamic numerical example and a three‐tank system process named Sim3Tanks. This system has gained widespread application in the field of process fault detection due to its ability to simulate and generate various types of faults. The proposed method is compared with principal component analysis (PCA), dynamic principal component analysis (DPCA), PCA similarity factor (SPCA), FA, and DFA. The experimental results thoroughly validate the effectiveness of the proposed method in detecting and diagnosing tiny faults in dynamic processes.

High-Resolution Remotely Sensed Evidence Shows Solar Thermal Power Plant Increases Grassland Growth on the Tibetan Plateau

Solar energy plays a crucial role in mitigating greenhouse gas emissions in the context of global climate change. However, its deployment for green electricity generation can significantly influence regional climate and vegetation dynamics. While prior studies have examined the impacts of solar power plants on vegetation, the accuracy of these assessments has often been constrained by the availability of publicly accessible multispectral, high-resolution remotely sensed imagery. Given the abundant solar energy resources and the ecological significance of the Tibetan Plateau, a thorough evaluation of the vegetation effects associated with solar power installations is warranted. In this study, we utilize sub-meter resolution imagery from the GF-2 satellite to reconstruct the fractional vegetation cover (FVC) at the Gonghe solar thermal power plant through image classification, in situ sampling, and sliding window techniques. We then quantify the plant’s impact on FVC by comparing data from the pre-installation and post-installation periods. Our findings indicate that the Gonghe solar thermal power plant is associated with a 0.02 increase in FVC compared to a surrounding control region (p &lt; 0.05), representing a 12.5% increase relative to the pre-installation period. Notably, the enhancement in FVC is more pronounced in the outer ring areas than near the central tower. The observed enhancement in vegetation growth at the Gonghe plant suggests potential ecological and carbon storage benefits resulting from solar power plant establishment on the Tibetan Plateau. These findings underscore the necessity of evaluating the climate and ecological impacts of renewable energy facilities during the planning and design phases to ensure a harmonious balance between clean energy development and local ecological integrity.

Advanced Trans-BiGRU-QA Fusion Model for Atmospheric Mercury Prediction

With the deepening of the Industrial Revolution and the rapid development of the chemical industry, the large-scale emissions of corrosive dust and gases from numerous factories have become a significant source of air pollution. Mercury in the atmosphere, identified by the United Nations Environment Programme (UNEP) as one of the globally concerning air pollutants, has been proven to pose a threat to the human environment with potential carcinogenic risks. Therefore, accurately predicting atmospheric mercury concentration is of critical importance. This study proposes a novel advanced model—the Trans-BiGRU-QA hybrid—designed to predict the atmospheric mercury concentration accurately. Methodology includes feature engineering techniques to extract relevant features and applies a sliding window technique for time series data preprocessing. Furthermore, the proposed Trans-BiGRU-QA model is compared to other deep learning models, such as GRU, LSTM, RNN, Transformer, BiGRU, and Trans-BiGRU. This study utilizes air quality data from Vietnam to train and test the models, evaluating their performance in predicting atmospheric mercury concentration. The results show that the Trans-BiGRU-QA model performed exceptionally well in terms of Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R-squared (R2), demonstrating high accuracy and robustness. Compared to other deep learning models, the Trans-BiGRU-QA model exhibited significant advantages, indicating its broad potential for application in environmental pollution prediction.

Simulated study relating dose-volume histogram metrics to three-dimensional gamma analysis results

This study aims to investigate the relationship between the three-dimensional gamma index (3DGI) results and its clinical significance, proposing a correlation between changes in dose values in the dose-volume histogram (DVH) of the evaluated structures and 3DGI percentages of approval. In this study, we created 30 plans by including 1 mm displacement errors in the lateral, vertical, and longitudinal axes of each table, and compared them to a simulated, error-free treatment plan for prostate cancer. The plans were made in a commercial treatment planning system, using 6MV Varian 120-leaf multileaf collimators (MLC) linear accelerators and intensity modulated radiation therapy sliding window technique. We used a calculation algorithm-based MATLAB programming to evaluate the 3DGI analysis of fluence maps. The acceptance criteria were 3%/2 mm, 10% dose threshold, and 95% gamma passing rate. We compared 3DGI results with differences in structures DVH. DVH metrics versus 3DGI analysis showed a correlation between the percentage of point&amp;rsquo;s approval and planning target volume (PTV) coverage, presenting a degree of agreement of 0.85%, 0.96%, and 0.94% in the longitudinal, lateral, and vertical axes, respectively. In summary, it was possible to establish a linear relationship between the percentage of points approved in the 3DGI analysis and the PTV dose. A similar behavior was also observed in bladder and rectum DVH, but for these structures, the relationship was not the same in the three displaced axes.

Three-Dimensional CKANs: UUV Noncooperative Target State Estimation Approach Based on 3D Convolutional Kolmogorov–Arnold Networks

Accurate and stable estimation of the position and trajectory of noncooperative targets is crucial for the safe navigation and operation of sonar-equipped underwater unmanned vehicles (UUVs). However, the uncertainty associated with sonar observations and the unpredictability of noncooperative target movements often undermine the stability of traditional Bayesian methods. This paper presents an innovative approach for noncooperative target state estimation utilizing 3D Convolutional Kolmogorov–Arnold Networks (3DCKANs). By establishing a non-Markovian model that characterizes state estimation of UUV noncooperative targets under uncertain observations, we leverage historical data to construct 3D Convolutional Kolmogorov–Arnold Networks. This network learns the patterns of sonar observations and target state transitions from a substantial offline dataset, allowing it to approximate the posterior probability distribution derived from past observations effectively. Additionally, a sliding window technique is integrated into the convolutional neural network to enhance the estimator’s fault tolerance with respect to observation data in both temporal and spatial dimensions, particularly when posterior probabilities are unknown. The incorporation of the Kolmogorov–Arnold representation within the convolutional layers enhances the network’s capacity for nonlinear expression and adaptability in processing spatial information. Finally, we present statistical experiments and simulation cases to validate the accuracy and stability of the proposed method.

Enhancing Video Anomaly Detection with Improved UNET and Cascade Sliding Window Technique

Computer vision video anomaly detection still needs to be improved, especially when identifying images with unusual motions or objects. Current approaches mainly concentrate on reconstruction and prediction methods, and unsupervised video anomaly detection faces difficulties because there are not enough tagged abnormalities, which reduces accuracy. This paper presents a novel framework called the Improved UNET (I-UNET), designed to counteract overfitting by addressing the need for complex models that can extract subtle information from video anomalies. Video frame noise can be eliminated by preprocessing the frames with a Weiner filter. Moreover, the system uses Convolution Long Short-Term Memory (ConvLSTM) layers to smoothly integrate temporal and spatial data into its encoder and decoder portions, improving the accuracy of anomaly identification. The Cascade Sliding Window Technique (CSWT) is used post-processing to identify anomalous frames and generate anomaly scores. Compared to baseline approaches, experimental results on the UCF, UCSDped1, and UCSDped2 datasets demonstrate notable performance gains, with 99% accuracy, 90.8% Area Under Curve (AUC), and 10.9% Equal Error Rate (EER). This study provides a robust and accurate framework for video anomaly detection with the highest accuracy rate.

Signature-based IaaS Performance Change Detection

We propose a novel change detection framework to identify changes in the long-term performance behavior of an IaaS service. An IaaS service’s long-term performance behavior is represented by an IaaS performance signature. The proposed framework leverages time series similarity measures and a sliding window technique to detect changes in IaaS performance signatures. We introduce a new IaaS performance noise model that enables the proposed framework to distinguish between performance noise and actual changes in performance. The proposed framework utilizes a novel Signal-to-Noise Ratio (SNR) based approach to detect changes when prior knowledge about performance noise is available. A set of experiments is conducted using real-world datasets to demonstrate the effectiveness of the proposed change detection framework.

Fault diagnosis of floating offshore wind turbine based on bidirectional long short-term memory networks with sliding window

Owing to its ability to harvest more power in deeper waters than other types of offshore wind turbines, the floating offshore wind turbine (FOWT) has attracted significant interest from both academics and industry. However, deterioration in system performance and unscheduled shutdowns will significantly increase operation and maintenance costs. To avoid system damage and ensure operation safety, there is a great demand for developing FOWT fault diagnosis to detect and identify faults as early as feasible. Due to the enormous complexity of FOWT including dynamics and nonlinearity, effective FOWT fault diagnosis poses a significant challenge. This paper develops a novel FOWT fault diagnosis method using bidirectional long short-term memory (BiLSTM) with sliding window. Firstly, the dynamics are embedded by stacking time-dependent measurements using the sliding window technique. Then, the augmented data is fed into a BiLSTM network to exploit the nonlinearity of FOWT. Consequently, a softmax classifier is used for fault diagnosis. A high-fidelity 10 MW spar FOWT benchmark based on the NREL Fatigue, Aerodynamics, Structures, and Turbulence (FAST) model is used to validate the capability and effectiveness of the proposed method. Experimental results show that the proposed method outperforms other related methods in diagnosing critical faults in FOWTs under various operating conditions.

LSTM-based framework for predicting point defect percentage in semiconductor materials using simulated XRD patterns

In this paper, we present a machine learning-based approach that leverages Long Short-Term Memory (LSTM) networks combined with a sliding window technique for feature extraction, aimed at accurately predicting point defect percentages in semiconductor materials based on simulated X-ray Diffraction (XRD) data. The model was initially trained on silicon-simulated XRD data with defect percentages ranging from 1 to 5%, enabling it to predict defect percentages from 0 to 10% in silicon and other semiconductor materials, including AlAs, CdS, GaAs, Ge, and ZnS. Through extensive experimentation, we explored different sequence lengths and LSTM units, identifying the optimal configuration as a sequence length of 3501 and 4500 units, which yielded the best results. The model’s mean absolute error at 4500 units was 0.021, the lowest among the LSTM configurations tested. The sliding window technique plays a crucial role in capturing temporal dependencies within the XRD data, allowing the model to generalize to other semiconductor materials. Additionally, we observed that increasing defect percentages consistently led to a rise in background intensity. We further examined the relationship between crystal structure and defect precentage predictions, uncovering consistent trends for materials with Diamond Cubic and Zinc Blende structures. This LSTM-based method offers a novel approach to predicting defect percentages using simulated XRD patterns of materials.

Dynamic Multi-Factor Correlation Analysis for Prediction of Provincial Carbon Emissions in China’s Bohai Rim Region

This study presents a dynamic multi-factor correlation analysis method designed to predict provincial carbon dioxide emissions (CDE) within China’s Bohai Rim region, including Tianjin, Hebei, Shandong, and Liaoning. By employing the sliding window technique, dynamic correlation curves are computed between various influencing factors and CDE at different time intervals, thereby facilitating the identification of key feature attributes. A novel metric, the Consistency Index of Influencing Factors (CIIF), is introduced to evaluate the consistency of these factors across regions. Furthermore, the Accurate Predictive Capability Indicator (APCI) is defined to measure the impact of different feature categories on the prediction accuracy. The findings reveal that models relying on a single influencing factor exhibit limited accuracy, whereas combining multiple factors with diverse correlation features significantly improves the prediction accuracy. This study introduces a refined analytical framework and a comprehensive indicator system for CDE prediction. It enhances the understanding of the complex factors that influence CDE and provides a scientific rationale for implementing effective emission reduction strategies.

An Efficient Method of DRC Violation Prediction with a Serial Deep Learning Model

In VLSI design, the utilization of Design Rule Check (DRC) tools in the early stage is crucial for predicting and resolving violations, thereby expediting the physical design process. In our study, we present an efficient model that predicts DRC violations prior to the routing stage. Additionally, our model incorporates a sliding-window technique to enhance the feature extraction process. We extract structural features using Graph Convolutional Networks and utilize feature reuse techniques to fully recover the lost information in neural layers, which serves as input to the Convolutional Neural Network model, resulting in more accurate hotspot prediction. The experimental results demonstrate that our model successfully identifies 95.78% of DRC violations, with a mere 4.17% false-alarm rate. Not only does our method deliver improved feature preprocessing results, but it also enhances prediction accuracy compared to alternative approaches.

BIDS: An efficient Intrusion Detection System for in-vehicle networks using a two-stage Binarised Neural Network on low-cost FPGA

Automotive networks are crucial for ensuring safety as the number of Electronic Control Units (ECUs) grows to support vehicle intelligence. The Controller Area Network (CAN) is commonly used for efficient in-vehicle communication among ECUs. However, its broadcast nature and lack of a dedicated security layer make it vulnerable to attacks. This paper proposes a novel CAN bus Intrusion Detection System (IDS), named BNN-based IDS (BIDS), which efficiently provides both unknown attack detection and known attack classification using a hierarchical two-stage Binarised Neural Network (BNN) and Generative Adversarial Network (GAN). BIDS was validated on three datasets, and its implementation achieves an average inference time of less than 0.170 ms with minimal resource utilisation on a low-cost Field Programmable Gate Array (FPGA). This rapid inference speed enables real-time inference on individual CAN messages using a sliding window technique, eliminating the need to wait for multiple accumulated CAN messages required for data preprocessing. Evaluation metrics demonstrate that our IDS achieves high accuracy in both identifying unseen attacks and categorising known attacks. Furthermore, our FPGA implementation consumes merely 2.09 W, which is a 57% reduction compared to a cutting-edge FPGA-based IDS that is capable of detecting unknown attacks using the same dataset.

Intersubject Dynamic Conditional Correlation: A Novel Method to Track the Framewise Network Implication during Naturalistic Stimuli.

Background: Naturalistic stimuli have become increasingly popular in modern cognitive neuroscience. These stimuli have high ecological validity due to their rich and multilayered features. However, their complexity also presents methodological challenges for uncovering neural network reconfiguration. Dynamic functional connectivity using the sliding-window technique is commonly used but has several limitations. In this study, we introduce a new method called intersubject dynamic conditional correlation (ISDCC). Method: ISDCC uses intersubject analysis to remove intrinsic and non-neuronal signals, retaining only intersubject-consistent stimuli-induced signals. It then applies dynamic conditional correlation (DCC) based on the generalized autoregressive conditional heteroskedasticity to calculate the framewise functional connectivity. To validate ISDCC, we analyzed simulation data with known network reconfiguration patterns and two publicly available narrative functional Magnetic Resonance Imaging (fMRI) datasets. Results: (1) ISDCC accurately unveiled the underlying network reconfiguration patterns in simulation data, demonstrating greater sensitivity than DCC; (2) ISDCC identified synchronized network reconfiguration patterns across listeners; (3) ISDCC effectively differentiated between stimulus types with varying temporal coherence; and (4) network reconfigurations unveiled by ISDCC were significantly correlated with listener engagement during narrative comprehension. Conclusion: ISDCC is a precise and dynamic method for tracking network implications in response to naturalistic stimuli.

CDDA-MD: An efficient malicious traffic detection method based on concept drift detection and adaptation technique

With the rapid development of network environment, cyber attacks have become one of the major threats to network security, and maintaining network security requires accurate detection of malicious traffic generated by cyber attacks. However, due to the dynamic nature of network behavior, data distribution in network traffic may change over time, i.e., appearing concept drift phenomenon, and the emergence of concept drift causes existing malicious traffic detection models to suffer from the problem of decreased detection efficiency. To address this challenge, we propose a Concept Drift Detection and Adaptation-based Malicious traffic Detection method called CDDA-MD. Firstly, the network traffic is segmented using sliding window technique and the data samples are analyzed on the basis of each window. And then, a long short-term memory network (LSTM) is utilized to capture the long-term dependencies in the time-series features of network traffic; At the same time, a multi-head self-attention mechanism is introduced to provide larger weights for the important features. Moreover, we replace the ReLU activation function in LSTM with Tanh to overcome the neuron “death” problem, and replace the Adam optimizer with Nadam to accelerate convergence, thereby improving the detection performance. Next, the concept drift is detected based on the idea of error rate, and the detected concept drift data is used for incremental learning to make the model adapt to current network environment. Finally, based on the detected concept drift, malicious traffic detection operations are performed to effectively maintain the security of cyberspace. Experiments on four network traffic show that compared with existing state-of-the-art methods, the proposed CDDA-MD method improves 0.3%, 1.2% , 1.16% and 1.9% in F1-measure, 0.25%, 1.1%, 1.44% and 1.72% in TPR, respectively; It also has better stability.

Dynamic functional connections analysis with spectral learning for brain disorder detection

Dynamic functional connections (dFCs), can reveal neural activities, which provides an insightful way of mining the temporal patterns within the human brain and further detecting brain disorders. However, most existing studies focus on the dFCs estimation to identify brain disorders by shallow temporal features and methods, which cannot capture the inherent temporal patterns of dFCs effectively. To address this problem, this study proposes a novel method, named dynamic functional connections analysis with spectral learning (dCSL), to explore inherently temporal patterns of dFCs and further detect the brain disorders. Concretely, dCSL includes two components, dFCs estimation module and dFCs analysis module. In the former, dFCs are estimated via the sliding window technique. In the latter, the spectral kernel mapping is first constructed by combining the Fourier transform with the non-stationary kernel. Subsequently, the spectral kernel mapping is stacked into a deep kernel network to explore higher-order temporal patterns of dFCs through spectral learning. The proposed dCSL, sharing the benefits of deep architecture and non-stationary kernel, can not only calculate the long-range relationship but also explore the higher-order temporal patterns of dFCs. To evaluate the proposed method, a set of brain disorder classification tasks are conducted on several public datasets. As a result, the proposed dCSL achieves 5% accuracy improvement compared with the widely used approaches for analyzing sequence data, 1.3% accuracy improvement compared with the state-of-the-art methods for dFCs. In addition, the discriminative brain regions are explored in the ASD detection task. The findings in this study are consistent with the clinical performance in ASD.