Pub Date : 2026-01-24DOI: 10.1016/j.jestch.2026.102287
Shaima Safa Aldin Baha Aldin , Noor Baha Aldin , Mahmut Aykaç
The secure delivery of visual content over noisy or lossy communication networks requires strong cryptographic schemes that combine security with error control and resilience. Despite the security being available for most chaos-based encryption schemes, they are in general sensitive to transmission errors. This paper presents a simple but efficient Graphics Processing Unit (GPU) based image-encryption which combines chaotic encryption and integrated Error Correction Codes (ECC). It consists of a 3D logistic-map for producing different keystreams of rearranged pixels and mixup values using XOR operations. In order to make the cipher more robust to transmission issues, we have integrated a Combined ReedSolomon (RS) and Low-Density ParityCheck (LDPC) ECC layer. All packed in an interactive MATLAB framework for easy test, visualization, and realtime analysis. The experimental results on the USC-SIPI dataset show that the proposed framework has a high entropy of 7.9993, NPCR = 99.63%, and UACI = 33.52%. The systems got a 39 Mbps on a standard GPU with 5 times overall speed compared to the CPU. Thus, this design gives a practical, efficient, and robust approach for secure image communication, as well as a good educational tool for exploring multimedia security concepts.
{"title":"A lightweight, GPU-accelerated batch image encryption framework with integrated ECC and multi-attack resilience","authors":"Shaima Safa Aldin Baha Aldin , Noor Baha Aldin , Mahmut Aykaç","doi":"10.1016/j.jestch.2026.102287","DOIUrl":"10.1016/j.jestch.2026.102287","url":null,"abstract":"<div><div>The secure delivery of visual content over noisy or lossy communication networks requires strong cryptographic schemes that combine security with error control and resilience. Despite the security being available for most chaos-based encryption schemes, they are in general sensitive to transmission errors. This paper presents a simple but efficient Graphics Processing Unit (GPU) based image-encryption which combines chaotic encryption and integrated Error Correction Codes (ECC). It consists of a 3D logistic-map for producing different keystreams of rearranged pixels and mixup values using XOR operations. In order to make the cipher more robust to transmission issues, we have integrated a Combined ReedSolomon (RS) and Low-Density ParityCheck (LDPC) ECC layer. All packed in an interactive MATLAB framework for easy test, visualization, and realtime analysis. The experimental results on the USC-SIPI dataset show that the proposed framework has a high entropy of 7.9993, NPCR = 99.63%, and UACI = 33.52%. The systems got a 39 Mbps on a standard GPU with 5 times overall speed compared to the CPU. Thus, this design gives a practical, efficient, and robust approach for secure image communication, as well as a good educational tool for exploring multimedia security concepts.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"74 ","pages":"Article 102287"},"PeriodicalIF":5.4,"publicationDate":"2026-01-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146039707","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-23DOI: 10.1016/j.jestch.2026.102286
Osman Demirci , Sezai Taskin
Accurate state-of-charge (SOC) estimation is a key requirement for the safe and efficient management of lithium-ion batteries in electric vehicles, especially under varying thermal and dynamic operating conditions. This study presents a comprehensive, algorithm-oriented assessment of several deep learning and hybrid SOC estimation architectures—including feedforward neural networks (FNN), gated recurrent networks (GRU), long short-term memory networks (LSTM), temporal convolutional networks (TCN), and their hybrid combinations—using a multi-temperature dataset collected at 10 °C, 25 °C, and 40 °C under diverse dynamic load profiles and standardized drive cycles such as UDDS, HWFET, US06, and LA92. All architectures were trained and evaluated under a unified preprocessing and training configuration to ensure methodological consistency and a fair basis for comparison.
The evaluation highlights how different recurrent, convolutional, and hybrid architectures respond to thermal variations and dynamic load transitions, revealing model-specific strengths and limitations under realistic operating conditions. Among the evaluated models, the hybrid FNN + GRU architecture demonstrated the most reliable overall performance, achieving an RMSE of 1.11 % and reducing peak estimation errors to 3.6 % under nominal temperature conditions. SOC-zone analysis further showed characteristic error amplification at low and high SOC levels, emphasizing the importance of architectures capable of capturing nonlinear boundary dynamics. Computational benchmarking indicated that hybrid structures—particularly FNN + GRU—also provide an advantageous balance between estimation accuracy and inference speed, supporting their suitability for embedded Battery Management Systems (BMSs) with real-time constraints.
Overall, this study contributes a unified evaluation framework that simultaneously addresses thermal robustness, dynamic load variability, SOC-dependent behavior, and computational efficiency, offering practical guidance for selecting reliable and deployable SOC estimation models for next-generation electric vehicle BMSs.
{"title":"Algorithm-oriented benchmarking of deep learning and hybrid architectures for robust SOC estimation in electric vehicle batteries","authors":"Osman Demirci , Sezai Taskin","doi":"10.1016/j.jestch.2026.102286","DOIUrl":"10.1016/j.jestch.2026.102286","url":null,"abstract":"<div><div>Accurate state-of-charge (SOC) estimation is a key requirement for the safe and efficient management of lithium-ion batteries in electric vehicles, especially under varying thermal and dynamic operating conditions. This study presents a comprehensive, algorithm-oriented assessment of several deep learning and hybrid SOC estimation architectures—including feedforward neural networks (FNN), gated recurrent networks (GRU), long short-term memory networks (LSTM), temporal convolutional networks (TCN), and their hybrid combinations—using a multi-temperature dataset collected at 10 °C, 25 °C, and 40 °C under diverse dynamic load profiles and standardized drive cycles such as UDDS, HWFET, US06, and LA92. All architectures were trained and evaluated under a unified preprocessing and training configuration to ensure methodological consistency and a fair basis for comparison.</div><div>The evaluation highlights how different recurrent, convolutional, and hybrid architectures respond to thermal variations and dynamic load transitions, revealing model-specific strengths and limitations under realistic operating conditions. Among the evaluated models, the hybrid FNN + GRU architecture demonstrated the most reliable overall performance, achieving an RMSE of 1.11 % and reducing peak estimation errors to 3.6 % under nominal temperature conditions. SOC-zone analysis further showed characteristic error amplification at low and high SOC levels, emphasizing the importance of architectures capable of capturing nonlinear boundary dynamics. Computational benchmarking indicated that hybrid structures—particularly FNN + GRU—also provide an advantageous balance between estimation accuracy and inference speed, supporting their suitability for embedded Battery Management Systems (BMSs) with real-time constraints.</div><div>Overall, this study contributes a unified evaluation framework that simultaneously addresses thermal robustness, dynamic load variability, SOC-dependent behavior, and computational efficiency, offering practical guidance for selecting reliable and deployable SOC estimation models for next-generation electric vehicle BMSs.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"74 ","pages":"Article 102286"},"PeriodicalIF":5.4,"publicationDate":"2026-01-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146039659","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-22DOI: 10.1016/j.jestch.2025.102270
Ahmet Burak Kaydeci , Salih Baris Ozturk
Accurate modeling of powertrain efficiency is essential for optimizing energy management and range prediction in electric vehicles. This is particularly important under varying real-world driving conditions. To address the limitations of fixed efficiency assumptions in conventional models, this study proposes a hybrid approach combining experimental data with physics-based simulation. A feedforward artificial neural network (ANN) is trained to predict powertrain efficiency dynamically using real-world data collected from a prototype electric vehicle. The ANN utilizes four input variables—motor torque, motor speed, battery temperature, and state of charge—selected through a combined physical and experimental data-driven relevance analysis. The trained model is integrated into a longitudinal vehicle simulation framework, enabling dynamic efficiency estimation and energy consumption analysis. The validation was performed by comparing the ANN predictions against a separate set of experimental measurements. Compared to a baseline linear regression model, the ANN demonstrated a 95.2% lower mean squared error (MSE) and 80.4% lower mean absolute error (MAE) during efficiency interpolation, with a coefficient of determination () of 0.995. Simulations were conducted on both long-haul and city drive cycles, validating the model’s adaptability in diverse scenarios. These results support its application in predictive energy control, route-specific planning, and on-board performance evaluation.
{"title":"State-dependent efficiency estimation in electric vehicles using an artificial neural network approach","authors":"Ahmet Burak Kaydeci , Salih Baris Ozturk","doi":"10.1016/j.jestch.2025.102270","DOIUrl":"10.1016/j.jestch.2025.102270","url":null,"abstract":"<div><div>Accurate modeling of powertrain efficiency is essential for optimizing energy management and range prediction in electric vehicles. This is particularly important under varying real-world driving conditions. To address the limitations of fixed efficiency assumptions in conventional models, this study proposes a hybrid approach combining experimental data with physics-based simulation. A feedforward artificial neural network (ANN) is trained to predict powertrain efficiency dynamically using real-world data collected from a prototype electric vehicle. The ANN utilizes four input variables—motor torque, motor speed, battery temperature, and state of charge—selected through a combined physical and experimental data-driven relevance analysis. The trained model is integrated into a longitudinal vehicle simulation framework, enabling dynamic efficiency estimation and energy consumption analysis. The validation was performed by comparing the ANN predictions against a separate set of experimental measurements. Compared to a baseline linear regression model, the ANN demonstrated a 95.2% lower mean squared error (MSE) and 80.4% lower mean absolute error (MAE) during efficiency interpolation, with a coefficient of determination (<span><math><msup><mrow><mi>R</mi></mrow><mrow><mn>2</mn></mrow></msup></math></span>) of 0.995. Simulations were conducted on both long-haul and city drive cycles, validating the model’s adaptability in diverse scenarios. These results support its application in predictive energy control, route-specific planning, and on-board performance evaluation.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"74 ","pages":"Article 102270"},"PeriodicalIF":5.4,"publicationDate":"2026-01-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146039706","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-21DOI: 10.1016/j.jestch.2026.102285
Hejun Yang , Yangxu Yue , Jing Ma , Dabo Zhang , Xianjun Qi
The distributed generation (DG) and soft open point (SOP) have been connected to the distribution network, so distribution network fault recovery has changed from the single tie line recovery to collaborated recovery of DG and SOP, resulting in the reliability of distribution network is seriously underestimated under the traditional reliability assessment mode. Therefore, in order to overcome this shortcoming, this paper presents reliability assessment methodology for enhancing reliability of electrical distribution system using a network collaboration recovery technique. The paper employs a highly flexible model to fully exploit the synergistic restoration potential of flexible resources, enabling precise reliability evaluation through the formulation of optimal fault recovery strategies. Firstly, the restoration strategy for SOP and tie line reconfiguration in coordination with DG islanding is proposed in order to consider the mutual influence between SOP and DG in fault recovery and fully explore the collaborative recovery ability of DG and SOP; Secondly, this paper proposes a radial network constraint method that allows island recovery and load shedding operations. The method ensures to obtain the optimal solution for the restoration strategy while constraining the radial operation of the distribution network; Thirdly, in order to improve the computational accuracy of the proposed model, this paper uses the big M method and second-order cone relaxation to transform the model into a mixed-integer second-order cone programming problem and solves the model using a solver; Finally, the effectiveness and superiority of the proposed method is investigated through the case study on IEEE 33 and 54-node distribution systems, and the SAIDI index can be reduced by 5.98% for IEEE 33 system and 3.07% for 54-node system.
{"title":"Reliability enhancement method for distribution system using a network cooperation recovery optimization technique","authors":"Hejun Yang , Yangxu Yue , Jing Ma , Dabo Zhang , Xianjun Qi","doi":"10.1016/j.jestch.2026.102285","DOIUrl":"10.1016/j.jestch.2026.102285","url":null,"abstract":"<div><div>The distributed generation (DG) and soft open point (SOP) have been connected to the distribution network, so distribution network fault recovery has changed from the single tie line recovery to collaborated recovery of DG and SOP, resulting in the reliability of distribution network is seriously underestimated under the traditional reliability assessment mode. Therefore, in order to overcome this shortcoming, this paper presents reliability assessment methodology for enhancing reliability of electrical distribution system using a network collaboration recovery technique. The paper employs a highly flexible model to fully exploit the synergistic restoration potential of flexible resources, enabling precise reliability evaluation through the formulation of optimal fault recovery strategies. Firstly, the restoration strategy for SOP and tie line reconfiguration in coordination with DG islanding is proposed in order to consider the mutual influence between SOP and DG in fault recovery and fully explore the collaborative recovery ability of DG and SOP; Secondly, this paper proposes a radial network constraint method that allows island recovery and load shedding operations. The method ensures to obtain the optimal solution for the restoration strategy while constraining the radial operation of the distribution network; Thirdly, in order to improve the computational accuracy of the proposed model, this paper uses the big M method and second-order cone relaxation to transform the model into a mixed-integer second-order cone programming problem and solves the model using a solver; Finally, the effectiveness and superiority of the proposed method is investigated through the case study on IEEE 33 and 54-node distribution systems, and the <em>SAIDI</em> index can be reduced by 5.98% for IEEE 33 system and 3.07% for 54-node system.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"74 ","pages":"Article 102285"},"PeriodicalIF":5.4,"publicationDate":"2026-01-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146001841","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1016/j.jestch.2025.102272
Sai Babu Veesam , Lalitha Kumari Pappala , Aravapalli Rama Satish , Sravan Kumar Chirumamilla , Vunnava Dinesh Babu , Shonak Bansal , Krishna Prakash , Mohamad A. Alawad , Mohammad Tariqul Islam
Segmentation of lung lesions in volumetric CT data is crucial for the clinical aspects of diagnosis, therapy planning, and monitoring disease progression. Currently, deep learning applications are unable to model spatiotemporal coherency alongside anatomical consistency and uncertainty-aware refinement across sequential slices. In this study, we propose a hybrid quantum–classical framework that would accommodate multiple innovative modules. The architecture features a Quantum Latent Entanglement Consistency validator to establish spatiotemporal coherence across slices by maximizing von Neumann entropy. A Quantum-Classical Interventional Gradient Alignment ensures the harmony of gradients between classical CNN encoders and quantum discriminators. Further, the Temporal Quantum Attention for Boundary Stabilization captures the temporal context in the boundary refinement using controlled quantum gates. Alongside these, a Quantum-Enhanced Structural Similarity Feedback mechanism is proposed that exploits anatomical priors for retrofitting spatial lesion structures, as well as a Hybrid Quantum Adversarial Ensemble Validation, which provides confidence-aware validity through disagreement modeling. Collection and experimental evaluations over LIDC IDRI, NSCLC-Radiomics, and MosMedData datasets depict that the entirety of the systems significantly increases the Dice Similarity Coefficient by 5–7%, holds Hausdorff Distance lower at 10–12%, narrows down the over-segmentation errors by 8–10%, while reducing overall false positives near lung boundaries by 15% or even less. This represents a significant advancement toward fusing quantum learning with clinical-grade imaging pipelines, demonstrating clear improvements in segmentation stability, precision, and trustworthiness in real-world settings.
{"title":"Integrated quantum-classical hybrid architectures for robust lung lesion segmentation in volumetric CT video data samples","authors":"Sai Babu Veesam , Lalitha Kumari Pappala , Aravapalli Rama Satish , Sravan Kumar Chirumamilla , Vunnava Dinesh Babu , Shonak Bansal , Krishna Prakash , Mohamad A. Alawad , Mohammad Tariqul Islam","doi":"10.1016/j.jestch.2025.102272","DOIUrl":"10.1016/j.jestch.2025.102272","url":null,"abstract":"<div><div>Segmentation of lung lesions in volumetric CT data is crucial for the clinical aspects of diagnosis, therapy planning, and monitoring disease progression. Currently, deep learning applications are unable to model spatiotemporal coherency alongside anatomical consistency and uncertainty-aware refinement across sequential slices. In this study, we propose a hybrid quantum–classical framework that would accommodate multiple innovative modules. The architecture features a Quantum Latent Entanglement Consistency validator to establish spatiotemporal coherence across slices by maximizing von Neumann entropy. A Quantum-Classical Interventional Gradient Alignment ensures the harmony of gradients between classical CNN encoders and quantum discriminators. Further, the Temporal Quantum Attention for Boundary Stabilization captures the temporal context in the boundary refinement using controlled quantum gates. Alongside these, a Quantum-Enhanced Structural Similarity Feedback mechanism is proposed that exploits anatomical priors for retrofitting spatial lesion structures, as well as a Hybrid Quantum Adversarial Ensemble Validation, which provides confidence-aware validity through disagreement modeling. Collection and experimental evaluations over LIDC IDRI, NSCLC-Radiomics, and MosMedData datasets depict that the entirety of the systems significantly increases the Dice Similarity Coefficient by 5–7%, holds Hausdorff Distance lower at 10–12%, narrows down the over-segmentation errors by 8–10%, while reducing overall false positives near lung boundaries by 15% or even less. This represents a significant advancement toward fusing quantum learning with clinical-grade imaging pipelines, demonstrating clear improvements in segmentation stability, precision, and trustworthiness in real-world settings.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"73 ","pages":"Article 102272"},"PeriodicalIF":5.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884646","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1016/j.jestch.2025.102269
Saleh Mobayen , Mai The Vu , Reza Rahmani , Hamid Toshani , Wudhichai Assawinchaichote , Paweł Skruch
This paper presents a constrained optimal adaptive control strategy for formation control in nonlinear multi-agent systems (MASs) using a data-driven approach. In contrast to traditional methods that require detailed system models, the proposed method employs Locally Linearized Dynamic Models (LLDMs), in which key parameters as Pseudo-Partial Derivatives (PPDs) are estimated adaptively from input–output data. This removes the need for explicit mathematical modeling and broadens the method’s applicability to uncertain systems. To address actuator limitations and reduce control effort, a performance criterion incorporating control constraints is defined, and the problem is reformulated as a Constrained Quadratic Program (CQP) with control increments as optimization variables. A Projection Recurrent Neural Network (PRNN) is developed to solve this CQP in real time, which ensures convergence of the numerical optimizer and guarantees closed-loop stability using Lyapunov analysis and singular value approach. The proposed algorithm achieves robust, model-free formation control, explicitly manages input constraints, and enables fast convergence. Simulation results show that this approach outperforms existing data-driven methods under uncertainty, which demonstrates its potential for applications in multi-agent system applications.
{"title":"Constrained optimal formation control for nonlinear multi-agent systems using data-driven adaptive neural networks","authors":"Saleh Mobayen , Mai The Vu , Reza Rahmani , Hamid Toshani , Wudhichai Assawinchaichote , Paweł Skruch","doi":"10.1016/j.jestch.2025.102269","DOIUrl":"10.1016/j.jestch.2025.102269","url":null,"abstract":"<div><div>This paper presents a constrained optimal adaptive control strategy for formation control in nonlinear multi-agent systems (MASs) using a data-driven approach. In contrast to traditional methods that require detailed system models, the proposed method employs Locally Linearized Dynamic Models (LLDMs), in which key parameters as Pseudo-Partial Derivatives (PPDs) are estimated adaptively from input–output data. This removes the need for explicit mathematical modeling and broadens the method’s applicability to uncertain systems. To address actuator limitations and reduce control effort, a performance criterion incorporating control constraints is defined, and the problem is reformulated as a Constrained Quadratic Program (CQP) with control increments as optimization variables. A Projection Recurrent Neural Network (PRNN) is developed to solve this CQP in real time, which ensures convergence of the numerical optimizer and guarantees closed-loop stability using Lyapunov analysis and singular value approach. The proposed algorithm achieves robust, model-free formation control, explicitly manages input constraints, and enables fast convergence. Simulation results show that this approach outperforms existing data-driven methods under uncertainty, which demonstrates its potential for applications in multi-agent system applications.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"73 ","pages":"Article 102269"},"PeriodicalIF":5.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884643","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1016/j.jestch.2025.102267
Md. Khaliluzzaman , Kaushik Deb
Gait recognition, a promising behavioral soft biometric technology, has a significant research area in security and computer vision. Nowadays, joint position-based approaches are of significant interest in gait recognition. ST-GCN, the spatio-temporal graph convolutional network, is employed on the joint stream to identify the gait feature from the spatial–temporal graph, prone to provide attention to dynamic information. Many methods utilize multi-scale operations to integrate long-range relationships among joints. However, these approaches fail to assign equal significance to all joints, leading to an incomplete perception of long-range joint connections. Furthermore, considering the joint stream solely may fail to extract the discriminative features produced by motion and bone structures. This paper presents a multi-stream dynamic spatio-temporal graph convolution (DSTGCN) approach with attention, denoted as DGait. It leverages bone and joint data from the spatial frames and joint-motion data from successive frames to early fusion of informative skeleton features. An improved HOP-extraction approach is introduced to provide equal importance to the relationship between further and closer joints while avoiding redundant dependencies. To address the limitations of ST-GCN, Global Aware Attention (GAA) is incorporated into the ST-GCN units, enhancing the capability for dynamically correlating the spatial–temporal joints. The suggested model exhibits remarkable accuracy on widely used CASIA-B, OUMVLP-Pose, and GREW datasets. The CASIA-B reveals an average accuracy of 96.94 %, 93.56 %, and 90.78 % for the normal walking, carrying-bag, and clothing conditions, respectively. The OUMVLP-Pose and GREW exhibit an average and rank-1 accuracy of 92.7 % and 72.6 %, respectively.
{"title":"DGait: Robust gait recognition using dynamic ST-GCN with global aware attention","authors":"Md. Khaliluzzaman , Kaushik Deb","doi":"10.1016/j.jestch.2025.102267","DOIUrl":"10.1016/j.jestch.2025.102267","url":null,"abstract":"<div><div>Gait recognition, a promising behavioral soft biometric technology, has a significant research area in security and computer vision. Nowadays, joint position-based approaches are of significant interest in gait recognition. ST-GCN, the spatio-temporal graph convolutional network, is employed on the joint stream to identify the gait feature from the spatial–temporal graph, prone to provide attention to dynamic information. Many methods utilize multi-scale operations to integrate long-range relationships among joints. However, these approaches fail to assign equal significance to all joints, leading to an incomplete perception of long-range joint connections. Furthermore, considering the joint stream solely may fail to extract the discriminative features produced by motion and bone structures. This paper presents a multi-stream dynamic spatio-temporal graph convolution (DSTGCN) approach with attention, denoted as DGait. It leverages bone and joint data from the spatial frames and joint-motion data from successive frames to early fusion of informative skeleton features. An improved HOP-extraction approach is introduced to provide equal importance to the relationship between further and closer joints while avoiding redundant dependencies. To address the limitations of ST-GCN, Global Aware Attention (GAA) is incorporated into the ST-GCN units, enhancing the capability for dynamically correlating the spatial–temporal joints. The suggested model exhibits remarkable accuracy on widely used CASIA-B, OUMVLP-Pose, and GREW datasets. The CASIA-B reveals an average accuracy of 96.94 %, 93.56 %, and 90.78 % for the normal walking, carrying-bag, and clothing conditions, respectively. The OUMVLP-Pose and GREW exhibit an average and rank-1 accuracy of 92.7 % and 72.6 %, respectively.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"73 ","pages":"Article 102267"},"PeriodicalIF":5.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884647","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1016/j.jestch.2025.102268
Zhi Zhang
Interpreting frequency response analysis (FRA) data presents a formidable challenge in transformer fault diagnosis. Previous attempts to derive transfer functions (TF) for characterizing FRA curves have been both desirable and unsuccessful. The collected FRA data aims to represent the mechanical conditions of the transformer windings under examination. Nonetheless, the techniques applied to FRA results for assessing mechanical integrity face inherent uncertainty due to the lack of a direct link between the measured data and the electrical characteristics of an equivalent circuit (EC) consisting of resistance, inductance, and capacitance (RLC) components. As such, a rigorous analysis of the FRA data becomes crucial for a comprehensive assessment and interpretation of the mechanical state of these windings. The proposed investigation into TF is designed to offer a detailed mathematical interpretation of FRA characteristics, potentially enabling the early detection of potential faults through the derived TF and relevant parameters. This research paper revolves around the computation of TFs for power transformer helical windings. Consequently, a strong correlation emerges between the recorded FRA curves and the computed TF curves, affirming the precision of TF estimation and its significant contribution to advance FRA technology.
{"title":"Characterizing the FRA curves of transformer tertiary helical windings by deriving transfer functions from FRA data","authors":"Zhi Zhang","doi":"10.1016/j.jestch.2025.102268","DOIUrl":"10.1016/j.jestch.2025.102268","url":null,"abstract":"<div><div>Interpreting frequency response analysis (FRA) data presents a formidable challenge in transformer fault diagnosis. Previous attempts to derive transfer functions (TF) for characterizing FRA curves have been both desirable and unsuccessful. The collected FRA data aims to represent the mechanical conditions of the transformer windings under examination. Nonetheless, the techniques applied to FRA results for assessing mechanical integrity face inherent uncertainty due to the lack of a direct link between the measured data and the electrical characteristics of an equivalent circuit (EC) consisting of resistance, inductance, and capacitance (RLC) components. As such, a rigorous analysis of the FRA data becomes crucial for a comprehensive assessment and interpretation of the mechanical state of these windings. The proposed investigation into TF is designed to offer a detailed mathematical interpretation of FRA characteristics, potentially enabling the early detection of potential faults through the derived TF and relevant parameters. This research paper revolves around the computation of TFs for power transformer helical windings. Consequently, a strong correlation emerges between the recorded FRA curves and the computed TF curves, affirming the precision of TF estimation and its significant contribution to advance FRA technology.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"73 ","pages":"Article 102268"},"PeriodicalIF":5.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884645","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1016/j.jestch.2025.102271
Zongxing Wei , Mohamadariff Othman , Tarik Abdul Latef , Hazlee Azil Illias , S. M. Kayser Azam , Tengku Faiz Tengku Mohmed Noor Izam , Muhammad Ubaid Ullah , Mohamed Alkhatib , Mousa I. Hussein
This paper provides a comprehensive review of ultra-high frequency (UHF) noise-cancellation antenna (NCA) sensors. It identifies the critical challenges posed by noise interference in UHF bands and their impact on signal quality, particularly in partial discharge (PD) detection applications. The paper summarises the various types of noise present in the UHF range and highlights the importance of advanced design methods to enhance signal integrity. A significant contribution of this work is the detailed analysis of several noise-cancellation (NC) techniques, including the integrated feedline approach, embedded filter antenna technique, slot design modification, parasitic element incorporation, and shorting pin integration. These are systematically evaluated for their effectiveness in reducing interference. The review also provides a comparative analysis using tabular data, covering performance metrics such as NC implementation, radiation nulls (RN) frequency, bandwidth, gain, and other parameters. In addition, the paper identifies the most suitable techniques for PD detection and discusses their practical limitations. By highlighting potential directions for future research, this study offers valuable insights for advancing UHF antenna sensor design and its application in industrial PD monitoring systems.
{"title":"A comprehensive review of noise-cancellation antenna sensors in ultra-high frequency: techniques, challenges, and future directions","authors":"Zongxing Wei , Mohamadariff Othman , Tarik Abdul Latef , Hazlee Azil Illias , S. M. Kayser Azam , Tengku Faiz Tengku Mohmed Noor Izam , Muhammad Ubaid Ullah , Mohamed Alkhatib , Mousa I. Hussein","doi":"10.1016/j.jestch.2025.102271","DOIUrl":"10.1016/j.jestch.2025.102271","url":null,"abstract":"<div><div>This paper provides a comprehensive review of ultra-high frequency (UHF) noise-cancellation antenna (NCA) sensors. It identifies the critical challenges posed by noise interference in UHF bands and their impact on signal quality, particularly in partial discharge (PD) detection applications. The paper summarises the various types of noise present in the UHF range and highlights the importance of advanced design methods to enhance signal integrity. A significant contribution of this work is the detailed analysis of several noise-cancellation (NC) techniques, including the integrated feedline approach, embedded filter antenna technique, slot design modification, parasitic element incorporation, and shorting pin integration. These are systematically evaluated for their effectiveness in reducing interference. The review also provides a comparative analysis using tabular data, covering performance metrics such as NC implementation, radiation nulls (RN) frequency, bandwidth, gain, and other parameters. In addition, the paper identifies the most suitable techniques for PD detection and discusses their practical limitations. By highlighting potential directions for future research, this study offers valuable insights for advancing UHF antenna sensor design and its application in industrial PD monitoring systems.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"73 ","pages":"Article 102271"},"PeriodicalIF":5.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"145884644","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2026-01-01DOI: 10.1016/S2215-0986(26)00009-1
{"title":"Front Matter 1 - Full Title Page (regular issues)/Special Issue Title page (special issues)","authors":"","doi":"10.1016/S2215-0986(26)00009-1","DOIUrl":"10.1016/S2215-0986(26)00009-1","url":null,"abstract":"","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"73 ","pages":"Article 102283"},"PeriodicalIF":5.4,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"146037888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
扫码关注我们
求助内容：
应助结果提醒方式：
京公网安备 11010802042870号