Engineering Science and Technology-An International Journal-Jestech最新文献

{"title":"Investigating the effects of Gaussian noise on epileptic seizure detection: The role of spectral flatness, bandwidth, and entropy","authors":"Nuri Ikizler,&nbsp;Gunes Ekim","doi":"10.1016/j.jestch.2025.102005","DOIUrl":"10.1016/j.jestch.2025.102005","url":null,"abstract":"<div><div>This study investigates the effect of Gaussian noise on the classification of EEG signals from five classes in the Bonn University EEG dataset for epileptic seizure detection, using Power Spectral Density features. The EEG data are pre-processed with a low-pass filter at a cutoff frequency of 40 Hz, and a total of 11 features, including spectral flatness difference, spectral bandwidth difference, and entropy difference, are extracted. Feature vectors are generated for both original signals and signals with varying levels of injected Gaussian noise. The results demonstrate that noise injections significantly improve classification accuracy across all class combinations by enhancing feature separability and generalization. Notably, 100 % accuracy was achieved in classifications with different noise levels. Analyses performed using classifiers such as Random Forest, Multilayer Perceptron, and k-Nearest Neighbors show that the Random Forest classifier achieves high classification success across all noise levels. Additionally, it was found that incorporating spectral flatness difference, spectral bandwidth difference, and entropy difference features significantly contributes to classification accuracy when combined with noise injection. This study highlights the potential of noise injections to reduce overfitting and enhance the robustness of EEG classification, providing valuable insights for future biomedical signal analysis. Noise injection, traditionally viewed as a factor that could hinder performance, is utilized in this study as a novel approach to enhance classification accuracy, marking a significant innovation in the field.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 102005"},"PeriodicalIF":5.1,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143452869","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Detection of high-risk diseases in poultry feces through transfer learning","authors":"Abdulkadir Tasdelen,&nbsp;Yenal Arslan","doi":"10.1016/j.jestch.2025.102002","DOIUrl":"10.1016/j.jestch.2025.102002","url":null,"abstract":"<div><div>Poultry farming industry constitutes a significant part of the global economy. Deep learning technology possesses the ability to autonomously analyze images, allowing constructed models to aid in the analysis and management of the poultry farming industry, particularly in early detection of sick poultry. Ensuring a sustainable industrial white meat production relies significantly on maintaining a high-quality living environment and early detection of diseases with prompt preventive measures. Early diagnosis of infectious and high-risk diseases such as Coccidiosis, Salmonellosis, and Newcastle disease, coupled with taking necessary precautions, will contribute to the efficient functioning of global economies supply chain. This study aims to detect high-risk Coccidiosis, Salmonellosis, and Newcastle diseases in poultry through transfer learning using poultry feces. Six different transfer learning architectures, namely DenseNet201, Resnet152V2, InceptionV3, InceptionResnetV2, MobileNetV2, and Xception, were employed in the study due to their widespread use and high accuracy rates.</div><div>The analysis revealed that MobileNetV2 achieved the highest accuracy rate of 97.1%. Considering the training times, it was observed that MobileNetV2 also exhibited the fastest training. The results of the analysis provide evidence that disease analysis from poultry feces can be carried out with high accuracy through transfer learning in the context of sustainable white meat production.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 102002"},"PeriodicalIF":5.1,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143452868","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"GIS-based landslide susceptibility mapping using AHP, FMEA, and Pareto systematic analysis in central Yalova, Türkiye","authors":"Burak Demirel ,&nbsp;Eray Yildirim ,&nbsp;Eray Can","doi":"10.1016/j.jestch.2025.102013","DOIUrl":"10.1016/j.jestch.2025.102013","url":null,"abstract":"<div><div>Yalova is a region with high landslide risk due to its climate, terrain, geographical features, and geological structure. Landslides in the region are of critical importance to produce landslide susceptibility maps and risk management because of the material and moral damage they cause. This study aimed to produce a Geographic Information System (GIS)-based landslide susceptibility map (LSM) of the Yalova central region using the Analytic Hierarchy Process (AHP), Failure Mode and Effect Analysis (FMEA), and Pareto systematic analyses. Lithology, slope, aspect, distance from roads, NDVI (Normalized Difference Vegetation Index), distance from faults, land use, rainfall, distance from rivers, and elevation factors were used in the analyses. The FMEA, Pareto, and AHP methods were used in an integrated and sequential manner to determine the LCF weights. According to the analysis, lithology was identified as the most influential factor, with the highest weight at 29.5%, while appearance had the lowest weight at 1.5%. The LSM was generated by processing the weight values in the prepared LCFs. Based on the produced landslide susceptibility map, the study area was categorized as having 29.60% very low-risk, 29.51% low-risk, 24.04% moderate-risk, 13.18% high-risk, and 3.68% very high-risk. Regional planning should be undertaken according to the landslide risk categories, and appropriate measures should be determined for each level in advance. Upon comparing the produced LSM with the existing inventory, it was determined that 95.29% of the previously occurring landslides in the region were in risky areas on the LSM. The results demonstrate the integrated applicability of the AHP, FMEA, and Pareto methods and provide a more accurate weighting of LCFs compared to a single method. The approach used in this study can be easily adapted to different regions and can be used not only for landslide analysis but also for risk assessment studies in other disciplines.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 102013"},"PeriodicalIF":5.1,"publicationDate":"2025-02-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143452870","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Robust robot localization with visually adaptive consensus filters in dynamic corridor environments","authors":"Suhyeon Kang,&nbsp;Heoncheol Lee","doi":"10.1016/j.jestch.2025.101998","DOIUrl":"10.1016/j.jestch.2025.101998","url":null,"abstract":"<div><div>This paper deals with the problem of robot localization in dynamic corridor environments. If a robot uses only a LiDAR (light detection and ranging) for its localization, the accuracy of robot localization degenerates as time goes due to the occlusions by moving people around a robot and the lack of scan features in corridors. This paper proposes a robust robot localization method with visually adaptive consensus filters (VACF) to solve the problem. The VACF consists of LiDAR odometry estimation, probabilistic localization, visual odometry estimation, optical flow recognition, object detection and adaptive consensus filters. To deal with long corridor environments, optical flow methods are used to correct the robot’s position. For robust localization in dynamic environments, object detection algorithm is used to detect dynamic objects, and localization algorithms are adaptively used as input to a consensus filter based on the number of dynamic objects detected. The VACF was tested in real-world experiments in dynamic corridor environments and showed better accuracy than other existing methods when compared to pre-determined ground truth points.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 101998"},"PeriodicalIF":5.1,"publicationDate":"2025-02-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143452867","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Trajectory planning and tracking control in autonomous driving system: Leveraging machine learning and advanced control algorithms","authors":"Md Hafizur Rahman ,&nbsp;Muhammad Majid Gulzar ,&nbsp;Tansu Sila Haque ,&nbsp;Salman Habib ,&nbsp;Adnan Shakoor ,&nbsp;Ali Faisal Murtaza","doi":"10.1016/j.jestch.2025.101950","DOIUrl":"10.1016/j.jestch.2025.101950","url":null,"abstract":"<div><div>Automated vehicles may soon be seen on our roads as automation is becoming more and more prominent in transportation research. This comprehensive analysis provides a detailed synopsis of the cutting-edge algorithms and technologies propelling the advancement and adoption of autonomous driving. It begins with assessing the fundamental system architectures needed to operate autonomous vehicles: Control over tracking and trajectory planning. Also, this review proceeds to cover in-depth discussions on the decision-making, and trajectory planning techniques that are essential for seamless autonomous vehicle navigation, with a focus on the function of State-of-the-art algorithms, optimization algorithms, machine learning (ML), and deep learning (DL). In addition, Trajectory tracking control methods are also represented in this review, which describes types of tracking control techniques aligned with trajectory planning. Moreover, this review paper also discussed the challenges and limitations of algorithms or techniques implemented in the reviewed paper and suggested some future perspectives. In conclusion, the survey provides an extensive evaluation of the concepts and technologies required to move towards a safe and successful autonomous future, while also documenting the swift advancements in autonomous driving.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 101950"},"PeriodicalIF":5.1,"publicationDate":"2025-02-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429533","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"FAST: A pioneering unlearning framework integrating fine-tuning, adverse training, and student–teacher methods","authors":"Hoang Ngoc Tran ,&nbsp;Nguyen Trung Nguyen ,&nbsp;Nghi Vinh Nguyen ,&nbsp;Ha Xuan Nguyen ,&nbsp;Anh Duy Nguyen","doi":"10.1016/j.jestch.2025.101996","DOIUrl":"10.1016/j.jestch.2025.101996","url":null,"abstract":"<div><div>In the evolving field of machine unlearning, the imperative to protect data privacy while maintaining essential information has become increasingly critical. This paper introduces a pioneering unlearning framework named FAST (Fine-tuning, Adverse Training, and Student–Teacher Methods). FAST is designed to selectively erase privacy-sensitive data while robustly safeguarding valuable information. It employs an innovative integration of the student–teacher architecture, utilizing targeted data and a sophisticated distribution structure refined by the Kullback–Leibler (KL) divergence within the loss function. Enhanced by fine-tuning and adverse training techniques, this integration amplifies beneficial knowledge from competent teachers and reduces ineffective knowledge from less capable ones, thereby enabling more effective and efficient unlearning processes. Furthermore, a new evaluation method called the Unlearning Effectiveness Score (UES) has been proposed for our unlearning model, aimed at providing a comprehensive metric to assess the effectiveness of the unlearning process. This approach rigorously evaluates the model using two sophisticated methods: the Zero Retrain Forgetting (ZRF) metric and Membership Inference Attacks (MIA). The UES is designed to not only measure the effectiveness of forgetting but also to ensure that the model is not easily susceptible to these attacks. These methods facilitate comprehensive comparisons with previous techniques such as bad teaching, Amnesiac, SCRUB, and straightforward fine-tuning. Our thorough experimental analysis, conducted across a variety of deep networks including MobileNet, ResNet, and VGG on the CIFAR and MUFAC datasets, confirms that FAST substantially surpasses existing approaches in both effectively forgetting targeted data and retaining necessary information, as demonstrated by its superior performance on UES metrics.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"64 ","pages":"Article 101996"},"PeriodicalIF":5.1,"publicationDate":"2025-02-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143429535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Finite element analysis for partly using MONEL 400 material in plastic injection tile spacer holder mold for ceramic tiles","authors":"Güllü Akkaş ,&nbsp;Mehmet Cem Polat ,&nbsp;İhsan Korkut","doi":"10.1016/j.jestch.2025.101978","DOIUrl":"10.1016/j.jestch.2025.101978","url":null,"abstract":"<div><div>The plastics industry is one of the fastest growing industries in the world.The use of plastics in products used in daily life is quite common and most of these plastics can be produced by injection molding. The effects of the mold materials selected in the injection mold design stages on mechanical properties are very important. For this reason, it is one of the main topics to be investigated. In today’s technology, the use of additive manufacturing systems in metal processes has become widespread. As a result of these developments, new approaches in injection mold manufacturing have increased research opportunities on the selection of different materials. Superalloys, which are widely used in various industrial applications, have high mechanical strength, high corrosion resistance, good surface stability and high resistance to thermal creep deformation. The aim of the study is, as the technology advances, to increase the ability of the researchers to analyze how the change of the material used in molds affects the partial strength of the mold. For this purpose, two materials were used as structural elements of the support pin used in the plastic injection molds for tile spacer holders for ceramic tiles. One of the materials used is a superalloy called Monel 400 and the other material is the material that is used conventionally in making molds, called AISI 4130. By utilizing the finite elements analysis tool of SolidWorks, investigations were performed to determine the strength of support pins designed with both materials.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"63 ","pages":"Article 101978"},"PeriodicalIF":5.1,"publicationDate":"2025-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403082","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improved UWB-based indoor positioning system via NLOS classification and error mitigation","authors":"Shoude Wang ,&nbsp;Nur Syazreen Ahmad","doi":"10.1016/j.jestch.2025.101979","DOIUrl":"10.1016/j.jestch.2025.101979","url":null,"abstract":"<div><div>Non-Line-of-Sight (NLOS) conditions in indoor positioning systems significantly degrade positioning accuracy. Although Ultra-Wideband (UWB) technology is renowned for its high precision in Line-of-Sight (LOS) environments, under NLOS conditions, positioning errors typically exceed 30 cm. To address this issue, we propose a method for identifying and classifying NLOS signals based on Support Vector Machine Recursive Feature Elimination (SVM-RFE). We extract multiple features from the UWB Channel Impulse Response (CIR) and perform correlation analysis using the Pearson Correlation Coefficient (PCC) to select the most discriminative features via the SVM-RFE algorithm. The classification results are then utilized within an Adaptive Robust Extended Kalman Filter (AREKF) to establish an error model for mitigation. The proposed method was evaluated using both a public dataset from Ghent University and a locally collected dataset. On the public dataset, the SVM-RFE algorithm achieved classification accuracies of 97.6% in the hallway environment and 96.6% in the office environment, outperforming transfer learning (TL) deep neural networks (DNNs) tested on the same dataset. To further validate the robustness of the algorithm, experiments on the locally collected office dataset demonstrated a classification accuracy of 97.2%. In terms of distance measurement error mitigation, the proposed AREKF algorithm reduced errors at the 95th percentile by 70% and 75% in two different environments compared to transfer learning methods on the same public dataset. When tested on the locally collected dataset, the positioning error of the AREKF was significantly lower than that of other mainstream algorithms, highlighting the practical advantages of the proposed method.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"63 ","pages":"Article 101979"},"PeriodicalIF":5.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395907","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An optimized spatial target trajectory prediction model for multi-sensor data fusion in air traffic management","authors":"Jian Dong,&nbsp;Yuan Xu,&nbsp;Rigeng Wu,&nbsp;Chengwang Xiao","doi":"10.1016/j.jestch.2025.101994","DOIUrl":"10.1016/j.jestch.2025.101994","url":null,"abstract":"<div><div>With the evolution of air traffic safety management, the traditional single-sensor approach no longer meets the demands for spatial target surveillance. Consequently, there is increasing research interest in multi-sensor data fusion. This paper proposes an innovative network model based on the improved snow ablation optimizer algorithm. It employs convolutional neural network, structured within a bidirectional gated recurrent unit framework, combined with a multi-head attention mechanism, for spatial target trajectory prediction. We segment data from various sensors within the automatic dependent surveillance-broadcast system using a designed sliding window of equal time steps, inputting them into the feature extraction network to capture spatiotemporal features. The improved snow ablation optimizer algorithm optimizes hyperparameters of this network automatically, while the multi-head attention mechanism redistributes weighted features, integrating them into comprehensive features. Finally, predictions of spatial target trajectories are derived from outputs of fully connected layer. Through experiments on the constructed real dataset, it is evident that the improved snow ablation optimizer algorithm exhibits superior performance in optimization tasks. The sensor missing experiment underscore the advantages of multi-sensor data fusion. Furthermore, the ablation studies elucidate the functional disparities among various network architectures. In comparative analyses, the proposed network significantly outperforms prevailing trajectory prediction models across multiple dimensions. In this paper, we propose a new deep learning network, and apply it to the real-world engineering challenge of spatial target trajectory prediction in the air traffic management domain.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"63 ","pages":"Article 101994"},"PeriodicalIF":5.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143403084","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A comparative analysis of core material and gap sizing effect on the high-power inductor design","authors":"Funda Battal","doi":"10.1016/j.jestch.2025.102001","DOIUrl":"10.1016/j.jestch.2025.102001","url":null,"abstract":"<div><div>Air-gaps are used in the core structures of inductors, which are used as energy-storing components in power electronic circuits, to keep them away from saturation. As a result, changes in the electrical and magnetic parameters of the inductor are inevitable due to air-gaps. Depending on the electromagnetic properties of the core material used, the saturation current of the inductor and the change in inductance values are behaviors that need to be determined carefully. In this study, saturation flux values and inductance change graphs of high-power and medium-frequency inductors designed with soft magnetic core materials such as amorphous, nanocrystalline and 6,5%SiFe and using air-gaps in their core structures were comparatively analyzed. Although the amorphous core inductor exhibited better electrical performance at the relevant operating frequency and current values, according to the electromagnetic analysis made with the FEA software, the high magnetostriction coefficient of the amorphous material should be considered in applications that may be affected by vibration (applications of approximately 4 kHz and above). Additionally, evaluations regarding core losses and core dimensions are presented together with the results of comparative analyses.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"63 ","pages":"Article 102001"},"PeriodicalIF":5.1,"publicationDate":"2025-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143395908","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"工程技术","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}