Engineering reports : open access最新文献

{"title":"Explainable Machine Learning for Efficient Diabetes Prediction Using Hyperparameter Tuning, SHAP Analysis, Partial Dependency, and LIME","authors":"Md. Manowarul Islam,&nbsp;Habibur Rahman Rifat,&nbsp;Md. Shamim Bin Shahid,&nbsp;Arnisha Akhter,&nbsp;Md Ashraf Uddin,&nbsp;Khandaker Mohammad Mohi Uddin","doi":"10.1002/eng2.13080","DOIUrl":"https://doi.org/10.1002/eng2.13080","url":null,"abstract":"<p>Diabetes is a chronic metabolic disease characterized by elevated blood glucose levels and poses significant health risks, such as cardiovascular disease and cognitive damage. Understanding the causes of diabetes is crucial to managing it and preventing complications. The clinical community has a lot of diabetes diagnostic data. Machine learning algorithms may simplify finding hidden patterns, retrieving data from databases, and predicting outcomes. To tackle the challenge of designing an improved diabetes classification algorithm that is more accurate, random oversampling and hyper-tuning parameter techniques have been used in this study. Whereas most of the existing methods were built upon considering any single dataset, for getting more acceptability in general, our proposed model has been designed based on two benchmark datasets: the BRFSS dataset, which has multiple classes, and the Diabetes 2019 dataset, which has binary classes. What is more, to improve the comprehensibility of the proposed model, a variety of explainability methodologies such as SHapley Additive Explanations (SHAP), Partial Dependency, and Local Interpretable Model-agnostic Explanations (LIME) have been implemented which are not often noticed in the previous works. The detailed explainability charts will enable the end users or practitioners to understand the exact factors of any given diagnostic report. This research focused on classifying type 2 diabetes using machine learning and providing an explanation for the outcomes derived from the model predictions. Random oversampling and quantile transform are used to rectify imbalances in the dataset and guarantee the resilience of model training. By meticulously adjusting parameters with gridsearchCV, we successfully optimized our models to attain exceptional accuracy across binary and multi-class datasets. We evaluate the proposed model using two datasets and performance metrics. The extra trees classifier (ET) performed exceptionally, achieving 97.23% accuracy on the multi-class dataset and 97.45% on the binary dataset.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-12-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.13080","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143114211","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Thermal Runaway Detection Method for Smart Electric Bicycle Charger","authors":"Jing Ning,&nbsp;Bing Xiao,&nbsp;Wenbin Zhao","doi":"10.1002/eng2.13082","DOIUrl":"https://doi.org/10.1002/eng2.13082","url":null,"abstract":"<p>A novel algorithm for thermal runaway detection embedded in the electric bicycle charging system is proposed. The battery's internal temperature is a key indicator to diagnose battery safety and monitor the charging state. First, the relationship between the battery's internal temperature and the impedance's phase shift is derived theoretically. Second, given that random interference in the charging current, the current area integration algorithm (CAIA) is presented to measure the phase shift, so the internal temperature is estimated. Third, the smart charging system for electric bicycles is presented and results are discussed. The results show that the phase shift increases with the internal temperature in the range of 200–600 Hz when the internal temperature is 20°C–35°C. When the internal temperature reaches 45°C, the phase shift decreases sharply with the internal temperature. Therefore, smart electric bicycle charger realizes thermal runaway detection of electric bicycle.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-12-11","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.13082","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143113922","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Improvement of Concrete Construction Work Performance Through Employment of Lean Logistics Principles","authors":"Zuzana Strukova,&nbsp;Maria Kozlovska,&nbsp;Alena Tazikova","doi":"10.1002/eng2.13067","DOIUrl":"https://doi.org/10.1002/eng2.13067","url":null,"abstract":"<p>In logistics systems, the use of methods, approaches, and management procedures with the aim of optimizing all activities has increasingly been promoted. In the case studies, the logistics of the concrete construction work during the implementation of concrete frame structures of residential building projects is analyzed. The examination of the logistics of concrete construction work was carried out using a combination of monitoring, measurement, comparison, and modeling methods. In addition to obtaining real data on the mentioned logistics of concrete construction work, by applying the Just in Time method, as one of the methods of lean logistics, the optimal logistics of ready-mix concrete transport to construction sites was simulated. In order to reveal the most significant wastages during concrete construction work, the essential parameters of real logistics were compared with the parameters of simulated optimal logistics of ready-mix concrete transport. The goal of the research is to evaluate the intensity of the application of logistics and its elements in the implementation of construction and to point out the importance of the involvement of lean production methods and thus also lean logistics in the construction industry. Based on this study results from construction projects in Slovakia and also based on the experience of the authors of this work, it can be concluded that the use of logistic management in the supply of the main construction material in the production of monolithic concrete structures is poor, and this causes a lot of unnecessary waste, having an adverse effect not only on the construction time, but also on the management of individual construction resources. It has been proven that investment in planning and management of logistics can lead to increased overall efficiency of the construction and can bring profit in the form of system, synchronization of construction process resources.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-12-10","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.13067","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143113940","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Structural Behavior of Reinforced Fibrous Concrete Beams Incorporating Nano Silicon Dioxide Powder","authors":"Sheelan Mahmoud Hama,&nbsp;Enas Faeq Hamadi,&nbsp;Ali Jahami","doi":"10.1002/eng2.13078","DOIUrl":"https://doi.org/10.1002/eng2.13078","url":null,"abstract":"<p>This research investigated the combined effect of nano-silicon dioxide (NSD) and steel fibers (SF) on the structural behavior of reinforced concrete beams. Eight specimens were tested: four without SF and four with SF, with varying NSD percentages (1%, 2%, and 3%) replacing cement. The study examined the mechanical properties of concrete and structural behavior outputs, including load-deflection, ductility, and damage patterns. Results indicate that NSD significantly enhances compressive strength, with increases of 8.7%, 25.2%, and 32.5% for 1%, 2%, and 3% NSD, respectively. Combined with SF, there are additional improvements in tensile and flexural strengths, leading to higher load capacity and reduced deflection. Beams with 1% steel fibers showed a 30% higher load capacity compared with those without fibers. The ACI code was found to underestimate the load capacity of beams with NSD and SF, indicating the need for updated equations. While NSD increased concrete brittleness, SF enhanced ductility and energy absorption. Future research should focus on optimizing NSD and SF dosages, studying long-term durability, and validating findings through large-scale tests.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.13078","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143113349","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluating Machine Unlearning: Applications, Approaches, and Accuracy","authors":"Zulfiqar Ali,&nbsp;Asif Muhammad,&nbsp;Rubina Adnan,&nbsp;Tamim Alkhalifah,&nbsp;Sheraz Aslam","doi":"10.1002/eng2.13081","DOIUrl":"https://doi.org/10.1002/eng2.13081","url":null,"abstract":"<p>Machine learning (ML) enables computers to learn from experience by identifying patterns and trends. Despite ML's advancements in extracting valuable data, there are instances necessitating the removal or deletion of certain data, as ML models can inadvertently memorize training data. In many cases, ML models may memorize sensitive or personal data, raising concerns about data privacy and security. Machine unlearning (MU) techniques offer a solution to these concerns by selectively removing sensitive data from trained models without significantly compromising their performance. Similarly, we can analyze and evaluate whether MU can successfully achieve the “right to be forgotten.” In this paper, we investigate various MU approaches regarding their accuracy and potential applications. Experiments have shown that the data-driven approach emerged as the most efficient method in terms of both time and accuracy, achieving a high level of precision with a minimal number of training epochs. When fine-tuning, the full test error rises somewhat to 14.57% from the baseline model's 14.28%. One approach shows a high forget error of 99.90% with a full test error of 20.68%, while retraining yields a 100% forget error and a test error of 21.37%. While error-minimizing noise preserves performance, the SCRUB technique results in a 21.08% test error and an 81.05% forget error, in contrast to the degradation brought on by error-maximizing noise. On the other hand, the agnostic approach displayed sluggishness and generated less accurate results compared to the data-driven approach. Furthermore, the choice of approach may depend on the unique requirements of the task and the available training resources.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.13081","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143113350","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Enhancing System Capacity Through Joint Space-Ground Multi-Beam Coordination for LEO Satellite Systems","authors":"Yuyang Liu,&nbsp;Tong Shi,&nbsp;Hua Wang","doi":"10.1002/eng2.13052","DOIUrl":"https://doi.org/10.1002/eng2.13052","url":null,"abstract":"<p>Due to the long transmission distance of the constellation network represented by the low-orbit satellite system, the satellite-to-ground link is subject to large path loss and limited communication performance. This paper uses multi-satellite and multi-beam joint transmission technology to form a virtual multiplex network with ground multi-antenna terminals (Multiple-Input Multiple-Output [MIMO] system). However, due to the high-speed movement of satellites, the topology of the MIMO system is unstable, which in turn affects the stability of the system throughput. This article proposes two inter-satellite cooperation modes to improve the stability of MIMO system capacity. The first method is to optimize the channel capacity by rationally allocating the beam power of the gateway station so that the gateway station can achieve transparent forwarding through satellites. The second method rotates the angle of the user's receiving antenna to combat channel changes caused by changes in satellite position. Simulation results show that both methods can effectively improve the minimum channel capacity. Transparent forwarding can increase the capacity by about 22.7%, while the rotating antenna can still improve the performance gain by at least 36.3% even with a limited rotation angle. This research contributes to the development of stable and efficient communication systems in satellite-ground cooperative networks.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-12-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.13052","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143113553","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Non-Autoregressive Translation Algorithm Based on LLM Knowledge Distillation in English Corpus","authors":"Fang Ju,&nbsp;Weihui Wang","doi":"10.1002/eng2.13077","DOIUrl":"https://doi.org/10.1002/eng2.13077","url":null,"abstract":"<p>Although significant advancements have been made in the quality of machine translation by large-scale language models, their high computational costs and resource consumption have hindered their widespread adoption in practical applications. So this research introduces an English corpus-based machine translation algorithm that leverages knowledge distillation from large language model, with the goal of enhancing translation quality and reducing the computational demands of the model. Initially, we conducted a thorough analysis of the English corpus to identify prevalent language patterns and structures. Following this, we developed a knowledge distillation approach that transfers the translation expertise of a large teacher model to a smaller student model, thereby achieving increased translation accuracy and efficiency. We designed a dynamic temperature hyperparameter distillation strategy that effectively enhances the precision of translations. In the experimental phase, we utilized several standard English corpora to train and assess our algorithm. The findings indicate that, compared to current machine translation systems, our method significantly reduces the need for computational resources while preserving translation quality.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-12-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.13077","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143113043","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Barkhausen Noise- and Eddy Current-Based Measurements for Online Detection of Deformation-Induced Martensite During Flow Forming of Metastable Austenitic Steel AISI 304L","authors":"Julian Rozo Vasquez,&nbsp;Hanigah Kanagarajah,&nbsp;Bahman Arian,&nbsp;Lukas Kersting,&nbsp;Werner Homberg,&nbsp;Ansgar Trächtler,&nbsp;Frank Walther","doi":"10.1002/eng2.13070","DOIUrl":"https://doi.org/10.1002/eng2.13070","url":null,"abstract":"<p>This paper deals with micromagnetic measurements for online detection of strain-induced α′-martensite during plastic deformation of metastable austenitic steel AISI 304L. The operating principles of the sensors are magnetic Barkhausen noise (MBN) and eddy currents (EC), which are suitable for detection of microstructure evolution due to formation of ferromagnetic phases. The focus of this study was put on the qualification of different micromagnetic techniques and different measurement systems under conditions similar to the real ones during production, which is crucial for implementation of a property-controlled flow forming process. The investigation was carried out on tubular specimens produced by flow forming, which have different content of α′-martensite. To characterize the sensitivity of the sensors, different contact conditions between sensors and workpieces were reproduced. MBN sensors are suitable for detecting amount of α′-martensite, but the measurements are affected by the surface roughness. This entails that the calibration models for MBN sensors must take account of these effects. EC sensors show a closer match with the amount of α′-martensite without having major affectation by other effects.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.13070","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143112582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Research on the Impact of Coastal Land Reclamation on Geomorphic Complexity and Tidal Energy Dissipation—A Case Study of Zhoushan Islands, Hangzhou Bay","authors":"Shixia Zhang,&nbsp;Qiankun Hong,&nbsp;Huifang Guo","doi":"10.1002/eng2.13075","DOIUrl":"https://doi.org/10.1002/eng2.13075","url":null,"abstract":"<p>Coastal mudflats are vital land resources. In recent years, coastal reclamation has emerged as a vital strategy for alleviating coastal land supply shortages and for developing marine resources in coastal areas. However, large-scale coastal reclamation changes the natural landscape properties of sea areas, triggering alterations in the surrounding hydrodynamic and ecological environments. Despite the significant impact of coastal geomorphic features on tidal energy loss and disaster prevention, few studies have explored the intrinsic connection between the complexity of coastal landscapes and the rate of tidal reduction. This relationship is crucial for predicting potential tidal energy loss responses to large-scale changes in geomorphologic features caused by accelerating coastal land reclamation. This study focuses on Hangzhou Bay as the research area and develops a model that combines the correlation between the rate of tidal reduction and the complexity of coastal landscapes. The model is constructed using fractal geometry theory and quantitative methods, while also incorporating principles from ocean dynamics theory. The model is applied to assess the impacts of reclaimed land on the geomorphic complexity and tidal energy dissipation in the Zhoushan Islands. Results indicate a high correlation between differential tide reduction rates and coastal geomorphic complexity. Application of this model reveals that traditional reclamation planning and design substantially alter coastal morphology. Consequently, the significant reduction in the fractal dimension (D) and shape index (<i>S</i>) leads to a tidal reduction rate decrease of over 88%, posing substantial threats to coastal and estuarine bay disaster prevention and ecosystem services. The study proposes effective control indicators and scientific reclamation planning measures, providing a theoretical basis and novel methods for the rational utilization and sustainable development of coastal mudflat resources.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.13075","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143112796","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design of Hybrid Renewable Energy Systems: Integrating Multi-Objective Optimization Into a Multi-Criteria Decision-Making Framework","authors":"Tebello Ntsiki Don Mathaba,&nbsp;Khaled Abo-Al-Ez","doi":"10.1002/eng2.13074","DOIUrl":"https://doi.org/10.1002/eng2.13074","url":null,"abstract":"<p>Research into hybrid renewable energy systems (HRESs) fulfills the need for the development of sustainable and environmentally friendly energy systems to supply house-holds. The design of HRESs is a challenging endeavor requiring the optimization of multiple objectives considered over multiple criteria. This paper presents a new multi-criteria decision-making framework (MCDM) to automate the design. The proposed framework initially uses a metaheuristic multi-objective (MO) optimization algorithm to generate optimal candidate configurations and then objectively evaluates candidates to select the best configuration. A combination of the MO particle swarm optimization and a newly developed MO leaders-and-follower algorithms (MO-LaF/PSO) is used to generate optimal configurations based on minimal levelized cost of energy (LCOE), renewable energy (RE) power abandonment, and CO2 emissions, while maintaining an acceptable level of reliability. The evaluation phase applies the VIKOR (VIseKriterijumska Optimizacija I Kompromisno Resenje) ranking method that uses objective criteria weights calculated using MEREC (MEthod based on the Removal Effects of Criteria). This method is applied to a case-study of an off-grid Wind/PV/Diesel/Battery HRES. The results reveal that this newly proposed framework generates a unique top-ranking configuration with an LCOE of 0.199 $/kWh, 0% wastage of RE, and 982 tons of CO₂.</p>","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 1","pages":""},"PeriodicalIF":1.8,"publicationDate":"2024-12-07","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.13074","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143112583","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}