Hasan Erbay, Yassen Mohamed Abulgasim, Doğan Eren Özer, Fatih Ertürk
{"title":"Enhancing multi-class skin lesion diagnosis through ensemble learning of CNN and transformer architectures","authors":"Hasan Erbay, Yassen Mohamed Abulgasim, Doğan Eren Özer, Fatih Ertürk","doi":"10.1016/j.jestch.2025.102145","DOIUrl":"10.1016/j.jestch.2025.102145","url":null,"abstract":"<div><div>Skin cancer remains one of the most prevalent forms of cancer worldwide, highlighting the critical need for accurate and automated diagnostic systems to support early detection and improve patient outcomes. This study presents a deep learning-based framework for multi-class classification of dermoscopic skin lesion images using the HAM10000 dataset. A range of state-of-the-art convolutional neural networks (CNNs) — including DenseNet201, InceptionResNetV2, and Xception — were evaluated under both frozen and fully fine-tuned configurations. Additionally, the performance of Vision Transformer (ViT) architectures was assessed to examine their potential in skin lesion analysis. To enhance classification performance, ensemble learning strategies — namely hard voting, soft voting, and weighted soft voting — were implemented. Experimental results indicate that fully fine-tuned models outperform their frozen counterparts, with InceptionResNetV2(full) achieving the best individual performance with accuracy of 0.88% and F1-score of 0.77%. The highest overall performance was obtained using the proposed weighted soft voting ensemble, yielding an accuracy of 0.89% and an F1-score of 0.80%. These findings demonstrate the effectiveness of ensemble methods and transfer learning based models in advancing automated skin lesion classification. Moreover, the results highlight the potential and limitations of each architecture in clinical applications and provide valuable insights for future research in computer-aided dermatological diagnosis.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"70 ","pages":"Article 102145"},"PeriodicalIF":5.1,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144713614","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}
{"title":"Advancing sustainable shipbuilding through a hybrid risk prioritization model: integrating FMEA and machine learning","authors":"Ahmet Fatih Yılmaz , Ozan Köse","doi":"10.1016/j.jestch.2025.102158","DOIUrl":"10.1016/j.jestch.2025.102158","url":null,"abstract":"<div><div>Effective risk management is critical in modern shipbuilding, where production complexity continues to grow. Traditional Failure Modes and Effects Analysis (FMEA), despite its widespread use, often lacks objectivity and scalability. This study introduces a novel hybrid methodology that integrates FMEA with machine learning (ML), specifically, Random Forest (RF) regression, to enhance failure prediction and defect prioritization within a real-world shipyard context. The model was trained on 489 documented defects from the construction of an LNG-powered fishing vessel at Cemre Shipyard. Each defect was assessed using four risk factors: cost, time, frequency, and stage. Risk Priority Numbers (RPNs) were computed accordingly and used as target values in model training. The framework also incorporates Pareto analysis and feature importance evaluations to identify dominant risk contributors. The ML model achieved high predictive accuracy (Coefficient of Determination (R<sup>2</sup>) = 0.9738; Mean Absolute Error (MAE) = 1.3470) under current operational conditions. Deformation, inappropriate production, and defective part usage were identified as the most critical categories. Time loss and frequency emerged as the most significant features influencing RPNs. Improvement scenarios revealed the model’s robustness and capacity to estimate risk reduction potential for high-priority failure modes. This hybrid approach bridges expert judgment with data-driven intelligence and offers a scalable, objective framework for real-time quality control. Its potential for integration with enterprise systems suggests broader industrial applications, including automated risk monitoring and continuous improvement. The results demonstrate that combining FMEA with ML can significantly advance predictive defect management in maritime manufacturing.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"70 ","pages":"Article 102158"},"PeriodicalIF":5.1,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144713631","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}
Shahid A. Hasib , Muhammad Majid Gulzar , Sumaiya Rahman Oishy , Muhammad Maaruf , Salman Habib , Adnan Shakoor
{"title":"An investigation of innovative strategies in underwater soft robotics","authors":"Shahid A. Hasib , Muhammad Majid Gulzar , Sumaiya Rahman Oishy , Muhammad Maaruf , Salman Habib , Adnan Shakoor","doi":"10.1016/j.jestch.2025.102123","DOIUrl":"10.1016/j.jestch.2025.102123","url":null,"abstract":"<div><div>Soft robotics has become a transformative technology for underwater applications, providing distinct advantages such as flexibility, adaptability, and safe interactions with fragile environments. This review offers a comprehensive analysis of the latest developments in actuation mechanisms, intelligent materials, fabrication methods, and control strategies specific to underwater soft robotics. It highlights key challenges like material degradation, energy efficiency, and control in dynamic aquatic conditions. Noteworthy advancements include bio-inspired actuators that mimic marine life and the integration of smart materials to enhance responsiveness and durability. Unlike previous reviews that focused on general aspects, this paper emphasizes cutting-edge soft actuator technologies and interdisciplinary applications that address challenges in complex aquatic environments with greater precision. Additionally, innovative fabrication techniques such as 3D printing and soft lithography are explored, revolutionizing the design and construction of underwater robots. The review also identifies critical gaps in current research and suggests future directions, stressing the importance of interdisciplinary approaches to tackle the complexities of underwater environments. It serves as a valuable resource for researchers and professionals seeking to advance the field and its applications.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"70 ","pages":"Article 102123"},"PeriodicalIF":5.1,"publicationDate":"2025-07-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144713630","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}
{"title":"Transformer differential protection with wavelet transform and difference function","authors":"Merve Oztekin , Serap Karagol , Okan Ozgonenel","doi":"10.1016/j.jestch.2025.102144","DOIUrl":"10.1016/j.jestch.2025.102144","url":null,"abstract":"<div><div>The Transformer Differential Protection (TDP) algorithm instantly compares the target transformer’s terminal currents for each phase. The differential current is not expected to appear during regular operation. However, nonlinear characteristics of the core material, such as the hysteresis curve, result in significant variation in the differential current, known as magnetizing inrush current. This inrush current lasts for a while before disappearing, causing significant variation in the differential current. TDP algorithm is supposed to remain silent during this transient time (selectivity). In addition, one of the most difficult tasks for protection systems is detecting inter-turn faults in their early stages. This fault type typically begins at low levels due to moisture, high temperature, and so on, and gradually spreads to other turns. It is vital to detect inter-turn faults before they expand more than 10% of total windings [RW-2-1]. This paper presents a transformer differential protection algorithm that distinguishes between inter-turn, low-level internal faults, and inrush current. Maximum Overlapped Discrete Wavelet Transform (MODWT) energy and difference function are used for feature extraction, and the traditional 87T TDP method has been updated. Performance is evaluated using data collected from a laboratory-based experimental rig. The results demonstrate that the suggested approach performs very well in a range of low-level, inter-turn fault, and transient scenarios, including internal fault, inrush current, and sympathetic inrush current. These results are confirmed by the identified indices for Accuracy (AC), Dependability (DP), and Selectivity (SE).</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"70 ","pages":"Article 102144"},"PeriodicalIF":5.1,"publicationDate":"2025-07-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144712896","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}
{"title":"Front Matter 1 - Full Title Page (regular issues)/Special Issue Title page (special issues)","authors":"","doi":"10.1016/S2215-0986(25)00209-5","DOIUrl":"10.1016/S2215-0986(25)00209-5","url":null,"abstract":"","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"69 ","pages":"Article 102154"},"PeriodicalIF":5.1,"publicationDate":"2025-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144704009","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}
Csenge Tóth , Ábris Dávid Virág , István Halász-Kutasi , Norbert Krisztián Kovács , Tamás Bárány
{"title":"Additive manufacturing of thermoset elastomers: A review of emerging technologies","authors":"Csenge Tóth , Ábris Dávid Virág , István Halász-Kutasi , Norbert Krisztián Kovács , Tamás Bárány","doi":"10.1016/j.jestch.2025.102143","DOIUrl":"10.1016/j.jestch.2025.102143","url":null,"abstract":"<div><div>Thermoset elastomers (TSEs) are widely used in industries such as automotive, household appliances, healthcare, and fashion due to their flexibility and stability. However, these same properties make TSEs challenging to process using additive manufacturing (AM) techniques. This review categorizes AM technologies for producing TSEs into three main groups: photopolymerization-based, two-phase, and material extrusion–based techniques. Photopolymerization offers high resolution and material versatility but is constrained by build size and environmental impacts. Two-phase systems enable tunable properties but suffer from rheological and bonding issues, while material extrusion is more cost-effective yet less precise. Overall, current research primarily concentrates on technology and formulation development. Mechanical characterization of 3D-printed TSEs is typically limited to tensile properties. Comprehensive mechanical testing, including application-specific properties, is still rare and remains an essential area for future qualification of technological advances. The sustainability aspects of 3D printing TSEs are also addressed, with a focus on environmentally friendly raw material selection and the general environmental considerations of 3D printing methods. Emerging trends in this field include the development of smart materials, sustainable solutions, and integrated hybrid methods that incorporate artificial intelligence and machine learning.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"69 ","pages":"Article 102143"},"PeriodicalIF":5.1,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144656542","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}
{"title":"Optimizing multi-objective hybrid energy systems with pumped hydro storage for enhanced stability and efficiency in renewable energy integration","authors":"Junxian Li , Jiaxin Yuan , Xuxin Yue","doi":"10.1016/j.jestch.2025.102142","DOIUrl":"10.1016/j.jestch.2025.102142","url":null,"abstract":"<div><div>Renewable energy sources include the intermittent nature, which is a vital challenge that causes considerable wind and solar energy losses. To address this challenge, this paper introduces a new approach for the optimal multi-objective distribution of a hybrid energy production system. The proposed system comprises hydropower, wind, solar, and thermal energy, which is boosted by pumped hydro energy storage. The investigation primary aim is minimizing the electricity fluctuations’ impact through the renewable enegy sources integration in the large scale. The optimization strategy encompasses a series of complex constraints in term of hydropower plant, in which pumped hydro energy storage provides an accurate flexibity. This stragey aims to improve the overall efficiency and reliability of the hybrid production system. This efficient strategy consists of the inherent complexities, which is solved by the NSGA-II algorithm. The multi-objective approach of optimization procedure performs Pareto solution sets that reflects trade-offs between remaining load variations and operational costs. Therefore, the PROMETHEE-GAIA Method with CRITIC weighting is used to identify the most desirable solutions. The integration of different renewable energy sources provides insights into the dynamic response of the system to various conditions. Significantly, the results emphasize the considerable impact of allocating pumped hydro energy storage in the hybrid energy system, showcasing its potential to significantly reduce operational costs and load fluctuation. These findings are promising for the practical implementation of pumped hydro energy storage in addressing challenges associated with integrating renewable energy sources, thereby contributing to the stability and overall resilience of the power grid.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"69 ","pages":"Article 102142"},"PeriodicalIF":5.1,"publicationDate":"2025-07-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144656543","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}
Soule Issa Loutfi , Ibraheem Shayea , Ufuk Tureli , Ayman A. El-Saleh , Waheeb Tashan , Ramazan Caglar
{"title":"Machine learning for handover decision with mobile edge computing in 6G mobile network: a survey","authors":"Soule Issa Loutfi , Ibraheem Shayea , Ufuk Tureli , Ayman A. El-Saleh , Waheeb Tashan , Ramazan Caglar","doi":"10.1016/j.jestch.2025.102131","DOIUrl":"10.1016/j.jestch.2025.102131","url":null,"abstract":"<div><div>The forthcoming Six-Generation (6G) cellular network promises to provide novel developments in network architecture, offering greater data rates and ultra-low latency, ensuring seamless and reliable connectivity with a high quality of service for a massive number of connected devices. Even though efficient handover decision-making is one of the critical challenges in 6G networks, especially with high mobility scenarios and complex characterization of future networks. The case becomes more critical with the implementation of Mobile Edge Computing (MEC), which will lead to making the handover decision process more challenging due to its characterization and high requirements. This paper presents a systematic review of the handover decision (HOD) with MEC in 6G networks, providing a deep understanding of the most standing challenges and solutions addressing mobility management issues in 6G mobile networks. Moreover, machine learning (ML) and deep learning (DL) technologies are the key promising solutions for intelligent HOD-making in 6G networks with MEC. Therefore, this research work also aims to give a main focus on studying and highlighting the advanced ML methods that can be used to enhance HOD-making in 6G cellular networks with MEC. Furthermore, a comprehensive review of HOD-based ML solutions is provided to enhance the Quality of Service (QoS) of user experience in Heterogeneous Networks (HetNet), instilling confidence in the paper’s findings. Besides, proposed solutions for HODs using ML models with next-generation network requirements and possible technologies are presented. We also describe research challenges and future directions for achieving this study.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"69 ","pages":"Article 102131"},"PeriodicalIF":5.1,"publicationDate":"2025-07-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144656541","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}
{"title":"Effect of scoria powder on the strength and porosity of porous concrete produced with recycled porous concrete aggregate","authors":"Demet Yavuz","doi":"10.1016/j.jestch.2025.102141","DOIUrl":"10.1016/j.jestch.2025.102141","url":null,"abstract":"<div><div>In recent years, there has been a significant increase in the cycle of demolition and reconstruction, driven by the growing demand for housing and urbanization in developing countries. As new buildings are constructed at a rapid pace, the resulting debris from older structures presents a considerable challenge, particularly because of limited storage capacity. This study focused on the production of porous concretes using recycled aggregates. To address the low strength associated with recycled aggregates, 5 % (by weight) of silica fume was incorporated, while scoria was used to replace cement at varying levels of 5 %, 10 %, 15 %, 20 %, 25 %, and 30 % by weight. The research also analyzed the pore structure and distribution within the porous concrete through computed tomography, with an emphasis on its mechanical properties, porosity, and water permeability. The results demonstrate that scoria serves effectively as a binder, successfully substituting for cement. Additionally, the integration of scoria enhanced the compressive strength of the porous concrete after a 120-day curing period, due to pozzolanic reaction caused by scoria, while also reducing water permeability.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"69 ","pages":"Article 102141"},"PeriodicalIF":5.1,"publicationDate":"2025-07-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144631309","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}
{"title":"Time-dependent assessment of aircraft cable current capacity for lightweight design","authors":"Ali Can Yılmaz , Ahmet Akbulut","doi":"10.1016/j.jestch.2025.102136","DOIUrl":"10.1016/j.jestch.2025.102136","url":null,"abstract":"<div><div>This study proposes a time-dependent methodology for determining the current-carrying capacity of aircraft cables, addressing limitations in aviation standards such as AS50881. The aim is to enable more efficient cable selection by accounting for short-term, high-current scenarios — such as engine start-up or actuator engagement — that are typically neglected in existing standards. The proposed model incorporates environmental and operational parameters including ambient temperature, altitude, bundling conditions, and current duration. An empirical formula is developed and experimentally validated using a custom test setup replicating realistic aerospace conditions. Comparative analysis with other approaches demonstrates that the proposed method allows for accurate current rating while enabling significant reductions in cable size and weight. Experimental results indicate that current capacity predictions by AS50881 are conservative by approximately 12%, confirming opportunities for optimization. A case study on a two-pilot aircraft shows that adopting the proposed approach could reduce wiring weight by up to 20%, without compromising safety. This research provides a practical framework for incorporating time-dependent behavior into cable sizing, offering substantial benefits in terms of efficiency, sustainability, and compliance in modern aircraft wiring systems.</div></div>","PeriodicalId":48609,"journal":{"name":"Engineering Science and Technology-An International Journal-Jestech","volume":"69 ","pages":"Article 102136"},"PeriodicalIF":5.1,"publicationDate":"2025-07-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144631308","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}