Engineering reports : open access最新文献_第9页

Reliability Analysis and Optimality for a New Extended Topp-Leone Distribution Based on Progressive Censoring With Binomial Removal 基于二项去除渐进式审查的新型扩展Topp-Leone分布的可靠性分析与最优性

IF 1.8

Engineering reports : open access Pub Date : 2025-06-19 DOI: 10.1002/eng2.70239

Mohammed Elgarhy, Gaber Sallam Salem Abdalla, Ehab M. Almetwally, Mustapha Jobarteh, Amaal Elsayed Mubarak

{"title":"Reliability Analysis and Optimality for a New Extended Topp-Leone Distribution Based on Progressive Censoring With Binomial Removal","authors":"Mohammed Elgarhy, Gaber Sallam Salem Abdalla, Ehab M. Almetwally, Mustapha Jobarteh, Amaal Elsayed Mubarak","doi":"10.1002/eng2.70239","DOIUrl":"https://doi.org/10.1002/eng2.70239","url":null,"abstract":"In this article, a progressive Type II censoring plan with binomial removal is utilized to overcome the estimation issues associated with the truncated Cauchy power-inverted Topp-Leone distribution (TCPITLD). Using maximum likelihood and Bayesian estimation approaches is a means of estimating the unknown parameter. Bayesian estimators are studied using the likelihood function when observed data are produced. This is done by employing the assumption of an informative prior, a gamma prior, and a symmetric loss function. Both of these assumptions are made. In addition, the discussion also includes the approximate confidence intervals obtained by using both the classical technique and the credible intervals with the most significant posterior density. A detailed simulation experiment that considers a variety of sample sizes and censoring techniques is carried out to evaluate the various estimation procedures. A single actual dataset is investigated to validate the effectiveness of the TCPITLD and the estimators provided during the process. The findings indicate that the Bayesian strategy that uses the gamma prior is preferable to both the maximum likelihood technique and the Bayesian approach that uses the informative prior to acquiring the required estimators.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 6","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70239","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144315324","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}

引用次数: 0

Numerical Investigation of the Influence of Welding Parameters on Quality of Laser Welded 304L Stainless Steel Sheets 焊接参数对304L不锈钢板激光焊接质量影响的数值研究

IF 1.8

Engineering reports : open access Pub Date : 2025-06-19 DOI: 10.1002/eng2.70246

Nuepaul D. Kortu, Bruno Roberts, Rehema Ndeda, Abdel-Monem El-Batahgy

{"title":"Numerical Investigation of the Influence of Welding Parameters on Quality of Laser Welded 304L Stainless Steel Sheets","authors":"Nuepaul D. Kortu, Bruno Roberts, Rehema Ndeda, Abdel-Monem El-Batahgy","doi":"10.1002/eng2.70246","DOIUrl":"https://doi.org/10.1002/eng2.70246","url":null,"abstract":"304L Austenitic stainless steel (ASS) is preferred for various industrial applications, including gas, petroleum, petrochemicals, fertilizers, and food processing, due to its inherent corrosion resistance. Traditionally, arc welding processes have been widely used in the manufacturing of 304L austenitic stainless-steel components and structures. However, these methods are more likely to cause carbide precipitation and distortion due to their higher heat input compared to laser welding. Despite its advantages, laser welding requires precise parameters to achieve a suitable weld. In this study, a finite element (FE) model was developed to investigate the impact of laser power and welding speed on the weld quality of 304L ASS with a thickness of 3 mm. The model was validated through experimental methods by using a CO2 laser beam to create a full penetration butt weld. The results indicated that the welding heat input is the main factor influencing the quality of welded joints. Laser power and welding speed of 4 kW and 3 m/min, respectively, improved penetration depth and reduced weld width. These findings provide valuable insights for optimizing laser welding parameters to achieve the desired penetration depth, ensuring high-quality welds in industrial applications.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 6","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-06-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70246","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144315323","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}

引用次数: 0

Sentiment Analysis-Based Model for Monitoring User Engagement With Mental Health Chatbots 基于情感分析的心理健康聊天机器人用户参与监测模型

IF 1.8

Engineering reports : open access Pub Date : 2025-06-18 DOI: 10.1002/eng2.70247

Ian Igado Mmbayi, Consolata Gakii, Faith Mueni Musyoka

{"title":"Sentiment Analysis-Based Model for Monitoring User Engagement With Mental Health Chatbots","authors":"Ian Igado Mmbayi, Consolata Gakii, Faith Mueni Musyoka","doi":"10.1002/eng2.70247","DOIUrl":"https://doi.org/10.1002/eng2.70247","url":null,"abstract":"Mental health challenges, particularly among youth, are compounded by stigma and limited access to professional care. This has driven demand for scalable digital solutions like chatbots. This study introduces a sentiment analysis-based model to assess user satisfaction with mental health chatbots, analyzing 82 102 reviews from six popular apps on Google Play and Apple's App Stores. A multi-class sentiment classification of positive, negative, and neutral was implemented, enhanced by Synthetic Minority Over-sampling Technique for class balancing, comparing five traditional machine learning models with Bidirectional Encoder Representations from Transformers, a transformer model. Random Forest achieved 98.18% accuracy among traditional models, while BERT outperformed all with 99.17% accuracy, surpassing prior benchmarks. Aspect-based analysis revealed that Emotion and Usability drive positive feedback, while Reliability issues fuel negative sentiments, offering actionable insights for developers to enhance chatbot design. This work advances digital mental health research by integrating multi-class classification, transformer models, and aspect-based analysis, demonstrating a scalable framework for evaluating user feedback.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 6","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-06-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70247","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144315272","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}

引用次数: 0

Data Survey of Seismically Isolated Buildings in the Expected Tsunami Inundation Areas in Japan 日本预期海啸淹没地区隔震建筑的数据调查

IF 1.8

Engineering reports : open access Pub Date : 2025-06-17 DOI: 10.1002/eng2.70244

Masahito Kobayashi, Norifumi Hirata

{"title":"Data Survey of Seismically Isolated Buildings in the Expected Tsunami Inundation Areas in Japan","authors":"Masahito Kobayashi, Norifumi Hirata","doi":"10.1002/eng2.70244","DOIUrl":"https://doi.org/10.1002/eng2.70244","url":null,"abstract":"Tsunamis strike frequently around the world, causing enormous damage. Examples include the 2004 Indian Ocean earthquake and tsunami and the 2011 earthquake off the Pacific Coast of Tohoku. Japan is one of the countries most affected by tsunamis. Detailed data about the number of buildings in the expected tsunami inundation areas in Japan—including by use and inundation depth—are therefore useful in planning buildings not only in Japan, but also in other countries where tsunami damage is expected. Among more than 5000 seismically isolated buildings (SIBs) that have been constructed in Japan, however, only a very few were designed with tsunami countermeasures. In some SIBs, tsunamis have even inundated the seismic isolation device. The relationship between the locations planned for future SIBs and the expected tsunami inundation areas is therefore very important. In this work, we have surveyed approximately 1600 SIBs based on design data provided by performance-evaluation organizations and have used the data published by each prefecture to prepare tsunami inundation maps. Our survey results show that Kanagawa and Osaka have large percentages of SIBs constructed in the expected tsunami inundation areas. In addition, the largest percentage of all the SIBs in the expected tsunami inundation areas—40%—has been built in areas where the inundation depth is expected to be 1–3 m. Even buildings like hospitals and government buildings, which must maintain their functions during disasters, have been constructed in areas where the expected inundation depth is 5–10 m.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 6","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70244","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308646","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}

引用次数: 0

In-Depth Analysis of TiNiPdCu High-Temperature Shape Memory Alloys Synthesized Using Powder Metallurgy Technique 粉末冶金法制备tinpdcu高温形状记忆合金的深入分析

IF 1.8

Engineering reports : open access Pub Date : 2025-06-17 DOI: 10.1002/eng2.70245

Abid Hussain, Afzal Khan, M. Imran Khan, Saif Ur Rehman, Fakhre Alam Khan, Asnaf Aziz

{"title":"In-Depth Analysis of TiNiPdCu High-Temperature Shape Memory Alloys Synthesized Using Powder Metallurgy Technique","authors":"Abid Hussain, Afzal Khan, M. Imran Khan, Saif Ur Rehman, Fakhre Alam Khan, Asnaf Aziz","doi":"10.1002/eng2.70245","DOIUrl":"https://doi.org/10.1002/eng2.70245","url":null,"abstract":"The current research work investigates the effect of copper (Cu) addition on the properties of TiNiPdCu-based high-temperature shape memory alloys (HTSMAs) synthesized using powder metallurgy. Shape Memory Alloys (SMAs) with various Cu compositions were prepared and compared to those fabricated using argon arc melting. Microstructural analyses revealed similar characteristics between powder metallurgy and arc melting methods. Scanning Electron Microscope (SEM) observations indicated the presence of second phase precipitates. X-Ray Diffractometry (XRD) analyses confirmed the presence of martensite phases and second-phase precipitates. Texture coefficients indicated changes in lattice constants with Cu addition. Transformation temperatures increased by 30% in solution treatment, 31.57% in annealing, and 33.33% in aging, while thermal hysteresis decreased by 31.3% in solution treatment, 24.56% in annealing, and 24.85% in aging. The results suggest that Cu addition influences the microstructure and transformation behavior of TiNiPdCu SMAs, making powder metallurgy a viable method for their fabrication, with potential applications in high-temperature shape memory applications.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 6","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-06-17","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70245","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144308647","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}

引用次数: 0

Text2SQL Business Intelligence System Based on Retrieval-Augmented Generation (RAG) 基于检索增强生成（RAG）的Text2SQL商业智能系统

IF 1.8

Engineering reports : open access Pub Date : 2025-06-16 DOI: 10.1002/eng2.70249

Jie Liu, Shiwei Chu

{"title":"Text2SQL Business Intelligence System Based on Retrieval-Augmented Generation (RAG)","authors":"Jie Liu, Shiwei Chu","doi":"10.1002/eng2.70249","DOIUrl":"https://doi.org/10.1002/eng2.70249","url":null,"abstract":"Modern enterprises increasingly depend on data-driven decision-making, yet traditional SQL queries require technical expertise, limiting accessibility for nonspecialists. Advances in natural language processing, particularly deep learning generative models, have enabled text-to-SQL (text2SQL) conversion, making database interaction more intuitive. Retrieval-Augmented Generation (RAG) enhances this by integrating retrieval and generation for greater accuracy and relevance. This article proposes a text2SQL business intelligence system based on RAG, allowing enterprise users to extract insights from complex databases using natural language queries. By streamlining data retrieval and lowering technical barriers, the system achieves state-of-the-art performance in generating SQL queries for complex tasks. It leverages the BERT (Bidirectional Encoder Representations from Transformers) model for vectorized retrieval, Generative Pretrained Transformer 4 (GPT-4) for query generation, and Graph Neural Networks (GNNs) for modeling database structures. User interaction and feedback mechanisms further refine semantic understanding and query accuracy. Experimental results demonstrate the system's effectiveness. For multitable joins, query matching accuracy using BERT + GPT-4 + GNN reaches 52.3% and 55.1% with beam widths of 1 and 10, respectively. For nested queries involving multitable joins, accuracy increases to 60.2% and 61.9% under the same conditions. Additionally, the system achieves the highest user satisfaction scores, validating its practical utility. By enhancing the ability to handle complex queries and reducing data access barriers, the proposed RAG-based text2SQL system provides enterprise users with an efficient, user-friendly tool for database interaction, significantly improving decision-making processes.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 6","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70249","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144299954","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}

引用次数: 0

Model-Based Synchronization of Dielectric Elastomers and Membrane Pumps for Performance-Optimized, Space-Efficient, and Application-Specific Pump Design 基于模型的介电弹性体和膜泵同步，用于性能优化、空间效率和特定应用的泵设计

IF 1.8

Engineering reports : open access Pub Date : 2025-06-16 DOI: 10.1002/eng2.70237

M. Baltes, D. Bruch, P. Motzki

{"title":"Model-Based Synchronization of Dielectric Elastomers and Membrane Pumps for Performance-Optimized, Space-Efficient, and Application-Specific Pump Design","authors":"M. Baltes, D. Bruch, P. Motzki","doi":"10.1002/eng2.70237","DOIUrl":"https://doi.org/10.1002/eng2.70237","url":null,"abstract":"This work presents a new approach to designing high-performance and efficient pumps based on dielectric elastomer actuators. By considering the entire system including load from the beginning of the design process, the advantages of dielectric elastomers are specifically utilized to minimize the required space while optimizing performance within that compact volume. The process is model-based, ensuring that every aspect, from individual components to the complete system, is carefully optimized for efficiency and power. In the case of the dielectric elastomer, the modeling approach is simplified by restricting it to cases where viscoelastic effects and time-dependent deformation are not considered. This assumption is justified by the application of clearly defined electromechanical stress limits and the exclusive focus on silicone materials, where such effects are comparatively minor. This approach represents an important step in the use of dielectric elastomer actuators for real-world applications, as the pump is more powerful over a wide working range compared to the state of the art and can therefore be used in applications where conventional pumps are still commonly employed. Although the pump already achieves mechanical performance comparable to conventional systems, it still lacks custom electronics and a smart, efficiency-optimized control system to fully leverage the advantages developed in this work. Addressing this gap forms the basis for future research.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 6","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70237","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144292635","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}

引用次数: 0

Transient Stability Analysis of Wind-Thermal Bundled Systems Under Sequential Filter Removal 序贯滤波下风-热捆绑系统的暂态稳定性分析

IF 1.8

Engineering reports : open access Pub Date : 2025-06-16 DOI: 10.1002/eng2.70219

Di Che, Liang Wang, Xiufeng Han, Enyu Wei

{"title":"Transient Stability Analysis of Wind-Thermal Bundled Systems Under Sequential Filter Removal","authors":"Di Che, Liang Wang, Xiufeng Han, Enyu Wei","doi":"10.1002/eng2.70219","DOIUrl":"https://doi.org/10.1002/eng2.70219","url":null,"abstract":"Addressing issues such as insufficient transient stability and reduced transmission capacity in wind-thermal bundled systems during DC blocking faults, this paper proposes a coordinated control strategy for wind-thermal unit tripping under sequential filter removal. This strategy is based on the principle that retaining partial filters can enhance system stability and aims to improve system stability while reducing total unit tripping. By establishing a grid architecture model for a southwestern region, introducing static stability constraints, transient stability constraints, and filter capacity constraints as stability criteria, the study seeks to minimize the total wind-thermal unit tripping under DC blocking faults. Simulation results demonstrate that when the filter removal amount is 2610 MVar, the total wind-thermal unit tripping in this model is minimized to 3480 MW. This further proves that sequential filter removal can reduce unit tripping, enhance system stability, and improve transmission capacity. These findings provide an important basis for system operation optimization.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 6","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70219","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144292636","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}

引用次数: 0

An Overview of the Impact of Vibrations on Li-Ion Battery Performance, Degradation, Battery Thermal Management System and Key Focus Areas 振动对锂离子电池性能、性能退化、电池热管理系统和重点领域的影响综述

IF 1.8

Engineering reports : open access Pub Date : 2025-06-16 DOI: 10.1002/eng2.70235

Boozula Aravind Reddy

{"title":"An Overview of the Impact of Vibrations on Li-Ion Battery Performance, Degradation, Battery Thermal Management System and Key Focus Areas","authors":"Boozula Aravind Reddy","doi":"10.1002/eng2.70235","DOIUrl":"https://doi.org/10.1002/eng2.70235","url":null,"abstract":"Lithium-ion batteries (LIBs) have gained significant attention in recent years due to their widespread applications in electric vehicles, portable electronics, energy storage, and renewable energy systems. However, their increasing use raises concerns about safety, reliability, and performance under various operating conditions. Among these, the impact of vibrations encountered during transportation, operation in vehicles, and industrial environments on battery performance, state of charge (SoC) and other critical parameters is of particular importance. This study is an overview that focuses on understanding the effects of vibrations on Li-ion batteries (especially cylindrical, pouch, and prismatic cells) through a combination of experimental testing and simulation modeling results. The experimental results highlight the influence of vibration-induced stress on electrical performance and battery degradation behavior. Simulations complement these findings by providing insights into the mechanical and electrochemical responses, effect on battery thermal management systems under different vibration frequencies and amplitudes. By addressing these effects comprehensively, this overview aims to contribute to the design of more robust Li-ion battery systems capable of withstanding dynamic environments. The experimental studies show that discharge capacities were consistently decreasing depending on the cycles, frequencies, and the amplitudes of vibrations; this could be attributed to the separator and graphite anode material degradation. Also, the simulation results showed that the battery temperature management systems will be more effective under vibration conditions.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 6","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70235","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144292637","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}

引用次数: 0

RiceLeafClassifier-v1.0: A Quantized Deep Learning Model for Automated Rice Leaf Disease Detection and Edge Deployment RiceLeafClassifier-v1.0：用于水稻叶片病害自动检测和边缘部署的量化深度学习模型

IF 1.8

Engineering reports : open access Pub Date : 2025-06-16 DOI: 10.1002/eng2.70231

Oluwaseun O. Martins, Christiaan C. Oosthuizen, Dawood A. Desai

{"title":"RiceLeafClassifier-v1.0: A Quantized Deep Learning Model for Automated Rice Leaf Disease Detection and Edge Deployment","authors":"Oluwaseun O. Martins, Christiaan C. Oosthuizen, Dawood A. Desai","doi":"10.1002/eng2.70231","DOIUrl":"https://doi.org/10.1002/eng2.70231","url":null,"abstract":"Rice diseases critically threaten global food security, necessitating rapid, accurate detection methods. This study presents RiceLeafClassifier-v1.0, a lightweight quantized convolutional neural network (CNN) that classifies five rice leaf conditions: blast, bacterial blight, brown spot, healthy, and red stripe, with high accuracy and real-time performance. To improve generalization, the model was trained on 2807 images, 1144 field-collected and 1663 public. Training enhancements included data augmentation, dropout, dynamic learning rate scheduling, and early stopping. Unlike previous transfer learning approaches, RiceLeafClassifier-v1.0 was built from scratch to retain fine visual features while remaining efficient. Quantization reduced model size from 78.03 to 6.51 MB, enabling deployment on edge devices like the Raspberry Pi 4. Statistical validation (p < 0.05) confirmed that RiceLeafClassifier-v1.0 outperforms VGG-16, VGG-19, and ResNet-50, achieving a classification accuracy of 92% compared to 49% (VGG-16), 48% (VGG-19), and 44% (ResNet-50). Post-training quantization further improved accuracy from 92% to 94% (p = 0.0165) while reducing memory usage by 68% (from 82.14 to 26.24 MB, p < 0.0001). Additionally, inference time per image was significantly lower at 2.28 ± 0.35 s for the quantized model compared to 0.01 ± 0.01 s for the standard model (p < 0.0001), demonstrating substantial gains in efficiency. Despite some limitations, including dataset bias and sensitivity to extreme conditions, the model shows very strong and highly promising potential for real-time disease monitoring in precision agriculture. Future work will expand the dataset, adopt advanced optimization techniques, and integrate IoT systems to support smallholder farmers in reducing crop losses and boosting food security.","PeriodicalId":72922,"journal":{"name":"Engineering reports : open access","volume":"7 6","pages":""},"PeriodicalIF":1.8,"publicationDate":"2025-06-16","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1002/eng2.70231","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144292634","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}

引用次数: 0