http://ijaers.com/ Open Access international Journal to publish research paper en-us Faced with growing electricity demand, the frequency regulation capacity of traditional thermal power units is limited and difficult to meet the current power system. Combining thermal power units with energy storage facilitates flexibility upgrades by leveraging the ultra-fast response characteristics inherent to such system. The method of joint dispatching of thermal power and energy storage systems is called combined thermal and energy storage. This study develops a theoretical model of thermal-storage combined frequency regulation to analyze system dynamic responses. Combining lithium battery and flywheel energy storage systems with 1000MW thermal power units, a simulation model for dynamic frequency regulation and peak shaving was built in MATLAB/Simulink. The simulation experiments showed that the cooperative control strategy could enhance frequency regulation capacity and also improve the stability of thermal power units. http://ijaers.com/detail/comparison-of-thermal-storage-combined-power-generation-with-traditional-thermal-power-frequency-modulation-and-generator-output/ Lei Huang, Qiang-Sheng Xiao, Yan-Zuo Chang http://ijaers.com/uploads/issue_files/2IJAERS-0720266X-Comparison.pdf Fruit diseases impact global agricultural output, quality, and sustainability. Manual visual inspection by agricultural experts is time-consuming, subjective, and inaccurate, especially in large-scale farming. AI and DL have shown promise in automating plant disease diagnosis using image-based analysis. In particular, Convolutional Neural Networks (CNNs) can extract complicated visual characteristics and accurately diagnose disease signs. A CNN-based system for fruit disease diagnosis and symptom identification utilizing image-based datasets is proposed in this paper. The study aims to create an automated system that can efficiently classify healthy and unhealthy fruits and identify illness symptoms using visual interpretation. We use picture collections of healthy and damaged fruit samples from agricultural libraries. Data augmentation, normalization, and scaling were performed on images. Multiple convolutional, pooling, batch normalization, and fully connected layers in a TensorFlow-Keras CNN architecture learn disease-specific characteristics. Analyses include accuracy, precision, recall, F1-score, and confusion matrix analysis after Adam optimizer training. Gradient-weighted Class Activation Mapping (Grad-CAM) visualizes classification-influencing symptom areas. According to the analysis, the suggested framework has 96.4% classification accuracy, precision, recall, and F1-score values above 95%. The Grad-CAM visualizations show disease-affected lesions, spots, discolouration, and rotting areas, improving model interpretation. Analysis shows that the CNN framework outperforms traditional machine learning and rudimentary deep learning models. In conclusion, the suggested framework for automated fruit disease diagnosis and symptom identification is accurate, dependable, and explainable. The study shows that CNN-based systems can aid precision agriculture, crop health monitoring, and disease management. http://ijaers.com/detail/a-hypothetical-cnn-based-framework-for-disease-detection-and-symptom-identification-using-image-based-datasets/ S. Saleth Shanthi, Dr. M. P. Indra Gandhi http://ijaers.com/uploads/issue_files/1IJAERS-0720264X-AHypothetical.pdf The digital representation of a logistics warehouse within Enterprise Resource Planning (ERP) systems, particularly Warehouse Management Systems (WMS), is mainly based on operational data and warehouse activities. While these systems help improve inventory management, reduce operational costs, shorten delivery times, and increase distribution efficiency, they do not provide a mathematical representation of the warehouse's physical space. As a result, researchers have limited support for developing and testing optimization methods that depend on the spatial organization of the warehouse. This research proposes a mathematical three-dimensional (3D) grid model in which each storage cell is represented by its spatial coordinates and an associated weight. The proposed model provides a simple and generic digital representation of a logistics warehouse that can be used as a basis for research on warehouse optimization, including storage allocation, routing, robot navigation, and space utilization. http://ijaers.com/detail/a-grid-based-spatial-representation-of-logistics-warehouses-using-3rd-order-tensors/ Zine El Abidine Falouti http://ijaers.com/uploads/issue_files/3IJAERS-0820263-AGrid.pdf Accurate thermal field prediction is essential for optimizing battery thermal management systems and preventing thermal runaway of lithium battery modules. Traditional thermal prediction methods, including experimental measurement, numerical simulation, and pure data-driven modeling, suffer from obvious limitations such as heavy data dependence, high computational consumption, and poor physical interpretability. To address these issues, this paper develops a multi-physics constrained three-dimensional transient thermal field prediction framework for lithium battery modules based on physics-informed neural networks. The framework integrates transient heat conduction principles and couples Joule irreversible heat and entropy reversible heat to characterize internal heat generation. On the basis of conventional thermal boundary and initial constraints, charge consistency and material interface continuity constraints are innovatively introduced to optimize the loss function, combined with efficient training optimization strategies. The results indicate that the proposed mesh-free framework can achieve high-precision full-domain thermal field reconstruction using only sparse temperature data. It strictly complies with fundamental heat transfer and charge conservation laws, adapts to complex battery module structures, and provides an effective solution for fast, accurate thermal prediction of lithium batteries under sparse sensor working conditions. http://ijaers.com/detail/research-on-thermal-field-prediction-method-of-lithium-battery-module-based-on-pinn/ Qiang-Sheng Xiao, Yan-Zuo Chang, Lei Huang http://ijaers.com/uploads/issue_files/4IJAERS-0820261-Research.pdf With the deepening of the Belt and Road Initiative, cultural exchange between China and Bangladesh has intensified, and the number of Bangladeshi students in China continues to grow. China's high-speed rail network is the primary mode of transport for these students, yet the official ticketing platform, the 12306 app, exhibits clear shortcomings in cross-cultural usability. This study takes Bangladeshi international students as its research subject and, through in-depth interviews, literature review, and competitive analysis, systematically identifies five major pain points these users encounter with 12306: cumbersome registration and passport verification, incomplete English translation, restricted payment options, difficulty navigating stations, and excessive interface information density. Interviewees consistently reported that language barriers and uncertainty surrounding identity verification generated persistent use-related anxiety. Building on these findings, the study applies Hofstede's cultural dimensions theory to trace the cultural roots of these pain points across six dimensions and derives five design principles: step-by-step guidance, instant feedback, transparent trust, explicit expression, and multilingual support. An HTML interactive prototype comprising seven core screens was developed, alongside a conversational agent, "Railway Assistant," built on the Coze platform to deliver step-by-step guidance and Bengali greetings. Evaluation via 31 questionnaires showed that 93.5% of respondents endorsed the step-by-step registration flow, and the passport-login entry point and multilingual switching received highly positive ratings; unexpectedly, more than 70% of respondents regarded the AI assistant as a core requirement. This research systematically introduces Hofstede's cultural dimensions theory into railway app design, establishes a mapping framework linking cultural dimensions, user pain points, and design elements, and validates the effectiveness of the resulting cross-cultural design principles through the Coze-based agent. http://ijaers.com/detail/a-cross-cultural-design-study-of-a-railway-app-for-bangladeshi-international-students-in-china/ Rahman Md Ataur, Wang Xiaoxia http://ijaers.com/uploads/issue_files/5IJAERS-0820264-ACross.pdf Accurate brain age estimation from structural MRI serves as a sensitive biomarker of neurological health. We propose NeuroFusion, a unified framework that addresses two fundamental limitations of existing approaches: vanishing gradients in deep 3D architectures and poor generalization across clinical settings with limited labelled data. NeuroFusion combines (1) dual-objective self-supervised pretraining (SimCLR + MAE) on 42,000 unlabeled volumes, (2) a 3D Vision Transformer backbone, (3) a cross-modal fusion module integrating demographic metadata, and (4) deeply-supervised multitask learning with uncertainty-weighted loss balancing. On the OpenBHB benchmark (N=3,966 healthy controls), NeuroFusion achieves state-of-the-art brain age prediction (MAE = 2.84 years). Crucially, in few-shot adaptation to unseen sites, NeuroFusion maintains strong performance with only 5 labelled examples, demonstrating clinically relevant generalization. http://ijaers.com/detail/brain-age-prediction-via-self-supervised-multitask-learning-with-cross-modal-fusion/ Molla Md Rony, Rahman Md Takibur, Meheraj Hossain Dipu, Jubayer Ahmad Nurshi http://ijaers.com/uploads/issue_files/6IJAERS-0720263X-Brain.pdf Across Pakistan's creative capitals of Lahore, Karachi, and Islamabad, a quiet but profound shift is taking place as emerging designers repurpose discarded and reclaimed textiles into outfits with renewed worth and purpose a method known as upcycled apparel design. To explain what motivates this conduct, this research draws on Ajzen's Theory of Planned conduct, exploring how designers' attitudes, the social norms around them, and their sense of control over the practice come together to determine their purpose to upcycle. The study reveals a rich and frequently unexpected picture thru 30 in-depth interviews with designers and a thorough thematic analysis: designers' attitudes toward upcycling are deeply rooted in inherited craft traditions passed down thru generations, giving the practice a distinct moral and cultural weight, rather than in trendy sustainability language. At the same time, social perceptions remain divided while some families still identify reused materials with financial difficulty, a newer generation of design-school graduates is redefining sustainability as a badge of professional competence and artistic difference. Yet even with great desire and shifting perceptions, designers confront genuine challenges to putting their intentions into effect, particularly a fragmented supply chain for waste materials and a decreasing pool of craftspeople with the specialist skills needed to work with salvaged fabrics. Beyond the three primary motivations, the research reveals two additional forces affecting this environment the pull of cultural legacy and the fragility of the living craft infrastructure that upcycling depends on offering unique dimensions to extend how we interpret sustainable design behaviour. Together, these insights provide one of the first grounded, in-depth accounts of how Pakistani designers incorporate belief, tradition, and constraint into everyday practice, with important implications for how design education is taught, artisan communities are supported, and future textile-waste systems can be built. http://ijaers.com/detail/extending-theory-of-planned-behaviour-tpb-cultural-inheritance-and-craft-fragility-in-pakistan-s-upcycled-fashion-movement/ Um E Ammara, Worku Nigusie Libekunu, Prof Zhang Zhe http://ijaers.com/uploads/issue_files/7IJAERS-0820265-Extending.pdf