Intelligent Systems with Applications最新文献

{"title":"Enhancing lung disease diagnosis with deep-learning-based CT scan image segmentation","authors":"Rima Tri Wahyuningrum ,&nbsp;Achmad Bauravindah ,&nbsp;Indah Agustien Siradjuddin ,&nbsp;Budi Dwi Satoto ,&nbsp;Amillia Kartika Sari ,&nbsp;Anggraini Dwi Sensusiati","doi":"10.1016/j.iswa.2025.200565","DOIUrl":"10.1016/j.iswa.2025.200565","url":null,"abstract":"<div><div>The coronavirus disease 2019 (COVID-19) pandemic has underscored the need for efficient diagnostic methods owing to the limitations in sensitivity and time constraints associated with molecular tests such as reverse transcription PCR (RT-PCR). This research aims to enhance the efficiency of COVID-19 and other lung diseases such as pneumonia, tuberculosis, bronchitis, emphysema, asthma, and others diagnoses. As an alternative diagnostic, we considered an approach based on enhanced computed tomography (CT) scan images using deep learning (DL). However, we propose a preprocessing segmentation method to enhance the accuracy of DL-based classification that uses the UNet++ architecture, an encoder-decoder approach in DL. In this architecture, the encoder reduces the image resolution to extract informative feature maps while the decoder returns the resolution to the original size. UNet++ is available in four levels: UNet++ L1, L2, L3, and L4, and its performance is compared to that of several other models, including SegNet, FCANet, and DeepLabV3+. Using two different datasets, RSPHC (Indonesia) and Kaggle, testing was conducted to determine the model with the optimum performance. The criteria used to evaluate model performance included the Dice coefficient and IoU metrics, most efficient computational time, and minimal resource requirements (measured by trainable parameters). The UNet++ L4 model achieved a Dice coefficient of 0.994, IoU of 0.989, computational time of 0.925 s, and 9.16 million trainable parameters on the RSPHC dataset. Whereas on the Kaggle dataset it achieved a Dice coefficient of 0.961, IoU of 0.930, computational time of 1.189 s, and 9.16 million trainable parameters. Therefore, the UNet++ L4 model is ideal for accurate segmentation, computational efficiency, and affordable resource requirements. Thus, this research improves lung disease diagnosis through enhanced CT scan images using DL.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"27 ","pages":"Article 200565"},"PeriodicalIF":4.3,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144766984","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"The Role and Applications of Semantic Interoperability Tools and eXplainable AI in the Development of Smart Food Systems: Findings from a Systematic Literature Review","authors":"Donika Xhani,&nbsp;Gayane Sedrakyan,&nbsp;Anand Gavai,&nbsp;Renata Guizzardi,&nbsp;Jos van Hillegersberg","doi":"10.1016/j.iswa.2025.200547","DOIUrl":"10.1016/j.iswa.2025.200547","url":null,"abstract":"<div><div>Smart food systems generate vast and diverse data across the supply chain, yet inconsistent data structures and limited interoperability hinder their full potential. Achieving semantic interoperability, where systems can exchange and interpret data with shared meaning, is essential for enabling intelligent integration and decision-making. Tools such as ontologies, knowledge graphs, and reasoning engines play a key role in this process. In this paper, we refer to these as <em>Semantic Interoperability (SI) tools</em>: a broad category that includes technologies grounded in Semantic Web standards (e.g., RDF, OWL, SPARQL) but emphasizes their applied role in aligning meaning across heterogeneous systems. Coupled with eXplainable Artificial Intelligence (XAI), these technologies enhance transparency and trust in AI-driven decisions, such as personalized food recommendations tailored to an individual’s health conditions and preferences. This paper presents a Systematic Literature Review (SLR) examining the role of semantic interoperability tools and XAI in the development of smart food systems. Through an analysis of 39 studies, the review identifies key semantic technologies and XAI methods used in food systems, with a focus on their application in intelligent food recommendation systems. The findings reveal that while significant progress has been made, current systems often lack adequate transparency and personalization, limiting user trust and engagement. To address these gaps, the paper proposes the integration of semantic interoperability tools with XAI to create smarter, more reliable food systems. As part of this effort, the paper introduces the conceptual model for the Semantic Explainable Food Recommendation Ontology (SEFRO), a work-in-progress ontology, designed to connect entities and relationships within food systems in an intelligent manner, with the goal of enabling personalized, explainable, and interoperable food recommendations that meet the growing demands for smart food systems.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"27 ","pages":"Article 200547"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144548423","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Monkeypox optimizer: A TinyML bio-inspired evolutionary optimization algorithm and its engineering applications","authors":"Marwa F. Mohamed ,&nbsp;Ahmed Hamed","doi":"10.1016/j.iswa.2025.200557","DOIUrl":"10.1016/j.iswa.2025.200557","url":null,"abstract":"<div><div>High-dimensional optimization remains a key challenge in computational intelligence, especially under resource constraints. Evolutionary algorithms, which mimic the change in heritable characteristics of biological populations, have been proposed to address this. These algorithms apply selection pressure to favor better solutions over generations, and stochastic variations may occasionally introduce suboptimal candidates to preserve population diversity. However, they often struggle to balance exploration and exploitation, leading to suboptimal solutions, premature convergence, and significant computational demands, making them unsuitable for resource-constrained environments. This paper introduces Monkeypox Optimization (MO), a novel evolutionary algorithm inspired by the infection and replication lifecycle of the monkeypox virus. MO mimics the virus’s rapid spread by employing virus-to-cell infection, where the virus persistently seeks out vulnerable cells to penetrate—representing global exploration of the search space. Once inside, cell-to-cell transmission enables fast local propagation, modeling the refinement of high-potential solutions through accelerated replication. To conserve resources, MO continuously deletes the least effective virion copies, maintaining a compact and memory-efficient population. This biologically grounded design not only accelerates convergence but also aligns MO with TinyML principles, making it ideally suited for low-power, resource-constrained IoT environments. MO is benchmarked against 21 recent algorithms across 90 functions from CEC-2017, CEC-2019, and CEC-2020, and validated on three engineering design problems. Results show MO achieves up to 13% lower energy consumption and 34% shorter execution time compared to state-of-the-art competitors, while maintaining robust accuracy. A theoretical analysis reveals MO’s time complexity is <span><math><mrow><mi>O</mi><mrow><mo>(</mo><mi>m</mi><mi>n</mi><mo>+</mo><mi>R</mi><mi>T</mi><mi>n</mi><mo>)</mo></mrow></mrow></math></span>, confirming its scalability. Statistical validation via Friedman and Fisher tests further supports MO’s performance gains.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"27 ","pages":"Article 200557"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144687060","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Design and development of a dexterous soft-robotics based assistive exoglove with kinematic modeling","authors":"Nawara Mahmood Broti ,&nbsp;Shamim Ahmed Deowan ,&nbsp;A.S.M. Shamsul Arefin","doi":"10.1016/j.iswa.2025.200550","DOIUrl":"10.1016/j.iswa.2025.200550","url":null,"abstract":"<div><div>Necessity of a fully functional hand in our life is beyond description. Yet, a portion of the population is unable to move and control their hand due to paralysis. An assistive device can aid both daily activities and rehabilitation. This paper presents a dexterous soft robotics-based assistive glove with spatial kinematic model and control system. Unlike existing designs, our proposed five-fingered glove provides 20 degrees of freedom (DoFs), closely resembling a human hand. Each finger has 4 DoFs with controlled flexion, extension, abduction, and adduction motion ability. The tendon-driven mechanism simplifies design and control, while 3D-printed thermoplastic polyurethane (TPU) material ensures comfort, lightness, and an anthropomorphic appearance. The derived forward and inverse kinematics of each finger are capable of mapping joint angles to fingertip positions and orientations. To validate the kinematic model, virtual simulation was conducted to confirm its accuracy; while basic hand functionality experiments proved the gloves’ effectiveness. We expect this research to contribute to medical robotics, biomechanics, and assistive technology.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"27 ","pages":"Article 200550"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144597231","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Advancements and challenges of deep learning architectures for aerial image analysis: A systematic review","authors":"Hashibul Ahsan Shoaib ,&nbsp;Hadiur Rahman Nabil ,&nbsp;Md Anisur Rahman ,&nbsp;Md Mohsin Kabir ,&nbsp;M.F. Mridha ,&nbsp;Jungpil Shin","doi":"10.1016/j.iswa.2025.200537","DOIUrl":"10.1016/j.iswa.2025.200537","url":null,"abstract":"<div><div>The rapid advancement of deep learning (DL) technologies has significantly transformed the domain of aerial image analysis. This systematic review explores the forefront of deep learning architectures specifically designed for the processing and analysis of aerial imagery. It offers a comprehensive examination of updated models, such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Generative Adversarial Networks (GANs), and Transformers, highlighting their unique contributions and comparative effectiveness in aerial image analysis. This review critically compares these architectures through an extensive literature survey, focusing on their impact on enhancing accuracy, computational efficiency, and overall performance in critical aerial imaging tasks, such as classification, object detection, and semantic segmentation. Additionally, it sheds light on the innovative architectural improvements that have been crucial in overcoming traditional challenges associated with aerial image processing, such as handling high-resolution data, managing diverse and changing landscapes, and ensuring real-time analysis capabilities. By synthesizing current findings and identifying prevailing trends, this review not only charts the progress in the field but also outlines future research directions, emphasizing the need for more adaptable, robust, and efficient deep-learning solutions to meet the growing demands of aerial image analysis.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"27 ","pages":"Article 200537"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144272578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Temporal event localization in sports videos via self-supervised proposal generation and cross-modal fusion","authors":"Guang Xv ,&nbsp;Xingchen Wu","doi":"10.1016/j.iswa.2025.200539","DOIUrl":"10.1016/j.iswa.2025.200539","url":null,"abstract":"<div><div>Long-form sports videos present unique challenges for temporally localizing relevant segments described by text queries. In this paper, a novel two-stage method is proposed for text snippet localization in long sports videos, combining efficient retrieval with fine-grained refinement. First, an improved video encoding pipeline with a caching mechanism and a video-centric sampling strategy has been designed to efficiently process long videos. Then, a self-supervised proposal generation module is designed that leverages temporal consistency to generate candidate segments (proposals) with pseudo labels, reducing reliance on exhaustive manual annotation. Our model is trained in two stages: a segment-level discrimination stage that learns to identify short video snippets relevant to a query, followed by an instance-level completeness stage that ensures the entire event described by the query is accurately captured. To effectively fuse visual and textual information, a cross-modal fusion strategy is adopted that combines late fusion for scalable coarse retrieval with targeted cross-modal attention for precise alignment. Experiments on sports video datasets demonstrate that our method outperforms state-of-the-art baselines in both accuracy and efficiency.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"27 ","pages":"Article 200539"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144514039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Gradient-enhanced evolutionary multi-objective optimization (GEEMOO): Balancing relevance, learning outcomes, and diversity in educational recommendation systems","authors":"Youssef Jdidou ,&nbsp;Souhaib Aammou ,&nbsp;Hicham Er-radi ,&nbsp;Ilias Aarab","doi":"10.1016/j.iswa.2025.200568","DOIUrl":"10.1016/j.iswa.2025.200568","url":null,"abstract":"<div><div>The increasing complexity of educational recommendation systems, driven by the need to balance content relevance, learning outcomes, and diversity, demands advanced optimization solutions that overcome the limitations of traditional methods. As educational technology is exponentially improving, multi-objective optimization plays a vital role in adapting learning experiences to individual requirements. This study tackles the Gradient-Enhanced Evolutionary Multi-objective Optimization (GEEMOO) algorithm, which is considered as a hybrid framework that deals with three conflicting objectives: Relevance, Learning Outcomes, and Diversity. GEEMOO associates gradient-based methods for rapid integration with the correlative power of evolutionary strategies to deliver high-quality Pareto-optimal solutions. Extensive experimentation, using real-world datasets, has shown that GEEMOO consistently exceeded benchmark algorithms performance (NSGA-II and MOPSO) across key metrics, achieving greater Hypervolume, Generational Distance, and diversity indicators. While maintaining robust solution diversity, GEEMOO stands as an ideal solution for large-scale educational recommendation systems efficiency, requiring fewer fitness evaluations. GEEMOO showed better performance than NSGA-II and MOPSO in both convergence (Hypervolume: 0.85, Generational Distance: 0.02) and diversity (Spread Indicator: 0.88, Crowding Distance: 0.92). Although it required a bit more runtime (150 seconds compared to 120 seconds for NSGA-II), GEEMOO achieved this with fewer fitness evaluations (50,000 versus 60,000 for NSGA-II), highlighting its computational efficiency. The algorithm successfully balanced conflicting objectives, providing Pareto-optimal solutions that cater to various educational goals. This work traits GEEMOO’s adaptability and credibility to demonstrate how personalized learning models are adjusted, offering a solid groundwork for improving educational technology in both research and practice.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"27 ","pages":"Article 200568"},"PeriodicalIF":4.3,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144828696","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"LWR-Net: Learning without retraining for scalable multi-task adaptation and domain-agnostic generalisation","authors":"Haider A. Alwzwazy ,&nbsp;Laith Alzubaidi ,&nbsp;Zehui Zhao ,&nbsp;Ahmed Saihood ,&nbsp;Sabah Abdulazeez Jebur ,&nbsp;Mohamed Manoufali ,&nbsp;Omar Alnaseri ,&nbsp;Jose Santamaria ,&nbsp;Yuantong Gu","doi":"10.1016/j.iswa.2025.200567","DOIUrl":"10.1016/j.iswa.2025.200567","url":null,"abstract":"<div><div>In recent years, deep learning-based multi-class and multi-task classification have gained significant attention across various domains of computer vision. However, current approaches often struggle to incorporate new classes efficiently due to the computational burden of retraining large neural networks from scratch. This limitation poses a significant obstacle to the deployment of deep learning models in real-world intelligent systems. Although continual learning has been proposed to overcome this challenge, it remains constrained by catastrophic forgetting. To address these limitations, this study introduces a new framework called Learning Without Retraining (LWR-Net), developed for multi-class and multi-task adaptation, allowing networks to adapt to new classes with minimal training requirements. Specifically, LWR-Net incorporates four key components: (i) task-guided self-supervised learning with a dual-attention mechanism to enhance feature generalisation and selection; (ii) task-based model fusion to improve feature representation and generalisation; (iii) multi-task learning to generalise classifiers across diverse tasks; and (iv) decision fusion of multiple classifiers to improve overall performance and reduce the likelihood of misclassification. LWR-Net was evaluated across diverse tasks to demonstrate its effectiveness in integrating new data, classes, or tasks. These include: (i) a medical case study detecting abnormalities in five distinct bone structures; (ii) a surveillance case study detecting violence in three different settings; and (iii) a geology case study identifying lateral changes in soil compaction using ground-penetrating radar across two datasets. The results show that LWR-Net achieves state-of-the-art performance across all three scenarios, successfully accommodates new learning objectives while preserving performance, eliminating the need for complete retraining cycles. Moreover, the use of gradient-weighted class activation mapping (Grad-CAM) confirmed that the models focused on relevant regions of interest. LWR-Net offers several benefits, including improved generalisation, enhanced performance, and the capacity to train on new data without catastrophic failures. The source code is publicly available at: <span><span>https://github.com/LaithAlzubaidi/Learning-to-Adapt</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"27 ","pages":"Article 200567"},"PeriodicalIF":4.3,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144828697","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A novel binary Stellar Oscillation Optimizer for feature selection optimization problems","authors":"Ali Rodan ,&nbsp;Sharif Naser Makhadmeh ,&nbsp;Yousef Sanjalawe ,&nbsp;Rizik M.H. Al-Sayyed ,&nbsp;Mohammed Azmi Al-Betar","doi":"10.1016/j.iswa.2025.200558","DOIUrl":"10.1016/j.iswa.2025.200558","url":null,"abstract":"<div><div>Stellar Oscillation Optimizer (SOO) takes its core inspiration from the study of stellar pulsations, a domain often referred to as asteroseismology which is formulated as an optimization algorithm for continuous domain. In this paper, the Binary version of Stellar Oscillation Optimizer (BSOO) is proposed for Feature Selection (FS) problems. BSOO introduces binary adaptations, including threshold-based encoding, controlled oscillatory movements, and a top-solution influence mechanism. In order to evaluate the BSOO, sixteen FS datasets are used with different numbers of features, samples, and class labels. Seven performance measures are also used, which are: fitness value, number of selected features, accuracy, sensitivity, specificity, Precision, and F-measure. An intensive comparative evaluation against 18 state-of-the-art optimization algorithms using the same datasets has been conducted. The results show that the proposed BSOO version is able to compete well with the other FS-based methods where it is able to overcome several methods and produce the best overall results for some datasets on different measurements. Furthermore, the convergence behavior to show the optimization behavior of BSOO during the search is investigated and visualized. Interestingly, the BSOO is able to provide a suitable trade-off between the global wide-range exploration and local nearby exploitation during the optimization process. This is proved using the statistical Wilcoxon Rank-Sum Test Results. In conclusion, this paper provides a new alternative solution for FS research community that is able to work well for many FS instances and find the optimal solution. The source code of BSOO is publicly available for both MATLAB at: <span><span>https://www.mathworks.com/matlabcentral/fileexchange/180096-bsoo-binary-stellar-oscillation-optimizer</span><svg><path></path></svg></span> and PYTHON at: <span><span>https://github.com/AliRodan/BSOO-Binary-Stellar-Oscillation-Optimizer</span><svg><path></path></svg></span>.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"27 ","pages":"Article 200558"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144694572","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A multi-source multi-layer-based transfer learning approach for forecasting customer demands of newly launched products","authors":"Supriyo Ahmed ,&nbsp;Ripon K. Chakrabortty ,&nbsp;Daryl L. Essam","doi":"10.1016/j.iswa.2025.200548","DOIUrl":"10.1016/j.iswa.2025.200548","url":null,"abstract":"<div><div>Forecasting the future demand for newly launched products has been challenging for supply chain practitioners, often due to the lack of data. However, market surveys and extracting knowledge by examining similar market products to find the behaviour of a new product can be inaccurate and lead to erroneous results, which ultimately lead to a misestimation of the overall cost of a business. Meanwhile, with the advancement of artificial intelligence (AI) approaches, such as Transfer Learning (TL), this misestimation of cost can be reduced by more accurately forecasting the demand for newly launched products by seeking knowledge from the historical data of other similar products. Consequently, this paper investigates several classical AI-based TL approaches to predict customer demand for new products and stores. Thereafter, a novel <strong>M</strong>ulti-<strong>S</strong>ource <strong>M</strong>ulti-<strong>L</strong>ayer <strong>T</strong>ransfer <strong>L</strong>earning approach with a <strong>R</strong>ecursive <strong>F</strong>eature <strong>E</strong>limination (MSML-TL-RFE) strategy is proposed to exploit the knowledge extraction power of the model from multiple sources for different days-ahead-prediction, distinguishing itself from the other investigated approaches. In this paper, an abstract concept of a supply chain, with information sharing among retailers, is investigated to show that such concepts can escalate the knowledge transfer ability of a system. A hierarchical two-echelon supply chain model with different attributes is developed to validate the proposed MSML-TL-RFE approach against a few other TL-based forecasting approaches. The feature-rich datasets are then transformed in such a way that they depict a hierarchical supply chain structure, allowing for the effective application of TL for forecasting consumer demand for recently introduced products. Continuing with that idea of information sharing, finding comparable sources for a quick and effective knowledge transfer procedure is investigated, considering all the peculiarities of a certain data set. MSML-TL-REF predictions and other TL-based approaches are analysed by calculating overall supply chain costs. Based on overall supply chain costs under static and dynamic lead time settings, the effectiveness and applicability of the proposed MSML-TL-RFE against traditional forecasting approaches are demonstrated. Incorporating MSML-TL-RFE with three sources improves accuracy, defined as the reciprocal of Root Mean Square Error (RMSE), from 4.83 (no TL) to 5.67 and further increases to 5.76 with additional sources, enabling more accurate predictions and reduced supply chain costs for businesses.</div></div>","PeriodicalId":100684,"journal":{"name":"Intelligent Systems with Applications","volume":"27 ","pages":"Article 200548"},"PeriodicalIF":0.0,"publicationDate":"2025-09-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"144516953","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}