Bernd Hader , Martin Schellander , Somin Jeon , Lukas Leitner , Alexandra Saliger , Zahra Safari Dehnavi , Manfred Grafinger , Franz Haas , Sebastian Schlund
{"title":"Requirements Engineering for Data Spaces in Cross-Organizational Co-Design: A Case Study Approach","authors":"Bernd Hader , Martin Schellander , Somin Jeon , Lukas Leitner , Alexandra Saliger , Zahra Safari Dehnavi , Manfred Grafinger , Franz Haas , Sebastian Schlund","doi":"10.1016/j.procs.2026.02.124","DOIUrl":"10.1016/j.procs.2026.02.124","url":null,"abstract":"<div><div>Due to increasing product complexity and numerous suppliers, CAD-based co-design is becoming increasingly important. However, cross-company collaboration via email, cloud services, or centralized platforms raises issues around data sovereignty, transparency, efficiency, and security. Data space technology, seems to be a promising solution for the secure exchange of sensitive data with partners across company boundaries. However, in the field of industrial co-design, specific requirements must be considered for future data space applications. During the collaborative development of a product involving 12 organisations, a focus group was formed to identify current challenges in cross-company collaboration and derive requirements. These were assessed qualitatively and quantitatively using a mixed methods approach. Six key requirements were identified, highlighting the need for structured workflows, fine-grained access control, and flexible integration. These findings provide concrete design guidance for future data space solutions.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"277 ","pages":"Pages 831-840"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147554377","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":"Interoperability in IoT-Integrated Smart Packaging for Inventory Tracking: Challenges, Opportunities, and Operational Impact","authors":"Jawaher J. Alghawi , Atidel B. Hadj-Alouane","doi":"10.1016/j.procs.2026.02.119","DOIUrl":"10.1016/j.procs.2026.02.119","url":null,"abstract":"<div><div>The evolution of inventory tracking from manual methods to advanced IoT-enabled smart packaging has significantly improved accuracy and efficiency in supply chain management. However, the integration of these technologies presents interoperability challenges, particularly due to the coexistence of legacy and modern inventory systems. This study examines the impact of interoperability challenges on inventory tracking performance and operational efficiency, as well as the role of standardization in mitigating these challenges. A mixed-methods approach is employed, combining a quantitative survey of 160 industry professionals and qualitative insights from 10 expert interviews. We propose a Structural Equation Model (SEM) to analyze the relationships between interoperability, inventory tracking, and operational efficiency. The findings confirm that interoperability challenges negatively affect inventory tracking accuracy and operational efficiency. The results confirm that interoperability challenges significantly hinder the implementation success of IoT-enabled smart packaging. However, standardization efforts appear to play a moderating role by mitigating the adverse effects of interoperability challenges and facilitating smoother integration between systems. The qualitative analysis provides additional insights into real-world challenges, including system integration difficulties, data synchronization issues, and cybersecurity risks. Participants highlighted potential solutions such as middleware integration, cloud-based platforms, and industry-wide standardization efforts. This study contributes to the growing body of research on IoT-enabled inventory tracking by offering empirical evidence on the role of interoperability and providing actionable insights for overcoming integration barriers.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"277 ","pages":"Pages 780-790"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147554378","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}
Mushari Alothman , Abdullah Altammami , Muneera Alhoshan , Amal Almazrua , Raghad Al-Rasheed , Rawan Almatham , Afrah Altamimi , Omar Elnashar , Mohamed Amin , Bayan Almuqhim , Abdulrahman Alosaimy , Abdullah Alfaifi
{"title":"ARAG: An Agent-Based Hybrid Semantic-Lexical Retrieval-Augmented Generation Pipeline for Arabic Texts","authors":"Mushari Alothman , Abdullah Altammami , Muneera Alhoshan , Amal Almazrua , Raghad Al-Rasheed , Rawan Almatham , Afrah Altamimi , Omar Elnashar , Mohamed Amin , Bayan Almuqhim , Abdulrahman Alosaimy , Abdullah Alfaifi","doi":"10.1016/j.procs.2026.01.079","DOIUrl":"10.1016/j.procs.2026.01.079","url":null,"abstract":"<div><div>Arabic Retrieval-Augmented Generation (RAG) systems face significant challenges, especially beyond hundreds of millions of words. Persistent issues include low retrieval and generation accuracy for queries involving person names, dates, religious discourse, and Arabic poetry. Additionally, high redundancy from near-duplicate content reduces accuracy and slows retrieval.</div><div>This paper introduces an Arabic-centric RAG pipeline designed to address these limitations. Evaluated on a set of 575 questions covering diverse Arabic query types, the proposed system demonstrates strong performance. The best-performing retriever, multilingual-e5-large, achieved an Acc@1 of 58.7% and an MRR of 0.715. Meanwhile, the top large language model (LLM), Gemini-2-Flash, reached an answer relevance of 0.83, a context utilization rate of 0.84, and a faithfulness score of 0.94.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"275 ","pages":"Pages 682-691"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147552850","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}
Nada Eissa Beshet , Abeer Hadi Salih , Furat.Z. Salih , Hamsa E. Mahmood , Amjed Abbas Ahmed , Aladdin Al Zahran , Taher M. Ghazal
{"title":"Trends Sentiment Unveiled Through Deep Dive into Social Media Data","authors":"Nada Eissa Beshet , Abeer Hadi Salih , Furat.Z. Salih , Hamsa E. Mahmood , Amjed Abbas Ahmed , Aladdin Al Zahran , Taher M. Ghazal","doi":"10.1016/j.procs.2026.01.092","DOIUrl":"10.1016/j.procs.2026.01.092","url":null,"abstract":"<div><div>Through this paper, the authors describe the application of revolutionary data mining and deep learning technologies that have been implemented for the extraction and processing of sentiment trends from social network communication. The importance of public sentiments has increased due to the exponential growth of user-generated content on social media platforms such as X (formerly Twitter), Facebook, and Instagram. The purpose of this study is to apply a natural language processing algorithm to examine large volumes of data, organize them, and identify the various patterns of sentiments that have changed over time on different topics. The study aims to produce the desired outcomes of understanding human feelings along with their minute differences that are communicated on the internet by employing deep learning models of convolutional neural networks (CNNs) and recurrent neural networks (RNNs). The findings reveal that there are both trends and variations in public opinions among the different demographic groups and across the various geographic regions, thus providing a basis for substantial influence at both the strategic decision-making level and at the marketing campaign level.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"275 ","pages":"Pages 799-808"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147552858","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}
Nouran ELhadad , Amal Aboulhassan , Yomna M.I. Hassan
{"title":"LLM-based 3D Model Generation of MHE for OpenSCAD","authors":"Nouran ELhadad , Amal Aboulhassan , Yomna M.I. Hassan","doi":"10.1016/j.procs.2026.01.077","DOIUrl":"10.1016/j.procs.2026.01.077","url":null,"abstract":"<div><div>Mechanical design is considered a fundamental factor in ensuring the structural integrity and functionality of engineering systems. This research offers a parametric design technique for automating the generation of 3D models of Material Handling Equipment (MHE). By integrating this automated solution into the process, the gap between conceptual design and practical implementation will be bridged. The objective is to streamline the generation process by employing the parametric capabilities of programming-based CAD. A tailored system has been developed to turn natural language user design prompts into precise, modifiable models. The Methodology highlights the deployment of a custom Large Language Model (LLM), trained to generate 3D models with high reusability and scalability, enabling OpenSCAD users of all levels of expertise to have a smooth experience. The work in this research supports the development of cognitive CAD tools, especially where flexibility and customization are vital. The model implemented has been tested on a range of common MHE parts, successfully generating accurate and fully parametric OpenSCAD models. The results demonstrate the model’s ability to understand various prompts and produce modifiable outputs suitable for rapid prototyping and design analysis.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"275 ","pages":"Pages 664-671"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147552907","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}
Amberlynn Bonello , Emmanuel Francalanza , Paul Refalo , Maria Victoria Gauci
{"title":"Assistive Device Selection for Operators with Disabilities in Industry 5.0 Manufacturing: A Kansei Engineering Approach","authors":"Amberlynn Bonello , Emmanuel Francalanza , Paul Refalo , Maria Victoria Gauci","doi":"10.1016/j.procs.2026.02.105","DOIUrl":"10.1016/j.procs.2026.02.105","url":null,"abstract":"<div><div>Human-centricity, a cornerstone of Industry 5.0, calls for accessible manufacturing environments. Inclusive workstations comprise assistive devices which facilitate information reception, task execution and inspection for operators with various disabilities. Nonetheless, state-of-the-art literature fails to acknowledge the negative impacts of such assistive devices on operators with disability. Additionally, whilst one assistive device can be used to enhance physical accessibility, it could cause adverse effects on one’s cognitive or sensory abilities. This study therefore addresses these gaps by adopting Kansei Engineering to capture the emotions and perceptions of 48 persons with disabilities towards assistive devices in manufacturing workstations. Both positive and negative emotions and perceptions are elicited, addressing another gap. A unique physical, cognitive and sensory accessibility index for eight assistive devices was created, with each index then employed in a Pareto optimisation approach which maximises accessibility whilst reducing the number of devices. The most optimal combination (achieving an 88% total accessibility score) comprised a microphone, a keyboard and mouse, a touch screen, projected instructions and a monitor. This study has contributed an innovative approach towards guiding which and how assistive devices can be chosen carefully to address diverse abilities, ensuring a more inclusive manufacturing shopfloor in the age of Industry 5.0.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"277 ","pages":"Pages 637-646"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147554429","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":"Heat Pump Integration in Food Industry Pasteurization: A Bibliometric and Technical Review","authors":"Giovanni Paolo Carlo Tancredi, Giuseppe Vignali","doi":"10.1016/j.procs.2026.02.118","DOIUrl":"10.1016/j.procs.2026.02.118","url":null,"abstract":"<div><div>This research has been carried out to address the optimization of industrial heat management in the pursuit of sustainable energy. The focus has been placed on the food processing sector, exploring the implementation of heat pump’s system to manage energy waste into energy-intensive processes such as pasteurization. While prior research has explored specific case studies on heat pump integration, a comprehensive review that combines a bibliometric analysis with a technical synthesis of real-world outcomes has been lacking. The study has started with a comprehensive review of existing academic literature. Utilizing the Scopus database, a first research has been conducted using keywords such as \"pasteurization,\" \"heat pump,\" \"high temperature,\" \"energy consumption,\" \"case study,\" and \"food industry.\" This initial search results with a set of 67 documents, useful to provide first bibliometric outcome such as publication trends and key topics. However, it has become evident that merely analysing publication patterns would not suffice for obtaining the necessary technical insights. The study has advanced to more thorough technical examination. This paper aims to present a deep, fact-based analysis of the real-world effects of the integration of heat pumps into food processing. The study assess performance measures, i.e., energy savings, Coefficient of Performance (COP), and temperature ranges, together with the methodology to provide a concise technical summary of the key elements relevant to industry application. The results demonstrate a wide range of COPs (1.6 to 5.8), a shift towards natural refrigerants that are more environmentally friendly, a significant reduction in energy consumption (e.g., 37.9% in dairy systems), and an expansion of temperature capabilities on both the hot (up to 280 °C) and cool (20-120 °C) sides.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"277 ","pages":"Pages 772-779"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147554914","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":"Application of Generative AI-Based Robotic Process Automation to Alleviate Pain Points in Last-mile Delivery Operations","authors":"Omar Al Khass , Omid Fatahi Valilai","doi":"10.1016/j.procs.2026.02.034","DOIUrl":"10.1016/j.procs.2026.02.034","url":null,"abstract":"<div><div>The explosive growth of e-commerce has magnified last-mile delivery (LMD) inefficiencies, generating disproportionate transportation costs, empty vehicle-miles and rising greenhouse-gas emissions. Confronting this dual logistical-environmental problem, this study proposes an integrated framework that combines Robotic Process Automation (RPA), artificial intelligence (AI) and social-media analytics to create adaptive, low-carbon LMD ecosystems. RPA orchestrates repetitive fulfillment workflows, while generative-AI interfaces negotiate real-time delivery slots and consolidate orders using customer sentiment mined from social platforms. Dynamic routing engines then translate these preferences into eco-efficient tours, maximising vehicle load factors and minimising total distance travelled. The chief contribution is a detailed, end-to-end architecture that fuses AI-enhanced e-commerce portals, automated social engagement and sustainability-centred decision rules. Obtained results indicate up to 30 % cuts in delivery emissions and 18 % savings in cost per drop, validating the synergy between operational performance and environmental stewardship. Concurrently, the study outlines governance mechanisms like privacy-preserving data pipelines, explicit consent layers and transparent opt-in green options, crucial for trustworthy deployment. By framing LMD as a multi-objective optimisation problem solvable through cognitive automation, the work charts a research agenda extending RPA toward self-learning, priority-balancing agents that adapt to volatile demand, regulatory pressure and carbon targets. The framework thus offers retailers a practical pathway to resilient, customer-centric and climate-aligned logistics.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"276 ","pages":"Pages 289-296"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147552784","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 rule-based model with Fuzzy matching for disease named entity recognition in Arabic biomedical texts","authors":"Lamiaa Eldouby , Islam A. Moneim , Hamada Nayel","doi":"10.1016/j.procs.2026.01.072","DOIUrl":"10.1016/j.procs.2026.01.072","url":null,"abstract":"<div><div>Named Entity Recognition (NER) is a fundamental task in Natural Language Processing (NLP), and its significance is amplified in the biomedical field, especially for resource-constrained languages like Arabic. This study proposes a rule-based system for the identification of disease-related entities in Arabic biomedical texts. The method accurately finds relevant terms by using dictionary matching along with a set of linguistic rules. The system uses fuzzy matching based on the Levenshtein similarity measure to deal with the common changes in spelling and terminology. This lets it find entities that are spelled differently but are still the same. The model achieved strong evaluation results, with an F1-score of 90.8%, a recall of 90.8%, and a precision of 90.7%. These outcomes demonstrate that competitive performance can be achieved through a well-structured rule-based framework enhanced by similarity techniques, without the need for advanced machine learning methods or external resources.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"275 ","pages":"Pages 618-627"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147552915","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}
Furat Z. Salih , Nada E. Beshet , Abeer Hadi Salih , Amjed Abbas Ahmed , Hamsa E. Mahmood , Bushra Saadoon Mohammed , Mohammed Ridha Abbas Yousif
{"title":"Interpreting Quality Ratings in Consumer Products Using AI","authors":"Furat Z. Salih , Nada E. Beshet , Abeer Hadi Salih , Amjed Abbas Ahmed , Hamsa E. Mahmood , Bushra Saadoon Mohammed , Mohammed Ridha Abbas Yousif","doi":"10.1016/j.procs.2026.01.087","DOIUrl":"10.1016/j.procs.2026.01.087","url":null,"abstract":"<div><div>The huge online market that grew very fast is the reason why consumer reviews and quality ratings have increased tremendously not only in numbers but also in details. Although this trend is beneficial, it also creates challenges in efficiently analyzing such large volumes of data. This research tries to find out how AI can be applied to sensible interpretation of quality ratings that would result in easier and more reliable access for users, manufacturers, and retailers. The paper continues with a discussion of AI-based technologies, for example, natural language processing (NLP) and machine learning, for the simplification of the identification of the needs fulfilled by the ratings and reviews. This paper uses various AI models to verify their suitability in practice, mainly through the evaluation of their potential to neutralize biases, promote trustworthiness, and anticipate communication patterns among consumers. It has been validated by the findings that the use of AI tools for quality rating data interpretation and finding of the underlying issues, which in turn, may present the possibility of better decisions, is a very important role of the product ecosystem actors, is very advantageous.</div></div>","PeriodicalId":20465,"journal":{"name":"Procedia Computer Science","volume":"275 ","pages":"Pages 751-761"},"PeriodicalIF":0.0,"publicationDate":"2026-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"147552920","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}