Bilgisayar Mühendisliği Bölümü Diğer Yayınlar Koleksiyonu
Bu koleksiyon için kalıcı URI
Güncel Gönderiler
Öğe Sparsity in transformers: A systematic literature review(Elsevier B.V., 2024) Farina, M.; Ahmad, U.; Taha, A.; Younes, H.; Mesbah, Y.; Yu, X.; Pedrycz W.Transformers have become the state-of-the-art architectures for various tasks in Natural Language Processing (NLP) and Computer Vision (CV); however, their space and computational complexity present significant challenges for real-world applications. A promising approach to address these issues is the introduction of sparsity, which involves the deliberate removal of certain parameters or activations from the neural network. In this systematic literature review, we aimed to provide a comprehensive overview of current research on sparsity in transformers. We analyzed the different sparsity techniques applied to transformers, their impact on model performance, and their efficiency in terms of time and space complexity. Moreover, we identified the major gaps and challenges in the existing literature. Our study also highlighted the importance of investigating sparsity in transformers for computational efficiency, reduced resource requirements, scalability, environmental impact, and hardware-algorithm co-design. By synthesizing the current state of research on sparsity in transformer-based models, we also provided valuable insights into their efficiency, impact on model performance, and potential trade-offs, contributing to advancing the field further. © 2024 Elsevier B.V.Öğe Broad-deep network-based fuzzy emotional inference model with personal information for intention understanding in human–robot interaction(Elsevier Ltd, 2024) Li, M.; Chen, L.; Wu, M.; Hirota, K.; Pedrycz, W.A broad-deep fusion network-based fuzzy emotional inference model with personal information (BDFEI) is proposed for emotional intention understanding in human–robot interaction. It aims to understand students’ intentions in the university teaching scene. Initially, we employ convolution and maximum pooling for feature extraction. Subsequently, we apply the ridge regression algorithm for emotional behavior recognition, which effectively mitigates the impact of complex network structures and slow network updates often associated with deep learning. Moreover, we utilize multivariate analysis of variance to identify the key personal information factors influencing intentions and calculate their influence coefficients. Finally, a fuzzy inference method is employed to gain a comprehensive understanding of intentions. Our experimental results demonstrate the effectiveness of the BDFEI model. When compared to existing models, namely FDNNSA, ResNet-101+GFK, and HCFS, the BDFEI model achieved superior accuracy on the FABO database, surpassing them by 12.21%, 1.89%, and 0.78%, respectively. Furthermore, our self-built database experiments yielded an impressive 82.00% accuracy in intention understanding, confirming the efficacy of our emotional intention inference model. © 2024 Elsevier LtdÖğe Artificial intelligence for production, operations and logistics management in modular construction industry: A systematic literature review(Elsevier B.V., 2024) Liu, Q.; Ma, Y.; Chen, L.; Pedrycz, W.; Skibniewski, M.J.; Chen, Z.-S.Artificial intelligence (AI) has garnered significant attention within the modular construction industry, emerging as a prominent frontier development trend. A comprehensive and systematic analysis is required to gain a thorough understanding of the existing literature on the use of AI in the management of production, operations, and logistics within the modular construction industry. This review delves into the various aspects of AI implementation in this sector, adopting a critical perspective. The objective of this paper is to analyze the progress, suitability, and research patterns in the field of AI for the management of productions, operations, and logistics within the modular construction industry. First, a concise overview of AI technologies pertaining to the contemporary research on the production, operations and logistics management of the modular construction industry is provided. Second, a bibliometric analysis is performed to provide a comprehensive overview of the existing publications pertaining to this subject matter. Subsequently, this paper presents literature reviews and outlines future directions for each component, specifically AI in the context of production management, operations management, and logistics management within the modular construction industry. The review provides a valuable knowledge base and roadmap to guide future research and development efforts in AI-enhanced modular construction management. © 2024 Elsevier B.V.Öğe Editorial: Innovation and trends in the global food systems, dietary patterns and healthy sustainable lifestyle in the digital age(Frontiers Media, 2023) Hoteit, Maha; Qasrawi, Radwan; Al Sabbah, Haleama; Tayyem, ReemaThe global food systems are undergoing significant changes due to evolving dietary habits and the digital era's influence, impacting health and overall global stability. As processed foods and sedentary lifestyles become more prevalent, there's a marked increase in non-communicable diseases like obesity and diabetes. Despite advancements in food security in developed regions, low-to-middle-income countries still grapple with substantial challenges, exacerbated by the COVID-19 pandemic's disruptions. Technology offers promising solutions. Developments in artificial intelligence, data science, and ICT are reshaping our understanding and approaches to global food systems, dietary choices, and sustainable health behaviors. This Research Topic compiles studies examining the intersection of food security, nutrition, and technological innovation. Comprising 15 papers, the collection emphasizes global dietary trends, especially in the Eastern Mediterranean Region, both pre and post-COVID-19. Highlights include the growing prevalence of nutrition-related diseases in the region, the efficacy of long-term dietary interventions for obesity, the links between dietary patterns and childhood anemia, and the ripple effect of parental dietary habits on families. The importance of maintaining practices like the Mediterranean Diet is also underscored, given its health benefits.Öğe Boron nitride nanosheet-reinforced WNiCoFeCr high-entropy alloys: the role of B4C on the structural, physical, mechanical, and radiological shielding properties (vol 128, 694, 2022)(SPRINGER HEIDELBERG, 2022) Kavaz, Esra; Gül, Ali Oktay; Başgöz, Öyküm; Güler, Ömer; Almisned, Ghada; Bahçeci, Ersin; Güler, Seval Hale; Tekin, Hüseyin OzanNo Abstract Available.
