Article
Engineering, Multidisciplinary
Deepika Shukla, C. Ravindranath Chowdary
Summary: The study presents a method for peer recommendation using nodes with weighted attributes in a graph, incorporating negative relevance feedback to enhance system performance and utilizing CL-tree for node indexing. Through comparison experiments on standard datasets, the research shows that the proposed system outperforms its competitor.
SADHANA-ACADEMY PROCEEDINGS IN ENGINEERING SCIENCES
(2021)
Article
Chemistry, Analytical
Sung-Yuk Kim, Sang-Chul Ryu, Yong-Du Jun, Young-Choon Kim, Jong-Seok Oh
Summary: With the development of autonomous vehicles, there is a need to analyze the relationship between the noise characteristics of motors and sound quality in order to reduce operating noise. This study proposes a methodology to analyze the relationship between noise frequency components and sound quality of motors used in automobile interior parts.
Article
Public, Environmental & Occupational Health
Nancy L. Black, Samuelle St-Onge
Summary: The switch to full-time home-work during the COVID-19 pandemic has both positive and negative impacts on workers' health. Working conditions, postures, and equipment used in the home office can potentially increase health risks.
WORK-A JOURNAL OF PREVENTION ASSESSMENT & REHABILITATION
(2022)
Article
Computer Science, Information Systems
Maria Lua Nunes, Duarte Folgado, Carlos Fujao, Luis Silva, Joao Rodrigues, Pedro Matias, Marilia Barandas, Andre Carreiro, Sara Madeira, Hugo Gamboa
Summary: Musculoskeletal disorders (MSD) are a prevalent work-related health issue, and hazardous postures pose a risk to their development. This study developed an inertial sensor-based approach to evaluate posture in industrial contexts, and found that traditional posture risk assessment tools do not consider posture risk differences among different operators.
Article
Computer Science, Information Systems
Fuguan Bao, Wenqian Xu, Yao Feng, Chonghuan Xu
Summary: This study proposes a topic-rank recommendation model based on user topic relevance and user preference, using topic screening and user influence calculation to provide personalized recommendations. Experimental results show that the recommendation model has wider coverage and higher accuracy.
HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES
(2022)
Article
Computer Science, Information Systems
Nana Huang, Ruimin Hu, Xiaochen Wang, Hongwei Ding, Xinjian Huang
Summary: Cross-platform sequential recommendations are proposed to address the issues of sparse data and cold starts in recommendation systems. The NATSR model, which transfers item embedding cross-platform and only shares item-level relevance data, achieves the best recommendation performance and effectively addresses data sparsity and user privacy preservation.
INFORMATION SCIENCES
(2023)
Article
Surgery
Ennie Bijkerk, Jop Beugels, Sander M. J. van Kuijk, Arno Lataster, Rene R. W. J. van Der Hulst, Stefania M. H. Tuinder
Summary: This study aimed to evaluate the clinical relevance of nerve coaptation in deep inferior epigastric perforator (DIEP) flap breast reconstruction. The results showed that nerve coaptation in DIEP flap breast reconstruction, especially in delayed reconstruction, resulted in clinically relevant improved patient-reported outcomes on the physical well-being of the chest domain and better sensation perception.
PLASTIC AND RECONSTRUCTIVE SURGERY
(2022)
Article
Computer Science, Cybernetics
H. Onan Demirel, Molly H. H. Goldstein, Xingang Li, Zhenghui Sha
Summary: Generative design uses AI algorithms to optimize concept creation beyond traditional design, but lacks human factors integration. This paper presents a collaborative research effort to inject human factors in generative design, with three case studies showcasing the potential to enhance human factors representation. Strategies like data-driven design and digital human modeling are discussed as potential approaches to augment designers.
INTERNATIONAL JOURNAL OF HUMAN-COMPUTER INTERACTION
(2023)
Article
Computer Science, Artificial Intelligence
Qi Zhang, Bin Wu, Zhongchuan Sun, Yangdong Ye
Summary: Sequential recommendation has become popular and essential in various online services. This study proposes a Gating Augmented Capsule Network (GAC) to model personalized item- and factor-level transitions in a fine-grained manner, capturing both item co-occurrence patterns and transitions among items' latent attributes. Extensive experiments demonstrate the effectiveness of GAC compared to state-of-the-art baselines.
KNOWLEDGE-BASED SYSTEMS
(2022)
Article
Hospitality, Leisure, Sport & Tourism
David Massimo, Francesco Ricci
Summary: Recommender Systems are often evaluated based on their precision in predicting user behavior, but in online settings, precise recommendations may lack novelty. This paper addresses the issue by studying four different RSs that excel on different target criteria such as precision, relevance, and novelty. The study finds that different systems optimize different aspects of recommendation quality, highlighting the importance of balancing precision, relevance, and novelty in RS design.
INFORMATION TECHNOLOGY & TOURISM
(2021)
Article
Computer Science, Artificial Intelligence
Xiaolin Zheng, Menghan Wang, Renjun Xu, Jianmeng Li, Yan Wang
Summary: This article proposes a new method to address the missing data issue in implicit feedback and applies it to recommender systems. The method uses temporal dependencies among items and users' dynamic preferences to model and exploit the dynamics of missingness, employing a user intent model and a hidden Markov model. The results of experiments demonstrate the superiority of this method.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Computer Science, Information Systems
Chenyan Zhang, Jing Li, Jia Wu, Donghua Liu, Jun Chang, Rong Gao
Summary: Recommender systems provide effective solutions for handling information overload and have become a popular research topic in both industry and academia. However, existing implicit feedback methods still have some shortcomings, such as biased solutions due to uneven sampling of negative samples and lack of interpretability in recommendation results. Therefore, we propose a new deep recommendation model (DRAT) that utilizes an encoder-decoder structure and adversarial training to provide personalized recommendations. Experimental results show that our proposed model significantly outperforms baseline methods.
IEEE TRANSACTIONS ON EMERGING TOPICS IN COMPUTING
(2022)
Article
Engineering, Industrial
Jeffrey Lidstone, Gwen Malone, Ryan Porto, Allison Stephens, Marty Smets, Marc Banning, Joel Cort
Summary: The survey conducted in automotive assembly plants provided insight into RAPT operation data, helping to accurately simulate RAPT operations in a laboratory setting and improving workstation layouts in automotive manufacturing.
APPLIED ERGONOMICS
(2021)
Review
Chemistry, Analytical
Roger Lee, Carole James, Suzi Edwards, Geoff Skinner, Jodi L. Young, Suzanne J. Snodgrass
Summary: The use of WIST feedback shows potential in improving posture and movement behaviors during work or work-related activities, but does not alleviate pain. However, the studies included in the review have limitations in terms of bias, reproducibility, and inconsistent reporting of sensor technology.
Article
Acoustics
Alessandro Opinto, Marco Martalo, Alessandro Costalunga, Nicolo Strozzi, Carlo Tripodi, Riccardo Raheli
Summary: This article presents a performance analysis on the estimation of the observation filter for the Virtual Microphone Technique (VMT) in a realistic automotive environment. The performance of adaptive and fixed observation filter estimation methods was compared. Experimental results show that the fixed observation filter estimation method achieves better performance with remarkable broadband estimation accuracy. Design guidelines are proposed to balance estimation accuracy and material costs in different setups.
IEEE-ACM TRANSACTIONS ON AUDIO SPEECH AND LANGUAGE PROCESSING
(2022)