Article
Computer Science, Artificial Intelligence
Chen Kong, Simon Lucey
Summary: The paper introduces a novel hierarchical sparse coding model to overcome limitations of current NRSfM algorithms in terms of image quantity and shape variability handling. By training an unsupervised deep neural network auto-encoder, the approach achieves impressive precision and robustness in solving NRSfM problems.
IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE
(2021)
Article
Chemistry, Physical
Arni Sturluson, Ali Raza, Grant D. McConachie, Daniel W. Siderius, Xiaoli Z. Fern, Cory M. Simon
Summary: Nanoporous materials selectively adsorb gases and offer a variety of candidate structures. Leveraging observed values to impute missing entries can help match NPMs with adsorption tasks. Commercial recommendation systems use similar methods to recommend products to customers.
CHEMISTRY OF MATERIALS
(2021)
Article
Computer Science, Artificial Intelligence
Fan Liu, Zhiyong Cheng, Lei Zhu, Chenghao Liu, Liqiang Nie
Summary: This paper presents an attribute-aware attentive graph convolution network (A(2)-GCN) to address the problem of attribute missing in recommender systems. By constructing a graph and utilizing graph convolution network to learn node representation, this method is able to incorporate associate attributes in user and item representation learning, and filter the message passed from an item to a target user based on attribute information using an attention mechanism.
IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING
(2022)
Article
Automation & Control Systems
Juan Deng, Lin Wang, Zhixin Liu
Summary: This paper discusses the combination of attitude synchronization and rigid formation problem of multiple moving rigid bodies. By utilizing finite-time control and potential function techniques in the design of distributed control laws, the theoretical results on attitude synchronization, rigidity maintenance, and collision avoidance are simultaneously established. Moreover, the local asymptotic stability of rigid formations is shown to be achievable by transforming the stability of rigid formations into the stability of parameterized systems.
Article
Computer Science, Artificial Intelligence
Weina Zhang, Xingming Zhang, Dongpei Chen
Summary: Implicit feedback data has various forms of interaction, such as clicking, collection, and play count, posing a challenge to recommendation systems. This paper introduces a Causal Neural Fuzzy Inference algorithm to address missing data in implicit recommendations through joint learning, demonstrating effectiveness and advancement in experiments on realistic datasets.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Multidisciplinary Sciences
Se-Joon Park, Chul-Ung Kang, Yung-Cheol Byun
Summary: This study investigates enhancing recommendation accuracy using Word2Vec technology, transforming user click sequences into symmetric vectors to recommend suitable products. Experimental results show that multidimensional Word2Vec vectors can improve recommendation accuracy, and for recommending multiple products, a regression model outperforms a classification model in all dimensions.
Article
Computer Science, Theory & Methods
Stefano Aguzzoli, Matteo Bianchi
Summary: In this paper, a full classification of the SJI varieties of BL-algebras is provided, with the main result being that a variety of BL-algebras is SJI if and only if it is generated by a BL-chain with finitely many components, each of them being a cancellative hoop or a Wajsberg hoop with finite rank.
FUZZY SETS AND SYSTEMS
(2021)
Article
Computer Science, Information Systems
Bernd Heinrich, Marcus Hopf, Daniel Lohninger, Alexander Schiller, Michael Szubartowicz
Summary: The rapid development of e-commerce has increased competition among providers, making data quality crucial for recommender systems. This paper proposes a data extension procedure that improves recommendation quality, as evidenced by evaluation results using real-world data sets.
INFORMATION SYSTEMS FRONTIERS
(2022)
Article
Computer Science, Software Engineering
Zachary Ferguson, Minchen Li, Teseo Schneider, Francisca Gil-Ureta, Timothy Langlois, Chenfanfu Jiang, Denis Zorin, Danny M. Kaufman, Daniele Panozzo
Summary: We have introduced the first implicit time-stepping algorithm for rigid body dynamics, with contact and friction, that ensures intersection-free configurations at every time step. Our algorithm explicitly models the curved trajectories traced by rigid bodies in collision detection and response.
ACM TRANSACTIONS ON GRAPHICS
(2021)
Article
Economics
Christoph Breunig, Peter Haan
Summary: In this study, we address the issue of regression with selectively observed covariates in a nonparametric setting using instrumental variables. Identification of the fractional probability weight (FPW) function is achieved through a partial completeness assumption. This method provides a constructive approach for estimation without suffering from the inverse problem.
JOURNAL OF ECONOMETRICS
(2021)
Article
Multidisciplinary Sciences
Stefan Catheline
Summary: The starting point of this manuscript is classical rigid body rotation, which violates the principles of relativity due to infinite speed at infinite distance from the rotation center. To solve this problem, a phenomenological circle-based construction using Euclidean trigonometry is introduced: relativistic rigid body rotation. The physical Eulerian acceleration implied by this geometrical construction establishes links with Maxwell's equation and Lense-Thirring effect. Importantly, relativistic rigid body rotation is shown to be compatible with Lorentz transformation and provides new geometric interpretations of time and space intervals.
SCIENTIFIC REPORTS
(2023)
Article
Computer Science, Software Engineering
Ziyan Zhao, Li Zhang, Xiaoli Lian
Summary: Detecting missing requirements in software development is crucial but challenging. Using requirement-oriented domain models can help identify omissions, but they are often incomplete. This study investigates the overlap between domain models and requirements and proposes recommendations for missing requirements. Experimental results show significant improvements with the proposed metric AHME.
SOFTWARE-PRACTICE & EXPERIENCE
(2023)
Article
Environmental Sciences
Maria Grazia Pennino, Stephanie Brodie, Andre Frainer, Priscila F. M. Lopes, Jon Lopez, Kelly Ortega-Cisneros, Samiya Selim, Natasa Vaidianu
Summary: Marine Spatial Planning (MSP) is a relatively new approach to ocean management that is currently driven primarily by economic interests rather than by sociocultural goals. Integrating sociocultural layers into MSP can help reduce governance rigidity, promote adaptability in decision-making, support environmental justice, and improve MSP acceptance and uptake. Providing a more inclusive definition of the MSP process that considers users' rights and sociocultural objectives may increase the chances of success in both the human and nature aspects.
FRONTIERS IN MARINE SCIENCE
(2021)
Article
Computer Science, Interdisciplinary Applications
Qihua Wang, Miaomiao Su, Ruoyu Wang
Summary: Imputation and the inverse probability weighting are commonly used methods in missing data analysis, but they are not robust due to model misspecification. This paper proposes a beyond multiple robust method that balances these techniques and alleviates model misspecification and dimension problems. The proposed estimator is proven to be consistent and asymptotically normal, and its asymptotic variance equals the semiparametric efficiency bound under certain conditions.
COMPUTATIONAL STATISTICS & DATA ANALYSIS
(2021)
Article
Mechanics
Jun-Yu Ni, Wei-Xi Huang, Chun-Xiao Xu
Summary: The interaction between a rigid-flexible system and ambient fluid was numerically simulated using the immersed boundary method. It was found that as the length of the flexible filament increases, the filament experiences different modes including plate-like (P), cylinder-like (C), slender-shape (S), and wriggling (W) modes. When the filament length reaches a critical value, the second harmonic becomes dominant, indicating a transition from the S mode to the W mode, and at this transition point, the drag on the system becomes minimum. The occurrence of the S-W mode transition is caused by the increased inertia of the filament.
Article
Engineering, Industrial
Xiaoliang Yan, Reed Williams, Elena Arvanitis, Shreyes Melkote
Summary: This paper extends prior work by developing a semantic segmentation approach for machinable volume decomposition using pre-trained generative process capability models, providing manufacturability feedback and labels of candidate machining operations for query 3D parts.
JOURNAL OF MANUFACTURING SYSTEMS
(2024)
Article
Engineering, Industrial
Jing Huang, Zhifen Zhang, Rui Qin, Yanlong Yu, Guangrui Wen, Wei Cheng, Xuefeng Chen
Summary: In this study, a deep learning framework that combines interpretability and feature fusion is proposed for real-time monitoring of pipeline leaks. The proposed method extracts abstract feature details of leak acoustic emission signals through multi-level dynamic receptive fields and optimizes the learning process of the network using a feature fusion module. Experimental results show that the proposed method can effectively extract distinguishing features of leak acoustic emission signals, achieving higher recognition accuracy compared to typical deep learning methods. Additionally, feature map visualization demonstrates the physical interpretability of the proposed method in abstract feature extraction.
JOURNAL OF MANUFACTURING SYSTEMS
(2024)
