检索结果-内蒙古大学图书馆

Data-driven explainable machine learning approaches for predicting hydrogen adsorption in porous crystalline materials

引用

Journal of Alloys and Compounds 2025年 1028卷

作者： Thanh, Hung Vo Dai, Zhenxue Rahimi, Mohammad Laboratory for Computational Mechanics Institute for Computational Science and Artificial Intelligence Van Lang University Ho Chi Minh City Viet Nam Faculty of Mechanical - Electrical and Computer Engineering School of Technology Van Lang University Ho Chi Minh City Viet Nam School of Environmental and Municipal Engineering Qingdao University of Technology Qingdao266520 China College of Construction Engineering Jilin University Changchun China Department of Mechanical Engineering McMaster University HamiltonON Canada

The efficient storage of hydrogen is crucial for its adoption as a sustainable energy carrier, addressing the growing need for clean energy sources. Porous crystals such as metal-organic frameworks (MOFs) exhibit exceptional potential among potential storage solutions due to their high surface areas, tunable pore structures, and strong adsorption capacities. However, optimizing these materials for practical hydrogen storage remains challenging, requiring advanced predictive techniques to accelerate material discovery and design. This study utilizes a comprehensive dataset comprising 14,544 experimental and simulated hydrogen adsorption samples to evaluate and develop advanced machine learning (ML) models. Five models, including Extreme Gradient Boosting (XGB), Gradient Boosting (GRB), Support Vector Regression (SVR), Multi-Layer Perceptron (MLP), and K-Nearest Neighbors (KNN), were applied to predict hydrogen uptake based on features including temperature, pressure, void fraction, specific surface area, and pore dimensions. XGB demonstrated superior performance with the lowest RMSE and highest R² values, ensuring accurate and generalizable predictions. Explainable AI techniques, particularly Shapley Additive Explanations (SHAP), were employed to interpret the models, identifying critical factors such as specific surface area and adsorption enthalpy as key drivers of hydrogen uptake. The results underscore the advantages of integrating ML models with experimental and computational datasets, offering a scalable framework for designing high-performance hydrogen storage materials. This research highlights the transformative potential of ML in hydrogen storage optimization, bridging the gap between computational modeling and material innovation. This study contributes significantly to developing sustainable energy technologies and global carbon neutrality initiatives by advancing predictive capabilities and offering interpretable insights. © 2025 Elsevier B.V.

关键词： Crystallites

来源：评论

学校读者我要写书评

暂无评论

C2AV-TSE: Context and Confidence-aware Audio Visual Target Speaker Extraction

引用

IEEE Journal on Selected Topics in Signal Processing 2025年

作者： Wu, Wenxuan Chen, Xueyuan Wang, Shuai Wang, Jiadong Meng, Lingwei Wu, Xixin Meng, Helen Li, Haizhou The Chinese University of Hong Kong Department of Systems Engineering and Engineering Management Hong Kong Nanjing University School of Intelligence Science and Technology Suzhou215163 China The Chinese University of Hon g Kong Shenzhen Research Institute of Big Data Shenzhen518172 China Technical University of Munich Germany The Chinese University of Hon g Kong Shenzhen Research Institute of Big Data School of Data Science Shenzhen China National University of Singapore Department of Electrical and Computer Engineering 119077 Singapore

Audio-Visual Target Speaker Extraction (AV-TSE) aims to mimic the human ability to enhance auditory perception using visual cues. Although numerous models have been proposed recently, most of them estimate target signals by primarily relying on local dependencies within acoustic features, underutilizing the human-like capacity to infer unclear parts of speech through contextual information. This limitation results in not only suboptimal performance but also inconsistent extraction quality across the utterance, with some segments exhibiting poor quality or inadequate suppression of interfering speakers. To close this gap, we propose a model-agnostic strategy called the Mask-And-Recover (MAR). It integrates both inter- and intra-modality contextual correlations to enable global inference within extraction modules. Additionally, to better target challenging parts within each sample, we introduce a Fine-grained Confidence Score (FCS) model to assess extraction quality and guide extraction modules to emphasize improvement on low-quality segments. To validate the effectiveness of our proposed model-agnostic training paradigm, six popular AV-TSE backbones were adopted for evaluation on the VoxCeleb2 dataset, demonstrating consistent performance improvements across various metrics. © 2025 IEEE.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Introducing QuantConn: Overcoming Challenging Diffusion Acquisitions with Harmonization 15th

Introducing QuantConn: Overcoming Challenging Diffusion Acqu...

引用

15th International Workshop on Computational Diffusion MRI, CDMRI 2024, held in conjunction with 27th International Conference on Medical Image Computing and computer-Assisted Intervention, MICCAI 2024

作者： Newlin, Nancy Schilling, Kurt Koudoro, Serge Chandio, Bramsh Qamar Kanakaraj, Praitayini Moyer, Daniel Kelly, Claire E. Genc, Sila Yang, Joseph Yuan-Mou Wu, Ye Adluru, Nagesh Nath, Vishwesh Pathak, Sudhir Schneider, Walter Gade, Anurag Consagra, William Rathi, Yogesh Hendriks, Tom Vilanova, Anna Chamberland, Maxime Pieciak, Tomasz Ciupek, Dominika Vega, Antonio Tristán Aja-Fernández, Santiago Malawski, Maciej Ouedraogo, Gani Machnio, Julia Thompson, Paul M. Jahanshad, Neda Garyfallidis, Eleftherios Landman, Bennett Department of Computer Science Vanderbilt University NashvilleTN United States Department of Radiology and Radiological Sciences Vanderbilt University Medical Center Nashville United States Indiana University Bloomington BloomingtonIN United States Mark and Mary Stevens Neuroimaging and Informatics Institute Keck School of Medicine of USC Los AngelesCA United States Developmental Imaging Murdoch Children’ Research Institute Melbourne Australia Murdoch Children’s Research Institute Melbourne Australia Turner Institute for Brain and Mental Health School of Psychological Sciences Monash University Melbourne Australia Department of Neurosurgery Royal Children’s Hospital Melbourne Australia Neuroscience Research Murdoch Children’s Research Institute Melbourne Australia Department of Paediatrics University of Melbourne Melbourne Australia School of Computer Science and Technology Nanjing University of Science and Technology Nanjing China Waisman Center Department of Radiology University of Wisconsin Madison United States NVIDIA Santa Clara United States Learning Research and Development Center University of Pittsburgh Pittsburgh United States Brigham and Women’s Hospital Boston United States Brigham and Women’s Hospital Harvard Medical School Boston United States Department of Computer Science and Mathmatics Eindhoven University of Technology Eindhoven Netherlands LPI ETSI Telecomunicación Universidad de Valladolid Castilla y León Spain Sano Centre for Computational Medicine Kraków30-054 Poland Aix-Marseille Université Marseille France Vanderbilt University Institute of Imaging Science Vanderbilt University NashvilleTN United States Department of Electrical and Computer Engineering Vanderbilt University NashvilleTN United States

ISBN: (纸本)9783031869198

White matter alterations are increasingly implicated in neurological diseases and their progression. Diffusion-weighted magnetic resonance imaging (DW-MRI) has been included in many international-scale studies to identify alterations in white matter microstructure and connectivity. Yet, quantitative investigation of DW-MRI data is hindered by a lack of consistency due to variations in acquisition protocols, sites, and scanners. Specifically, there is a need to harmonize the preprocessing of DW-MRI datasets to ensure that compatible and reproducible quantitative metrics are derived from each site, including (1) bundle-wise microstructure measures, (2) features of white matter fiber bundles, and (3) connectomics measures. In the MICCAI CDMRI 2023 QuantConn challenge, participants are provided raw data from the same individuals taken with two different acquisition protocols on a single 4 tesla scanner in the same scanning session and asked to preprocess the data in order to minimize acquisition differences while retaining biological variation. Here, we outline the testing framework, provide baseline pre-harmonized results, and discuss the learning implications of this challenge. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Photointerpretation

来源：评论

学校读者我要写书评

暂无评论

FAST COMPUTATION OF A-STAR-B MODULO-N

引用

ELECTRONICS LETTERS 1987年第15期23卷 794-795页

作者： BAKER, PW Department of Computer Science School of Electrical Engineering & Computer Science University of New South Wales Kensington Australia

The computation of A*BmoduloN is an important arith-metic operation in security cryptosystems. Since the word length n involved is large, speed-up techniques are important. The letter demonstrates that, for n-bit arguments, at most 2n carry-save additions are required, followed by at most two carry-propagate additions for final assimilation, using components no more than n + 3 bits wide.

关键词： word length n-bit arguments A* B modulo N security cryptosystems assimilation Data handling techniques cryptography speed-up techniques carry-propagate additions Digital arithmetic methods digital arithmetic security of data carry-save additions arithmetic operation

来源：评论

学校读者我要写书评

暂无评论

Preface

Lecture Notes in Networks and Systems

引用

Lecture Notes in Networks and Systems 2025年 1181卷 v-vi页

作者： Gunjan, Vinit Kumar Zurada, Jacek M. Department of Computer Science and Engineering CMR Institute of Technology Telangana Hyderabad India Department of Electrical and Computer Engineering University of Louisville LouisvilleKY United States

来源：评论

学校读者我要写书评

暂无评论

Investigating Mitochondrial Calcium-Phosphate Dissolution Fractional Order System with Robust Control

引用

International Journal of Applied and Computational Mathematics 2025年第3期11卷 1-17页

作者： Partohaghighi, Mohammad Ahmad, Shabir Akram, Tayyaba Electrical Engineering and Computer Science Department University of California Merced Merced United States Department of Mathematics and Physics University of Campania “Luigi Vanvitelli” Caserta 81100 Italy Department of Mathematics King Fahd University of Petroleum and Minerals Dhahran 31261 Saudi Arabia Interdisciplinary Research Center for Biosystems and Machines King Fahd University of Petroleum and Minerals Dhahran Saudi Arabia

Mitochondrial calcium-dissociation gathers inside the mitochondria of vascular soft tissue cells and is able to interrupt phosphate resolution for up to an hour. In this study, we study the fractional model of mitochondrial calcium-phosphate dissolution (MCD) a system utilizing the Caputo-Fabrizio operator equipped by order α. Furthermore, the theory of the existence of solutions is demonstrated to ensure there exists at least single solution to the considered model. The Picard-Lindelof approach and Banach fixed point theorem are adopted to explore the existence of the solution of the proposed model. Additionally, numerical outcomes of the system are achieved by the three-step Adams-Bashforth method. Graphs of approximate solutions are simulated to show complex behavior of the mitochondrial calcium-dissociation model for a few fractional orders and initial conditions. Some theoretical results of the robust control are obtained to control chaos dynamics. © The Author(s), under exclusive licence to Springer Nature India Private Limited 2025.

关键词： Mathematical modelling Mitochondrial calcium-phosphate dissolution system Numerical method Numerical simulation

来源：评论

学校读者我要写书评

暂无评论

Vr-Hmt: Virtual Reality-Driven Human Motion Tracking System via Mask Rcnn for Real-Time Monitoring

Vr-Hmt: Virtual Reality-Driven Human Motion Tracking System ...

引用

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： Kannan R Suguna T Sivasubramanian R Bhuvanesh A Vemulapalli Sri Lakshmi Harshitha Kulwant Singh Chellam S Ahilan Appathurai Department of Electrical and Electronics Engineering Nehru Institute of Engineering and Technology Coimbatore India Department of Information Technology Government College of Technology Coimbatore Tamil Nadu India Department of AIML Malla Reddy University Dulapally Hyderabad India Department of Electrical and Electronics Engineering PSN College of Engineering and Technology Tirunelveli India Department of BE Computer Science and Design Rmk Engineering College (An Autonomous College) Kavaraipettai Tamil Nadu India Yadavindra Department of Engineering Electronics And Communication Engineering Punjabi University Guru Kashi Campus Department of Electrical and Electronics Engineering Velammal College of Engineering and Technology Madurai Tamil Nadu India Department of Electronics and Communication Engineering PSN College of Engineering and Technology Tirunelveli Tamilnadu India

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

Human motion tracking (HMT) is capturing and analyzing the movement of individuals and objects, focusing on their location, speed, and acceleration. It is used in various fields including filmmaking, animation, sports analysis, robotics, and augmented reality. Unauthorized physical access to facilities presents significant challenges for organizations as it can result in theft, sabotage, and data breaches, these incidents lead to financial losses, and compromised sensitive information. To overcome these challenges, a novel virtual reality (VR) based XXX system has been proposed for tracking human motion to identify any suspicious activity within an organization. The system uses various sensors such as cameras and motion sensors to capture real-world activity in a monitored space. These sensors capture continuous video, which has been converted into frames for further processing. The bilateral filter is used as a pre-processing step to minimize sound while maintaining edges in the frames. The Mask R-CNN model is used for HMT from the frames assigns bounding boxes around each detected human and predicts segmentation masks on each detected frame. The tracking data is stored in a database server and displayed on a large screen to observe the environment. The processed data is further transferred to an application server which serves as a control unit for managing the data and coordinating with the central platform. According to the result, the proposed model attains a 98.45% accuracy rate for human motion tracking. The proposed XXX model achieves an overall accuracy of 2.18%, 8.99%, and 1.47% compared to the existing method such as DBSCAN, cluster segmentation, and k-fold cross-validation.

关键词： Solid modeling Accuracy Tracking Motion segmentation Organizations Predictive models Sensor systems Sensors Servers Monitoring

来源：评论

学校读者我要写书评

暂无评论

Preface

Lecture Notes in Networks and Systems

引用

Lecture Notes in Networks and Systems 2025年 1182卷 V-Vi页

来源：评论

学校读者我要写书评

暂无评论

Recurrent 3D attentional networks for end-to-end active object recognition

引用

Computational Visual Media 2019年第1期5卷 91-103页

作者： Min Liu Yifei Shi Lintao Zheng Kai Xu Hui Huang Dinesh Manocha School of Computer National University of Defense Technology Department of Computer Science and Electrical & Computer Engineering University of Maryland Visual Computing Research Center Shenzhen University

Active vision is inherently attention-driven:an agent actively selects views to attend in order to rapidly perform a vision task while improving its internal representation of the scene being *** by the recent success of attention-based models in 2D vision tasks based on single RGB images, we address multi-view depth-based active object recognition using an attention mechanism, by use of an end-to-end recurrent 3D attentional network. The architecture takes advantage of a recurrent neural network to store and update an internal representation. Our model,trained with 3D shape datasets, is able to iteratively attend the best views targeting an object of interest for recognizing it. To realize 3D view selection, we derive a 3D spatial transformer network. It is dierentiable,allowing training with backpropagation, and so achieving much faster convergence than the reinforcement learning employed by most existing attention-based models. Experiments show that our method, with only depth input, achieves state-of-the-art next-best-view performance both in terms of time taken and recognition accuracy.

关键词： active object recognition recurrent neural network next-best-view 3D attention

来源：评论

学校读者我要写书评

暂无评论

Dynamic Pricing based Near-Optimal Resource Allocation for Elastic Edge Offloading

引用

IEEE Transactions on Mobile Computing 2025年

作者： Xia, Yun Xue, Hai Zhang, Di Mumtaz, Shahid Xu, Xiaolong Rodrigues, Joel J. P. C. University of Shanghai for Science and Technology School of Optical-Electrical and Computer Engineering Shanghai200093 China Zhengzhou University School of Electrical and Information Engineering Henan International Joint Laboratory of Intelligent Health Information System National Telemedicine Center National Engineering Laboratory for Internet Medical Systems and Applications Zhengzhou450001 China Nottingham Trent University Department of Engineering NottinghamNG1 4FQ United Kingdom Kyung Hee University Department of Electronic Engineering Gyeonggi-do Yongin-si17104 Korea Republic of Nanjing University of Information Science and Technology School of Software Nanjing210044 China Amazonas State University Manaus Brazil

In mobile edge computing (MEC), task offloading can significantly reduce task execution latency and energy consumption of end user (EU). However, edge server (ES) resources are limited, necessitating efficient allocation to ensure the sustainable and healthy development for MEC system. In this paper, we propose a dynamic pricing mechanism based near-optimal resource allocation for elastic edge offloading. First, we construct a resource pricing model and accordingly develop the utility functions for both EU and ES, the optimal pricing model parameters are derived by optimizing the utility functions. In the meantime, our theoretical analysis reveals that the EU's utility function reaches a local maximum within the search range, but exhibits barely growth with increased resource allocation beyond this point. To this end, we further propose the Dynamic Inertia and Speed-Constrained particle swarm optimization (DISC-PSO) algorithm, which efficiently identifies the near-optimal resource allocation. Comprehensive simulation results validate the effectiveness of DISC-PSO algorithm, demonstrating that it significantly outperforms existing schemes by reducing the average number of iterations to reach a near-optimal solution by 86.88%, increasing the EU utility function value by 0.13%, and decreasing the variance of results by 96.78%. © 2025 IEEE. All rights reserved.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：