检索结果-内蒙古大学图书馆

23rd International Symposium on Intelligent Data Analysis, IDA 2025

作者： Nasri, Maedeh Baratchi, Mitra Koutamanis, Alexander Rieffe, Carolien Department of Developmental Psychology Leiden University Leiden Netherlands Leiden Institute of Advanced Computer Science Leiden University Leiden Netherlands Faculty of Architecture and the Built Environment Delft University of Technology Delft Netherlands Faculty of Electrical Engineering Mathematics and Computer Science University of Twente Enschede Netherlands Department of Psychology and Human Development Institute of Education UCL London United Kingdom

ISBN: (纸本)9783031913976

Trajectory representation learning (TRL) is an intermediate step in handling trajectory data to realize various downstream machine-learning tasks. While most previous TRL research focuses on modeling structured movements in large-scale urban spaces (e.g., cars or pedestrians on streets), this paper focuses on a more challenging scenario of modeling free movement in small-scale social spaces (e.g., children playing in a schoolyard). We present a TRL model, SiamCircle, to process raw trajectories without additional feature extraction to prevent information loss. SiamCircle adopts a Siamese network with Circle Loss to learn trajectory embeddings. Furthermore, SiamCircle employs a data augmentation process to enable self-supervised learning and enrich the input data to address the limited access to high-quality data and ground truth. We evaluate the performance of SiamCircle in downstream tasks using trajectory ranking and clustering performance via seven evaluation metrics collectively. Using an ablation study, we explored the impact of different loss functions on the model’s performance. Accordingly, we selected a 2-D convolutional design with Circle Loss as the best-performing model. In a comparative study, we compared our model against three other baselines. We observed up to 19% improvements in trajectory ranking tasks and achieved the highest average rank in supervised clustering tasks. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Clustering Trajectory Representation Learning Triplet Loss

来源：评论

学校读者我要写书评

暂无评论

Maximizing Energy Efficiency in IRS-Assisted Phase Cooperative PS-SWIPT based Self-Sustainable IoT Network

IEEE Open Journal of the Communications Society

引用

IEEE Open Journal of the Communications Society 2025年 6卷 4311-4327页

作者： Sadia, Haleema Hassan, Ahmad Kamal Abbas, Ziaul Haq Abbas, Ghulam Baker, Thar Saeed, Nasir United Arab Emirates University College of Engineering Department of Electrical and Communication Engineering Al Ain United Arab Emirates Ghulam Ishaq Khan Institute of Engineering and Technology Faculty of Electrical Engineering Pakistan Ghulam Ishaq Khan Institute of Engineering and Technology Faculty of Computer Science and Engineering Pakistan University of Brighton School of Architecture Technology and Engineering Brighton BN2 4GJ United Kingdom

Power splitting based simultaneous wireless information and power transfer (PS-SWIPT) appears to be a promising solution to support future self-sustainable Internet of Things (SS-IoT) networks. However, the performance of these networks is constrained by radio frequency signal strength and channel impairments. To overcome this challenge, intelligent reflecting surfaces (IRSs) have recently been introduced in IoT networks to improve network efficiency by controlling signal reflections. In this article, we propose a novel IRS-enabled phase cooperative framework that aims to maximize the energy efficiency (EE) of the PS-SWIPT based SS-IoT network. Our framework leverages the idea of phase cooperation between two distinct networks without requiring additional hardware resources. We employed transmit beamforming (BF) at access points (APs) and phase shift optimization at the IRS with effective phase cooperation between APs. The EE maximization problem turns out to be NP-hard, so first, an alternating optimization (AO) is solved for the user’s network using heuristic BF approaches and phase optimization via semidefinite relaxation (SDR) approaches. To combat the computational complexity of AO, we also propose a low-complexity alternative solution by exploiting heuristic BF schemes and an iterative algorithm, i.e., the element-wise block-coordinate descent method for phase shifts optimization. The proposed solutions’ analysis shows low computational complexity and fast convergence, achieving near-optimal EE performance for different network settings. We conducted extensive simulations to evaluate our proposed framework’s performance and unveiled significant EE performance achieved by the IoT network consistent with the numerical findings. This work demonstrates the potential of IRS phase cooperation for enhancing the EE of different networks without constraining hardware resources. © 2020 IEEE.

关键词： beamforming energy efficiency Intelligent reflecting surface (IRS) Internet of Things (IoT) phase cooperative network power splitting SWIPT

来源：评论

学校读者我要写书评

暂无评论

Investigating Context-Aware Collaborative Text Entry on Smartphones using Large Language Models 25

Investigating Context-Aware Collaborative Text Entry on Smar...

引用

Proceedings of the 2025 CHI Conference on Human Factors in Computing Systems

作者： Weihao Chen Yuanchun Shi Yukun Wang Weinan Shi Meizhu Chen Cheng Gao Yu Mei Yeshuang Zhu Jinchao Zhang Chun Yu Department of Computer Science and Technology Tsinghua University Beijing China Department of Computer Science and Technology Tsinghua University Beijing China and Qinghai University Xining Qinghai China School of Architecture Tsinghua University Beijing China Pattern Recognition Center WeChat AI Tencent Inc. Beijing China

来源：评论

学校读者我要写书评

暂无评论

NSGA-III and MOACO-based decision-making framework for optimizing time, cost, quality, and carbon footprint in bridge construction: a hybrid approach

引用

Asian Journal of Civil Engineering 2025年第6期26卷 2331-2347.0页

作者： Behera, Amir Prasad Chauhan, Trupti Ravindra Manjunath, T.C. Chandini, Shaik Chandrakar, Vinay Kumar Singh Verma, Swapnil School of Management Centurion University of Technology and Management Odisha Paralakhemundi India Department of Design Manipal School of Architecture and Planning Manipal Academic of Higher Education Manipal Karnataka Udupi India Department of Computer Science and Engineering Rajarajeswari College of Engineering Bengaluru India Gulf American University Fajairah United Arab Emirates School of Civil Engineering Faculty of Engineering and Technology Madhyanchal Professional University Bhopal India Synviro Solutions Pvt. Ltd. Indore India

This study presents a hybrid optimization framework combining Non-dominated Sorting Genetic Algorithm III (NSGA-III) and Multi-Objective Ant Colony Optimization (MOACO) to optimize time, cost, quality, and carbon footprint in bridge construction projects. The construction industry faces growing demands for sustainable practices while maintaining efficiency and cost-effectiveness. The proposed framework addresses these challenges by leveraging NSGA-III’s capability to maintain diversity in Pareto-optimal solutions and MOACO’s strength in refining local solutions through pheromone-based exploration. The framework models construction activities with multiple execution modes, each characterized by specific costs, durations, quality levels, and carbon emissions. Four objective functions are developed to minimize time, cost, and carbon footprint while maximizing quality. Constraints such as precedence relationships and resource availability ensure realistic project planning. The framework is validated through a case study of a 300-m reinforced concrete girder bridge, using input data derived from practical project scenarios. Results demonstrate the hybrid framework’s superior performance compared to standalone NSGA-III, MOACO, Multi-Objective Teaching-Learning-Based Optimization, and Multi-Objective Particle Swarm Optimization. Trade-off and correlation analyses provide actionable insights, revealing relationships between objectives and enabling informed decision-making. This study contributes to sustainable project management by integrating advanced optimization techniques and practical decision-support tools. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2025.

关键词： Hybrid optimization MOACO Multi-objective decision-making NSGA-III Sustainable bridge construction

来源：评论

学校读者我要写书评

暂无评论

DHAG-DTA: Dynamic Hierarchical Affinity Graph Model for Drug-Target Binding Affinity Prediction

IEEE Transactions on Computational Biology and Bioinformatic...

引用

IEEE Transactions on Computational Biology and Bioinformatics 2025年第2期22卷 697-709页

作者： Cheng Wang Yang Liu Shitao Song Kun Cao Xiaoyan Liu Gaurav Sharma Maozu Guo School of Computer Science and Technology Harbin Institute of Technology Harbin China School of Electrical Engineering Liaoning University of Technology Liaoning China Department of Electrical and Computer Engineering University of Rochester Rochester NY USA School of Electrical and Information Engineering Beijing Key Laboratory of Intelligent Processing for Building Big Data Beijing University of Civil Engineering and Architecture Beijing China

Computational methods for predicting drug-target binding affinity (DTA) are critical for large-scale screening of prospective therapeutic compounds during drug discovery. Deep neural networks (DNNs) have recently shown significant promise for DTA prediction. By leveraging available data for training, DNNs can expand the use of DTA prediction to situations where only sequence information is available for potential drug molecules and their targets, and there is no prior knowledge regarding the molecular geometric conformations. We propose DHAG-DTA, a general dynamic hierarchical affinity graph DNN approach, for DTA prediction using molecular sequence information and already known drug-target interactions. DHAG-DTA introduces a two-level hierarchical graph structure: at the upper level, interactions between drug and target molecules are represented via an affinity graph and at the lower level, embedded molecular graphs represent interactions within the individual molecules. This allows for integration of information from both inter and intra molecular interactions for DTA prediction, which has also been addressed in other recent independent work. The fundamental innovations introduced by DHAG-DTA include: (a) a single overall hierarchical graph that allows better assimilation of information during the learning process compared with loosely-coupled individual graphs, (b) dynamic determination of the affinity graph structure via the introduction of unlabeled edges and a maximum entropy criterion for active edge selection, (c) skip connections in the DNN for fusing intra and inter molecular information, and (d) fusion of both model-based and similarity-based feature embeddings to get robust embeddings of unseen molecules. Experimental results on two common benchmark datasets demonstrate that DHAG-DTA outperforms other existing models on multiple evaluation metrics, achieving state-of-the-art performance.

关键词： Drugs Predictive models Graph neural networks Artificial neural networks Biological system modeling Proteins Atoms Computational modeling Bioinformatics Entropy

来源：评论

学校读者我要写书评

暂无评论

URL Spam Detection Using Machine Learning Classifiers

URL Spam Detection Using Machine Learning Classifiers

引用

Computational Intelligence Approaches and Applications (ICCIAA), International Conference on

作者： Omar Almomani Adeeb Alsaaidah Mosleh M. Abualhaj Mohammed Amin Almaiah Ammar Almomani Shahzad Memon Department of Networks and Cybersecurity Al-Ahliyya Amman University Amman Jordan Department of Computer Science King Abdullah the II IT School The University of Jordan Amman Jordan Department of Information Technology Al-Huson University College Al-Balqa Applied University Irbid Jordan Department of Computer Information Science Higher Colleges of Technology Sharjah United Arab Emirates Department of Computer Science and Digital Technologies Faculty of Architecture Computing and Engineering University of East London UK

ISBN: (数字)9798331523657

ISBN: (纸本)9798331523664

Cybersecurity has emerged as one of the most prevalent and significant challenges in recent years due to the advancement of technology. Among the most frequent and hazardous cybersecurity threats are spam URLs (Uniform Resource Locators), which are also one of the most popular methods for user fraud. Users are the victims of this attack, which also steals their data and infects their devices with harmful software. The detection of spam URLs has become very important in protecting the user. Therefore, this study aims to investigate the efficiency of machine learning classifiers in detecting spam URLs. The following machine learning classifiers were chosen: Random Forest, Decision Tree, and SVM. The evaluation was based on the ISCXURL2016 dataset, which is divided into three groups: All Features, BestFirst Features, and Infogain Features and evaluation matrices were the Accuracy, Precision, Sensitivity, and F-measure. The results obtained showed that Random Forest with All Features is superior to others with an accuracy of 99.75%, Precision of 99.74%, and Sensitivity of 99. 79%, and F-measure 99.76 %.

关键词： Uniform resource locators Support vector machines Sensitivity Accuracy Phishing Metaheuristics Feature extraction Malware Decision trees Random forests

来源：评论

学校读者我要写书评

暂无评论

Integrating Structural Information: Comparing Classification-Based and Segmentation-Based Predictors in Bioinformatics (Case Study: Protein-Peptide Region Residue-Level Interaction) Using Structural Information

Integrating Structural Information: Comparing Classification...

引用

International CSI computer Conference, CSICC

作者： Shima Shafiee Abdolhossein Fathi Faezeh Safari Department of Computer Engineering and Information Technology Razi University Kermanshah Iran Faculty of Eng. Architecture and Info. Tech. School of Electrical Eng. and Computer Science University of Queensland Brisbane QLD Australia

ISBN: (数字)9798331523114

ISBN: (纸本)9798331523121

Understanding the regions where proteins bind to peptides is vital for studying diseases like cancer, as it sheds light on various cellular processes and aids in drug discovery. Although researchers can experimentally investigate protein-peptide interactions at the region level by analyzing the structures of their complexes, only a limited number of these structures are known. Additionally, experiments to determine these interactions can be both costly and time-consuming. Computational methods provide an alternative and complementary approach to experimental techniques. As a result, using computational methods to predict peptide-binding regions can significantly enhance the efficiency and cost-effectiveness of experimental research. To leverage these advantages, this study introduces a new method named Structure-based Prediction of Residue-level Interaction of Peptides (SPRINT-Pep), designed to pinpoint the binding regions between proteins and peptides. This approach leverages two distinct predictive models: a classification-based model combining DeepResNet with a Support Vector Machine (SVM) and a segmentation-based model called DeepU-Net. Our predictions outperform other state-of-the-art methods in terms of F-measures (by at least 23%), precision (by at least 3.7%), and the balance between sensitivity and specificity (by about 7.7%). These findings demonstrate the proficiency of the proposed method.

关键词： Proteins Support vector machines Deep learning Peptides Predictive models Sensitivity and specificity Prediction algorithms Robustness Drug discovery Testing

来源：评论

学校读者我要写书评

暂无评论

Relip: Reliable in-Band Parallel Communication for Magnetic MIMO Wireless Power Transfer System

引用

IEEE Transactions on Mobile Computing 2025年

作者： Wang, Xinyu Zhou, Wangqiu Zhou, Hao Jiang, Shenyao Liu, Zhi Wang, Xiaoyan Ji, Yusheng Song, Qi City University of Hong Kong Department of Computer Science Hong Kong University of Science and Technology of China School of Computer Science and Technology Hefei230027 China The University of Electro-Communications Graduate School of Informatics and Engineering Tokyo182-8585 Japan Ibaraki University Graduate School of Science and Engineering Ibaraki310-8512 Japan National Institute of Informatics Information Systems Architecture Science Research Division Tokyo101-0003 Japan

In magnetic resonant coupling (MRC) based wireless power transfer (WPT) systems, receiver (RX) feedback communication is promising to enhance the capability and efficiency of the system. Although some studies have explored in-band implementations with low overhead costs, it has not been comprehensively investigated. In this paper, we propose Relip, a Reliable layer-level in-band parallel feedback communication mechanism for MIMO MRC-WPT systems, which addresses the impact of RX-RX couplings (i.e., non-negligible interference from strong couplings and positive effects of relay phenomenon), and provides a theoretical analysis of communication reliability. Technically, we first devise an On-Off based two-phase modulation mechanism to achieve RX identification and dependency detection under relay phenomenon. Then, we utilize observed channel decomposability to collect group-level power transfer channel conditions for eliminating the interference caused by strong RX-RX couplings. Furthermore, we perform RX selection to optimize the trade-off between communication reliability and time overhead. We design and implement the Relip prototype and conduct extensive experiments. The results validate the effectiveness of our mechanism, i.e., Relip can provide ≥99% average decoding accuracy for concurrent feedback communication of 14 devices, achieving an 18.31% improvement compared to the state-of-the-art solution. © 2002-2012 IEEE.

关键词： Inductive power transmission

来源：评论

学校读者我要写书评

暂无评论

Reliable Multihop Routing and Congestion Aware Chicken Swarm Optimization in Vehicular Ad-Hoc Network 3

Reliable Multihop Routing and Congestion Aware Chicken Swarm...

引用

3rd International Conference on Integrated Circuits and Communication Systems, ICICACS 2025

作者： Anitha, Cuddapah Al-Tarazi, Dalia Vignesh, G.D. Vasuki, A. Vinotha Giri, Jayant Dinesh, M. School of Computing Mohan Babu University Erstwhile Sree Vidyanikethan Engineering College Department of Computer Science and Engineering Tirupati India Zarqa University Faculty of Engineering Department of Architecture Engineering Zarqa Jordan College of Engineering University of Business and Technology Jeddah Saudi Arabia St. Joseph's College of Engineering Department of Electronics and Communication Engineering Chennai India J.P. College of Engineering Department of Computer Science and Engineering Tenkasi India Yeshwantrao Chavan College of Engineering Department of Mechanical Engineering Nagpur India Lovely Professional University Division of Research and Development Phagwara India Department of Vlsi Microelectronics Chennai India

ISBN: (纸本)9798331508456

Background: Vehicular Ad Hoc Networks (VANETs) play a crucial role in intelligent transportation by facilitating communication between vehicles and vehicles with infrastructure-based models. They encounter problems such as significant movement, overcrowding, and loss of data. This research presents a novel deep reinforcement learning-based resource allocation and congestion optimization (DRLRCO) framework aimed at improving communication efficiency and high reliability using an effective learning process. Method Used: The DRLRCO framework employs agent-based learning to ensure precise data transmission, AdMAC Protocol for dynamic packet delivery, and Congestion-Aware Chicken Swarm Optimization (CSO) to enhance network performance. Result: The DRLRCO framework surpasses reinforcement learning models for comprehensive testing. Significant enhancements involve improved accuracy, reduced data loss, minimized overhead, increased throughput, and shorter average delays for real-time communication. Conclusion: The DRLRCO framework successfully tackles congestion and data loss in vehicular communication. Future studies might involve Artificial Intelligence (AI) for traffic forecasting, experimentation among high-speed vehicles and investigating blockchain for enhanced security. © 2025 IEEE.

关键词： Deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Co-design of virtual reality exergames for balance rehabilitation

Co-design of virtual reality exergames for balance rehabilit...

引用

Virtual Reality and 3D User Interfaces Abstracts and Workshops (VRW), IEEE Conference on

作者： Signe Toftgaard Henriksen Ali Adjorlu Stefania Serafin Marius George Onofrei Federico Fontana Kasper Søndergaard Department of Architecture Design and Media Technology Aalborg University Copenhagen Denmark Department of Mathematics Computer Science and Physics University of Udine Udine Italy Department of Occupational and Physical Therapy University Hospital Herlev and Gentofte Hellerup Denmark

ISBN: (数字)9798331514846

ISBN: (纸本)9798331525637

Balance disorders, particularly in the elderly population, pose a significant public health challenge due to the associated risk of falls. Exercise-based therapies are effective for reducing this risk but face limitations like cost, accessibility, and sustaining patient engagement. By enabling personalized rehabilitation through engaging exergames, Virtual Reality (VR) offers a promising, cost-effective solution. This paper presents the collaborative design and preliminary evaluation of two VR-based games targeting specific balance skills. Developed in collaboration with a physiotherapist with extensive experience with patients with balance disorders, the games align with a rehabilitation protocol used by the therapist that categorizes training based on individual balance skills. Inspired by traditional physiotherapy exercises, the gameplay aims to train the same skills. Six health professionals agreed on the games’ therapeutic potential, while recommending improvements in usability, difficulty adjustment and monitoring of patient progress.

关键词： Training Three-dimensional displays Protocols Collaboration Virtual reality Games User interfaces Usability Public healthcare Older adults

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：