检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Duong, Viet Wu, Qiong Zhou, Zhengyi Zavesky, Eric Chen, Jiahe Liu, Xiangzhou Hsu, Wen-Ling Shao, Huajie Department of Computer Science College of William and Mary United States AT &T Labs United States College of Control Science and Engineering Zhejiang University China School of Computer Science Zhejiang University China

Out-of-distribution (OOD) detection identifies test samples that differ from the training data, which is critical to ensuring the safety and reliability of machine learning (ML) systems. While a plethora of methods have been developed to detect uni-modal OOD samples, only a few have focused on multi-modal OOD detection. Current contrastive learning-based methods primarily study multi-modal OOD detection in a scenario where both a given image and its corresponding textual description come from a new domain. However, real-world deployments of ML systems may face more anomaly scenarios caused by multiple factors like sensor faults, bad weather, and environmental changes. Hence, the goal of this work is to simultaneously detect from multiple different OOD scenarios in a fine-grained manner. To reach this goal, we propose a general-purpose weakly-supervised OOD detection framework, called WOOD, that combines a binary classifier and a contrastive learning component to reap the benefits of both. In order to better distinguish the latent representations of in-distribution (ID) and OOD samples, we adopt the Hinge loss to constrain their similarity. Furthermore, we develop a new scoring metric to integrate the prediction results from both the binary classifier and contrastive learning for identifying OOD samples. We evaluate the proposed WOOD model on multiple real-world datasets, and the experimental results demonstrate that the WOOD model outperforms the state-of-the-art methods for multi-modal OOD detection. Importantly, our approach is able to achieve high accuracy in OOD detection in three different OOD scenarios simultaneously. The source code will be made publicly available upon publication. Copyright © 2023, The Authors. All rights reserved.

关键词： Wood

来源：评论

学校读者我要写书评

暂无评论

Robust Length of Stay Prediction Model for Indoor Patients

引用

computers, Materials & Continua 2022年第3期70卷 5519-5536页

作者： Ayesha Siddiqa Syed Abbas Zilqurnain Naqvi Muhammad Ahsan Allah Ditta Hani Alquhayz M.A.Khan Muhammad Adnan Khan Department of Mechatronics and Control Engineering University of Engineering and TechnologyLahore54000Pakistan Department of Information Sciences Division of Science and TechnologyUniversity of EducationLahore54000Pakistan Department of Computer Science and Information College of Science in ZulfiMajmaah UniversityAl-Majmaah11952Saudi Arabia Riphah School of Computing&Innovation Faculty of ComputingRiphah International UniversityLahore CampusLahore54000Pakistan Pattern Recognition and Machine Learning Lab Department of SoftwareGachon UniversitySeongnam13557Korea

Due to unforeseen climate change,complicated chronic diseases,and mutation of viruses’hospital administration’s top challenge is to know about the Length of stay(LOS)of different diseased patients in the *** management does not exactly know when the existing patient leaves the hospital;this information could be crucial for hospital *** could allow them to take more patients for *** a result,hospitals face many problems managing available resources and new patients in getting entries for their prompt ***,a robust model needs to be designed to help hospital administration predict patients’LOS to resolve these *** this purpose,a very large-sized data(more than 2.3 million patients’data)related to New-York Hospitals patients and containing information about a wide range of diseases including Bone-Marrow,Tuberculosis,Intestinal Transplant,Mental illness,Leukaemia,Spinal cord injury,Trauma,Rehabilitation,Kidney and Alcoholic Patients,HIV Patients,Malignant Breast disorder,Asthma,Respiratory distress syndrome,*** been analyzed to predict the *** selected six Machine learning(ML)models named:Multiple linear regression(MLR),Lasso regression(LR),Ridge regression(RR),Decision tree regression(DTR),Extreme gradient boosting regression(XGBR),and Random Forest regression(RFR).The selected models’predictive performance was checked using R square andMean square error(MSE)as the performance evaluation *** results revealed the superior predictive performance of the RFRmodel,both in terms of RS score(92%)and MSE score(5),among all selected *** Exploratory data analysis(EDA),we conclude that maximumstay was between 0 to 5 days with the meantime of each patient 5.3 days and more than 50 years old patients spent more days in the *** on the average LOS,results revealed that the patients with diagnoses related to birth complications spent more days in the hospital than other *** finding coul

关键词： Length of stay machine learning robust model random forest regression

来源：评论

学校读者我要写书评

暂无评论

Efficient Coordination and Synchronization of Multi-Robot Systems Under Recurring Linear Temporal Logic

arXiv

引用

arXiv 2025年

作者： Peron, Davide Fernandez-Ayala, Victor Nan Vlahakis, Eleftherios E. Dimarogonas, Dimos V. Department of Information Engineering University of Padova Padova35122 Italy Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm10044 Sweden

We consider multi-robot systems under recurring tasks formalized as linear temporal logic (LTL) specifications. To solve the planning problem efficiently, we propose a bottom-up approach combining offline plan synthesis with online coordination, dynamically adjusting plans via real-time communication. To address action delays, we introduce a synchronization mechanism ensuring coordinated task execution, leading to a multi-agent coordination and synchronization framework that is adaptable to a wide range of multi-robot applications. The software package is developed in Python and ROS2 for broad deployment. We validate our findings through lab experiments involving nine robots showing enhanced adaptability compared to previous methods. Additionally, we conduct simulations with up to ninety agents to demonstrate the reduced computational complexity and the scalability features of our work. © 2025, CC BY.

关键词： Multipurpose robots

来源：评论

学校读者我要写书评

暂无评论

Maximizing social power in multiple independent Friedkin-Johnsen models

Maximizing social power in multiple independent Friedkin-Joh...

引用

European control Conference (ECC)

作者： Lingfei Wang Yu Xing Claudio Altafini Karl H. Johansson Division of Decision and Control Systems Digital Futures School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Stockholm Sweden Department of Electrical Engineering Division of Automatic Control Linköping University Linköping Sweden

ISBN: (数字)9783907144107

ISBN: (纸本)9798331540920

This paper investigates the problem of maximizing social power for a group of agents, who participate in multiple meetings described by independent Friedkin-Johnsen models. A strategic game is obtained, in which the action of each agent (or player) is her stubbornness over all the meetings, and the payoff is her social power on average. It is proved that, for all but some strategy profiles on the boundary of the feasible action set, each agent's best response is the solution of a convex optimization problem. Furthermore, even with the non-convexity on boundary profiles, if the underlying networks are given by a fixed complete graph, the game has a unique Nash equilibrium. For this case, the best response of each agent is analytically characterized, and is achieved in finite time by a proposed algorithm.

关键词： Network topology Europe Games Nash equilibrium Cost function Convex functions

来源：评论

学校读者我要写书评

暂无评论

SELM: From Efficient Autonomous Exploration to Long-term Monitoring in Semantic Level

引用

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Lang, Fang Qin, Yongsen Wang, Yinchuan Liu, Jin Wang, Chaoqun Song, Wei Zhu, Qiuguo Song, Rui Zhejiang University Polytechnic Institute Hangzhou310015 China Shandong University School of Control Science and Engineering Jinan China Zhejiang University Robotics Institute Hangzhou China Zhejiang University College of Computer Science and Technology Hangzhou China

Maintaining up-to-date environmental models from initial deployment through long-term autonomy in service is critical for applications like navigation and task planning. To address the challenges of persistent monitoring in unknown environments, we introduce a Two-Stage monitoring strategy, termed the Semantic-level autonomous Exploration and Long-term environment Monitoring (SELM) framework. In the first stage, we introduce a novel semantic exploration method to adapt to new environments quickly. Leveraging the semantic information within the incrementally constructed 3D Scene Graph (3DSG), we combine the Next-Best-View (NBV) selection with room semantics, introducing a more efficient and comprehensive approach for multi-room indoor environment exploration. In addition, the exploration provides patrol routes, the room distance-connectivity graph, and complete environment initial states for subsequential monitoring. The monitoring stage aims to persistently patrol to update the world model in the presence of dynamic changes, including changes in objects' positions. We formulate the long-term monitoring problem as the Partially Observable Markov Decision Process (POMDP) to cope with the environmental uncertainty. To solve the POMDP, we propose the Graph Attention Bidirectional long short-term memory Proximal Policy Optimization (GABPPO) algorithm for the optimal patrol strategy. The feasibility and effectiveness of the proposed SELM framework are verified through extensive experiments. © 2016 IEEE.

关键词： Environmental monitoring

来源：评论

学校读者我要写书评

暂无评论

Transfer Route Recommendation for Metro Systems Based on Multi-source Data Fusion 24

Transfer Route Recommendation for Metro Systems Based on Mul...

引用

24th IEEE International Conference on High Performance Computing and Communications, 8th IEEE International Conference on Data science and Systems, 20th IEEE International Conference on Smart City and 8th IEEE International Conference on Dependability in Sensor, Cloud and Big Data Systems and Application, HPCC/DSS/SmartCity/DependSys 2022

作者： Yuan, Tailan Xiong, Wen Yun, Lijun School of Information Science and Technology Yunnan Normal University Kunming China Engineering Research Center of Computer Vision and Intelligent Control Technology Department of Education of Yunnan Province Kunming China

ISBN: (纸本)9798350319934

As the network-structure complexity and the passenger volume continuously grow, how to accurately perform passenger flow guidance is a crucial issue for metro operators. Transfer route recommendation is a core approach for passenger flow guidance. Existing works are limited in obtaining route attributes (such as transfer walking time and waiting time, etc.). Furthermore, most of existing methods may not work well in the scenario of sudden passenger flow, because of their limited capability to accurately measure the real-time crowding. To address these issues, a data fusion based transfer route recommendation method (DFTRR) is proposed. Specifically, we first propose a spatio-temporal diversity-based method (STD) to measure the trajectory similarity. Based on that, we fuse two kinds of heterogeneous data, i.e., swiping records of smart cards and Wi-Fi signal records of mobile devices to extract a passenger's complete trip. And then we present the historical median travel time to alleviate the computation issue of route attributes. Meanwhile the mean crowding level is introduced to accurately measure the real-time crowding of routes. Finally, a generalized travel cost based on median travel time, number of transfers and mean crowding level is constructed for transfer route recommendation. The experimental results illustrate that the accuracy of STD algorithm is higher than the baseline 34.92% at maximum;DFTRR can offer the optimal transfer route according to passengers' preferences under sudden passenger flow. © 2022 IEEE.

关键词： Smart cards

来源：评论

学校读者我要写书评

暂无评论

On-line detection model of total alkalinity of water based on improved genetic algorithm

On-line detection model of total alkalinity of water based o...

引用

2021 International Conference of Social Computing and Digital Economy, ICSCDE 2021

作者： Jin, Tao Wang, Zhen Cai, Shao-Bin Jiang, Yong-Zeng Wang, Yi-Ping College of Computer Science and Technology Harbin Engineering University Harbin150001 China College of Computer and Control Engineering Qiqihar University Qiqihar161006 China College of Computer Science and Technology Huaqiao University Xiamen361021 China

ISBN: (纸本)9781665401425

In order to quantitatively analyze the total alkalinity of water in eco-industrial park, conduct on-line detection of total alkalinity of water in eco-industrial park, and improve the monitoring and dredging ability of total alkalinity of water and related pollutants in eco-industrial park, an on-line detection model of total alkalinity of water in eco-industrial park based on improved genetic algorithm was proposed. The statistical information mining model of total alkalinity and concentration characteristic distribution of related pollutants in eco-industrial park is constructed, the hydrogeological conditions are identified, the characteristic structural parameters of total alkalinity in eco-industrial park are determined, the improved genetic evolutionary algorithm method is adopted to manage the distribution characteristic of total alkalinity and concentration of related pollutants in eco-industrial park, and the aquifer parameters in the evaluation area are simulated. A transfer conduction control model of total alkalinity and related pollutants concentration characteristic distribution in eco-industrial park was established. The diversion rate and throughput of total alkalinity and related pollutants concentration characteristic distribution in eco-industrial park were taken as constraint indicators, and the transfer control of total alkalinity and related pollutants concentration characteristic distribution in eco-industrial park was carried out, so as to realize numerical quantitative detection and analysis of total alkalinity in eco-industrial park. The simulation results show that this method has good performance in online detection of total alkalinity of water quality in eco-industrial park, and has strong dredging ability, which improves the treatment level of total alkalinity of water quality and related pollutants in eco-industrial park. © 2021 IEEE.

关键词： Water quality

来源：评论

学校读者我要写书评

暂无评论

Detection of False Data Injection Attacks Based on Spatio-Temporal Characterization in Smart Grids

Detection of False Data Injection Attacks Based on Spatio-Te...

引用

Chinese control and Decision Conference, CCDC

作者： Shouxuan Jiao Qiang Zhao Yinghua Han Jinkuan Wang Hantong Feng College of Information Science and Engineering Northeastern University Shenyang China School of Control Engineering Northeastern University at Qinhuangdao Qinhuangdao China School of Computer and Communication Engineering Northeastern University at Qinhuangdao Qinhuangdao China

ISBN: (数字)9798350387780

ISBN: (纸本)9798350387797

With the increasing popularization of information and communication technologies, the development of smart grids has also emerged. However, the high reliance on information technology puts the grid at risk of malicious attacks. False Data Injection Attack (FDIA)have become a serious threat to the smart grid. While most of the current methods for detecting FDIA focus on determining whether the grid has been subjected to such attacks, they often overlook the importance of considering the topology and temporal correlations within the grid data and are unable to localize their attacks. To address this limitation, we have proposed a novel multi-label attack localization detection method based on spatio-temporal features. Our method considers both time and space and enables the localisation of attacks. Spatial feature extraction is conducted using a Convolutional Neural Network (CNN), which is subsequently subjected to feature filtering through an Attention Mechanism. The filtered features are then channeled into both Long-Term and Short-Term Memory network (LSTM) via a channel fusion process. This intricate process allows for the extraction of spatio-temporal features, ultimately facilitating the accurate localization of attacks. To evaluate the efficacy of our approach, we conducted extensive simulation experiments using the IEEE 14bus system and the IEEE 118-bus system. The results showcase remarkable performance with an overall accuracy of 99.6% for the former and 98.7% for the latter, underscoring the effectiveness of our proposed model.

关键词： Location awareness Correlation Attention mechanisms Accuracy Feature extraction Smart grids Topology

来源：评论

学校读者我要写书评

暂无评论

Transit Search Optimized Least Squares Support Vector Machine for the State of Health Estimation of Lithium-Ion Batteries

Transit Search Optimized Least Squares Support Vector Machin...

引用

Chinese Automation Congress (CAC)

作者： Kangjie Wang Fangshu Cui Yuanhao Shi Bohui Wang School of Electrical and Control Engineering North University of China Taiyuan China School of Computer Science and Technology North University of China Taiyuan China School of Cyber Science and Engineering Xi'an Jiaotong University Xi'an China

ISBN: (数字)9798350368604

ISBN: (纸本)9798350368611

The State of Health (SOH) of lithium-ion batteries is a critical parameter that mirrors the performance of their health monitoring systems. To achieve accurate prediction of SOH, we propose a novel prediction model. The model combines the advantages of variational mode decomposition (VMD) and transit search optimization-least squares support vector machine (TSOA-LSSVM). The constant-current charging time (CCCT), constant-current discharging time (CCDT), and Constant voltage charging time(CVCT) with Internal resistance(IR) are extracted as health indicators (HIs), and the correlations between HIs and SOH are evaluated by using Spearman correlation coefficient (spearman) respectively. With the VMD method, the most correlated HI is decomposed into multiple intrinsic modal functions (IMFs), and each IMF is fitted by the LSSVM. TSOA is used to obtain the most appropriate hyperparameters. The efficacy of the newly developed VMD-TSOA-LSSVM model is assessed by utilizing battery aging data sourced from the Center for Advanced Life Cycle engineering (CALCE). Its performance is then compared to that of the solo LSSVM, the VMD-LSSVM, and the VMD-TSOA-SVM methods. The laboratory outcomes demonstrate that the VMD-TSOA-LSSVM model outperforms other models in prediction and has better robustness and generalization ability.

关键词： Support vector machines Lithium-ion batteries Correlation Noise Voltage Predictive models Search problems Prediction algorithms Robustness Optimization

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving Task-Oriented Semantic Communications Against Model Inversion Attacks

arXiv

引用

arXiv 2023年

作者： Wang, Yanhu Guo, Shuaishuai Deng, Yiqin Zhang, Haixia Fang, Yuguang School of Control Science and Engineering Shandong University Jinan250061 China Department of Computer Science City University of Hong Kong Hong Kong

Semantic communication has been identified as a core technology for the sixth generation (6G) of wireless networks. Recently, task-oriented semantic communications have been proposed for low-latency inference with limited bandwidth. Although transmitting only task-related information does protect a certain level of user privacy, adversaries could apply model inversion techniques to reconstruct the raw data or extract useful information, thereby infringing on users’ privacy. To mitigate privacy infringement, this paper proposes an information bottleneck and adversarial learning (IBAL) approach to protect users’ privacy against model inversion attacks. Specifically, we extract task-relevant features from the input based on the information bottleneck (IB) theory. To overcome the difficulty in calculating the mutual information in high-dimensional space, we derive a variational upper bound to estimate the true mutual information. To prevent data reconstruction from task-related features by adversaries, we leverage adversarial learning to train encoder to fool adversaries by maximizing reconstruction distortion. Furthermore, considering the impact of channel variations on privacy-utility trade-off and the difficulty in manually tuning the weights of each loss, we propose an adaptive weight adjustment method. Numerical results demonstrate that the proposed approaches can effectively protect privacy without significantly affecting task performance and achieve better privacy-utility trade-offs than baseline methods. © 2023, CC BY.

关键词： Economic and social effects

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：