检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Niu, Luyao Sahanbandu, Dinuka Clark, Andrew Poovendran, Radha The Network Security Lab Department of Electrical and Computer Engineering University of Washington SeattleWA98195-2500 United States The Department of Electrical and Systems Engineering Washington University in St. Louis St LouisMO63130-4899 United States

Disturbances may create cascading failures in power systems and lead to widespread blackouts. Controlled islanding is an effective approach to mitigate cascading failures by partitioning the power system into a set of disjoint islands. To retain the stability of the power system following disturbances, the islanding strategy should not only be minimally disruptive, but also guarantee post-disturbance stability. In this paper, we study the problem of synthesizing post-disturbance stability-aware controlled islanding strategies. To ensure post-disturbance stability, our computation of islanding strategies takes load-generation balance and transmission line capacity constraints into consideration, leading to a hybrid optimization problem with both discrete and continuous variables. To mitigate the computational challenge incurred when solving the hybrid optimization program, we propose the concepts of hybrid submodularity and hybrid matroid. We show that the islanding problem is equivalent to a hybrid matroid optimization program, whose objective function is hybrid supermodular. Leveraging the supermodularity property, we develop an efficient local search algorithm and show that the proposed algorithm achieves 1/2 -optimality guarantee. We compare our approach with a baseline using mixed-integer linear program on IEEE 118-bus, IEEE 300-bus, ActivSg 500-bus, and Polish 2383-bus systems. Our results show that our approach outperforms the baseline in terms of the total cost incurred during islanding across all test cases. Furthermore, our proposed approach can find an islanding strategy for large-scale test cases such as Polish 2383-bus system, whereas the baseline approach becomes intractable. © 2023, CC BY.

关键词： Integer programming

来源：评论

学校读者我要写书评

暂无评论

NM-LUD: A NLOS Mitigation Method with Low-cost UWB Devices for Indoor Positioning

NM-LUD: A NLOS Mitigation Method with Low-cost UWB Devices f...

引用

International Conference on computers, Communications, and Systems (ICCCS)

作者： Tong Wu Han Li Bo Gao Ke Xiong Pingyi Fan Khaled Ben Letaief Engineering Research Center of Network Management Technology for High Speed Railway of Ministry of Education School of Computer and Information Technology Beijing Jiaotong University Beijing China Collaborative Innovation Center of Railway Traffic Safety Beijing Jiaotong University Beijing China National Engineering Research Center of Advanced Network Technologies Beijing Jiaotong University Beijing China Department of Electronic Engineering Tsinghua University Beijing China Department of Electrical and Computer Engineering Hong Kong University of Science and Technology Hong Kong

Ultra-wideband (UWB) is a popular technology for indoor positioning. However, non-line-of-sight (NLOS) propagation caused by human occlusion dramatically affects the accuracy of UWB-based indoor positioning. Most of the existing works focused on mitigating NLOS errors in the scenarios with building structure occlusion, but the NLOS mitigation under human occlusion has not been well addressed. To this end, this paper aims to mitigate the NLOS impact of human occlusion, and then proposes a method of NLOS mitigation to reduce NLOS ranging errors under human occlusion with low-cost UWB devices (i.e., NM-LUD). It takes a set of signal features extracted from low-cost devices as input, calculates their weights and mitigates the ranging error based on the features' weights. Experiment results on the two data sets collected by LinkTrack S and UML1 UWB devices show that the method reduces ranging error from 0.9009 m to 0.1435 m (about by 84.07%) and from 0.7466 m to 0.0792 m (about by 89.39%) respectively, which greatly mitigates the influence of NLOS caused by human occlusion.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Optimizing Cloud Resource Management Through AI Enhancing Efficiency and Scalability in Modern Computing Environments

Optimizing Cloud Resource Management Through AI Enhancing Ef...

引用

Artificial Intelligence and Emerging Technology (Global AI Summit), International Conference on

作者： Y.L. Malathi Latha Sajjan Choudhuri Abhinaya Reddy Jannepally Yogita D. Bhise Togaru Swathi Sivakoteswara rao Katta Department of Information Technology Stanely College of Engineering and Technology for Women Hyderabad India Management Brainware University Solutions Architect computers and network security Edith Cowan University Australia Computer Engineeriang K. K. Wagh Institute of Engineering Education and Research Nashik MH Department of Master of Business Administration Malla Reddy Engineering College(A) Hyderabad Department of mechanical KITEW Kakinada

ISBN: (数字)9798350379716

ISBN: (纸本)9798350379723

The term “cloud computing“ describes a technique that allows both individuals and organisations to access and utilise resources in a way that has changed and revolutionised society. However, because these environments are dynamic, heterogeneous, and scalable, effective resource management in cloud computing systems remains a major difficulty. Artificial intelligence (AI) technology has emerged as a workable solution to these problems, one that can improve resource management efficiency. This study aims to provide an overview of AI-based approaches for effective resource management in cloud computing services, applications, and systems. This study aims to provide a comprehensive analysis of the ways in which artificial intelligence and cloud computing are impacting education, with a focus on accessibility, effectiveness, and the calibre of the educational process. We found that artificial intelligence led to a 25% improvement in the personalisation of educational information, and cloud computing led to a 60% rise in the capacity of simultaneous users. This was discovered through a mixed-research methodology. Additionally, without compromising the quality of the service, there was a notable decrease in the number of administrative errors and improvements in the scalability of the environment. The results show that the use of these technologies improves the quality of education as a whole in addition to increasing the efficacy and accessibility of educational experiences. In a world where technology is growing at a breakneck pace, this study presents itself as a crucial instrument for propelling future advancements and improvements in the education sector. It accomplishes this by contrasting these results with those of past studies, highlighting the technologies' beneficial synergies.

关键词： Cloud computing Technological innovation Scalability Instruments Education Learning (artificial intelligence) Propulsion Dynamic scheduling Resource management Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Distributed Potential iLQR: Scalable Game-Theoretic Trajectory Planning for Multi-Agent Interactions

Distributed Potential iLQR: Scalable Game-Theoretic Trajecto...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Zach Williams Jushan Chen Negar Mehr Department of Electrical and Computer Engineering University of Illinois Urbana-Champaign Urbana IL USA Raytheon BBN Technologies in the Network & Cyber Technologies Group Cambridge MA USA Department of Aerospace Engineering University of Illinois Urbana-Champaign Urbana IL USA

In this work, we develop a scalable, local tra-jectory optimization algorithm that enables robots to interact with other robots. It has been shown that agents' interactions can be successfully captured in game-theoretic formulations, where the interaction outcome can be best modeled via the equilibria of the underlying dynamic game. However, it is typically challenging to compute equilibria of dynamic games as it involves simultaneously solving a set of coupled optimal control problems. Existing solvers operate in a centralized fashion and do not scale up tractably to multiple interacting agents. We enable scalable distributed game-theoretic planning by leveraging the structure inherent in multi-agent interactions, namely, interactions belonging to the class of dynamic potential games. Since equilibria of dynamic potential games can be found by minimizing a single potential function, we can apply distributed and decentralized control techniques to seek equi-libria of multi-agent interactions in a scalable and distributed manner. We compare the performance of our algorithm with a centralized interactive planner in a number of simulation studies and demonstrate that our algorithm results in better efficiency and scalability. We further evaluate our method in hardware experiments involving multiple quadcopters. 1 1 Code Repository - https://***/labicon/dp-ilqr

关键词：

来源：评论

学校读者我要写书评

暂无评论

SAM-Event-Adapter: Adapting Segment Anything Model for Event-RGB Semantic Segmentation

SAM-Event-Adapter: Adapting Segment Anything Model for Event...

引用

IEEE International Conference on Robotics and Automation (ICRA)

作者： Bowen Yao Yongjian Deng Yuhan Liu Hao Chen Youfu Li Zhen Yang College of Computer Science Beijing University of Technology Beijing China Key Lab of Computer Network and Information Integration (Southeast University) Ministry of Education Nanjing China Department of Mechanical Engineering City University of Hong Kong Kowloon Hong Kong SAR

ISBN: (数字)9798350384574

ISBN: (纸本)9798350384581

Semantic segmentation, a fundamental visual task ubiquitously employed in sectors ranging from transportation and robotics to healthcare, has always captivated the research community. In the wake of rapid advancements in large model research, the foundation model for semantic segmentation tasks, termed the Segment Anything Model (SAM), has been introduced. This model substantially addresses the dilemma of poor generalizability of previous segmentation models and the disadvantage in requiring to retrain the whole model on variant datasets. Nonetheless, segmentation models developed on SAM remain constrained by the inherent limitations of RGB sensors, particularly in scenarios characterized by complex lighting conditions and high-speed motion. Motivated by these observations, a natural recourse is to adapt SAM to additional visual modalities without compromising its robust generalizability. To achieve this, we introduce a lightweight SAM-Event-Adapter (SE-Adapter) module, which incorporates event camera data into a cross-modal learning architecture based on SAM, with only limited tunable parameters incremental. Capitalizing on the high dynamic range and temporal resolution afforded by event cameras, our proposed multi-modal Event-RGB learning architecture effectively augments the performance of semantic segmentation tasks. In addition, we propose a novel paradigm for representing event data in a patch format compatible with transformer-based models, employing multi-spatiotemporal scale encoding to efficiently extract motion and semantic correlations from event representations. Exhaustive empirical evaluations conducted on the DSEC-Semantic and DDD17 datasets provide validation of the effectiveness and rationality of our proposed approach.

关键词： Adaptation models Visualization Semantic segmentation Motion segmentation Transportation Cameras Transformers

来源：评论

学校读者我要写书评

暂无评论

A STABLE, FAST, AND FULLY AUTOMATIC LEARNING ALGORITHM FOR PREDICTIVE CODING networkS 12

A STABLE, FAST, AND FULLY AUTOMATIC LEARNING ALGORITHM FOR P...

引用

12th International Conference on Learning Representations, ICLR 2024

作者： Salvatori, Tommaso Song, Yuhang Yordanov, Yordan Millidge, Beren Emde, Cornelius Xu, Zhenghua Sha, Lei Bogacz, Rafal Lukasiewicz, Thomas VERSES AI Research Lab Los AngelesCA90016 United States MRC Brain Network Dynamics Unit University of Oxford United Kingdom Department of Computer Science University of Oxford United Kingdom School of Health Sciences and Biomedical Engineering Hebei University of Technology China Institute of Logic and Computation Vienna University of Technology Austria Fractile Ltd. London United Kingdom

Predictive coding networks are neuroscience-inspired models with roots in both Bayesian statistics and neuroscience. Training such models, however, is quite inefficient and unstable. In this work, we show how by simply changing the temporal scheduling of the update rule for the synaptic weights leads to an algorithm that is much more efficient and stable than the original one, and has theoretical guarantees in terms of convergence. The proposed algorithm, which we call incremental predictive coding (iPC), is also more biologically plausible than the original one, as it is fully automatic. In an extensive set of experiments, we show that iPC constantly performs better than the original formulation on a large number of benchmarks for image classification, as well as for the training of both conditional and masked language models, in terms of test accuracy, efficiency, and convergence with respect to a large set of hyperparameters. © 2024 12th International Conference on Learning Representations, ICLR 2024. All rights reserved.

关键词： Bayesian networks

来源：评论

学校读者我要写书评

暂无评论

Leveraging Advanced computer Vision for Hazardous Behavior Monitoring on Campus Safety Maintenance

Leveraging Advanced Computer Vision for Hazardous Behavior M...

引用

Electronic Communications, Internet of Things and Big Data (ICEIB), International Conference on

作者： Shang-Te Tsai Zong-Rong Wu Yu-Cheng Chang Wei-Hsin Lin Jia-Yi Lee Wei Chien Business School Yulin Normal University Yulin China Department of Technical and Vocational Program in Artificial Intelligence National Yunlin University of Science and Technology Yunlin Taiwan Department of Computer Science and Information Engineering National Taipei University of Technology Taipei Taiwan Department of Computer Information and Network Engineering Lunghwa University of Science and Technology Taoyuan Taiwan Department of International Business National Pingtung University Pintung Taiwan

There was an incident on a campus involving the casualty of students. It created social unrest and heightened concerns over campus security. Consequently, it becomes important to prevent such incidents. Thus, we devel... 详细信息

ISBN: (数字)9798350360721

ISBN: (纸本)9798350360738

关键词： computer vision Electric potential Neural networks Safety Maintenance Security Sparks

来源：评论

学校读者我要写书评

暂无评论

Deep Learning-Based Approach for Identification of Potato Leaf Diseases Using Wrapper Feature Selection and Feature Concatenation

arXiv

引用

arXiv 2025年

作者： Naeem, Muhammad Ahtsam Saleem, Muhammad Asim Sharif, Muhammad Imran Akber, Shahzad Saleem, Sajjad Akhtar, Zahid Siddique, Kamran School of Information and Software Engineering University of Electronic Science and Technology of China China Faculty of Computing Riphah International University Faisalabad Campus Pakistan Department of Computer Science COMSATS University Islamabad Wah Campus Pakistan Department of Information and Technology Washington University of Science and Technology AlexandriaVA United States Department of Network and Computer Security State University of New York Polytechnic Institute United States Department of Computer Science and Engineering University of Alaska Anchorage Anchorage United States

The potato is a widely grown crop in many regions of the world. In recent decades, potato farming has gained incredible traction in the world. Potatoes are susceptible to several illnesses that stunt their development. This plant seems to have significant leaf disease. Early Blight and Late Blight are two prevalent leaf diseases that affect potato plants. The early detection of these diseases would be beneficial for enhancing the yield of this crop. The ideal solution is to use image processing to identify and analyze these disorders. Here, we present an autonomous method based on image processing and machine learning to detect late blight disease affecting potato leaves. The proposed method comprises four different phases: (1) Histogram Equalization is used to improve the quality of the input image;(2) Feature extraction is performed using a Deep CNN model, then these extracted features are concatenated;(3) Feature selection is performed using wrapper-based feature selection;(4) Classification is performed using an SVM classifier and its variants. This proposed method achieves the highest accuracy of 99% using SVM by selecting 550 features. © 2025, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Diagnosis of Schizophrenia from EEG signals Using ML Algorithms

Diagnosis of Schizophrenia from EEG signals Using ML Algorit...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Tariq Qayyum Zouheir Trabelsi Assadullah Tariq Abdelkader Nasreddine Belkacem Mohamed Adel Serhani College of Information and Technology United Arab Emirates University Al Ain UAE Department of Computer and Network Engineering United Arab Emirates University Al Ain UAE

Early treatment is required to control the symptoms and serious complications caused by schizophrenia (SZ). People suffering from SZ require lifelong treatment. The use of machine learning (ML) models to detect various health problems such as SZ has received considerable attention from researchers in recent years. This study investigated the effectiveness of various ML models to detect and predict SZ using electroencephalogram data. A dataset of 14 healthy schizophrenic patients was used, and 12 features were extracted after applying independent component analysis. Three traditional ML models (logistic regression, support vector machine, and K-nearest neighbors) and a convolutional neural network (CNN) were trained, and their performance was compared. Results demonstrated that the CNN model outperformed the other three models with the highest accuracy score of 95% on validation data. Our results highlight the potential of using ML in the early detection and prediction of SZ, which can help in timely and effective treatment.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Joint Beamforming and Resource Allocation for Integrated Satellite-Terrestrial networks

Joint Beamforming and Resource Allocation for Integrated Sat...

引用

IEEE International Conference on Communications (ICC)

作者： Girim Kwon Wonjae Shin Andrea Conti William C. Lindsey Moe Z. Win Wireless Information and Network Sciences Laboratory Massachusetts Institute of Technology Cambridge MA USA Department of Electrical and Computer Engineering Ajou University Gyeonggi-do South Korea Department of Engineering and CNIT University of Ferrara Ferrara Italy Ming Hsieh Department of Electrical Engineering University of Southern California Los Angeles CA USA

Integrated satellite-terrestrial networks (ISTNs) are essential for providing ubiquitous mobile ultra-broadband service in beyond 5G networks. The spectral efficiency and reliability of ISTN depend on the integrated architecture and its operational strategies including interference management and resource allocation. Our view is to integrate terrestrial access and satellite backhaul networks and to develop an optimization technique for their joint operation. This paper proposes an efficient integrated access and backhaul (IAB) architecture for satellite-terrestrial networks (STNs) based on reverse time division duplexing (TDD) considering both uplink (UL) and downlink (DL). In particular, in-band backhauling and gNodeB (gNB) cooperation are considered for high spectral efficiency and reliability. A framework for joint optimization of cooperative beamforming and resource allocation is developed to maximize the UL-DL rate region of the in-band IAB. The proposed scheme is verified using the 3rd Generation Partnership Project (3GPP) standard channel models. Results show that the proposed scheme significantly outperforms the conventional wireless backhauling, while approaching to an outer bound of the UL-DL rate region.

关键词：

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：