检索结果-内蒙古大学图书馆

4th IEEE International Conference on Mobile Networks and Wireless Communications, ICMNWC 2024

作者： Mohamad, Fayazoddin Dhumpati, Raghu Reenadevi, R. Rao, P.S.V. Srinivasa Sutaria, Kamal Kulkarni, Shirish NY United States Bahrain Polytechnic Department of Computer Science & Engineering Bahrain City Bahrain Salem India Joginpally B R Engineering College Department of Computer Science and Engineering Hyderabad India Parul institute of Engineering and Technology Parul University Faculty of Engineering and Technology Department of Computer Science and Engineering Post Limda India Faculty of Law Pune India

ISBN: (纸本)9798350352931

The detection and tracking of changes in the progression of GI disease using endoscopic video analysis remains difficult due to temporal changes and image complexity. Proper models of prediction are critical in diagnosing individuals at an early stage and offering them treatment. In the work presented in this paper, we introduce novel Attention-Guided Convolutional Neural Network (AG-CNN) combined with LSTM networks to analyze temporal endoscopic video sequences. It uses spatial attention to catch necessary areas and temporal attention to capture assertive illness transformation in video frames. For disease progression prediction the proposed model yield 94.8% accuracy with 93.2% sensitivity and 95.6% specificity. The attention mechanism increased the feature extraction speed by 22 percent when compared to traditional CNN-LSTM classes. Independent validation checks confirmed that the two models produced a prediction concordance of 92.7% based on different patient samples. The overall performance of temporal GI disease progression prediction by the AG-CNN-LSTM framework shows potential usage in clinical diagnosis by providing automated disease progression monitoring and treatment planning. © 2024 IEEE.

关键词： Video analysis

来源：评论

学校读者我要写书评

暂无评论

Principled Penalty-based Methods for Bilevel Reinforcement Learning and RLHF 41

Principled Penalty-based Methods for Bilevel Reinforcement L...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Shen, Han Yang, Zhuoran Chen, Tianyi Department of Electrical Computer and Systems Engineering Rensselaer Polytechnic Institute United States Department of Statistics and Data Science Yale University United States

Bilevel optimization has been recently applied to many machine learning tasks. However, their applications have been restricted to the supervised learning setting, where static objective functions with benign structures are considered. But bilevel problems such as incentive design, inverse reinforcement learning (RL), and RL from human feedback (RLHF) are often modeled as dynamic objective functions that go beyond the simple static objective structures, which pose significant challenges of using existing bilevel solutions. To tackle this new class of bilevel problems, we introduce the first principled algorithmic framework for solving bilevel RL problems through the lens of penalty formulation. We provide theoretical studies of the problem landscape and its penalty-based (policy) gradient algorithms. We demonstrate the effectiveness of our algorithms via simulations in the Stackelberg game and RLHF. Copyright 2024 by the author(s)

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

FairCIM: Fair Interference Mitigation by DNN Switching for Latency-Sensitive Inference Jobs

FairCIM: Fair Interference Mitigation by DNN Switching for L...

引用

2024 IEEE International Conference on Autonomic Computing and Self-Organizing Systems, ACSOS 2024

作者： Nabavinejad, Seyed Morteza Reda, Sherief Guo, Tian Worcester Polytechnic Institute Computer Science Department WorcesterMA United States Brown University School of Engineering ProvidenceRI United States

ISBN: (纸本)9798350363876

It is a common practice to co-locate several jobs, such as DNN inference ones, on a single machine to improve resource utilization, energy efficiency, and overall performance. However, individual job performance might degrade when these jobs compete for shared resources. This degradation can in particular affect latency-sensitive jobs bound by Service Level Agreements (SLA), and result in SLA violations. To tackle this issue and mitigate the impact of interference on latency, we design a system called FairCIM. For certain applications such as image classification, various DNNs with varying accuracy and computational complexity are proposed. Upon detection of SLA violations, FairCIM dynamically switches between those DNNs to maintain the latency in the presence of co-location interference. To ensure fairness, FairCIM selects the jobs for DNN switching based on their resource utilization. We conduct experiments using diverse DNNs, datasets, and hardware platforms to evaluate the FairCIM effectiveness. Compared to another approach that uses a resource exchange mechanism, FairCIM's flexibility achieved by DNN switching substantially reduces SLA violations and improves the effective accuracy by up to 244%. © 2024 IEEE.

关键词： Energy efficiency

来源：评论

学校读者我要写书评

暂无评论

IP-RPL: A Protocol for Efficient Point-to-Point Communication in Low Power and Lossy Networks 20

IP-RPL: A Protocol for Efficient Point-to-Point Communicatio...

引用

20th IEEE India Council International Conference, INDICON 2023

作者： Jaisooraj, J. Sudevan, K. Kumar, S D Madhu National Institute of Technology Calicut Department of Computer Science and Engineering Calicut India Government Polytechnic College Palakkad Department of Computer Hardware Engineering Palakkad India

ISBN: (纸本)9798350305593

The Internet of Things (IoT) has become a reality, and with it a host of challenges for fulfilling its potential. Being a key IoT-enabling technology, the Low Power and Lossy Network (LLN) has a decisive role in the future of the IoT paradigm. The LLN routing protocols, including the IPv6 Routing Protocol for LLNs (RPL), lack efficiency in handling point-to-point communications. Considering the rapidly changing Internet scenario in which point-to-point communications have a share of approximately half of the total traffic, the need to address the concerns of point-to-point routing in LLNs is increasingly experienced than ever before. In this paper, we present an Improved P2P RPL (IP-RPL) that efficiently handles the point-to-point traffic in LLNs. The proposed protocol constructs up to four point-to-point source routes, satisfying the constraints given by the higher layers, on-demand towards the destination(s). IP-RPL mitigates the control overhead and latency associated with frequent point-to-point route discoveries through a well-defined route caching technique. The simulation results indicate a better performance for IP-RPL compared to its existing counterparts in terms of packet delivery ratio, average power consumption of nodes, packet overhead, and end-to-end delay. © 2023 IEEE.

关键词： Internet of Things Low Power and Lossy Networks Point-to-Point Communications RPL

来源：评论

学校读者我要写书评

暂无评论

Dermoscopic Skin Lesion Classification using Color Features Based on Fine-Tuning of Resnet50 and Densenet121 Transfer Learning Models

Dermoscopic Skin Lesion Classification using Color Features ...

引用

2024 International Conference on Intelligent Algorithms for Computational Intelligence Systems, IACIS 2024

作者： Kujani, T. Kumar, V. Dhilip Bhuvanya, R. Kavitha, A. Sathya, T. Sathiya Priya, S. Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Sri Ramachandra Institute of Higher Education and Research Sri Ramachandra Faculty of Engineering and Technology Chennai India Government Polytechnic College Computer Engineering Karur India Sri Sairam Engineering College Computer Science and Business Systems Chennai India

ISBN: (纸本)9798350360660

Skin cancer, which stands as the most prevalent form of human malignancy, is primarily identified through visual examination. The procedure for identifying skin lesions typically starts with an initial clinical assessment, which might be followed by dermoscopic analysis, a biopsy, and a subsequent histopathological checkup. Image-based Skin lesion classification presents a significant challenge due to the subtle and intricate variations in their appearance. Deep Convolutional Neural Network (DCNN) show promising results in managing diverse and intricate tasks involving a wide array of finely detailed object categories. Skin lesions Classification is shown in this work initially using a six-layered CNN performed on the skin cancer dataset to classify seven classes of lesions with 10015 images. Exploratory data analysis of the dataset is performed to identify any outliers and to verify the balance of samples in each class. It was observed after 50 epochs, the training accuracy was 98.03% and the testing accuracy was 67.40%. To avoid the overfitting observed in the CNN approach, the pre-trained transfer learning models, Resnet50 and Densenet121 were finetuned with data augmentation to handle the imbalance of samples present in seven classes. The results obtained prove that the Densenet121 model achieves high performance compared with the other Resnet50 model after augmentation. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Collision-Aware Evolutionary Algorithm for Multi-Agent Coverage Path Planning 11

Collision-Aware Evolutionary Algorithm for Multi-Agent Cover...

引用

11th International Conference on Machine Intelligence Theory and Applications, MiTA 2024

作者： Ma, Xiu-Wen Huang, Ting Liu, Wei-Li Gong, Yue-Jiao Guangzhou Institute of Technology Xidian University Guangzhou China Guangdong Polytechnic Normal University School of Computer Science Guangzhou China South China University of Technology School of Computer Science and Engineering Guangzhou China

ISBN: (纸本)9798350385670

Multi-agent coverage path planning (MACPP) aims to find the shortest paths for agents to collaboratively accomplish an area coverage task. Most current MACPP studies focus on introducing various area decomposition methods to decouple the MACPP problem into individual single-agent path planning problem. However, these methods often neglect the collisions among agents in the planning process, which may result in agent crashes. In this paper, we introduce a collision-aware evolutionary algorithm to provide a collision-free path set for agents. The proposed algorithm adopts the trapezoidal decomposition to divide the region into convex areas and evenly assigns these areas to agents. Based on the decomposed areas, we propose an interarea visiting order planning method for agents. Within each area, we implement intra-area coverage path planning for each agent. Furthermore, we incorporate collision detection between agents and adjust the paths of conflict agents to prevent collisions. Finally, we conduct experiments with three state-of-the-art approaches in four different environments to verify that the proposed algorithm can effectively complete the task and avoid the collision risk. © 2024 IEEE.

关键词： Multi agent systems

来源：评论

学校读者我要写书评

暂无评论

A Scheme Library-Based Ant Colony Optimization with 2-Opt Local Search for Dynamic Traveling Salesman Problem

引用

computer Modeling in engineering & sciences 2023年第5期135卷 1209-1228页

作者： Chuan Wang Ruoyu Zhu Yi Jiang Weili Liu Sang-Woon Jeon Lin Sun Hua Wang College of Software Henan Normal UniversityXinxiang453007China College of Computer and Information Engineering Henan Normal UniversityXinxiang453007China School of Computer Science and Engineering South China University of TechnologyGuangzhou510006China School of Computer Science Guangdong Polytechnic Normal UniversityGuangzhou510665China Department of Military Information Engineering Hanyang UniversityAnsan15588South Korea College of Engineering and Science Institute for Sustainable Industries and Liveable CitiesVictoria UniversityMelbourneVIC 8001Australia

The dynamic traveling salesman problem(DTSP)is significant in logistics distribution in real-world applications in smart cities,but it is uncertain and difficult to *** paper proposes a scheme library-based ant colony optimization(ACO)with a two-optimization(2-opt)strategy to solve the DTSP *** work is novel and contributes to three aspects:problemmodel,optimization framework,and ***,in the problem model,traditional DTSP models often consider the change of travel distance between two nodes over time,while this paper focuses on a special DTSP model in that the node locations change dynamically over ***,in the optimization framework,the ACO algorithm is carried out in an offline optimization and online application framework to efficiently reuse the historical information to help fast respond to the dynamic *** framework of offline optimization and online application is proposed due to the fact that the environmental change inDTSPis caused by the change of node location,and therefore the newenvironment is somehowsimilar to certain previous *** way,in the offline optimization,the solutions for possible environmental changes are optimized in advance,and are stored in a mode scheme *** the online application,when an environmental change is detected,the candidate solutions stored in the mode scheme library are reused via ACO to improve search efficiency and reduce computational ***,in the algorithm design,the ACO cooperates with the 2-opt strategy to enhance search *** evaluate the performance of ACO with 2-opt,we design two challenging DTSP cases with up to 200 and 1379 nodes and compare them with other ACO and genetic *** experimental results show that ACO with 2-opt can solve the DTSPs effectively.

关键词： Dynamic traveling salesman problem(DTSP) offline optimization and online application ant colony optimization(ACO) two-optimization(2-opt)strategy

来源：评论

学校读者我要写书评

暂无评论

Chat with MES: LLM-driven user interface for manipulating garment manufacturing system through natural language

引用

Journal of Manufacturing Systems 2025年 80卷 1093-1107页

作者： Yuan, Zhaolin Li, Ming Liu, Chang Han, Fangyuan Huang, Haolun Dai, Hong-Ning Institute of Artificial Intelligence University of Science and Technology Beijing Beijing China Shunde Innovation School University of Science and Technology Beijing Guangdong China Department of Industrial and Systems Engineering The Hong Kong Polytechnic University Hong Kong Research Institute of Advanced Manufacturing The Hong Kong Polytechnic University Hong Kong Research Centre for Digital Transformation of Tourism The Hong Kong Polytechnic University Hung Hom Hong Kong Centre for Transformative Garment Production Hong Kong Science Park Pak Shek Kok Hong Kong Department of Computer Science Hong Kong Baptist University Hong Kong School of Intelligent Systems Science and Engineering Jinan University Zhuhai China

This paper presents Chat with MES (CWM), an AI agent system, which integrates LLMs into the Manufacturing Execution System (MES), serving as the "ears, mouth, and the brain". This system promotes a paradigm shift in MES interactions from Graphical User Interface (GUI) to natural language interface", offering a more natural and efficient way for workers to manipulate the manufacturing system. Compared with the traditional GUI, both the maintenance costs for developers and the learning costs and the complexity of use for workers are significantly reduced. This paper also contributes two technical improvements to address the challenges of using LLM-Agent in serious manufacturing scenarios. The first one is Request Rewriting, designed to rephrase or automatically follow up on non-standardized and ambiguous requests from users. The second innovation is the Multi-Step Dynamic Operations Generation, which is a pre-execution planning technique similar to Chain-of-Thought (COT), used to enhance the success rate of handling complex tasks involving multiple operations. A case study conducted on a simulated garment MES with 55 manually designed requests demonstrates the high execution accuracy of CWM (80%) and the improvement achieved through query rewriting (9.1%) and Multi-Step Dynamic operations generation (18.2%). The source code of CWM, along with the simulated MES and benchmark requests, is publicly accessible. © 2025 The Authors

关键词： Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Analyzing Neural Network Robustness Using Graph Curvature 3

Analyzing Neural Network Robustness Using Graph Curvature

引用

3rd International Conference on Assured Autonomy, ICAA 2024

作者： Tan, Shuhang Sia, Jayson Bogdan, Paul Ivanov, Radoslav Rensselaer Polytechnic Institute Computer Science Department TroyNY United States University of Southern California Dept. of Electrical and Computer Engineering Los AngelesCA United States

ISBN: (纸本)9798331521011

This paper presents a new look at the neural network (NN) robustness problem, from the point of view of graph theory analysis, specifically graph curvature. Graph curvature (e.g., Ricci curvature) has been used to analyze system dynamics and identify bottlenecks in many domains, including road traffic analysis and internet routing. We define the notion of neural Ricci curvature and use it to identify bottleneck NN edges that are heavily used to "transport data"to the NN outputs. We provide an evaluation on MNIST that illustrates that such edges indeed occur more frequently for inputs where NNs are less robust. These results will serve as the basis for an alternative method of robust training, by minimizing the number of bottleneck edges. © 2024 IEEE.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Research of Technologies and Methods of Web Application Protection in the Infrastructure of a Higher Education Institution with the Assistance of Specialized Systems 6

Research of Technologies and Methods of Web Application Prot...

引用

6th International Congress on Human-computer Interaction, Optimization and Robotic Applications, HORA 2024

作者： Dunayev, Serhii Milevska, Tetiana Voropay, Natalia Murr, Pierre Khvostenko, Vladyslav Sevriukova, Yelyzaveta Cybersecurity department National Technical University "Kharkiv polytechnic institute" Kharkiv Ukraine Computer Engineering Department International University of Science and Technology in Kuwait Kuwait

ISBN: (纸本)9798350394634

We live in a dynamic time when digitalization is taking place all over the world and we are witnessing the transition from analog to digital sources of information. The emergence of various services on the Internet makes people's lives easier every day. The education sector is not standing still either. It is confidently moving with the times. The process of acquiring new knowledge is becoming easier, more convenient and accessible anytime, anywhere with the emergence of interactive online learning platforms. However, the number of cyber threats is growing along with the rapid digitization of our environment. News of new threats and backdoors in operating systems, applications, and Web sites are revealed on a daily basis. Cyber criminals do not stand still, every day they test new ways of system penetration, modify the means of attack on users and hardware, and improve their skills in the field of social engineering. In the process of creating services for the needs of educational institutions, considerable attention should be paid to the protection of personal data and intellectual property. © 2024 IEEE.

关键词： Cybersecurity

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：