检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Zhang, Qianyi Ma, Shijian Liu, Boyi Liu, Jingtai Jiao, Jianhao Kanoulas, Dimitrios Institute of Robotics and Automatic Information System Nankai University Tianjin300350 China Electrical and Computer Engineering Department Hong Kong University of Science and Technology China Centre for Data Science University of Macau China Department of Computer Science University College London United Kingdom

Robust and flexible leader-following is a critical capability for robots to integrate into human society. While existing methods struggle to generalize to leaders of arbitrary form and often fail when the leader temporarily leaves the robot’s field of view, this work introduces a unified framework addressing both challenges. First, traditional detection models are replaced with a segmentation model, allowing the leader to be anything. To enhance recognition robustness, a distance frame buffer is implemented that stores leader embeddings at multiple distances, accounting for the unique characteristics of leader-following tasks. Second, a goal-aware adaptation mechanism is designed to govern robot planning states based on the leader’s visibility and motion, complemented by a graph-based planner that generates candidate trajectories for each state, ensuring efficient following with obstacle avoidance. Simulations and real-world experiments with a legged robot follower and various leaders (human, ground robot, UAV, legged robot, stop sign) in both indoor and outdoor environments show competitive improvements in follow success rate, reduced visual loss duration, lower collision rate, and decreased leader-follower distance. Visit the website for the video and code. © 2025, CC BY.

关键词： Motion planning

来源：评论

学校读者我要写书评

暂无评论

ODLCP: A Novel Methodology to Predict Immune system Strength by Using Optimized Deep Learning and Classification Principle

ODLCP: A Novel Methodology to Predict Immune System Strength...

引用

Innovative Computing, Intelligent Communication and Smart Electrical systems (ICSES), International Conference on

作者： Sahunthala S R. Jayasri Neela K Ashwini R S. P. Raut A. Amer Department of AI&DS Rajalakshmi Institute of Technology Chennai Department of Artificial Intelligence and Data Science St. Joseph's college of Engineering Chennai Department of IT Sri Sairam Engineering College Chennai Department of ECE S.A. Engineering College Chennai Department of Civil Engineering Yeshwantrao Chavan College of Engineering Nagpur Maharashtra India Department of Energy Engineer Zarqa University Zarqa Jordan College of Engineering University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Immune responses that are mediated by antibodies are essential to the functioning of the immune system in vertebrates. Due to the fact that antibodies have the ability to connect to antigens, they are employed widely in the treatment of cancer as well as other dangerous ailments. The process of experimentally finding antibody-antigen interactions is an essential stage in antibody therapy. This process is typically laborious, costly, and time-consuming. Because of the continued reliance on multidimensional structures, the deployment of computational methodologies that have been recommended for screening potential antibodies continues to be restricted. We introduce a unique deep learning strategy called Optimized Deep Learning and Classification Principle (ODLCP) for accurate immune strength prediction in this paper. In order to evaluate the effectiveness of this method, we cross-validate it with a more conventional learning method known as Convolutional Neural Network (CNN). By incorporating a wide range of clinical and immunological data, our goal is to develop a prediction model that is capable of accurately determining the strength of an individual's immune system. It is possible that the proposed paradigm would revolutionize healthcare since it will make it possible to develop individualized treatments that will improve immune health and allow for the early detection of disorders connected to immunological processes.

关键词： Deep learning Learning systems data privacy Infectious diseases Medical treatment Antibodies Predictive models data models Convolutional neural networks Public healthcare

来源：评论

学校读者我要写书评

暂无评论

Privacy-Preserving and Lightweight V2I and V2V Authentication Protocol Using Blockchain technology

引用

Intelligent Automation & Soft Computing 2024年第5期39卷 783-803页

作者： Muhammad Imran Ghafoor Awad Bin Naeem Biswaranjan Senapati Md.Sakiul Islam Sudman Satyabrata Pradhan Debabrata Das Friban Almeida Hesham A.Sakr Department of Engineering Pakistan Television CorporationLahore54501Pakistan Department of Computer Science National College of Business Administration and EconomicsMultan60000Pakistan Department of Computer Science and Data Science Parker Hannifin CorpChicagoIL 60503USA Department of Electrical Engineering University of TexasArlingtonTX 76019USA General Motors WarrenMI 48092USA Department of Computer Science and Data Science ECOLABSAuroraIL 60503USA Lecturer at Communications and Electronics Department Nile Higher Institute for Engineering and TechnologyMansoura35111Egypt

The confidentiality of pseudonymous authentication and secure data transmission is essential for the protection of information and mitigating risks posed by compromised *** Internet of Vehicles has meaningful applications,enabling connected and autonomous vehicles to interact with infrastructure,sensors,computing nodes,humans,and fellow *** hoc networks play an essential role in enhancing driving efficiency and safety by reducing traffic congestion while adhering to cryptographic security *** paper introduces a privacy-preserving Vehicle-to-Infrastructure authentication,utilizing encryption and the Moore *** proposed approach enables a vehicle to deduce the planned itinerary of Roadside Units(RSUs)before embarking on a ***,the Certification Authority remains unaware of the specific route design,ensuring *** method involves transforming all Roadside Units(RSUs)in a region into a vector,allowing for instant authentication of a vehicle’s route using RSU ***-world performance evaluations affirm the effectiveness of the proposed model.

关键词： Vehicle-to-vehicle vehicle-to-infrastructure internet of things block chain technology

来源：评论

学校读者我要写书评

暂无评论

Enhanced Condition Monitoring of Low Voltage Motors in Harsh Environments with Ladybug Beetle Optimization and Context-Aware Graph Convolutional Networks

Enhanced Condition Monitoring of Low Voltage Motors in Harsh...

引用

Sustainable Expert systems (ICSES), International Conference on

作者： P. Rajasekar Praveen Prakash Tiwari L. Sharmila Akriti Garg Rayudu Srinivas V V Satyanarayana Tallapragada Department of Data Science and Business System SRM Institute of Science and Technology Kattankulathur Tamil Nadu India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Electrical Engineering Mahatma Jyotiba Phule Rohilkhand University Bareilly Uttar Pradesh India Department of Electrical and Electronics Engineering Aditya College of Engineering & Technology Surampalem Andhra Pradesh India Department of Electronics and Communication Engineering School of Engineering Mohan Babu University Tirupati Andhra Pradesh India

ISBN: (数字)9798331540364

ISBN: (纸本)9798331540371

Low voltage motors are essential in many applications in contemporary industrial settings, as they power machines and guarantee efficient operations. However, these motors often operate in harsh environments where they are exposed to factors such as extreme temperatures, moisture, dust, and vibrations, which can lead to premature wear and failure. This paper proposes a hybrid method for low voltage motor condition monitoring in challenging industrial environments. The proposed method is the combined execution of Ladybug Beetle Optimization algorithm (LBOA) and Heterogeneous Context-Aware Graph Convolutional Network (HCAGCN). Hence it is named as LBOA-HCAGCN technique. Initially, the input data is collected from Triboelectric vibration sensors. Then, the collected data is fed into preprocessing utilizing Generalized Multi-kernel Maximum Correntropy Kalman Filter (GMKMCKF). This filter normalizes and cleans the data by effectively removing noise. Recursive Hilbert Transform (RHT) is used to extract time domain features such as mean, Root Mean Square (RMS), Peak-to-Peak Value, Skewness, and Kurtosis. Then the extracted features are given to HCAGCN for classify the motor health conditions such as normal, broken-bar, bowed-bar, bowed-rotor, faulty bearing, and voltage imbalance. In general, HCAGCN does not express adapting optimization strategies to determine optimal parameters to classify motor conditions. Hence, the LBOA is used to optimize the weight parameter of the HCAGCN which accurately classify motor conditions. The proposed LBOA-HCAGCN is implemented in MATLAB. Performance indicators such as Mean Absolute Error (MAE), Precision, and Accuracy were used to analyze the effectiveness of the proposed approach. Comparing the proposed LBOA-HCAGCN methodology to other existing techniques like Deep Residual Neural Network (DRNN), Convolutional Neural Network (CNN), and Recursive Neural Network (RNN), it achieves 25.8%, 26.4%, and 24.7% greater accuracy, 26.7%, 29.4%, and

关键词： Vibrations Condition monitoring Low voltage Accuracy Graph convolutional networks Transforms Motors Feature extraction Kalman filters Optimization

来源：评论

学校读者我要写书评

暂无评论

Evaluation of Wireless Sensor Networks Module using IoT Approach

Evaluation of Wireless Sensor Networks Module using IoT Appr...

引用

Artificial Intelligence and Smart systems (ICAIS), International Conference on

作者： L. Anand Padmalal S J. Seetha R. Juliana PS Naveen Kumar Gayatri Parasa Department of Networking and Communications School of Computing SRM Institute of Science and Technology Kattanguluthur Department of Computer Science and Engineering Mangalam College of Engg Kerala Department of Computer Science and Business Systems Panimalar Engineering College Chennai Department of Information Technology Loyola-ICAM College of Engineering and Technology Chennai India Department of CSE-DATA SCIENCE St. Ann's College Of Engineering And Technology Chirala AP Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Guntur Andhra Pradesh India

Microcomputers and medical devices with signal transceivers that operate on a specific radio display constitute the backbone of wireless sensor networks (WS Ns) that monitor environmental conditions (temperature, pressure, light, vibration levels, location). It is widely used in WAN sensor networks because of its flexible design and low setup fees. The u200b touch network allows for the connection of up to 65,000 devices, while the Intelligent sensors on other wireless networks are used to transfer data ports and assign wireless networks. Since the price of wireless solutions has been decreasing, and their functional capabilities have been growing, they are gradually replacing wired ones in telemetry data gathering systems and long- distance detecting communication. A deep learning model was used in this investigation to prevent the sensor nodes from manipulating data. Sensor nodes include a lot of parameters and estimations. If these projected data values are altered, network performance will suffer, and the node's lifetime will be reduced. data security became a priority when the sensor nodes were distributed. This new method is 98.82% more efficient than the previous one.

关键词： Temperature sensors Wide area networks Vibrations Temperature measurement Wireless sensor networks Wireless networks Transceivers

来源：评论

学校读者我要写书评

暂无评论

Study on Energy-Saving Optimization and Simulation of Wireless Sensor Networks Using Ant Colony Algorithm 6th

Study on Energy-Saving Optimization and Simulation of Wirele...

引用

6th Euro-China Conference on Intelligent data Analysis and Applications, ECC 2019

作者： Chang, Kuo-Chi Chu, Kai-Chun Lin, Yuh-Chung Nguyen, Trong-The Sung, Tien-Wen Zhou, Yu-Wen Pan, Jeng-Shyang School of Information Science and Engineering Fujian University of Technology Fuzhou China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China Department of Business Management Fujian University of Technology Fuzhou China College of Mechanical and Electrical Engineering National Taipei University of Technology Taipei Taiwan

ISBN: (纸本)9789811650352

The WSN uses wireless communication to realize its information transmission. WSN is a network data system composed of a large number of wireless data collectors with sensing functions. In the WSN-based sensing function structure, the size should be small, more power saving, low price, and can achieve design goals. This study first assumes that WSN uses routing algorithm assumptions in the protocol, and starts from the node position and direction information, and considers the dynamic evolution of the network. Each public node has random mobility, and the WSN node can help determine the location information of the public node, and then use the node location information to have effective routing performance and effective. However, the experimental results also strongly support the energy saving ability of this research. In the overall system energy saving and power consumption reduction, the actual electric energy hazard is greatly reduced, so in the spirit of ISD strategies, if the WSN system is installed in a high-risk and explosive atmosphere, it can significantly improve the safety level. © 2022, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Energy conservation

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence-based scheduling with Multi-Objective Power Optimization in Smart Homes Utilizing Particle Swarm Optimizer

Artificial Intelligence-based scheduling with Multi-Objectiv...

引用

2023 International Conference for Technological engineering and its Applications in Sustainable Development, ICTEASD 2023

作者： Jagan, S. Murugan, G. Rajasathiya, K. Badhoutiya, Arti Hemalatha, S. Ilyos, Kabulov Alzubaidi, Laith H. Indupalli, Tabitha Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology CSE India E.G.S. Pillay Engineering College Department of Computer Science and Business System Tamil Nadu Nagapattinam India P.S.R.R College of Engineering Department of Computer Science and Engineering Sivakasi626140 India GLA University Department of Electrical Engineering Mathura India Padmavathy Engineering College EEE Prince Shri Venkateshwara Chennai127 India National Research University Tashkent Institute of Irrigation and Agricultural Mechanization Engineers Tashkent Uzbekistan The Islamic University Najaf Iraq GRIET Telangana Hyderabad India

ISBN: (纸本)9798350336474

This research proposes a novel approach that integrates distinct Artificial Intelligence (AI) methodologies to address the issue of energy demand planning in Smart Homes (SH). The novel technique is designed to address a multi-objective scheduling issue, aiming to strike a balance between energy consumption and user convenience. The AI-based Power Scheduling issue in a Smart Home (AI-PSSH) involves efficiently scheduling intelligent home equipment within specified constraints and flexible pricing schemes. Various methods have been suggested to tackle the problem of AI-PSSH effectively, including both optimal and non-optimal strategies. This study presents a novel formulation for the Intelligent Home Batteries (IHB) in the context of AI-PSSH, which mitigates the impact of constraints in achieving the optimum or near-optimum outcomes. IHB may optimize the scheduling of intelligent home devices by saving excess power when it is not needed and using saved power when it is more suited to achieve the goals of PSSH. PSSH is a multi-objective optimization problem aimed at concurrently achieving all goals. Incorporating AI into smart homes has facilitated the development of sophisticated energy management techniques in scheduling and power optimization. The approach utilizes Particle Swarm Optimization (PSO) to improve the effectiveness of scheduling algorithms. Integrating PSO into the scheduling process enhances flexibility and enables smart decision-making based on real-time adjustments. The simulation results assess the proposed multi-objective AI-PSSH utilizing the IHB (MO-AI-PSSH) strategy by considering five possibilities of energy use and flexible pricing strategies. The efficiency of the suggested MO-AI-PSSH technique is compared to that of existing cutting-edge algorithms using the suggested databases utilizing the provided datasets. The MO-AI-PSSH technique, as suggested, demonstrates superior performance compared to the other algorithms in almost all instances. ©

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

E-Learning Privacy in the Context of Machine Learning

E-Learning Privacy in the Context of Machine Learning

引用

data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： N. Kirubakaran Varadha Rajan S R. Parijatham Ramya Bharathi K P. Jegadeeshwari V. Vijayaraja Chennai Institue Of Technology Chennai India Department Of Computer Science And Business System Chennai Institue Of Technology Chennai India Madha Institute of Engineering and Technology Chennai S. A. Engineering College Chennai India Dr. MGR Educational and Research Institute (Deemed to be University) Chennai India RMK College of Engineering and Technology Chennai

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

The present paper discusses the privacy issues associated with the usage of machine learning in e-learning systems. Although ML is a promising technology that increases personalization and engagement, it also poses significant security concerns in terms of gathering and using sensitive data. E-learning platforms are vulnerable to problems such as breaches, unauthorized access, and misutilization of personal information. The paper addresses two major concerns: recommendation engines and predictive performance systems, which emphasize the weaknesses and shortcomings in current data privacy and protection measures. In an attempt to address these challenges, the paper develops a privacy-preserving framework based on federated learning and data anonymization technologies. Together, these technologies work in the decentralization of data storage and reduction of exposure yet provide personalized experiences. There is a comparative study that will analyze whether such solutions could help improve data privacy and at the same time maintain functionality in ML. Finally, a balance between security and user experience is brought into discussion, but this time it puts emphasis on the need to have personalization without sacrificing privacy. The final result is a framework for privacy that supports the fulfillment of laws like GDPR, while in the meantime maintaining the best of the personalization that this brings with the ML approach so that an effective solution towards modern e-learning systems can be availed.

关键词： Training data privacy Privacy Electronic learning Federated learning data breach User experience Information filtering Protection Information integrity

来源：评论

学校读者我要写书评

暂无评论

A Surrogate-Assisted Evolutionary Algorithm for Expensive Dynamic Multimodal Optimzation

A Surrogate-Assisted Evolutionary Algorithm for Expensive Dy...

引用

Congress on Evolutionary Computation

作者： Xunfeng Wu Songbai Liu Junkai Ji Lijia Ma Victor C. M. Leung College of Computer Science and Software Engineering Shenzhen University Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China Department of Electrical and Computer Engineering The University of British Columbia Vancouver Canada

ISBN: (数字)9798350308365

ISBN: (纸本)9798350308372

Surrogate-assisted evolutionary algorithms (SAEAs) have demonstrated promising optimization performance in addressing expensive dynamic optimization problems or expensive multimodal optimization problems. However, none of existing SAEAs are designed specifically for tackling expensive dynamic multimodal optimization problems (EDMMOPs). Therefore, in this paper, a first SAEA for tackling EDMMOPs is proposed. First, a nearest density clustering is designed to divide the population into a number of subpopulations, enhancing the diversity of the population. Then, a surrogate-assisted evolutionary optimizer is developed to construct surrogate models for each subpopulation and evolve all solutions in subpopulations by means of the built surrogate models, accelerating the population's converge towards several optimal solutions rapidly. Finally, a transfer learning-based prediction is devised to generate initial samples for next environment by leveraging the stored training samples in the previous environments. To assess the performance of our proposed algorithm, a set of complex benchmark problems is adopted, and the experimental results confirm its superior performance over several competitive algorithms on most test cases.

关键词： Training Heuristic algorithms Computational modeling Sociology Clustering algorithms Evolutionary computation Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Machine Learning Techniques for Arabic Text Classification Using the SANAD dataset 11

Comparative Analysis of Machine Learning Techniques for Arab...

引用

11th International Conference on Mechatronics and Robotics engineering, ICMRE 2025

作者： Attar, Hani Sharrab, Yousef Smadi, Saja Jbaily, Safa Zarqa University Faculty of Engineering Zarqa Jordan University of Business and Technology College of Engineering Jeddah21448 Saudi Arabia Isra University Department of Data Science and Artificial Intelligence Amman Jordan Yarmouk University Dept. Computer Science Irbid Jordan

ISBN: (纸本)9798331509293

Applying Machine Learning (ML) models for Arabic text classification is a growing research field that has recently raised a large number of research. Generally, classifying text involves selecting a category based on its content from a list of pre-established categories. data classification is among the most popular Natural Language Processing (NLP) activities. Moreover, automatic article classifications, such as the Single-label Arabic News Articles dataset (SANAD), are desperately needed to improve the retrieval of the requested data, which this paper investigates. The ML leverages large datasets to improve efficiency;indeed, by locating focal spots within the text, the learning mechanisms facilitate attention tools better suited for handling lengthy texts. The proposed work employs a dataset of 7,000 articles of separately classified Arab news items and then breaks them into seven categories of 1,000 news stories each: politics, education, sports, religion, culture, finance, and medicine. The investigated SANAD consists of three primary datasets from three news portals: Akhbarana, AlArabiva, and AlCtrl. Finally, to obtain trustable information, this study implements a variety of Conventional ML techniques, K-Nearest Neighbor (KNN), Artificial Neural Network (ANN), Support Vector Machine (SVM), and Logistic Regression model to classify the investigated dataset. Our results show that the suggested solution outperformed the analytical search in the Arabic language in terms of accuracy, whereas the Logistic Regression model shows the best results among the seven utilized publicly available dataset classifications. © 2025 IEEE.

关键词： Logistic regression

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：