检索结果-内蒙古大学图书馆

6th International Conference on Control and Robotics, ICCR 2024

作者： Phadke, Abhishek Hadimlioglu, Alihan School of Engineering and Computing Christopher Newport University Newport NewsVA United States Texas A&M University-Corpus Christi Department of Computer Science Corpus ChristiTX United States

ISBN: (纸本)9798331518158

UAVs (Unoccupied Aerial Vehicles) work in high-risk environments where disruptions and failures impede their progress. A UAV must exhibit a degree of robustness to these disruptions in order to conduct operations satisfactorily. Like all current vehicular robots, UAVs rely on GNSS (Global Navigation Satellite System) and onboard sensor data to perform navigation, communication, and execute critical actuated behaviors. However, these UAVs may often travel to regions where signal availability is sparse, and incidents arise when critical information such as location and telemetry from primary onboard sensors, ground control, or satellites is unavailable. In such cases, external beacon networks are the solution to address this information scarcity. In critical situations, these beacons can sometimes be the only source of information for an agent that could prevent catastrophic agent or mission failure. This study provides a comprehensive overview of external beacons supporting UAV operations. A taxonomy of sensors, beacons, and marker systems is provided, and four primary categories of beacon systems are discussed. Potential limitations in applying the solution and critical factors for proper implementation are also explored. © 2024 IEEE.

关键词： Global positioning system

来源：评论

学校读者我要写书评

暂无评论

Cooperative Air-Ground Instant Delivery by UAVs and Crowdsourced Taxis 40

Cooperative Air-Ground Instant Delivery by UAVs and Crowdsou...

引用

40th IEEE International Conference on Data engineering, ICDE 2024

作者： Gao, Junhui Wang, Qianru Zhang, Xin Shi, Juan Zhao, Xiang Han, Qingye Pan, Yan School of Computer Science Northwestern Polytechnical University China School of Computer Science and Technology Xidian University China Air Force Engineering University China National University of Defense Technology Laboratory for Big Data and Decision China School of Management Science and Real Estate Chongqing University China National University of Defense Technology National Key Laboratory of Information Systems Engineering China National University of Defense Technology National Key Laboratory of Parallel and Distributed Computing China

ISBN: (纸本)9798350317152

Instant delivery has become a fundamental service in people's daily lives. Different from the traditional express service, the instant delivery has a strict shipping time constraint after being ordered. However, the labor shortage makes it challenging to realize efficient instant delivery. To tackle the problem, researchers have studied to introduce vehicles (i.e., taxis) or Unmanned Aerial Vehicles (UAVs or drones) into instant delivery tasks. Unfortunately, the delivery detour of taxis and the limited battery of UAVs make it hard to meet the rapidly increasing instant delivery demands. Under this circumstance, this paper proposes an air-ground cooperative instant delivery paradigm to maximize the delivery performance and meanwhile minimize the negative effects on the taxi passengers. Specifically, a data-driven delivery potential-demands-aware cooperative strategy is designed to improve the overall delivery performance of both UAVs and taxis as well as the taxi passengers' experience. The experimental results show that the proposed method improves the delivery number by 30.1% and 114.5% compared to the taxi-based and UAV-based instant delivery respectively, and shortens the delivery time by 35.7% compared to the taxi-based instant delivery. © 2024 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Sentiment classification of MOOC courses by merging local context focus and Bi-directional gated recurrent unit 4

Sentiment classification of MOOC courses by merging local co...

引用

4th International Conference on computer Vision, Application, and Algorithm, CVAA 2024

作者： Jin, Jiayong Dong, Yongquan He, Bugui Zhou, Nan Yan, Linke School of Computer Science and Technology Jiangsu Normal University Jiangsu Xuzhou221116 China Xuzhou Cloud Computing Engineering Technology Research Center Jiangsu Xuzhou221116 China Jiangsu Engineering Technology Research Center of ICT in Education Jiangsu Xuzhou221116 China

ISBN: (数字)9781510687622

ISBN: (纸本)9781510687615

Existing MOOC review sentiment classification methods do not fully utilize the local context information associated with aspect, and they ignore the connection between local and global contexts, while resulting in modeled features that lack the information connection between aspect and contexts. In this paper, we propose a model that incorporates Local Context Focus (LCF) and Bi-Directional Gated Recurrent Unit (Bi-GRU). First, the BERT model is used to dynamically encode course reviews. Then, global semantic features are extracted using the Bi-GRU model to strengthen the connection between the preceding and following texts. Then, the LCF model based on multi-head self-attention is used to obtain local contextual features and splice them with global semantic features. Finally, the Softmax function is utilized to output the classification results. The experimental accuracies of the proposed model on the three MOOC course review datasets reach 97.96%, 96.76%, and 94.16%, respectively, which are improved by 0.70%, 0.42%, and 0.03% over the suboptimal baseline model. The proposed model significantly improves the effectiveness of MOOC course review sentiment classification, and provides a useful reference for the optimization and improvement of MOOC courses. © 2025 SPIE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Integrating AI and Semi-Immersive AR Technology for Brain Tumor Diagnosis 10

Integrating AI and Semi-Immersive AR Technology for Brain Tu...

引用

10th International Conference on engineering and Emerging Technologies, ICEET 2024

作者： Amara, Kahina Guerroudji, Mohamed Amine Kerdjidj, Oussama Khedir, Meriem Zenati, Nadia Atalla, Shadi Mansoor, Wathiq Ramzan, Naeem Centre for Development of Advanced Technologies Algiers Algeria College of Engineering and It University of Dubai Dubai United Arab Emirates Higher School of Computer Science Sidi Bel Abbes Algeria School of Computing Engineering and Physical Sciences University of the West of Scotland Scotland Paisley United Kingdom

ISBN: (纸本)9798331532895

Brain tumours, characterised by abnormal cell development inside the brain, pose a significant risk to individuals due to their high mortality rate. Early identification is essential for accurate diagnosis and successful treatment to enhance patient outcomes. However, diagnosing small tumours can be difficult and error-prone, as it largely depends on the experience and qualifications of medical personnel. Therefore, an automated diagnostic approach that reduces diagnostic time while increasing accuracy is desperately needed. This study addresses the challenges of manual diagnosis by applying deep learning algorithms to brain tumour segmentation. Additional challenges in applying deep learning for tumour segmentation include handling low-quality scans, variations in tumour features, and insufficient data. We present an emerging concept combining Artificial Intelligence and Augmented Reality as a valuable tool, providing deep learning model deployment, immersive visualisation, and interactive functionalities to support diagnosis and surgical interventions for brain tumours. The achieved performance is competitive with the literature, and feedback from medical professionals after deployment evaluation is satisfactory. © 2024 IEEE.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Benchmarking Hallucination in Large Language Models based on Unanswerable Math Word Problem 30

Benchmarking Hallucination in Large Language Models based on...

引用

Joint 30th International Conference on Computational Linguistics and 14th International Conference on Language Resources and Evaluation, LREC-COLING 2024

作者： Sun, Yuhong Yin, Zhangyue Guo, Qipeng Wu, Jiawen Qiu, Xipeng Zhao, Hui Software Engineering Institute East China Normal University China School of Computer Science Fudan University China Shanghai AI Laboratory China Shanghai Key Laboratory of Trustworthy Computing Shanghai China

ISBN: (纸本)9782493814104

Large language models (LLMs) are highly effective in various natural language processing (NLP) tasks. However, they are susceptible to producing unreliable conjectures in ambiguous contexts called hallucination. This paper presents a new method for evaluating LLM hallucination in Question Answering (QA) based on the unanswerable math word problem (MWP). To support this approach, we innovatively develop a dataset called Unanswerable Math Word Problem (UMWP) which comprises 5200 questions across five categories. We developed an evaluation methodology combining text similarity and mathematical expression detection to determine whether LLM considers the question unanswerable. The results of extensive experiments conducted on 31 LLMs, including GPT-3, InstructGPT, LLaMA, and Claude, demonstrate that in-context learning and reinforcement learning with human feedback (RLHF) training significantly enhance the model's ability to avoid hallucination. We show that utilizing MWP is a reliable and effective approach to assess hallucination. Our code and data are available at https://***/Yuki-Asuuna/UMWP. © 2024 ELRA Language Resource Association: CC BY-NC 4.0.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

MLforGait: Using Machine Learning Models for Automatic Gait Recognition Without Subject Cooperation

引用

National Academy science Letters 2025年 1-5页

作者： Abdullah, Muhammad Irsyad Sudhamsu, Gadug Rani, Pooja Jagtap, Jayant Chohan, Mandeep Kaur Ramudu, M. Janaki Singh, Devendra Alkhayyat, Ahmed Management and Science University Shah Alam Malaysia Department of Computer Science and Engineering School of Engineering and Technology JAIN (Deemed to be University) Bangalore India Department of Computer Science and Engineering Chandigarh Engineering College Chandigarh Group of Colleges Jhanjeri Mohali India NIMS School of Computing Science and Artificial Intelligence NIMS University Rajasthan India Department of Computer Science and Engineering Vivekananda Global University Jaipur India Department of Computer Science and Engineering Raghu Engineering College Dakamarri India Department of Computer Science and Engineering Uttaranchal Institute of Technology Uttaranchal University Dehradun India College of Technical Engineering The Islamic University Najaf Iraq

Gait recognition enables non-intrusive identification of individuals through their walking patterns, eliminating the need for active cooperation. It has gained popularity due to its remote applicability and ability to work with low-resolution videos. This study explores the effectiveness of Scale-Invariant Feature Transform and Speeded-Up Robust Features for gait recognition. Decision Tree and Random Forest classifiers are employed to evaluate the recognition performance of these features, achieving accuracies of 85.20% and 87.80%, respectively, on the CASIA-A dataset.

关键词： Classification Decision tree Gait recognition Human identification Random forest SIFT SURF

来源：评论

学校读者我要写书评

暂无评论

Advanced Machine Learning Models for Electrical Fault Detection and Classification in Transmission Lines

Advanced Machine Learning Models for Electrical Fault Detect...

引用

Intelligent Data Communication Technologies and Internet of Things (IDCIoT), International Conference on

作者： Dugganapalli Deepika Maridinapalli Madhu Charan Sri Chakradhar Nossam P.V Manitha Department of Electrical and Electronics Engineering Amrita School of Engineering Bengaluru India Department of Computer Science and Engineering Amrita School of Computing Bengaluru India

ISBN: (数字)9798331527549

ISBN: (纸本)9798331527556

With the fast development of power systems, efficient methods for fault detection and classification are needed to maintain the stability, safety and efficiency of the systems. In particular, this paper investigates advanced machine learning techniques for fault detection and classification in transmission lines using supervised learning algorithms, including Support Vector Machines (SVM), Decision Trees, Random Forests, Naïve Bayes and Linear Discriminant Analysis (LDA). A dataset consisting of three phase currents and voltages from MATLAB simulations of normal and faulty system operations are used to study the problem. These models classify faults to be single line to ground, line to line and the three phase faults. Performance evaluation is done by metrics such as accuracy, precision, recall, F1 score, and AUC with respect to ROC analysis. Decision Trees are of high reliability and have good computational efficiency for fault detection among the models. The results presented in this research point to the importance of machine learning in reducing fault diagnosis circuit in order to achieve a more intelligent and resilient power transmission systems.

关键词： Support vector machines Fault diagnosis Power transmission lines Computational modeling Fault detection Power system stability Electrical fault detection Transmission line measurements Decision trees Random forests

来源：评论

学校读者我要写书评

暂无评论

Zero-day Android botnet detection using neural networks

引用

Neural computing and Applications 2025年第17期37卷 10795-10805页

作者： Seraj, Saeed Pimenidis, Elias Trovati, Marcello Polatidis, Nikolaos Department of Computer Science Royal Holloway University EghamTW20 0EX United Kingdom School of Computing and Creative Technologies University of the West of England BristolBS16 1QY United Kingdom Department of Computer Science Edge Hill University OrmskirkL39 4QP United Kingdom School of Architecture Technology and Engineering University of Brighton BrightonBN2 4GJ United Kingdom

Android devices have evolved to offer a diverse array of services, spanning applications related to banking, business, health, and entertainment. The widespread adoption of Android devices, coupled with the open-source architecture of the Android operating system, has rendered them a prime target for malicious actors. Among the most perilous threats are Android botnets, which enable malicious actors, often referred to as botmasters, to exert remote control for the execution of destructive attacks. Android botnets have huge potential to be an emerging threat to mobile device security. In this paper, we focus on detecting evolving Android botnets and introduce a new dataset of 3458 apps, represented by 455 permission-based features. We propose an improved multilayer perceptron neural network for zero-day botnet detection. Our methodology, in this way, achieves an accuracy of 98.5%, thus outperforming traditional classifiers. It has a lot of functionality and is based on the neural network approach, making it able to identify slight botnet behaviours in order to improve Android security. © The Author(s) 2024.

关键词： Bot (Internet)

来源：评论

学校读者我要写书评

暂无评论

Drug Recommendation System Using LDA 1

Drug Recommendation System Using LDA

引用

1st International Conference on Futuristic Technologies, INCOFT 2022

作者： Sripathi, Satwik Reddy Pradyumna, Nadella Venkata Sai Dhanush, Akula Subramani, R. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science and Engineering Bengaluru India Amrita School of Engineering Department of Mathematics Bengaluru India

ISBN: (纸本)9781665450461

These days, people are very much concerned about their health. Many want to lead a healthy and long life. However, studies reveal that errors due to doctor's and pharmacist's experience resulted in many people's death. These medical errors are costing us our lives. Technical algorithms like LDA, PCA and other machine learning algorithms can help in topic modelling that would play a major role in the industry. These technologies can aid in the investigation of medical history and, by being doctor-friendly, can help to prevent medical errors. In this paper, a medicine is proposed based on the review taken from the patient as it would be identified with our model created with LDA. Recommendation system that analyses sentiment analysis of patient review data to discover the best medication for a disease is done in our work. © 2022 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Guarding Voices, Protecting Homes: A Comprehensive Case Study on Voice Assistant Security in Smart Living 12

Guarding Voices, Protecting Homes: A Comprehensive Case Stud...

引用

12th International Symposium on Digital Forensics and Security, ISDFS 2024

作者： Rehman, Fazalur Hashmi, Joudat Abdullah, Moiz Zaman, Hafsah School of Electrical Engineering and Computer Science National University of Sciences and Technology Islamabad Pakistan College of Engineering Georgia Tech University Department of Analytics United States Air University Faculty of Computing and Artificial Intelligence Department of Cyber Security Islamabad Pakistan

ISBN: (纸本)9798350330366

The evolution of technologies in the last decades has transformed the whole human interaction experience with the digital world. Integrated into users' home voice assistant devices has rationalized personal interaction with the technology however convenience of intelligent voice assistant presents security and privacy risks. This paper investigates the security vulnerabilities of smart voice assistant devices specifically focusing on Google Home Mini. Through a series of simulated attacks and comprehensive analysis, this study uncovers potential risks ranging from unauthorized access to user data privacy compromise within home networks. The objective is to raise awareness about these vulnerabilities and their implication urging the need for robust security measures and providing valuable observation for future research. As voice devices are becoming an integral part of daily life addressing these challenges is paramount to ensuring user privacy data integrity and overall security of the smart home ecosystem. © 2024 IEEE.

关键词： Risk assessment

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：