检索结果-内蒙古大学图书馆

5th International Conference on Data science, Machine Learning and Applications, ICDSMLA 2023

作者： Singh, Vishvendra Jain, Garima Nidhya, M.S. Chaudhary, Chetan Department of Agriculture Vivekananda Global University Jaipur India Noida Institute of Engineering and Technology Uttar Pradesh Noida India Department of Computer Science and Information Technology Jain University Karnataka Bangalore India Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh Lucknow India

ISBN: (纸本)9789819780426

This paper aims to comprehensively examine diverse knowledge switch techniques used in scientific photograph segmentation with deep mastery. Specifically, we know the latest advances in transfer, gaining knowledge of model adaptation, first-rate-tuning, and transfer mastering techniques. For each technique, we discuss the motivations, techniques, and demanding situations concerned with their software for medical picture segmentation. Similarly, we discuss a variety of open issues and destiny studies guidelines. Furthermore, we overview present applications of these methods in clinical photograph segmentation. Sooner or later, we provide a complete contrast of these processes based on the evaluation metrics hired in the literature. This paper aims to shed light on the modern state of understanding switch techniques in medical picture segmentation and to provide a roadmap for future research on this unexpectedly evolving field.. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Optimizing mmWave UAV Networks: Mobility-Aware Deployment and Resource Allocation 100

Optimizing mmWave UAV Networks: Mobility-Aware Deployment an...

引用

100th IEEE Vehicular technology Conference, VTC 2024-Fall

作者： Li, Sicong Yoshii, Kazutoshi Shimamoto, Shigeru Ho, Tu Dac Waseda University Dept. of Communications and Computer Engineering Tokyo Japan Norwegian University of Science and Technology Dept. of Information Security and Communication Technology Trondheim Norway

ISBN: (纸本)9798331517786

Application of Unmanned Aerial Vehicles (UAVs) as small airborne base stations is gradually becoming a research hotspot in the field of wireless communications. With the flexible deployment, wide coverage and low cost, UAV communications show great potential in the fields of emergency rescue, environmental monitoring and military operations. In particular, the easier availability of line-of-sight (LOS) links for UAVs makes its combination with millimetre wave (mmWave) technology significantly enhance the communication bandwidth and data transfer rate. However, the very limited coverage of mmWave communications greatly affects the actual data rates provided by small aerial base stations of mmWave UAVs, especially considering user movement on the ground. In this paper, we study the joint optimisation problem of UAV deployment, user association, spectrum resource allocation in millimetre-wave heterogeneous networks, and explore the impact of different user movement models on system performance. Given that this problem is NP-hard, our paper proposes an MCR-SAC method to maximize the network's total throughput. Simulation results demonstrate an average 18% improvement in total transmission rate compared to the conventional. © 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

DERLight: A Deep Reinforcement Learning Traffic Light Control Algorithm with Dual Experience Replay

引用

Journal of Internet technology 2024年第1期25卷 79-86页

作者： Yang, Zhichao Kong, Yan Hsia, Chih-Hsien School of Computer and Software Nanjing University of Information Science and Technology China Department of Computer Science and Information Engineering National Ilan University Taiwan Department of Business Administration Chaoyang University of Technology Taiwan

In recent years, with the increasingly severe traffic environment, most cities are facing various traffic congestion problems, and the demand for intelligent regulation of traffic signals is also increasing. In this study, we propose a new intelligent traffic light control algorithm, dual experience replay light (DERLight), which innovatively and efficiently designs a dual experience replay training mechanism based on the classic deep Q network (DQN) framework and considers the dynamic epoch function. As results show that compared with some state-of-the-art algorithms, DERLight can shorten the average travel time of vehicles, increase the throughput at intersections, and also speed up the convergence of the network. In addition, the design of this algorithm framework is not only limited to the field of intelligent transportation, but also has transferability for some other fields. © 2024 Taiwan Academic Network Management Committee. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Security of Examination Question Paper Through Blockchain – SecureQ

Security of Examination Question Paper Through Blockchain –...

引用

2024 IEEE International Conference on Innovation and Novelty in engineering and technology, INNOVA 2024

作者： Solomon Raju, G. Sowmya, K.N. Chennamma, H.R. Dept. of Computer Applications JSS Science and Technology University Mysuru India Dept. of Information Science and Engineering JSS Academy of Technical Education Bengaluru India

ISBN: (纸本)9798331505134

Ensuring the security of confidential information is a daunting task for any concerned authority. Proving the authenticity and integrity of exam question papers is a prime responsibility of examination authorities. Storing and sharing question papers on open networks makes them vulnerable to unauthorized access and alterations. The proposed approach redefines question paper management using the Interplanetary File System (IPFS) and blockchain technology, providing a secure, decentralized, and tamper-resistant platform. This solution addresses long-standing challenges and ensures security, accessibility, and data integrity, establishing new standards for examination management. A user-friendly text editor in the framework allows paper setters to create, modify, and format questions effortlessly while preserving content integrity. The integration of this editor streamlines question paper preparation and enhances both efficiency and security. By leveraging a decentralized framework, the proposed solution ensures that the critical tasks of any concerned authority are handled securely and efficiently, overcoming limitations of conventional methods. © 2024 IEEE.

关键词： Data integrity

来源：评论

学校读者我要写书评

暂无评论

Efficient Deep Molecular Dynamic Model Training on Heterogeneous System 29

Efficient Deep Molecular Dynamic Model Training on Heterogen...

引用

29th IEEE International Conference on Parallel and Distributed Systems, ICPADS 2023

作者： Du, Shaokang You, Xin Yang, Hailong Shang, Jing Xiao, Zhiwen Wu, Zhihui Luan, Zhongzhi Qian, Depei Beihang University School of Computer Science and Engineering Beijing China China Mobile Information Technology Center China

ISBN: (纸本)9798350330717

Molecular dynamics is a widely adopted simulation method for analyzing the movement of atoms and molecules. Traditional molecular dynamics simulation methods are computationally intensive and difficult to simulate a large number of atoms. In contrast, molecular dynamics based on deep potential models such as DeePMD can leverage deep learning techniques to improve simulation efficiency. Although DeePMD has incorporated mainstream deep learning frameworks, it still suffers from low performance and efficiency during its model training on heterogeneous systems such as CPU and GPU. Particularly, a large number of operators cannot be accelerated by GPU, resulting in low utilization of GPU computational resources. In this paper, we comprehensively analyze the computational bottlenecks and the corresponding root causes of DeePMD. We correspondingly propose several novel optimization strategies. Specifically, for preprocessing, we identify the computation redundancies and the GPU parallelization opportunities for performance optimization. For training, we propose optimization strategies such as operator fusion, redundancy elimination, and concurrent execution of multiple streams and threads in the computation process. Moreover, we apply systematical optimization of computational graphs and operators. The evaluation results show that DeePMD can achieve significant speedups in several cases after applying our proposed optimizations, resulting in a maximum overall speedup of 6.36× with acceptable accuracy. © 2023 IEEE.

关键词： DeePMD GPU Performance Optimization

来源：评论

学校读者我要写书评

暂无评论

Intelligent Irrigation Mechanism to Enhance The Sensor Network Topology by Using Machine Learning And Artificial Intelligence 2

Intelligent Irrigation Mechanism to Enhance The Sensor Netwo...

引用

2nd IEEE International Conference on Advances in information technology, ICAIT 2024

作者： Sriram, K.P. Anbalagan, E. Sasikumar, S. Kumar, M. Guru Vimal Paramesh, J. Sujatha, P. Kola Assistant Professor Information technology St.Joseph's Institute of Technology OMR Chennai – 600119 Professor Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Professor Department of Computer Science and Engineering Saveetha Engineering College Chennai Associate Professor Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Professor Department of Computer Science and Engineering Mohamed Sathak A.J. College of Engineering Ekattur OMR Siruseri Chennai Associate Professor Department of Information Technology MIT Campus Anna University Chennai Tamil Nadu India – 600044

ISBN: (纸本)9798350383867

This research paper is about the effectiveness of a fusion of machine learning and artificial intelligence into smart irrigation systems in terms of both safety and benefit of the environment and the economy in farming. We've experienced a intensive process of experiment and application of this succeeded method in a real world scenario and we've also detailed the performance of the dynamic irrigation scheduling and the adapter sensor network optimization. Results indicate a significant improvement in key metrics: scheduling was done dynamically which on average was a 10% rise in crop yield and 15% water saving, on the other hand, sensor network optimization with adaptive technology resulted into a 15% increase in cover area and 20% improvement achieved in data transmission reliability. Furthermore, the introduction of the smart irrigation system got impressive results signified by a 10 kg more production per hectare, irrigation efficiency that rose from 70% to 85%, and saving 20% of the water consumed. This calls to mind the capability of cutting-edge technologies to contribute to innovative water management paradigms, improved resource use, and security in food production in face of unpredictable climatic variability. ©2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Hybrid Adam Coati Optimization with DLSTM for Biomedical Parameter Prediction Using Sensor 3

Hybrid Adam Coati Optimization with DLSTM for Biomedical Par...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Rajesh, L. Mohan, H.S. Bindiya, M.K. Visvesvaraya Technological University Dayananda Sagar Academy Of Technology And Management Department Of Information Science And Engineering Karnataka Bengaluru India Karnataka Bengaluru India Sjb Institute Of Technology Department Of Computer Science And Engineering Karnataka Bengaluru India

ISBN: (数字)9798350318609

ISBN: (纸本)9798350318609

A real-time patient monitoring system procesfses a wide range of biomedical parameters and can store and safely capture biomedical parameters. It lowers the diagnosis time of the several diseases that are prevalent in healthcare services. Accurate prediction of biomedical parameters can significantly reduce healthcare costs and assist in effective decision-making. This research proposes a deep learning approach with hybrid optimization for biomedical parameter prediction by using sensors. At first, a healthcare centre with many patients having various disorders is considered. Several biomedical sensors are placed on the patients and these sensors include a respiratory Rate (RR) sensor, Heart rate (HR) sensor, Pulse Rate (PR) sensor, Ambulatory Blood Pressure (ABP)-sensor, and Saturation of Peripheral Oxygen (SpO2). Based on these sensed parameters, biomedical parameter prediction by using sensor based Deep Long Short-Term Memory (DLSTM)is executed. The DLSTM is trained using the proposed Hybrid Adam Coati Optimization(HAdCO). Here, the HAdCO is developed by incorporating of Coati Optimization Algorithm (COA) with Adam Optimizer. Furthermore, the HAdCO-DLSTM is evaluated by utilising metrics, like Mean Absolute Error (MAE), Root Mean Squared Error (RMSE), and Mean Squared Error (MSE). The HAdCO-DLSTM had a minimal value of MAE at 0.0063, MSE at 0.0062, and RMSE at 0.0078. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-Based Plant Disease Detection for Agricultural Applications: A Review 2

Machine Learning-Based Plant Disease Detection for Agricultu...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Chanyal, Himanshu Yadav, Rakesh Kumar Department of Computer Science IFTM University U.P Moradabad India Department of Computer Science & Engineering Maharshi School of Engineering & Technology Maharshi University of Information Technology U.P Lucknow India

ISBN: (纸本)9798350305418

The agriculture sector plays a major role in supplying high-quality food and makes the biggest contribution to growing economies and people. Plant ailments have the power to drastically limit food production and eliminate species diversity. Early identification of plant diseases using accurate or automatic detection techniques can increase the quality of food output and decrease financial losses. In recent years, deep learning has considerably improved the identification precision of image classification and object detection systems. The development of agricultural products is crucial for the economy of the country. Farmers have a wide range of alternatives for the production of numerous goods. However, plant diseases can impair any agricultural product. information technology advancements can be utilised to quickly identify and locate agricultural illnesses. Plant diseases must be categorised in order to evaluate agricultural output, increase market value, and maintain quality standards. Despite the fact that many eminent researchers have contributed their suggestions for developing such systems, there are several shortcomings in the recommended and developed systems. The paper provides in-depth discussions on plant illnesses, disease detection systems, and disease classification using image acquisition, image pre-processing, picture segmentation, feature extraction, and classification. © 2023 IEEE.

关键词： Classification Feature Extraction Image Processing Plant Diseases

来源：评论

学校读者我要写书评

暂无评论

Application of Edge Detection technology Based on YOLOv8 in Smart Mobility Aids 6

Application of Edge Detection Technology Based on YOLOv8 in ...

引用

6th IEEE Eurasia Conference on Biomedical engineering, Healthcare and Sustainability, ECBIOS 2024

作者： Kao, Chiao-Wen Wang, Shih-Tung Huang, Chi-Sheng Ming Chuan University Department of Applied Artificial Intelligence Taipei Taiwan National Taichung University of Science and Technology Department of Computer Science and Information Engineering Taichung Taiwan

ISBN: (纸本)9798350396133

Global aging presents profound challenges, especially concerning the well-being and mobility of the elderly. Fortunately, technological progress offers means for those with mobility limitations. With the aging population, the significance of the safety and accessibility of passive mobility methods becomes increasingly apparent. In this context, many individuals are using wheelchairs or other assistive devices to maintain their independence for daily mobility. Outdoor environments pose numerous challenges for wheelchair users, such as curbs, uneven road surfaces, and unexpected obstacles. These challenges elevate the risk of accidents and limit freedom of movement. To address these challenges and enhance the adaptability of assistive devices outdoors, we proposed a method by combining YOLOv8 for semantic segmentation with real-time edge detection of road scenes to accurately estimate curb positions. By leveraging the proposed method, various elements of the environment are accurately identified in real-time, including curbs and road conditions. Moreover, by calculating the distance between the wheelchair and the curbs, the system provides timely alerts and guidance to users regarding potential hazards or obstacles, empowering them to swiftly respond to their surroundings and avoid collisions for safety. For the elderly with visual impairments or declining reaction capabilities, the benefits of the system are significant. By enhancing safety, accessibility, and adaptability, the system revolutionizes mobility assistance and empowers individuals to lead more fulfilling and independent lives as they age. © 2024 IEEE.

关键词： Wheelchairs

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Assistive Tools with Hand Skeleton Analysis in Online Arts Education 6

AI-Enhanced Assistive Tools with Hand Skeleton Analysis in O...

引用

6th IEEE Eurasia Conference on Biomedical engineering, Healthcare and Sustainability, ECBIOS 2024

作者： Kao, Chiao-Wen Wu, Wen-Hsuan Huang, Chi-Sheng Ming Chuan University Department of Applied Artificial Intelligence Taipei Taiwan National Taichung University of Science and Technology Department of Computer Science and Information Engineering Taichung Taiwan

ISBN: (纸本)9798350396133

The global COVID-19 pandemic has significantly impacted education worldwide, leading to a transition from traditional in-person teaching to asynchronous online learning. Thanks to the valuable contributions of numerous high-quality educational content creators, online audiovisual materials have opened up boundless opportunities for cross-border, crossdisciplinary online learning. This removes geographical and temporal barriers and broadens the spectrum of learning resources available to individuals with diverse needs. Particularly for individuals with disabilities, mobility impairments, or social anxiety, online learning offers an inclusive and accessible environment, fostering the democratization and equity of education and ensuring highquality education regardless of physical conditions or locations. However, unlike foundational subjects, the learning process for arts heavily relies on live demonstrations by teachers and imitation by students, presenting a challenge in the online learning setting especially true for beginners as learning arts often necessitates personalized guidance and real-time feedback. To address this challenge, Mediapipe technology was used to capture the hand movements of both teachers and students in this study. Aeep learning model was used to analyze the similarity of pen-holding postures between students and teachers, thereby providing real-time feedback to supplement the lack of interactivity in online drawing learning and enhance learning outcomes. The developed learning method simulates the role of teachers in traditional classrooms and widens the scope of arts education, providing AI-powered tools for those interested in cultivating aesthetics and lifelong learning opportunities. For the care of the elderly, in addition to enhancing emotional and psychological well-being through aesthetics, the method can be utilized for rehabilitation or the assessment of degenerative conditions. © 2024 IEEE.

关键词： Students

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：