检索结果-内蒙古大学图书馆

Robotics and Technologies for Industrial Automation (ROBOTHIA), IEEE International Conference on

作者： Lee Wei San Samuel-Soma M. Ajibade Muhammed Basheer Jasser Adefemi Ayodele Babatunde Adedotun Ajayi Mbiatke Anthony Bassey Department of Data Science and Artificial Intelligence Faculty of Engineering and Technology Sunway University Selangor Darul Ehsan Malaysia Research Centre for Nanomaterials and Energy Technology (RCNMET) Faculty of Engineering and Technology Sunway University Selangor Malaysia Research Centre for Human-Machine Collaboration (HUMAC) Faculty of Engineering and Technology Sunway University Petaling Jaya Selangor Malaysia University of East London London UK Department of Cyber security Faculty of Computing & Informatics Ladoke Akintola University of Technology Ogbomoso Nigeria Department of Business Administration Universiti Tun Hussein Onn Malaysia Batu Pahat Malaysia

ISBN: (数字)9798350356755

ISBN: (纸本)9798350356762

image recognition, powered by machine learning (ML), has significantly advanced applications in both dance movement recognition and robotic vision. This review examines key ML techniques, including Convolutional neural networks (CNNs), Deep neural networks (DNNs), Self-Organizing Maps (SOMs), and Long Short-Term Memory (LSTM) networks, alongside pose estimation methods like OpenPose and Part Affinity Fields (PAFs). These techniques enhance dance classification, real-time feedback, and motion analysis, with OpenPose + LSTMs and PAFs + LSTMs demonstrating the highest accuracy. Notwithstanding progress, obstacles such as high computational costs, data dependency, and real-time implementation challenges persist. Beyond dance, these methods are critical in robotic vision, intelligent automation, and industrial image processing, enabling autonomous robotic navigation, defect detection in manufacturing, and AI-driven motion tracking. By leveraging human movement analysis for robotics, ML improves human-robot interaction, robotic-assisted rehabilitation, and industrial automation. Despite progress, challenges such as high computational demands, data dependency, and real-time constraints remain. This review explores future directions, including multimodal data fusion, hybrid AI models, and real-time optimization, bridging the gap between AI-driven motion systems and intelligent automation to enhance adaptability and efficiency across domains.

关键词： Intelligent automation Humanities Solid modeling image recognition Accuracy Service robots Robot sensing systems Real-time systems Robots Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Improvement of image Classification Technique Using Transfer Learning

Improvement of Image Classification Technique Using Transfer...

引用

Advances in Electrical, Computing, Communication and Sustainable Technologies (ICAECT), International Conference on

作者： Devanand Bhonsle Ruhi Uzma Priyanka Prasad Rushikesh Bankar Manjushree Nayak Sampada Vishwas Massey Tanu Rizvi Eiectrical Engineering Shri Shanakaracharya Technical Campus Bhilai India Electrical Engineering Anjuman College of Engineering & Technology Nagpur India Artificial Intelligence and Machine Learning Shri Shanakaracharya Institute of Professional Management & Tech Bhilai India Electronics & Telecommunication Engineering G. H. Raisoni Institute of Engineering and Technology Nagpur India Computer Science Engineering NIST University Berhampur Odisha India Computer Science Engineering Shri Shanakaracharya Technical Campus Bhilai India

ISBN: (数字)9798350356236

ISBN: (纸本)9798350356243

image classification is one of the fundamental task in the digital image processing and computer vision. It is very essential to get high accuracy in it which requires substantial computational resources and a large dataset for the training using deep neural networks. Transfer learning technique is one of the solution which mitigate various challenges by leveraging pre-trained models on large datasets. In this paper; the effectiveness of the transfer technique is exhibited for the purpose of enhancing the image classification. A comprehensive survey has been done of the recent advancement for the purpose to investigate the strategies of transfer learning technique including feature extraction, fine tuning and domain adaption. Experimental results exhibits the efficacy of the transfer learning in the improvement of classification accuracy with less computational complexity. This paper also discusses practical consideration, challenges and future research scope for the utilization of transfer learning for image classification applications.

关键词： Training Surveys Adaptation models Accuracy Computational modeling Transfer learning Lighting License plate recognition Tuning image classification

来源：评论

学校读者我要写书评

暂无评论

Intelligent Resource Allocation for Edge-IoT: Enhancing QoE with Deep Reinforcement Learning

Intelligent Resource Allocation for Edge-IoT: Enhancing QoE ...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： B Sreedhar C Sasikala V T Ram Pavan Kumar M Ruhisulthana Shaik Syed Muqthadar Ali Yadaiah Balagoni Department of CSE (AI&ML) G Pulla Reddy Engineering College Kurnool India Department of CSE Srinivasa Ramanujan Institute of Technology Ananthapuramu India Department of Computer Science Kakaraparti Bhavanarayana College Vijayawada India Department of ECE Sir C Ramalinga Reddy Polytechnic College Eluru India Department of CSE CVR College Of Engineering Hyderabad India Department of Emerging Technologies Mahatma Gandhi Institute of Technology Gandipet India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

A resource allocation framework zeroed in on Quality of Experience (QoE) that is explicitly intended for the heterogeneous edge Internet of things (IoT) environment's dynamic and fluctuated situation. applications for the Internet of Things (IoT) are confronting edge figures. Be that as it may, because of the heterogeneity of usages, the edge cloud finds it trying to relegate complex compelled resources (handling, memory, limit, information transmission, etc) with limitations in light of the Quality of Service (QoS) necessities of clients. In this exploration, we tackle the issue of resource allocation in Edge-IoT structures by supporting a canny framework called Deep Edge that assigns resources to the different IoT applications with the sole motivation behind working on the Quality of Experience (QoE) of the clients. To accomplish this objective, we create a complex QoE model that considers adjusting the different prerequisites of Internet of Things applications to the accessible edge resources. The arrangement is accomplished by choosing a QoS necessity arrive at that the accessible resources can meet. Moreover, we propose a brilliant two-stage deep reinforcement learning (DRL) move toward that successfully allots edge resources to help IoT applications and further develop QoE for people. Not at all like the famous DRL, our arrangement utilizes deep neural networks (DNN) to design the Edge-IoT state to joint resource allocation movement, which incorporates resource allocation and QoS class. Along these lines, DNN can be used to deal with exercises' exploration. The cooperative exertion not just builds the quality of experience (QoE) of clients and fulfills the prerequisites of assorted applications, yet it likewise adjusts the QoS necessities to the accessible resources.

关键词： image edge detection Quality of service artificial neural networks Information processing Deep reinforcement learning Dynamic scheduling Quality of experience Internet of Things Resource management Edge computing

来源：评论

学校读者我要写书评

暂无评论

GRU Based Multiview Summarisation to obtain fast effective Key-frame

GRU Based Multiview Summarisation to obtain fast effective K...

引用

International Conference on Computer, Electrical & Communication Engineering (ICCECE)

作者： Vijay Anand Kandaswamy S Joshua Kumaresan Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences. Saveetha University Chennai India

ISBN: (数字)9798331513894

ISBN: (纸本)9798331513900

This paper proposes a novel approach to video summarisation by introducing a feature variance model that enhances video frame extraction. In typical video record aggregation systems, a variety of image processing tasks, such as acquisition, preprocessing, segmentation, and feature extraction, should be carried out with high precision to guarantee seamless system performance. Among these, feature extraction is essential since it breaks down large amounts of visual data into more manageable, informative vectors, and the success of the system is directly impacted by how effectively this process functions. Widely Recurrent neural networks (RNNs) are used in supervised video summarisation processes to obtain a model for the temporal dependencies between video frames. RNN’s ability to learn long-range memory in the video is limited, and CNN often focusses on local information while losing long-term knowledge when the input sequence is lengthy. Therefore, a Gated Recurrent Unit based neural Network (GRU-NN) for video summarisation is proposed, to classify them into keyframes and non-keyframes. Keyframes are selected for summarisation, while non keyframes are discarded or reduced. We explore various keyframe extraction techniques, analyse the performance of the proposed summarisation model, and discuss the results. Finally, we offer insights into the model’s potential improvements and its broader applications in video summarisation tasks.

关键词： Deep learning image segmentation Computer vision Analytical models Computational modeling Visual analytics System performance Feature extraction Vectors artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Exploring Retinal Vessel Segmentation: Deep Learning Models and Their applications

Exploring Retinal Vessel Segmentation: Deep Learning Models ...

引用

Advancement in Computation & Computer Technologies (InCACCT), International Conference on

作者： Tanishq Soni Sheifali Gupta Komuravelly Sudheer Kumar Chitkara University Institute of Engineering and Technology Chitkara University Punjab India School of Computer Science and Artificial Intelligence SR University Warangal Telangana India

ISBN: (数字)9798331543891

ISBN: (纸本)9798331543907

Retinal vascular segmentation is essential for the early identification and monitoring of numerous ocular and systemic conditions, including diabetic retinopathy, glaucoma, and hypertension. The emergence of deep learning methodologies, particularly convolutional neural networks (CNNs) and U-Net architectures, has markedly enhanced the precision and efficacy of retinal vascular segmentation. This review paper extensively examines contemporary deep learning methodologies, concentrating on model structures, problems, and assessment measures. This paper discusses the strengths of deep learning techniques in improving upon the limitations of traditional image processing methods, such as thresholding and edge detection, while handling complex vascular structures and varied image quality. It also emphasizes the availability of publicly accessible datasets, namely DRIVE, STARE, and CHASE_DB1, as research tools in this discipline. Despite this significant progress, a lot remains to be desired, including large-scale annotated datasets, computational demand, and problems in generalization across diverse populations. Finally, the paper concluded with some future directions by integrating explainable deep learning, multi-modal imaging, and the development of lightweight models that are more appropriate for real-time clinical use.

关键词： Deep learning image segmentation Thresholding (Imaging) Reviews Computational modeling Computer architecture Real-time systems Data models Retinal vessels Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

A collaborative inference strategy for medical image diagnosis in mobile edge computing environment

引用

PeerJ Computer Science 2025年 11卷 e2708-e2708页

作者： Zhang, Shiqian Cui, Yong Xu, Dandan Lin, Yusong School of Computer and Artificial Intelligence Zhengzhou University Henan Zhengzhou China Collaborative Innovation Center for Internet Healthcare Zhengzhou University Henan Zhengzhou China School of Computer and Communication Engineering Zhengzhou University of Light Industry Henan Zhengzhou China School of Cyber Science and Engineering Zhengzhou University Henan Zhengzhou China

The popularity and convenience of mobile medical image analysis and diagnosis in mobile edge computing (MEC) environments have greatly improved the efficiency and quality of healthcare services, necessitating the use of deep neural networks (DNNs) for image analysis. However, DNNs face performance and energy constraints when operating on the mobile side, and are limited by communication costs and privacy issues when operating on the edge side, and previous edge-end collaborative approaches have shown unstable performance and low search efficiency when exploring classification strategies. To address these issues, we propose a DNN edge-optimized collaborative inference strategy (MOCI) for medical image diagnosis, which optimizes data transfer and computation allocation by combining compression techniques and multi-agent reinforcement learning (MARL) methods. The MOCI strategy first uses coding and quantization-based compression methods to reduce the redundancy of image data during transmission at the edge, and then dynamically segments the DNN model through MARL and executes it collaboratively between the edge and the mobile device. To improve policy stability and adaptability, MOCI introduces the optimal transmission distance (Wasserstein) to optimize the policy update process, and uses the long short-term memory (LSTM) network to improve the model’s adaptability to dynamic task complexity. The experimental results show that the MOCI strategy can effectively solve the collaborative inference task of medical image diagnosis and significantly reduce the latency and energy consumption with less than a 2% loss in classification accuracy, with a maximum reduction of 38.5% in processing latency and 71% in energy consumption compared to other inference strategies. In real-world MEC scenarios, MOCI has a wide range of potential applications that can effectively promote the development and application of intelligent healthcare. © 2025 Zhang et al.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

VexNet: Vector-Composed Feature-Oriented neural Network

引用

Electronics (Switzerland) 2025年第9期14卷 1897-1897页

作者： Du, Xiao Guo, Ziyou Li, Zihao Cao, Yang Chen, Xing Wu, Tieru School of Mathematics Jilin University Qianjin Street No. 2699 Changchun130012 China School of Artificial Intelligence Jilin University Qianjin Street No. 2699 Changchun130012 China

Extracting robust features against geometric transformations and adversarial perturbations remains a critical challenge in deep learning. Although capsule networks exhibit resilience through vector-encapsulated features and dynamic routing, they suffer from computational inefficiency due to iterative routing, dense matrix operations, and extra activation scalars. To address these limitations, we propose a method that integrates (1) compact vector-grouped neurons to eliminate activation scalars, (2) a non-iterative voting algorithm that preserves spatial relationships with reduced computation, and (3) efficient weight-sharing strategies that balance computational efficiency with generalizability. Our approach outperforms existing methods in image classification on CIFAR-10 and SVHN, achieving up to a 0.31% increase in accuracy with fewer parameters and lower FLOPs. Evaluations demonstrate superior performance over competing methods, with 0.31% accuracy gains on CIFAR-10/SVHN (with reduced parameters and FLOPs) and 1.93%/1.09% improvements in novel-view recognition on smallNORB. Under FGSM and BIM attacks, our method reduces attack success rates by 47.7% on CIFAR-10 and 32.4% on SVHN, confirming its enhanced robustness and efficiency. Future work will extend vexel representations to MLPs and RNNs and explore applications in computer graphics, natural language processing, and reinforcement learning. © 2025 by the authors.

关键词： Linear transformations

来源：评论

学校读者我要写书评

暂无评论

Advancing Peer Review Integrity: Automated Reviewer Assignment Techniques with a Focus on Deep Learning applications 1st

Advancing Peer Review Integrity: Automated Reviewer Assignme...

引用

1st International Conference on Computation of artificial Intelligence and Machine Learning, ICCAIML 2024

作者： Bhaisare, Bhumika Bharati, Rajesh Department of Computer Engineering Dr. D. Y. Patil Institute of Technology Pune Pimpri India

ISBN: (纸本)9783031714801

The reviewer assignment process in academic research papers is crucial for ensuring peer review integrity and fairness, and it is often referred to as the reviewer assignment problem (RAP). This initial step lays the foundation for the entire review process. To address the limitations of manual reviewer assignment, there is a growing trend among journal and conference editors to explore automated solutions. For quite some time, machine learning techniques have found application in this domain, recent attention has shifted toward the application of Deep Learning in the education sector. Deep Learning, rooted in neural networks with diverse processing components, is gaining prominence in fields like natural language processing (NLP) and image recognition. In this comprehensive review, we aim to evaluate the key research achievements in the realm of reviewer assignment algorithms. It commences by presenting background information and discussing the necessity for automated reviewer assignment. The paper then systematically examines the existing research in this domain, with a particular focus on recent advancements in Deep Learning techniques. The review provides an unbiased assessment of the current algorithms’ strengths and weaknesses. Overall, this analysis emphasizes the growing significance of RAP research and the demand for further innovation and framework development in this field. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

applications of artificial neural networks in image processing V : 25-26 January, 2001, San Jose, California / Nasser M. Nasrabadi, Aggelos K. Katsaggelos, chairs/editors;sponsored by IS&T--the Soci

Applications of artificial neural networks in image processi...

引用

2001年

作者： Nasser M. Nasrabadi Aggelos K. Katsaggelos chairs/editors sponsored by IS&T--the Society for Imaging Science and Technology [and] SPIE--the International Society for Optical Engineering publishe

来源：评论

学校读者我要写书评

暂无评论

A Novel Approach to Brain Tumor Classification Using RNN and CNN Algorithm

A Novel Approach to Brain Tumor Classification Using RNN and...

引用

Automation and Computation (AUTOCOM), International Conference on

作者： Hannah Jessie Rani R Trapty Agarwal J Jesupriya Tarang Bhatnagar Swagat Kumar Jena Mithhil Arora School of Engineering and Technology Electrical and Electronics Engineering JAIN (Deemed to be University) Bangalore Karnataka Maharishi School of Engineering & Technology Maharishi University of Information Technology Uttar Pradesh India Department of Computer Applications (DCA) Presidency College Bengaluru India Centre of Research Impact and Outcome Chitkara University Rajpura Punjab India Department of Computer Science and Engineering Siksha ‘O’ Anusandhan (Deemed to be University) Bhubaneswar Odisha India Chitkara Centre for Research and Development Chitkara University Baddi Himachal Pradesh India

ISBN: (数字)9798331542375

ISBN: (纸本)9798331542382

They are aiming to establish a solution for brain tumors that are prevailing neurological diseases and subsequently leading to cancer-related deaths. Correct classification of brain tumors is important for proper diagnosis and planning treatment. Existing methods for brain tumor classification are performed manually and tend to be subjective, not to mention time-consuming. Hence, we require an automated and effective mechanism for brain tumor classification. The present study introduces a novel ensemble procedure utilizing a combination of the Recurrent neural Network (RNN) and Convolutional neural Network (CNN) for brain cancer categories. The LSTM RNN is used to analyze the time-varying features of the magnetic resonance imaging (MRI) scans, whereas 3D CNNs are exploited for spatial appearance descriptions. These two network types collaborate in the brain tumor classification process to determine each class according to its properties. This method enhances the accuracy and swiftness of brain tumor classification. They trained their RNN-CNN model using thousands of MRI scans and found that they could be used to distinguish between these different types of bratypesumors accurately. In addition, our method also decreased processing time compared with standard methods used for manual analysis. Finally, the overall results suggest that our proposed method could be an efficient automated solution for brain tumor classification with the potential to improve early diagnosis and treatment planning of patients suffering from such malignant disease. It is also readily integrated into current health systems, providing it a worthwhile position for neurologists.

关键词： Recurrent neural networks image analysis Accuracy Magnetic resonance imaging Brain tumors Brain modeling Planning Convolutional neural networks artificial intelligence Medical diagnostic imaging

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：