检索结果-内蒙古大学图书馆

16th IEEE International Conference on Computational Intelligence and Communication Networks, CICN 2024

作者： Shanmugam, Thirumurugan Chandrashekar, Chirag Sivaraman, Arun Kumar Nithiyanantham, Janakiraman Ravindran, Priya Narayanan, S T Sarvesh University of Technology and Applied Sciences Department of Computing and Information Sciences Suhar Oman School of Cse Vellore Institute of Technology Chennai India Digital Engineering Solution Centre Photon Interactive Inc. ON Canada K.L.N. College of Engineering Department of ECE Tamilnadu India School of Computer Science Dalhousie University Halifax Canada

ISBN: (纸本)9798331505264

Accurate weather forecasting is essential for sectors like agriculture, aviation, and disaster management. However, deep learning algorithms face challenges in prediction accuracy due to issues like vanishing gradients, overfitting, and high computational demands. This research proposes a novel U-Net based architecture utilizing a Convolutional Neural Network (CNN) bottleneck layer to improve weather forecasting. Key features include a skip-connection mechanism, modified weight update rules, Gaussian-mutation operations, and the Adam optimizer for enhanced feature extraction and faster, more accurate predictions. The model was tested using precipitation data from Doppler Weather Radar (DWR) Chennai Radar and weather parameters from European centre for Medium-Range Weather Forecasts (ECMWF). A dedicated GeoServer facilitates realtime data processing. Experimental results show the proposed algorithm achieves 97.5% accuracy, outperforming CNN and long short-term memory (LSTM) models by 5.84% and 2.41%, respectively. © 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

Sentence Classification Using Quantum Natural Language Processing and Comparison of Optimization Methods 14th

Sentence Classification Using Quantum Natural Language Proce...

引用

12th International Advanced computing Conference, IACC 2022

作者： Rajashekharaiah, K.M.M. Chickerur, Satyadhyan Hegde, Goutam Bhat, Subrahmanya L. Sali, Shubham Annappa School of Computer Science and Engineering K L E Technological University Karnataka Hubballi580 031 India Centre for High Performance Computing K L E Technological University Karnataka Hubballi580 031 India

ISBN: (纸本)9783031356438

The natural language processing (NLP) demands high computing resourses to process language related problems. The evolution of quantum computing hardware and simulators create avenues to design and develop NLP methods to test on these platforms. This research uses quantum natural language processing (QNLP) to simulate the sentence classification and compares optimization techniques (Simultaneous perturbation stochastic approximation: SPSA and convergent optimization via most-promising-area stochastic search: COMPASS) for small dataset and simple sentence structures and the results are promising to show that with the COMPASS optimization technique the model performs better Table 1. When the ansatz depth is less and vice-versa. The research in quantum natural language processing is infancy, the simulation results are promising and the better results can be expected for large datasets with different sentence structures if real quantum computers are available in near future. © 2023, Springer Nature Switzerland AG.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Powerpoint Slide Presentation Control Based on Hand Gesture 3rd

Powerpoint Slide Presentation Control Based on Hand Gesture

引用

3rd International Semantic Intelligence Conference, ISIC 2023

作者： Kumar, Ankit Singh, Kamred Udham Kumar, Gaurav Singh, Teekam Choudhury, Tanupriya Kotecha, Ketan Department of Computer Engineering and Applications GLA University UP Mathura India School of Computing Graphic Era Hill University Dehradun India Department of Computer Science and Engineering Graphic Era Deemed to Be University Dehradun India Uttarakhand Dehradun248007 India Symbiosis Centre for Applied Artificial Intelligence Symbiosis Institute of Technology Symbiosis International University Pune411045 India

ISBN: (纸本)9789819773558

HCI, which stands for "human–computer interaction," has been increasingly concerned with natural interaction methods in recent years. Various ways we interact with computers have benefited from the development of real-time hand gesture recognition programs. The detection of hand motions calls for the use of a camera. The primary form of participation is the employment of a web camera as a virtual human–computer interaction device. In this body of work, we look into how vision-based HCI methods of the present day make use of hand gestures. In the event that consumers are unable to utilise any input device or touch it, this project becomes incredibly useful. Gesture recognition makes it possible to complete an activity without physically accessing the usual input devices (mouse, keyboard, etc.). The user may doodle with his index finger and use his index and middle fingers together to control the pointer's movement on the screen. The user may erase their artwork using the tips of their index, middle, and ring fingers. Using their little finger, the user may go on to the next file, and using their thumb finger and pointing to the left, they can return to the previous file. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Gesture recognition

来源：评论

学校读者我要写书评

暂无评论

Flowmind2Digital: The First Comprehensive Flowmind Recognition and Conversion Approach

arXiv

引用

arXiv 2024年

作者： Liu, Huanyu Cai, Jianfeng Zhang, Tingjia Li, Hongsheng Wang, Siyuan Zhu, Guangming Shah, Syed Afaq Ali Bennamoun, Mohammed Zhang, Liang School of Artificial Intelligence Xidian University China School of Computer Science and Technology Xidian University China School of Science Centre for AI and Machine Learning ECU School of Physics Maths and Computing Computer Science and Software Engineering UWA

Flowcharts and mind maps, collectively referred to as flowmind, play an important role in our daily, and many companies have developed dedicated tools. Hand-drawn flowminds offer significant advantages for real-time and collaborative communication. However, there is an increasing demand to convert them into a digital format for further processing. Automated conversion methods are crucial in addressing the challenges associated with manual conversion, such as the cost of time and learning. Previous works have proposed diverse sketch recognition methods. However, these methods face significant limitations in practical situations. Firstly, most methods are designed for specific fields, making it challenging to extend their usage to other fields. Additionally, none of these methods address the critical step of digital conversion after recognition, which is essential to users. Moreover, existing datasets exhibit significant biases relative to actual data, hindering the methods’ generalization ability. Our paper proposes the Flowmind2digital method and hdFlowmind dataset to address the aforementioned challenges. Flowmind2digital is the first comprehensive recognition and conversion method for flowminds, utilizing a neural network architecture and keypoint detection technology to enhance overall recognition accuracy. Our hdFlowmind dataset consists of 1,776 hand-drawn and manually annotated flowminds, covering 22 scenarios and surpassing existing datasets in size. Our experiments showcase the effectiveness of our method, with an accuracy rate of 87.3% on the hdFlowmind dataset, surpassing the previous state-of-the-art work by 11.9%. Additionally, our dataset demonstrates effectiveness, with a 2.9% increase in accuracy after pre-training and fine-tuning on Handwritten-diagram-dataset. We also highlight the importance of simple graphics for sketch recognition, which can improve accuracy by 9.3%. Copyright © 2024, The Authors. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Intervention of Digital Twin for Smart Monitoring of Battery Management System 14

Intervention of Digital Twin for Smart Monitoring of Battery...

引用

14th International Conference on computing Communication and Networking Technologies, ICCCNT 2023

作者： Joshi, Kapil Gupta, Amit Kaushik, Vishal Anandaram, Harishchander Gupta, Himanshu Kumar, Anil Uttaranchal University Uttaranchal Institute of Technology Department of Cse Dehradun India Graphic Era Hill University Department of Computer Science and Engineering Uttarakhand Dehradun India Upes School of Computer Science Dehradun India Amrita Vishwa Vidyapeetham Centre for Computational Engineering and Networking Tamil Nadu Coimbatore India Coer University Roorkee India Dit University School of Computing Dehradun India

ISBN: (纸本)9798350335095

The use of digital twins (DT) has made important improvements not just from the beginning of the process of automobile development through the final phases of vehicle building, but additionally during its usage, collecting essential information from its everyday activities to make traveling more joyful, relaxed, and secure. This study organizes the DT development history, fundamental principles, and essential technologies, as well as summarizing current research methodologies and problems in battery simulation, state estimate, remaining useful life (RUL) projection, battery protection, and management. In addition, study provide methods for batteries digital simulation, real-time status calculation, variable charging supervision, dynamic heat leadership, and energetic leveling regulation in the smart battery management system (BMS) using DT. The study also provides prospects for DT growth in the industry of battery. Lastly, the article concludes with an examination of the technological economic effects of DT technology, which will revolutionize conventional automobile manufacturing, as well as the barriers to continued growth. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

A Framework for Tele-rehabilitation Gaming System 6

A Framework for Tele-rehabilitation Gaming System

引用

6th International Conference on Applied Computational Intelligence in Information Systems, ACIIS 2023

作者： Elaklouk, Ahmed M. S. Zuarni Ramli, Ratna Edris, Ibrahim Padilla-Valdez, Nena Jumaily, Adel Al Universiti Teknologi Brunei School of Computing and Informatics Bandar Seri Begawan Brunei Universiti Teknologi Mara Negeri College of Computing Informatics and Mathematics Seremban Malaysia Universiti Teknologi Brunei Centre for Communication Bandar Seri Begawan Brunei Faculty of Engineering University of Technology Brunei Brunei Department of Computer Science and Software Engineering School of Computing University of Western Australia Australia Ensta Bretagne University France

ISBN: (纸本)9798350317428

Brain damage resulting from stroke and traumatic brain injury is the primary cause of complicated disability and one of the major causes of mortality in most countries, burdening healthcare systems owing to the growth in the number of brain injury victims. Rehabilitation is required to deal with the brain damage. With fewer therapists available, it is very challenging to manage patients and even motivate them to participate actively in their rehabilitation. Patients have frequently complained that many traditional rehabilitation systems are monotonous and uninteresting. The study's objective is to propose a telerehabilitation gaming system framework that can serve as guidance for developing an affordable rehabilitation gaming system that can motivate and engage patients and increase rehabilitation effectiveness. The research methodology is based on synthesizing related research and currently available technologies. The proposed framework includes the therapist and patient attached with vital constructs: tailoring tools, instructional content, game characteristics, tailored games, and performance. It is an internet-based communication structure that connects the Rehabilitation Gaming System to the hospital and other care provider networks. The proposed framework is evaluated by a panel of five experts. The results reveal that all experts believe that the proposed framework can serve as a useful guide for creating gaming interventions that can boost the patient's motivation and engagement and increase the effectiveness of rehabilitation. © 2023 IEEE.

关键词： Serious games

来源：评论

学校读者我要写书评

暂无评论

Intelligent traffic prediction system using hybrid convolutional neural networks for smart cities

引用

Multimedia Tools and Applications 2024年 1-19页

作者： J, Jeba Sonia G, Arun Kumar kumar, ERajesh Raju, K. Narasimha Sudha, V. Kshirsagar, Pravin R. Tirth, Vineet Rajaram, A. Department of Data Science and Business Systems School of Computing College of Engineering and Technology SRM Institute of Science and Technology Tamil Nadu Chennai603203 India Department of Electronics and Communication Engineering JSS Academy of Technical Education Uttar Pradesh Noida201301 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Andhra Pradesh Vaddeswaram522302 India Andhra Pradesh Visakhapatnam530048 India Department of Electronics and Communication Engineering Sona College of Technology Tamil Nadu Salem636005 India Department of Electronics & amp Telecommunication Engineering J D College of Engineering & ampManagement Maharashtra Nagpur India Mechanical Engineering Department Centre for Engineering and Technology Innovations College of Engineering King Khalid University Asir Abha61421 Saudi Arabia Department of Electronics and Communication Engineering EGS Pillay Engineering College Nagapattinam India

Intelligent Traffic Management Systems (ITMS) play a crucial role in advancing smart city applications by addressing the rapid increase in road traffic due to the growing number of vehicles. Effective real-time traffic prediction is essential to avoid congestion, yet existing systems often struggle with high delays and insufficient accuracy. This paper introduces an innovative ITMS based on a Hybrid Convolutional Neural Network (HCNN) to overcome these challenges. The proposed system integrates numerous smart devices, including smart vehicles, with an edge computing framework where the HCNN model is deployed. The HCNN combines Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to enhance prediction accuracy and reduce latency. Experimental results demonstrate that the HCNN model achieves up to 95% prediction accuracy while reducing delays by up to 50% compared to conventional methods. These improvements are significant for smart city applications, ensuring timely and precise traffic management. The study validates the effectiveness of the HCNN model in improving traffic prediction and proposes its potential for broader smart city implementation. © The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Aatma Yoga: Automation of Yoga Pose Recognition and Recommendation using Deep Learning 7

Aatma Yoga: Automation of Yoga Pose Recognition and Recommen...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Duppala, Vijaya Raghava Marepalli, Harika Yadav Kirti Jain, S. Anusha, Koduru Thangavel, Senthil Kumar Kumar, B Senthil Bindu, Avadhani Satish, Latha Sekar, Jeeva Amrita Vishwa Vidyapeetham Amrita School of Computing Department of Computer Science And Engineering Coimbatore India Amrita Vishwa Vidyapeetham Amrita Darshanam-International Centre For Spiritual Studies Coimbatore India Krishnamacharya Yoga Mandiram Research Department Chennai India Prana Yoga Studio Chennai India

ISBN: (纸本)9798350359299

Youngsters often face stress, pressure, and various challenges in today's fast-paced world. The need for yoga arises as a powerful tool to alleviate stress, promote mental well-being, and enhance resilience. The purpose of this research is to present an innovative approach to personalized yoga practice by leveraging deep learning and computer vision techniques for real-time monitoring and correction of yoga poses. The system consists of mood-based yoga recommendation, yoga pose detection, yoga pose estimation, and pose correction. Through the seamless integration of Singular Value Decomposition (SVD), YOLOv3, PoseNet, and an angle heuristic algorithm, this work ensures accurate analysis and correction of the user's yoga poses, facilitating an effective and personalized yoga experience. By addressing the lack of personalization and emotional oversight prevalent in traditional yoga practices, the work aims to promote emotional balance, stress relief, and physical wellness. Through this innovative approach, the work endeavors to transform the traditional paradigm of yoga practice, offering a more personalized, effective, and holistic wellness experience for practitioners. © 2024 IEEE.

关键词： Heuristic algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep Reinforcement Learning for Addressing Disruptions in Traffic Light Control

引用

computers, Materials & Continua 2022年第5期71卷 2225-2247页

作者： Faizan Rasheed Kok-Lim Alvin Yau Rafidah Md Noor Yung-Wey Chong School of Engineering and Computer Science University of HertfordshireHatfieldAL109ABUK Department of Computing and Information Systems Sunway UniversitySubang Jaya47500Malaysia Faculty of Computer Science and Information Technology University of MalayaKuala Lumpur50603Malaysia National Advanced IPv6 Centre Universiti Sains MalaysiaUSMPenang11800Malaysia

This paper investigates the use of multi-agent deep Q-network(MADQN)to address the curse of dimensionality issue occurred in the traditional multi-agent reinforcement learning(MARL)*** proposed MADQN is applied to traffic light controllers at multiple intersections with busy traffic and traffic disruptions,particularly *** is based on deep Q-network(DQN),which is an integration of the traditional reinforcement learning(RL)and the newly emerging deep learning(DL)*** enables traffic light controllers to learn,exchange knowledge with neighboring agents,and select optimal joint actions in a collaborative manner.A case study based on a real traffic network is conducted as part of a sustainable urban city project in the Sunway City of Kuala Lumpur in *** is also performed using a grid traffic network(GTN)to understand that the proposed scheme is effective in a traditional traffic *** proposed scheme is evaluated using two simulation tools,namely Matlab and Simulation of Urban Mobility(SUMO).Our proposed scheme has shown that the cumulative delay of vehicles can be reduced by up to 30%in the simulations.

关键词： Artificial intelligence traffic light control traffic disruptions multi-agent deep Q-network deep reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Accelerating fluid flow in Quantum computing using GPU

Accelerating fluid flow in Quantum Computing using GPU

引用

computer, Electronics & Electrical engineering & their Applications (IC2E3), International Conference on

作者： Joel Dandin Satyadhyan Chickerur School of Computer Science and Engineering KLE Technological University Hubballi India Centre for High Performance Computing School of Computer Science and Engineering KLE Technological University Hubballi India

In the last few years, quantum computing has evolved as the next big technological breakthrough. Many big companies are actively researching this area and have built open-source frameworks which can be used to develop solutions for problems that connect be solved by classical computers. One such problem is the solution of Navier-Stokes equations which takes exponential time for simulation but using quantum computers, they can be solved in polynomial time. But the current state of quantum computation does not enable everyone to test their implementation on a real quantum computer. In this situation, a simulator enables rapid prototype and testing techniques and algorithms for when the real quantum computer is ready. This paper focuses on simulating fluid flow algorithms using a quantum framework, such as Navier- Stokes equations, with the lattice Boltzmann method (LBM) used to numerically solve the relevant system of equations on both CPU and GPU to speed up the process. The quantum framework used in this paper is Qiskit, an open-source software development kit created by IBM that allows developers to create and test quantum algorithms. NVIDIA cuQuantum is an SDK of optimized libraries and tools for expediting quantum computing operations used in this paper to solve the fundamental problem of modeling large-size quantum circuits using the power of GPU

关键词：

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：