检索结果-内蒙古大学图书馆

2024 International Conference on Communication, Computing and Internet of Things, IC3IoT 2024

作者： Mageswaran, J. Uma Indumathi, G. Kalpana, A.V. Elangovan, G. Lalitha, S.D. Nalini, S. Sohanda, Mayank Kumar Dept. of Computer Science Engineering Amrita School of Computing Vengal Campus Tiruvallur DistTamil Nadu India Srm Institute Of Science And Technology Ramapuram India Srm Institute Of Science And Technology Department Of Data Science And Business Systems Kattankulathur India R.M.K Engineering College Department Of Computer Science And Engineering India Srm Institute Of Science And Technolog Department Of Computing Technologies Kattankulathur India

ISBN: (纸本)9798350352689

Public bus stops in India are becoming more crowded due to the country's fast population expansion. People wait a long time for buses to come, then suddenly congregate around them when they do, packing the buses with people and pushing them up into the footboards, which causes accidents. An additional concern of overcrowding is theft. All of this is the result of numerous bus stops not having adequate information on when busses would arrive. The proposed work paves a very important role for the passengers. The passengers will be provided with the information of the arrival of next bus, seat occupancy and the total passengers inside the bus. The information about the seat occupancy, in-passengers and out-passengers is done with the help of Radio Frequency Identification (RFID) tags. The arrival of the next bus is determined by calculating the duration of the buses that are near using RFID readers placed in different bus stations. The count and the frequency will be interfaced in the web application. The passengers can check the application to know the occupancy and today's society where people can catch the right bus at the station and at the right time. This will solve the problems like waiting in bus stops and wasting time and going in a crowded bus. © 2024 IEEE.

关键词： Buses

来源：评论

学校读者我要写书评

暂无评论

Exploring the Integration of Reinforcement Learning for Enhancing Game Performance: A Comprehensive Review 15

Exploring the Integration of Reinforcement Learning for Enha...

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Bhavana, Munugapati Vatsal, K Vijay Krupa Satyavathi, Yerra Anjali Ravi, Navyatha Kavitha, J. Thrimurthulu, V. MLR Institute of Technology Affiliated to JNTUH Department of CSE Hyderabad India Malla Reddy University Department of CSE Hyderabad India MLR Institute of Technology Department of Data Science Hyderabad India Koneru Lakshmaiah Education Foundation Bowrampet Department of CSE Hyderabad India MLR Institute of Technology Department of Computer Science & Engineering Hyderabad India

ISBN: (纸本)9798350370249

Reinforcement learning, a subset of machine learning, encompasses the process by which an agent learns through trial-And-error feedback to anticipate its subsequent actions. Its versatility extends across various domains, with gaming being a prominent application. Success in gaming often pivots on the formulation of effective strategies, a task that necessitates repetitive game play, consuming valuable time, energy, and resources. This study aims tointegrate a reinforcement learning agent into gaming scenarios, replicating game dynamics and progressively refining outcomes with each iteration. By mimicking the agent's performance, human players can augment their likelihood of success. This document highlights the utilization of reinforcement learning techniques, focusing on the application of Value-based methods (Q-learning, Deep Q Network (DQN)), and Model-based methods(State-Action-Reward-State-Action (SARSA)). Q-learning from Value-based methodis designed as an off-policy algorithm, whereas SARSA from Model-based methods functions as *** outcomes presented encompass insights from previous research on Q-learning and SARSA across diverse test fields or settings. Furthermore, the proposed reinforcement learning methodologies address key facets such as data comprehension, problem categorization, algorithm identification, and algorithm implementation. © 2024 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Evolutionary Dynamic Optimization-Based Calibration Framework for Agent-Based Financial Market Simulators 13

Evolutionary Dynamic Optimization-Based Calibration Framewor...

引用

13th IEEE Congress on Evolutionary Computation, CEC 2024

作者： Yang, Zhenhua Zhong, Muyao Yang, Peng Southern University of Science and Technology Guangdong Provincial Key Laboratory of Brain-Inspired Intelligent Computation Department of Computer Science and Engineering Shenzhen518055 China Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Department of Statistics and Data Science Shenzhen518055 China

ISBN: (纸本)9798350308365

The agent-based financial market simulators serve as an important validation tool for trading strategies. For high-fidelity simulation, it is pivotal to calibrate the parameters of a simulator so that the generated simulation data resembles the observed real market data of interest. In traditional calibration methods, it is typical that the parameters of the simulator are set to be time-invariant. However, the dynamic nature of the real financial market introduces various variability into the behaviors of the market participants over different time intervals, posing in-herent limitations to the traditional methods. A more reasonable approach might involve employing a simulator with time-variant parameters. This suggests that the model parameters can be dynamically adjusted at different stages of the simulation to adapt to the evolving market. Consequently, the calibration problem of the financial market simulators can be treated as a dynamic optimization problem. To dynamically calibrate the simulators, we introduce an Evolutionary Dynamic Optimization (EDO) framework. By monitoring the changes of the best fitness, the whole simulation time interval is adaptively divided into multiple stages. Then the Negatively Correlated Search (NCS) algorithm is employed to effectively adjust the parameters at different simulation stages to better simulate the real financial market. Empirical results on both synthetic and real data verify that our dynamic calibration framework significantly outperforms traditional calibration methods that fixing a parameter for the whole simulation interval. The proposed strategy of detecting dynamic changes is also shown to be more reliable than the naive method of manually segmenting stages. In terms of calibration time, our proposed method significantly improves by nearly 93% compared to the fixed parameter setting, and approximately 61% compared to manual segmentation calibration. © 2024 IEEE.

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

A DCNN with Jellyfish Questoptimization Algorithm in Order to Find Fetus Images 5

A DCNN with Jellyfish Questoptimization Algorithm in Order t...

引用

5th IEEE International Conference on Computing, Power, and Communication Technologies, IC2PCT 2024

作者： Aravinda, K. Manjunatha, B. Kavin, Balasubramanian Prabhu Gangadevi, E. Balusamy, Balamurugan Gite, Shilpa New Horizon College of Engineering Ring Road Bellandur Post Bengaluru India Srm Institute of Science and Technology Department of Data Science and Business Systems Chengalpattu Kattankulathur India Loyola College Department of Computer Science Chennai India Delhi India Aiml Department Pune India

ISBN: (纸本)9798350383522

Incomplete closure around the spinal cord is the underlying cause of spina bifida, a birth condition. Multiple methods exist for identifying the presence of spina bifida. Ultrasound can be used to look for spinal axis deformities. However, due to the distortion inherent in prenatal ultrasound pictures, this method requires the expertise of a skilled physician in order to pinpoint the anomaly. Examining ultrasound pictures visually may be a subjective and error-prone process. The diagnosis procedure for spinal deformities may benefit from a computerised support system that can automatically locate the site of the abnormality. An algorithm for determining whether the entire spine in an ultrasound picture is healthy or diseased would be the first step in developing such software. In this study, we combine the power of the Jellyfish Search Optimisation Algorithm (JFSOA) with a deep convolution neural network to better identify SB. Improved classification accuracy is achieved by JFSOA's optimal selection of the SDL model's learning rate. Foetal ultrasound scans taken in the second trimester are widely regarded as a useful screening technique for identifying birth defects. The foetal spine picture from an ultrasound scan taken at the 18th week of pregnancy is used. Preprocessing pipelines, such as contrast improvement, intensity modification, and denoising, are used to improve the quality of ultrasound pictures and eliminate noise. Using this method, the suggested model can reliably recognise pictures of people with spina bifida. The suggested approach accurately identifies and labels ultrasound pictures as normal or defective based on the attributes retrieved © 2024 IEEE.

关键词： Fetus Abnormalities Jellyfish Search Optimization Algorithm Spina bifida Detection Synergic deep convolution neural network Ultrasound

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Optical Wireless Communication System in Fog Weather Conditions 2

Performance Evaluation of Optical Wireless Communication Sys...

引用

2nd International Conference on Electronics and Renewable systems, ICEARS 2023

作者： Venusamy, Kanagaraj Kannadhasan, S. Prakash, E. Priyadarsini, K. Study World College of Engineering Department of Electronics and Communication Engineering Chennai Coimbatore India Rajalakshmi Engineering College Department of Mechatronics Engineering Chennai India School of Computing Srm Institute of Science & Technology Department of Data Science and Business Systems Chennai Kattankulathur India

ISBN: (纸本)9798350346640

Free space optical communication being an emerging technology, has Fog as a primary challenge on its way which makes fog modelling necessary to manage wireless networks. In this paper, an analytical study was made on the performance of five mathematical fog models employing the NRZ-OOK modulation scheme for transmission and a Si PIN photodiode as the photo receptor. This article focuses on numerous performance specifications including Signal to noise ratio [SNR], Bit error rate [BER] and channel capacity all against visibility under fog for propagations wavelengths of 850 nm and 1550 nm and simulations were carried out in MATLAB. The results indicate that the wavelength of 1550nm as more advantageous option over the others for FSO wireless links and an investigation on different models and their characteristics define their suitability for implementation. © 2023 IEEE.

关键词： Visibility

来源：评论

学校读者我要写书评

暂无评论

Execution of Convolution Coding Method for FPGA in Industrial Automation using VERILOG HDL 7

Execution of Convolution Coding Method for FPGA in Industria...

引用

7th International Conference on Computing Methodologies and Communication, ICCMC 2023

作者： Venusamy, Kanagaraj Kannadhasan, S. Vimalesh, A. Chandramohan, P. Shanmugam, M. Priyadarsini, K. Department of Mechatronics Engineering Rajalakshmi Engineering College Chennai India Department of Electronics and Communication Engineering Study World College of Engineering Coimbatore Chennai India Department of Data Science and Business Systems School of Computing SRM Institute of Science & Technology Kattankulathur Chennai India

ISBN: (纸本)9781665464086

In this paper, the performance study of the FPGA-based encoder is delivered and received with little errors given the large number of applications that employ digital communication to store and retrieve data recently. Forward Error Correction units a wireless communication system region that is essential. Several types of encryption methods have been measured, and the error is completely different. Convolution code writing approach, an honest technique used to rectify mistakes during the data transfer. Convolutional encoder area unit compelled to provide the output in the kind of register style with specified positions in the register. The areas in which the region is entirely arranged are likewise shown as arrows. The position of the registers provides probable state transitions wherein example, L is the register's length. Using these facts, the best way to execute of data transmission in digital communication channels is to correct errors in codes. FPGA device utilized in convolutional encoder's hardware implementation. Vivado and XILINX ISE are usedfor performance analysis. © 2023 IEEE.

关键词： Convolution

来源：评论

学校读者我要写书评

暂无评论

Comprehensive Review of Capsule Networks with a Case Study on Potato Leaf Disease Detection Using CapsNet and Attention Mechanism 8th

Comprehensive Review of Capsule Networks with a Case Stud...

引用

8th International Symposium on Intelligent Informatics, ISI 2023

作者： Shenbaga Moorthy, Rajalakshmi Arikumar, K.S. Prathiba, Sahaya Beni Pabitha, P. Sri Ramachandra Faculty of Engineering and Technology Sri Ramachandra Institute of Higher Education and Research Chennai600 116 India Department of Data Science and Business Systems SRM Institute of Science and Technology Kattankulathur Chennai603 203 India Centre for Cyber Physical Systems School of Computer Science and Engineering Vellore Institute of Technology Chennai600127 India Department of Computer Technology Anna University Madras Institute of Technology Campus Chennai600044 India

ISBN: (纸本)9789819721467

Accurate solutions are needed for a variety of computer vision applications, including medical imaging, object detection, and recognition. Such complicated challenges are beyond the capabilities of artificial intelligence and machine learning, which mainly rely on data and algorithms to learn. The path to Deep Learning (DL) is thus paved. Even though deep learning is incredibly effective at solving complex problems, it is invariant, meaning that it ignores the spatial relationship between the features and instead searches for features only. This can cause the model’s performance to suffer. Additionally, because the model is invariant, gathering a large volume of training data is a difficult undertaking. To address this, the Capsule Network (CapsNet), whose performance outperforms Deep Learning techniques, was introduced. Despite its success, applications of CapsNet and working remain a mystery. Thus, the performance of CapsNet across many applications and obstacles is examined in this study together with the predecessors of CapsNet. Additionally, this paper explores the use of Capsule Networks with an attention mechanism (CapsNet-ATM) for predicting potato leaf diseases. The performance of CapsNet-ATM in this crucial agricultural application is thoroughly assessed and contrasted with the well-known models VGG-16 and VGG-19, providing insight into the system’s efficacy and promise as a reliable tool for the detection and prediction of potato leaf disease. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Quantum Computing's Double-Edged Sword Unravelling the Vulnerabilities in Quantum Key Distribution for Enhanced Network Security

Quantum Computing's Double-Edged Sword Unravelling the Vulne...

引用

2023 IEEE International Conference on Next Generation Electronics, NEleX 2023

作者： Anantraj, I. Umarani, B. Karpagavalli, C. Usharani, C. Lakshmi, S. Jothi Sri Krishna College of Engineering and Technology Department of Computer Science and Business Systems Coimbatore India Kongunadu College of Engineering and Technology Department of Electronics and Communication Engineering Namakkal India Ramco Institute of Technology Department of Artificial Intelligence and Data Science Rajapalayam India

ISBN: (纸本)9798350319088

Quantum computing has emerged as both a boon and a bane in the realm of network security. This paper delves into the intriguing interplay between quantum computing and the vulnerabilities of Quantum Key Distribution (QKD) protocols, a cornerstone of secure quantum communication. While QKD offers unmatched security through the principles of quantum mechanics, it is not impervious to attacks in the age of rapidly advancing quantum computing. We examine these vulnerabilities, highlighting the challenges of ensuring the long-term security of quantum networks in a post-quantum world. Through a comprehensive exploration of threat models and the practicality of QKD, we uncover potential weaknesses in quantum network security. In particular, we investigate QKD's susceptibility to evolving quantum algorithms, hardware vulnerabilities, and post-processing security concerns. This work aims to provide a roadmap for understanding and addressing these vulnerabilities, ensuring the continued robustness of quantum communication networks, and fostering the development of post-quantum cryptographic solutions. As quantum computing advances, its implications for quantum network security are far-reaching. This study underlines the critical need for research and innovation in securing quantum communication. By unravelling the vulnerabilities within Quantum Key Distribution and exploring post-quantum cryptographic alternatives, this research contributes to the development of more resilient and secure quantum networks, safeguarding sensitive information and communications in an increasingly quantum-enabled world. © 2023 IEEE.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Based Autonomous Transport System for Secure Vehicle and Cargo Matching

引用

Intelligent Automation & Soft Computing 2023年第1期35卷 957-969页

作者： T.Shanthi M.Ramprasath A.Kavitha T.Muruganantham Department of Electronics and Communication Engineering Sona College of TechnologySalem636005Tamil NaduIndia Department of Data Science and Business Systems School of ComputingSRM Institute of Science and TechnologyKattankulathur603203TamilnaduIndia Department of Electronics and Communication Engineering K.Ramakrishnan College of TechnologyTiruchirapalli621112TamilnaduIndia Department of Electronics and Communication Engineering K.Ramakrishnan College of EngineeringTiruchirapalli621112TamilnaduIndia

The latest 6G improvements secured autonomous driving's realism in Intelligent Autonomous Transport systems(IATS).Despite the IATS's benefits,security remains a significant *** technology has grown in popularity as a means of implementing safe,dependable,and decentralised independent IATS systems,allowing for more utilisation of legacy IATS infrastructures and resources,which is especially advantageous for crowdsourcing *** technology can be used to address security concerns in the IATS and to aid in logistics *** light of the inadequacy of reliance and inattention to rights created by centralised and conventional logistics systems,this paper discusses the creation of a blockchain-based IATS powered by deep learning for secure cargo and vehicle matching(BDL-IATS).The BDL-IATS approach utilises Ethereum as the primary blockchain for storing private data such as order and shipment ***,the deep belief network(DBN)model is used to select suitable vehicles and goods for ***,the chaotic krill herd technique is used to tune the DBN model’s *** performance of the BDL-IATS technique is validated,and the findings are inspected under a variety of *** simulationfindings indicated that the BDL-IATS strategy outperformed recent state-of-the-art approaches.

关键词： Blockchain ethereum intelligent autonomous transport system security deep belief network

来源：评论

学校读者我要写书评

暂无评论

Enhanced Bone Cancer Detection in MRI Scans via a Hybrid Quantum-Classical Convolutional Neural Network and War Strategy Optimization 4

Enhanced Bone Cancer Detection in MRI Scans via a Hybrid Qua...

引用

4th International Conference on Ubiquitous Computing and Intelligent Information systems, ICUIS 2024

作者： Harshavardhan, A. Sudalaikani, S. Saravanakumar, M. Saritha, S. Rao, Pothamsetty Kasi V. Vnr Vignana Jyothi Institute of Engineering and Technology Department of Computer Science and Engineering Telangana Hyderabad India Mvj college of Engineering Whitefield Department of Mathematics Karnataka India Nehru Institute of Engineering and tech Department of Artificial Intelligence & Data Science Tamil Nadu Coimbatore India Immaculate College for Women Department of Computer Science and Engineering Tamil Nadu Cuddalore India Koneru Lakshmaiah Education Foundation Department of Mechanical Engineering Andhra Pradesh Vaddeswaram India

ISBN: (纸本)9798331529635

Bone cancer is a relatively rare and aggressive form of cancer that originates in the bones and the adjacent soft tissues;the disease is characterized by marked morbidity and mortality. Frequently, early detection is possible, and such medical conditions should be treated to enhance the result of the therapy. MRI is very useful in diagnosing bone cancer since they give clear images of bones and soft tissues. In this work, a new method of bone cancer detection from MRI images is presented with unsharp structure guided filtering for preprocessing and a CSwin transformer to extract features from the preprocessed images. This method further improves visualization and selection of MRI images by improving the representation of features in the image. The main part of the designed method is the Hybrid Quantum-Classical Convolutional Neural Network with War Strategy Optimization (HQCCNN-WSO), which combines the fundamentals of quantum computing and traditional neural networks to enhance the classification performance. Based on the parameters of the War Strategy Optimization algorithm, the model distinguishes between cancerous lesions and healthy bone tissue, and the parameters are further refined for improved performance. The suggested approach demonstrates remarkable accuracy and dependability in the identification of bone cancer, achieving over 99% across all performance criteria. © 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

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：