检索结果-内蒙古大学图书馆

Carbonic Acid Gas Emission Rating by Vehicles Using Datascience Techniques 1

International Conference on Advances in Communication technology and computer engineering, ICACTCE 2023

作者： Prathiksha, C. Joshua, Christy Jackson Abdul Quadir, Md. Mohan, Senthilkumar Iwendi, Celestine School of Computer Science and Engineering Vellore Institute of Technology Vellore India School of Information Technology and Engineering Vellore Institute of Technology Vellore632014 India School of Creative Technologies University of Bolton BoltonBL3 5AB United Kingdom

ISBN: (数字)9783031371646

ISBN: (纸本)9783031371639

One factor contributing to the warming of the upper orbit is the rollout of man-made pollutants into the eco system (biogas, Dioxide, laughing gas, and so on). Approximately 14% of total worldwide carbon dioxide emissions are attributed to the road transport. Wheels dust are dangerous to us and contain global warm gases that leads to changes in climate. Products of gas and diesel fuels that include NO2, CO, CH, C6H6, CH2O. Wheels also emit CO2, common human-caused global warm gas. It has been set emission targets to dramatically reduce highway's contribution to Dioxide. These are inferred from the global weather conference's goal of keeping the peak warming of the planet to a maximum of 2 degrees Celsius until 2100. In order to accomplish, in this study, a machine learning hybrid algorithm was developed in the combination of many classifications’ algorithm to find the vehicle CO2 emission with high accuracy rate. The results show that hybrid models can produce more accuracy with a lower error rate when developing an application for emission rating. Accurate carbon emission prediction models can aid in the development of emission-reduction policies. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Carbon dioxide

来源：评论

学校读者我要写书评

暂无评论

Enhancing the Resolution of ChestX-ray Images with SRGAN and Sub-Pixel CNN 7

Enhancing the Resolution of ChestX-ray Images with SRGAN and...

引用

7th International Conference on Image Information Processing, ICIIP 2023

作者： Reddy, K. Lokeshwar Sudharson, S. Natarajan, B. Theetchenya, S. Amrita School of Computing Amrita Vishwa Vidyapeetham Department of Computer Science And Engineering Chennai India Computer Science And Engineering Vellore Institute of Technology Chennai India Computer Science And Engineering Sona College of Technology Salem India

ISBN: (纸本)9798350371406

A crucial diagnostic tool for respiratory and heart disorders is chest X-ray imaging. However, the limited resolution of acquired images can hinder accurate interpretation and subsequent treatment decisions. To address this challenge, we employ deep learning-based super-resolution techniques, specifically SRGAN and ESPCN, to enhance the chest X-ray images. In this study, we proposed a modified ESPCN and present our findings on the application of SRGAN and ESPCN for enhancing chest Xray images. The enhanced image resolution enables radiologists to visualize fine details and subtle abnormalities that were previously difficult to discern. This enhancement significantly improves image interpretation and diagnostic accuracy. Moreover, our findings demonstrate the potential of super-resolution techniques for medical education and training. Through extensive experimentation, we saw significant visual improvements, as evidenced by PSNR(peak signal-to-noise ratio) of SRGAN and proposed ESPCN are 40.46 and 40.17, and achieved SSIM values 0.84 and 0.71 respectively. In conclusion, our study showcases the efficacy of SRGAN and ESPCN in enhancing chest X-ray imaging. By improving image quality and diagnostic accuracy, these techniques have the potential to revolutionize medical diagnostics, leading to better patient outcomes and a more effective healthcare system. © 2023 IEEE.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

Investigations of standalone PV system with battery-supercapacitor hybrid energy storage system for household applications

引用

International Journal of Information technology (Singapore) 2023年第1期15卷 279-287页

作者： Karunanithi, K. Ramesh, S. Raja, S.P. Sreedhar, R. Kannan, S. Ramudu, V. Department of Electrical and Electronics Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai India School of Computer Science and Engineering Vellore Institute of Technology Tamilnadu Vellore 632014 India Department of Electrical and Electronics Engineering Ramco Institute of Technology Rajapalayam India

In this paper, a standalone Photovoltaic (PV) system with Hybrid Energy Storage System (HESS) which consists of two energy storage devices namely Lithium Ion Battery (LIB) bank and Supercapacitor (SC) pack for household applications is proposed. The design of standalone PV system is carried out by considering the average solar radiation of the selected city. During the frequent load variation conditions, the Supercapacitor can discharge its energy since it can discharge high current with less time and during constant load condition LIBs take care of supplying required energy to the load. In this system, P&O algorithm is used for Maximum Power Point Tracking (MPPT) to achieve higher efficiency. MATLAB-Simulink is used to evaluate the performance of the proposed standalone PV system with HESS under various solar irradiance as well as AC loading conditions. © 2022, The Author(s), under exclusive licence to Bharati Vidyapeeth's institute of computer Applications and Management.

关键词： Hybrid energy storage system (HESS) Lithium ion battery (LIB) Photovoltaic (PV) system Supercapacitor (SC)

来源：评论

学校读者我要写书评

暂无评论

Word Level LSTM CNN based sign language to sentence translator

引用

Procedia computer science 2025年 258卷 398-407页

作者： Soham Chatterjee Abinaya S School of Computer Science and Engineering Vellore Institute of Technology Chennai Chennai India

In this study, a robust and lightweight model for sign language gesture recognition is presented, compatible with various sign language standards. This approach addresses challenges such as tracing, occlusion, and computational efficiency by leveraging the MediaPipe framework to extract and preprocess features from the left hand, right hand, face, and body, converting them into NumPy arrays. A layered Long Short-Term Memory (LSTM) network is employed to combine with a Dense Network of Neurons which aid from the heart of Convolution (CNN) layer help and aid the model learn for language-agnostic gesture detection. This methodology achieves high accuracy, even with a limited dataset, demonstrating the model’s efficiency and effectiveness. The model’s simplicity results in a smaller set of trainable hyperparameters, leading to faster training and improved real-time performance. Additionally, the model incorporates a key-to-text pipeline using the T5 module, generating coherent sentences from detected gesture sequences for real-time translation. This enables real-time detection and translation of sign language, applicable across various domains. The model exhibits 95% classification accuracy on a test dataset of organically generated set of datasets and a loss percentage of 0.3% on the same set of classification. Further the sentence formation utilizing a transformer architecture of T5, enables coherent sentence formation from these keywords.

关键词： Sign Language MediaPipe Long Short Term Memory computational overhead gesture recognition key to text pipeline,transformer

来源：评论

学校读者我要写书评

暂无评论

Application of Machine Learning and Deep Learning Algorithms in Predicting Virtual Network Functions for Network Function Virtualization 14

Application of Machine Learning and Deep Learning Algorithms...

引用

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

作者： Spandana, Chereddy Srisurya, Ippatapu Venkata Priyadharshini, A.R. Krithika, S. Sridevi, S. Prasanna Kumar, R. Amrita School of Computing Amrita Vishwa Vidyapeetham Computer Science and Engineering Chennai India Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350335095

Network functions virtualization (NFV) is a methodology that replaces hardware middleboxes with more flexible software alternatives called virtualized network functions (VNFs). These VNFs need to be created and their resource allocation needs to be changed as per traffic demands to dynamically adapt to changes. However, determining the appropriate number of resources to be allotted for each VNF instance is challenging, as fixed resource consumption is often assumed in existing optimization methods. This can lead to either resource wastage or poor service quality. A novel machine learning algorithm trained on actual VNF data, which includes performance measures and resource needs is proposed to address this issue. These trained models can accurately predict the number of resources needed for each VNF to handle a specific traffic load. These machine learning models are incorporated into an algorithm for simultaneous VNF placement and scaling, and their effect on the final VNF placements is evaluated. © 2023 IEEE.

关键词： Network function virtualization

来源：评论

学校读者我要写书评

暂无评论

Comparison of Rule-based Chat Bots with Different Machine Learning Models

引用

Procedia computer science 2025年 259卷 788-798页

作者： Lavish Jain Rahul Ananthasayam Uditi Gupta Radha R School of Computer Science & Engineering Vellore Institute of Technology Chennai 600127 India

A chat bot is an assistant software which is capable of performing conversations with human users in textual or speech format. They can input, understand the context behind it and generate an appropriate response as per the query asked to them. The primary objective of this study is to evaluate and compare the performance and effectiveness of rule-based chat bot systems utilizing different machine learning approaches. The research methodology involves the implementation of multiple chat bot systems based on rule-based architectures, where each system is powered by a distinct machine learning model. These models encompass a range of techniques such as NLP, traditional machine learning algorithms (e.g., Decision trees, Naive Bayes, etc.), and deep learning models (e.g. sequential ANN). Furthermore, to enhance transparency and interpretability of the chat bot systems, the paper explores the integration of instance explanations using LIME.

关键词： Chat Bots Machine Learning Natural Language Processing Rule-based Chat Bots

来源：评论

学校读者我要写书评

暂无评论

引用

4th International Conference on Soft Computing for Security Applications, ICSCSA 2024

作者： Roselinkiruba, R. Jude Moses Anto Devakanth, J. Sharmila, L. Vasumathy, M. Misba, M. Saranya Jothi, C. Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R & D Institute of Science and Technology Chennai Avadi India Madanapalle Institute of Technology and Science Department of Computer Applications Andra Pradesh India Department of Information Technology Kingston Engineering College Vellore India

ISBN: (纸本)9798331515720

Steganography is the method that convert data into bits to make it suitable for hiding. While embedding data the factors such as stego image quality and distortion which cannot be observed by the human eyes. The aim of this study is to increase the stego image with good quality. Initially, the image pixels are separated into different bit planes then it is compared with the secret data bit planes using Fruitfly Optimization Improved Hybridized Algorithm Pixel Similarity (FOIS-PS). For that similar pixel Fitness Function (FF) is applied based on the three important criteria such as edge, entropy and correlation. Finally, the data is embedded in the LSB bits based on their Embedding Capacity (EC). Using this method, the size of the input is reduced. Then, the data is embedded based on difference of pixels within each group of similar pixels. Evaluation metrics shows the quality of the stego image is boosted and also reduces the processing time. © 2024 IEEE.

关键词： Image quality

来源：评论

学校读者我要写书评

暂无评论

An enhanced three factor based authentication protocol using wireless medical sensor networks for healthcare monitoring

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第1期15卷 1165-1186页

作者： Ali, Rifaqat Pal, Arup Kumar Kumari, Saru Sangaiah, Arun Kumar Li, Xiong Wu, Fan Dhanbad826004 India Department of Mathematics Ch. Charan Singh University Uttar Pradesh Meerut250004 India School of Computing Science and Engineering VIT University Vellore Tamil Nadu632014 India School of Computer Science and Engineering Hunan University of Science and Technology Xiangtan411201 China Department of Computer Science and Engineering Xiamen Institute of Technology Xiamen361021 China

With the rapid growth of wireless medical sensor networks (WMSNs) based healthcare applications, protecting both the privacy and security from illegitimate users, are major concern issues since patient’s precise information is vital for the proper diagnosis procedure. So, authentication protocol is one of the efficient mechanisms to deal with trustworthy and authentic users. Several authentication protocols have been proposed in WMSNs environment. However, the most of these protocols are so susceptible to security threats and not suitable for practical use. In this article, recently proposed Amin et al.’s authentication scheme is reviewed and some vulnerabilities like off-line password guessing attack, user impersonation attack, known session-key temporary information attack, the revelation of secret parameters, and identity guessing attack are pointed out. To overcome all the above mentioned vulnerabilities, we have proposed an enhanced three-factor based remote user authentication protocol in WMSNs environment. Further, the proposed protocol is validated using Burrows–Abadi–Needham logic and then simulated using Automated Validation of Internet Security Protocols and Applications tool. Moreover, the security analysis ensures that the proposed protocol is well protected from various types of malicious attacks. In addition, the performance evaluation shows better efficiency and suitability of our protocol over other related protocols. © Springer-Verlag GmbH Germany, part of Springer Nature 2018.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Convolutional Neural Network-based image tamper detection with Error Level Analysis 2

Convolutional Neural Network-based image tamper detection wi...

引用

2nd IEEE International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, ICIITCEE 2024

作者： Manjunatha, S. Swetha, M.D. Rashmi, S. Subramanian, Ananda Kumar Vinoth Kumar, V. Mallikarjuna Swamy, S. Global Academy of Technology Department of Information Science and Engineering Bengaluru India BNM Institute of Technology Department of Computer Science and Engineering Bengaluru India Bengaluru India Vit - University School of Computer Science Engineering Dept of Computational Intelligence Vellore India Vit - University School of Computer Science Engineering and Information Systems Vellore India Jss Academy of Technical Education Dept of Electronics and Communication Engineering Bengaluru India

ISBN: (纸本)9798350306415

Photography is the most important, powerful, and reliable means of expression. Today, digital images not only provide disinformation but also act as agents for secret communication. Users and editing professionals work with digital images for a variety of purposes. Images are often regarded as facts or proof of reality, so they are misleading and fake news or publications of any form that use images manipulated in a highly misleading way. To recognize image tampering needs multiple image data and a model that can handle all the pixels in the image. Furthermore, training the data more efficiently and needed flexibility support everyday use. Models based on Deep learning such as Convolutional Neural Networks with error level analysis (ELA) are the perfect solution. © 2024 IEEE.

关键词： Convolutional Neural Network Deep Learning Efficiency Error Level Analysis Image Forgery Detection

来源：评论

学校读者我要写书评

暂无评论

Zero-DCE++Inspired Object Detection in Less Illuminated Environment Using Improved YOLOv5

引用

computers, Materials & Continua 2023年第12期77卷 2751-2769页

作者： Ananthakrishnan Balasundaram Anshuman Mohanty Ayesha Shaik Krishnadoss Pradeep Kedalu Poornachary Vijayakumar Muthu Subash Kavitha Centre for Cyber Physical Systems Vellore Institute of Technology(VIT)ChennaiTamil Nadu600127India School of Computer Science and Engineering Vellore Institute of Technology(VIT)ChennaiTamil Nadu600127India School of Information and Data Sciences Nagasaki UniversityNagasaki8528521Japan

Automated object detection has received the most attention over the *** cases ranging from autonomous driving applications to military surveillance systems,require robust detection of objects in different illumination ***-of-the-art object detectors tend to fare well in object detection during daytime ***,their performance is severely hampered in night light conditions due to poor *** address this challenge,the manuscript proposes an improved YOLOv5-based object detection framework for effective detection in unevenly illuminated nighttime ***,the preprocessing strategies involve using the Zero-DCE++approach to enhance lowlight *** is followed by optimizing the existing YOLOv5 architecture by integrating the Convolutional Block Attention Module(CBAM)in the backbone network to boost model learning capability and Depthwise Convolutional module(DWConv)in the neck network for efficient compression of network *** Night Object Detection(NOD)and Exclusively Dark(ExDARK)dataset has been used for this *** proposed framework detects classes like humans,bicycles,and *** demonstrate that the proposed architecture achieved a higher Mean Average Precision(mAP)along with a reduction in model size and total parameters,*** proposed model is lighter by 11.24%in terms of model size and 12.38%in terms of parameters when compared to baseline YOLOv5.

关键词： Object detection deep learning nighttime road scenes YOLOv5 DWConv Zero-DCE++ CBAM

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：