检索结果-内蒙古大学图书馆

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

作者： Vespa, M.Mary Stanley, Berakhah F. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of computer Science and Engineering Chennai India

ISBN: (纸本)9798350370249

diabetic retinopathy (dr) is a prevalent retinal vascular condition that can lead to significant visual impairment. The early classification of dr and precise grading of dr are essential for maintaining eyesight and providing prompt treatment, which is known as dr classification. The images go through a preprocessing stage to reduce noise from the dataset that was obtained. Initially, the input image is initiated by a preprocessing technique. This process is handled by the spatial processing technique called the Wiener Filter, which lowers image noise and raises the visibility of hazy images. The following step sends the image to the areas for segmentation. Fuzzy C-means (FCM) segmentation is used to accurately determine the size and shape of the disease. The proposed research uses the deep Neural Network based YOLOV7 (dNN-YOLOV7) classifier. All five stages of diabetic retinopathy (dr) can be identified with this method: no dr, mild, moderate, severe, and proliferative dr (Pdr). This research provides a high degree of sensitivity and precision in identifying whether a picture has diabetic retinopathy or not. The work involved is implemented with MATLAB simulation software. © 2024 IEEE.

关键词： deep neural network dNN-YOLOV7 FCM segmentation Fundus images

来源：评论

学校读者我要写书评

暂无评论

Analysis of Landlord's Land Price Prediction using Machine Learning 5

Analysis of Landlord's Land Price Prediction using Machine L...

引用

5th International Conference on Smart Electronics and Communication, ICOSEC 2024

作者： Sankar, M. Chithambaramani, r. Sivaprakash, P. Ithayan, Vimala Charaan, r.M. dilip Marichamy, d. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331504403

This Paper presents an analysis of landlord land price prediction utilizing machine learning techniques. The objective is to develop a predictive model that can accurately forecast land prices, aiding landlords in making informed decisions regarding property investments. The research employs various machine learning algorithms, including but not limited to regression and ensemble methods, to analyze a dataset comprising relevant features such as location, land size, demographics, and economic indicators. The accuracy of the predictive models is evaluated through rigorous testing and validation processes, with performance metrics such as Mean Absolute Error (MAE), root Mean Square Error (rMSE), and r-squared (r2) utilized to gauge predictive accuracy, the accuracy of the deployed model is 94 percent. The findings demonstrate the efficacy of machine learning in predicting landlord land prices, with the proposed models achieving a high level of accuracy, thus offering valuable insights for landlords and real estate stakeholders in strategic decision-making processes. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Navigating Space: A ddPG-Based Approach to Autonomous Satellite Navigation 10

Navigating Space: A DDPG-Based Approach to Autonomous Satell...

引用

10th International Conference on Electrical Energy Systems, ICEES 2024

作者： Alex david, S. Appala, Charan Balurgi, Shreya Nagisetty, Anil Kumar Manam, Anusha Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350353778

This study developed a modern autonomous navigation system using proximity and accelerometer sensors, along with deep reinforcement learning algorithms. The system ensures safety by providing real-time data on obstacles and distance through proximity sensors, forming the basis for quick decision-making. Accelerometers measure movement precision and navigation orientation, determining the necessary distance and force for maneuvers. deep reinforcement learning, using ddPG algorithms, enables the system to learn and make decisions independently. The system can navigate, avoid obstacles, and seek cover autonomously, promoting the development of more independent systems. © 2024 IEEE.

关键词： Accelerometers

来源：评论

学校读者我要写书评

暂无评论

Advancing conservation: Internet of Things-driven initiatives for marine animal rescue due to climate changes [Climate Change]

引用

IEEE Potentials 2024年第2期43卷 21-29页

作者： Gopi, rahul Sanmugam ramasamy, rajkumar Babu, M. david Honesty Vel Tech Rangarajan Dr. Sagunthala R and D Institute of Science and Technology Department of Electronics and Communication Engineering Chennai600062 India

Beneath the expansive oceans lies a complex ecosystem where marine animals, from whales to delicate coral polyps, sustain the vitality of the marine environment. However, these creatures are facing significant challenges due to evolving climate changes. rising sea temperatures, ocean acidification, habitat degradation, and increasing natural disasters threaten their survival. © 1988-2012 IEEE.

关键词： Invertebrates

来源：评论

学校读者我要写书评

暂无评论

Ensemble of deep Learning Enabled Tamil Handwritten Character recognition Model 2nd

Ensemble of Deep Learning Enabled Tamil Handwritten Characte...

引用

2nd International Conference on Big data, Machine Learning, and Applications, BigdML 2021

作者： Thanga Selvi, r. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9789819934805

recently, digitalization of handwritten characters has become a hot research topic and finds applicability in different domains. At the same time, recognition of Tamil handwritten characters is a tedious task compared to other languages. Therefore, this paper presents a new ensemble deep learning-based Tamil handwritten character recognition (EdL-THCr) model. The EdL-THCr model recognizes and classifies the Tamil handwritten characters. In addition, data preprocessing approach is involved using bilinear interpolation technique to normalize the images. Besides, an ensemble of capsule network (CapsNet) and VGGNet models take place for feature extraction process. Finally, softmax layer is employed to classify the Tamil characters in an effective way. A comprehensive experimental analysis is carried out on benchmark dataset, and the results portrayed the better performance of the EdL-THCr technique. © 2024, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Character recognition

来源：评论

学校读者我要写书评

暂无评论

Implementation of waste plastic as a sustainable partial replacement of fine aggregate

引用

Interactions 2024年第1期245卷 1-7页

作者： Jessie, J. Anita Gaayathri, K.K. Yarramsetty, Jetendra Ashok, Bagde Aman Civil Engineering Department Vel Tech Rangarajan Dr. Sagunthala R & ampD Institute of Science and Technology Chennai Avadi India

Plastic waste is the most environmentally damaging type of garbage. Since plastic cannot decompose naturally, it must be recycled or reused to prevent further harm. The study aims to examine the behavior and certain physical properties of concrete made from recycled plastic *** study investigates the probability and efficiency of utilizing disposed plastic as a fractional replacement of fine aggregate in construction materials. research focuses on understanding the concrete mechanical properties, when merging waste plastic particles in lieu of a portion of traditional fine aggregates. Various types of waste plastic, including plastic bottles, bags, and packaging materials, are analyzed for their suitability as a replacement material. Additionally, various treatment methods, such as shredding, melting, and chemical modification, are considered to enhance the compatibility of plastic with the base materials. Compressive strength was found to investigate the impact of disposed plastic on the concrete mechanical characteristics. A comparative study between conventional concrete and 20% replacement of shredded plastic in fine aggregate was done. 20% replacement mix showed almost equal strength to the conventional concrete. The strength of 20% replacement was found to be 41 MPa, whereas the 30% and 40% was observed to be 38 MPa and 35 MPa respectively. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Compressive strength

来源：评论

学校读者我要写书评

暂无评论

Pressure exertion and heat dissipation analysis on uncoated and ceramic (Al2O3, TiO2 and ZrO2) coated braking pads

引用

Materials Today: Proceedings 2023年 74卷 774-787页

作者： Sunil kumar, K. Bishnoi, deepika Department of Mechanical Engineering Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Chennai 600062 India School of Energy Science and Engineering Indian Institute of Technology Guwahati 781039 India

This paper focuses on heat dissipation analysis of brake pads uncoated and coated with a layer of Al2O3,TiO2 and ZrO2 with in the time intervals when a pressure of 0.5 subjected to 35οC (Load case 1) and 1 mpa subjected to 55οC (Load case II). The plasma arc coating process was done for brake pads to estimate the analysis within the atmospheric temperature. The coating is done in the range of 300 µm to perform the analysis;In addition to that salt spraying technique is employeed to estimate the corrosion resistance for these materials. The coated braking pads are dipped in the sodium based solution for 2 h with the presence of 6 % as chloride agents to identify the possibilities of corrosion. The model was drawn using CATIA, and heat dissipation analysis was performed on the model by ansys workbench by multiphysics software. The parameters such as Total deformation, directional deformation,max shear strain and max shear stress also calculated in ansys multiphysics. However it was noted that Al2O3 coatings posess better performance as compared to uncoated materials. The other parameters investigated in this analysis were heat dissipation, total heat flux, total directional heat flux and error analysis. From this analysis it was observed that the pressure exertion for load case I, it was observed that the maximum heat dissipation rate for Al2O3 coated braking systems was found to 22οC, maximum heat dissipation 2.5 w/m2, directional heat flux 2.1w/m2 and 3 % error. which is as compared to uncoated materials, For load case II, it was observed that the maximum heat dissipation rate for Al2O3 coated braking systems was found to 40οC, total heat flux was found to be 2.5 w/m2, directional heat flux of 4.9 w/m2.;with error of 2.2 % compared to uncoated materials. For all the load cases, Al2O3 coated braking materials possses better performance as compared to uncoated materials. Hence it was suggested to use Al2O3 coated materials to improve the brake pad efficiency and life

关键词： Titanium dioxide

来源：评论

学校读者我要写书评

暂无评论

Modelling of electric vehicle charging station and controlled by fuzzy logic controller with different modes of operation

引用

Journal of Control and decision 2023年第1期10卷 26-39页

作者： S.C.Vijay Kumar K.Karunanithi S.P.raja S.ramesh P.Chandrasekar r.Obulupathy vel tech rangarajan dr.sagunthala r&d institute of science and technology chennaitamil naduindia school of computer science and engineering vellore institute of technologyvelloretamil naduindia

The main objective of implementing charging stations is to ensure the good charging to theElectric Vehicles by using a solar PV array which is interconnected to the battery energy storagesystems. The charging station regulates the supply voltage and frequency without the use of amechanical speed governor. It also assures that energy gained from grid or by the dG set willhave the unity power factor (UPF) when the load is nonlinear. Besides this, the Point of CommonCoupling (PCC) voltage is synchronised with the grid/generator voltage in order to providecontinuous charging. In order to increase the optimal efficiency of the charging stations, thecharging stations will perform the active/reactive power transfer from the vehicle to grid, vehicleto house and vehicle to vehicle (V2V) power transfer. The operational experiment of the chargingstation is simulated and verified by using MATLAB/SIMULINK.

关键词： Electric vehicle charging station solar photo-voltaic generation energy transfer diesel-generator set fuzzy logic controller total harmonic distortion

来源：评论

学校读者我要写书评

暂无评论

Street Light Cum Garbage System Optimal design Based on IOT 2

Street Light Cum Garbage System Optimal Design Based on IOT

引用

2nd International Conference on Emerging Trends in Information technology and Engineering, ic-ETITE 2024

作者： rajesh, G. deepa, J. Ezilarasan, M.r. Syed Fiaz, A. Siva rama Lingham, N. Jagannathan, J. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Information Technology Chennai India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Department of Software and Systems Engineering Vellore India

ISBN: (纸本)9798350328202

Street lights currently use more energy than other types of lighting because of an inefficient mechanism that makes the bulbs use a lot of electricity. The suggested approach uses various sensors on intelligent streetlights to keep an eye on and manage the lights. It has sensors for measuring temperature, brightness, and power that control dimming levels and keep track of status. One Zigbee network serves as the connection point for these lights. In the modification, a cloud- and IoT-based installation was made. Through Zigbee -based data transmission, sensor values are recorded on a distant server known as the Cloud. Additionally, it lowers electricity theft. We include a trash can notice in addition to this street light idea. When the garbage can is whole, a machine automatically notifies the business as people approach the sun, and the brightness of the street lights changes or is increased. © 2024 IEEE.

关键词： Light emitting diodes

来源：评论

学校读者我要写书评

暂无评论

CNNs for Early detection of Plant diseases: A deep Learning Perspective 6

CNNs for Early Detection of Plant Diseases: A Deep Learning ...

引用

6th International Conference on Mobile Computing and Sustainable Informatics, ICMCSI 2025

作者： Vinod, dasari Naga Sai revanth, r. Bhaskar, B. Jaya Prakash, P. Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9798331522667

In India, where agriculture sustains over 70% of the population, the impact of millet diseases on crop yield and economic outcomes for farmers cannot be overstated. With the advent of digitalization permeating various sectors, including agriculture, leveraging technology becomes imperative for enhancing productivity and ensuring food security. The ability to detect and manage Millet’s diseases efficiently is crucial for maximizing crop yield and minimizing losses. deep learning, mostly Convolutional Neural Networks (CNNs), has appeared as well as an influential tool in digital image processing, offering significant advantages over traditional methods. Leveraging CNNs for the recognition and categorization of Millet's diseases presents a promising solution to this longstanding challenge. The process of Millet's disease detection using CNN involves several key steps, together with acquiring images, initialization, partition, division, as well as disease identification. In conclusion, the integration of CNN-based Millet’s disease detection systems holds immense potential for revolutionizing agricultural practices in India. By connecting the supremacy of deep learning and digitalization, stakeholders can work towards confirming food security, increasing farm profitability, and promoting supportable agricultural practices. In this article, we obtained a 97.8% accuracy in detecting Plant diseases using a CNN-based approach. © 2025 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：