检索结果-内蒙古大学图书馆

2nd International Conference on Advances in Computation, Communication and Information technology, ICAICCIT 2024

作者： Sathiya Priya, S. Kujani, T. Gnana Prasanna, S. ramya Sree, K.M. Hemasri, Bachina Hussain, Shaik Khadar Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Tamilnadu Chennai India Department of Computer Science & Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai600062 India Department of Computer Science and Engineering Aalim Muhammad Salegh College of Engineering AvadiIAF Chennai India

ISBN: (纸本)9798331541217

Plant disease detection is a cornerstone of sustainable agriculture, directly influencing crop yield and quality. Early detection and timely intervention are crucial for mitigating these impacts. This study investigates the potential of Convolutional Neural Networks (CNNs) to automate and enhance crop disease detection. CNNs, capable of learning intricate spatial patterns from image data, provide a promising alternative to traditional disease diagnosis methods. The paper delves into the technical aspects of CNN-based plant disease detection, including popular frameworks like TensorFlow and PyTorch. These tools provide a user-friendly environment for building, training, and deploying CNN models, streamlining the process of implementing AI solutions in agricultural settings. The advantages of CNNs for plant disease detection are multifaceted. Their hierarchical architecture enables automatic feature extraction, reducing the need for manual engineering. Additionally, CNNs are robust to variations in image conditions, making them suitable for real-world agricultural applications. To further improve performance, various techniques are integrated into CNN-based systems. data expansion and model adaptation methos are utilized to expand the variety and size of training datasets, resulting in more precise and generalized models. In conclusion, CNNs offer a promising approach to automating and improving plant disease detection, contributing to sustainable agriculture and food security. By harnessing the capabilities of AI, farmers and researchers can make informed decisions to safeguard crops and maximize yields. These techniques increase the diversity and size of training datasets, leading to more accurate and generalized models, with studies reporting achievements of up to 97% accuracy. The potential integration of CNN-based systems into precision agriculture frameworks to optimize resource allocation and enhance overall crop health. © 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

Brain Tumour Classification Using Convolutional Neural Network 15

Brain Tumour Classification Using Convolutional Neural Netwo...

引用

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

作者： Pandiyarajan, M. reddy, P. Anji Valarmathi, r.S. Manideep, N. Sai Mokshitha, P. Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350370249

This study presents an investigation into the development of a brain tumor classification and treatment planning system leveraging deep learning methods, particularly Convolutional Neural Networks (CNNs). The research aims to enhance accuracy and efficiency in this domain by leveraging the capabilities of deep learning. An extensive assessment of the brain tumor classification model is carried out, showcasing its effectiveness in accurately identifying various tumor types, including glioma, meningioma, pituitary tumors, and cases without tumors. The model achieves high precision, recall, and F1-score values across these tumor categories, demonstrating robust performance in clinical decision-making scenarios. Leveraging Magnetic resonance Imaging (MrI) data, the CNNbased model achieves an impressive overall accuracy of 95%. Methodologically, the study involves preprocessing MrI images for contrast enhancement and noise reduction, followed by feature extraction using CNN architectures comprising convolutional and pooling layers. The model undergoes training on a sizable collection of annotated brain tumor images, with data augmentation techniques employed to enhance generalization and mitigate overfitting. © 2024 IEEE.

关键词： Cerebral tumor Classification Model Convolutional neural network

来源：评论

学校读者我要写书评

暂无评论

design and Analysis of Wide-Band 2-Port MIMO Antenna for 5G Wireless Applications 7

Design and Analysis of Wide-Band 2-Port MIMO Antenna for 5G ...

引用

7th International Conference on Inventive Computation technologies, ICICT 2024

作者： Koushick, V. Kumar, d. rajesh Hussain Basha, Shaik Asadh, Syed Khadri, Shaik Mohammed Waseem Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science And Technology Department of Ece Chennai Tamil Nadu Avadi India

ISBN: (纸本)9798350359299

As technology evolves, modern devices are likely to support multiple bands and higher data rates. The proposed wide band 2-port MIMO antenna for wireless applications with high-speed data rates. The existing antennas are not much compatible and resonated in multiple frequency bands due to the substantial size of an antenna. In the environment with multiple devices are not having good network performance and good signal quality due to massive traffic in a frequency at a time. To overcome this problem, likely to design a wide band 2-port MIMO antenna. The proposed circular slotted antenna is designed by using AdS (Advanced design System) simulation tool. Fr-4 core material is used as substrate with 4.4 permittivity and loss tangent of 0.018. The proposed antenna is simulated in the frequencies over 4.5GHz to 5.2GHz and expected to yields the better radiation results. © 2024 IEEE.

关键词： design

来源：评论

学校读者我要写书评

暂无评论

Autonomous Traffic Sign detection and recognition in real Time 3rd

Autonomous Traffic Sign Detection and Recognition in Real Ti...

引用

3rd International Conference on recent Trends in Machine Learning, IoT, Smart Cities and Applications, ICMISC 2022

作者： Malarvizhi, N. Jupudi, Athreayasa Kalyan velpuri, Manikanta dheeraj, T.V.K. CSE Vel Tech Rangarajan Dr Sagunthala R&D Institute of Science and Technology Tamilnadu Chennai India

ISBN: (纸本)9789811960871

Every day, over 400 traffic accidents occur in India, according to official statistics. Traffic sign recognition plays very important role in intelligent autonomous vehicles as well as in driver assistant system to disburden the driver. The main aim of this project is to reduce the cause of road accidents because of an inactive drivers on the road. We are developing a model which makes image classification and buzzer to avoid drivers distraction. In this model we are improving the performance to detect the Indian road signs to assist the drivers. And we will also reduce the over speed problems, they will follow traffic rules strictly by using this model. Our project will also help new learners to improve their driving experience. A skeleton for an Autonomous Traffic Sign detection and recognition (TSdr) in real time has been proposed. The proposed framework includes two parts: traffic sign detection and recognition of detected traffic signs. Future autonomous vehicles will benefit from this framework because it allows for the traffic sign detection and recognition in real time from the complex images that occur on the road. The proposed framework helps the drivers to improve road safety as well to help new learners to improve their driving experience also. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Computer vision

来源：评论

学校读者我要写书评

暂无评论

design and analysis of a rear diffuser in a sedan car

引用

Materials Today: Proceedings 2022年 59卷 1324-1339页

作者： Senthilkumar, P.B. Parthasarathy, M. Aravind, L. Narayanan, r.G. Satthya Vegesh, B. Sam Nelson, d.r. Department of Automobile Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai600062 India Department of Mechanical Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi Chennai600062 India

The aerodynamic characteristics have a great influence on the fuel economics and the steering stability of a high-speed vehicle. Thus, this aerodynamics is considered as one of the main ergonomics of the vehicle. Aerodynamics consists of four forces which an object or material moves. The forces are lift, drag, weight, thrust. From these four forces lift and drag plays a major role in the vehicle which runs on the road surface. To maintain steady aerodynamics various add-on devices, help in maintaining the forces that act on the vehicle. The add-on devices are spoilers, rear wing, tail plates, vortex generator, and diffuser. From these add-on devices, we take a diffuser for our project and make a design and analyze and compare it with the existing diffuser. Usually, the diffuser is first implemented in the racing field then it gradually came to use in commercial vehicles. As time moves on the people and automotive industry focuses on the efficiency of the vehicle. The main aspect to provide the best efficiency is aerodynamics. So, the add-on devices are added to the vehicle to provide the best efficiency. A modified diffuser is designed based on the aspects of the car model. By modeling these three designs using CATIA we are going to analyze them using ANSYS. In that, using CFd (Computational Fluid dynamics) which specializes in the flow of air and water. Analyze the drag and lift coefficient based on the velocity and the different diffusers. The expected outcome of the project work is to reduce the drag and lift coefficient compared to the existing diffuser. This project deals with the design and analysis of the car model without a diffuser, with an existing diffuser, and with a modified diffuser which results in the comparison of their values. © 2021

关键词： Efficiency

来源：评论

学校读者我要写书评

暂无评论

IoT-Based Smart Signal System for Traffic density Management and Emergency Vehicle Priority

IoT-Based Smart Signal System for Traffic Density Management...

引用

2024 IEEE International Conference on Intelligent Systems and Advanced Applications, ICISAA 2024

作者： Kanimozhi, T. reddy, Gongal reddy V. Kishore Kumar, N. rahul Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Electronics and Communication Engineering Chennai600062 India

ISBN: (纸本)9798331539948

The rapid growth of urban populations has led to a surge in vehicular traffic, posing significant challenges for conventional traffic management systems. Traditional traffic lights, with their fixed time allocations for each road, often struggle to accommodate fluctuating traffic volumes, resulting in frustrating delays for drivers. In response to this issue, our proposed traffic light control system offers a tailored solution. By utilizing advanced sensors to measure real-time vehicle density in each lane, our system dynamically adjusts signal timings. roads are categorized into low, medium, and high-density zones, with green light durations corresponding to the current traffic conditions. This adaptive approach aims to alleviate congestion and improve overall traffic flow efficiency, providing a smoother driving experience for commuters. Furthermore, our system integrates priority control features for emergency vehicles such as ambulances and fire trucks. Equipped with radio frequency (rF) transmitters and global positioning system (GPS) modules, these vehicles can activate a special signal to grant them priority passage through the traffic lights. This ensures rapid response times during emergencies, enhancing public safety and emergency services' effectiveness in urban areas. In conclusion, our traffic light control system offers a flexible and responsive solution to the challenges posed by increasing urban traffic. By optimizing signal timings based on real-time data and prioritizing emergency vehicles, it contributes to safer and more efficient transportation networks in cities. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

An Ensemble of InceptionNet and MobileNet Pretrained deep Learning Models for Classifying Stages of dementia 15

An Ensemble of InceptionNet and MobileNet Pretrained Deep Le...

引用

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

作者： Pandiyarajan, M. Valarmathi, r.S. Eda, G. Mounika Kurma, Uday Vinay Charan Tej, K.J.S. ravi Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Tamilnadu Chennai India

ISBN: (纸本)9798350370249

dementia is a growing brain disorder, with Alzheimer's disease accounting for 60-70% of cases. By 2050, nearly 10 million people may be affected. To help early detection, we proposed an ensemble of pretrained deep learning models using InceptionNet and MobileNet. Open Access Series of Imaging Studies (OASIS) dataset is used and the models InceptionNet, MobileNet and EfficientNet is trained and tested to choose the best two models for ensembling and achieved 75%, 81.6% and 64% of accuracy respectively. The models with high accuracy is chosen for ensembling by concatenating the features extracted from InceptionNet and MobileNet followed by classification layer to classify stages of dementia as demented and non-demented. The proposed model achieved a classification accuracy of 92%. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

IOT Enabled Cloud Based risk Monitoring System in Food Supply Chain 1

引用

7th International Conference on Intelligent Computing and Optimization, ICO 2023

作者： Sathyasri, B. Mary, G. Aloy Anuja Bhuvaneswari, C. Ambika Aanandha Saravanan, K. Kumar, S. Vishnu Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Avadi600062 India

ISBN: (数字)9783031733185

ISBN: (纸本)9783031733178

The world of supply chains is a complex and ever-changing landscape, driven by the demanding needs of customers who want top-notch quality, lightning-fast delivery times, and a commitment to sustainability. Within this intricate web of logistics, the handling of perishable goods is a particularly intimidating challenge, with strict regulations in place to ensure safety and quality. But fear not, for a revolutionary new solution is at hand, this essential model proposes an IoT-based risk monitoring system (IoTrMS) that uses a path following robot equipped with a suite of cutting-edge devices like Ir, Ultrasonic and MQ4 sensors to manage and mitigate risks related to product quality and occupational safety in cold storage facilities. With real-time monitoring and risk assessment throughout the supply chain, this prototype promises to reduce health risks for the dedicated human workers. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Cold storage

来源：评论

学校读者我要写书评

暂无评论

Advancing Glaucoma detection: Synthetic Image Generation via Generative Adversarial Networks and Classification with Pretrained MobileNetV2

Advancing Glaucoma Detection: Synthetic Image Generation via...

引用

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： ramprasad, S.r. rampriya, r. Poongodai, A. Govindharaj, I. Vimal raja, r. Yazhinian, S. Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Computer Science and Engineering Chennai India Madanapalle India Ck College of Engineering and Technology Department of Computer Science and Engineering Cuddalore India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India

ISBN: (数字)9798331510022

ISBN: (纸本)9798331510022

Irreversible vision loss, generally insidious in start and lacking apparent symptoms, is usually attributed to glaucoma. detecting glaucoma in its early stages is crucial since it may reduce disease progression. Conventional diagnostic approaches, depending on manual assessments, are notably prone to mistakes. Hence, automated glaucoma analysis acquires vital relevance for precise and prompt detection. Moreover, medical picture databases frequently display asymmetries, creating a problem. To solve these challenges, this paper presents a unique framework employing generative adversarial networks (GANs) to generate images, thus addressing dataset imbalances. Specifically., in the context of fundus images, standard approaches like image-to-image translation are applied to build synthetic fundus images and associated vascular networks, attempting to boost overall image quality and capture finer details. Gaussian filtering is originally done to pre-process the raw dataset, eliminating unwanted noise. Subsequently, GANs are applied for dataset balancing, providing synthetic images that boost classification accuracy. Optic cup segmentation is conducted using the Enhanced Level Set Algorithm. Finally, Pretrained MobileNetV2 permits accurate classification of glaucomatous images into normal and pathological categories. Experimental results illustrate the efficacy of our suggested framework, obtaining an accuracy of 98.9%, exceeding existing techniques. © 2024 IEEE.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Skill Adam Optimization based deep Spiking Neural Network for retinal Multi disease Classification in Fundus Images 2

Skill Adam Optimization based Deep Spiking Neural Network fo...

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Suganthi, N. Mohana Arun, M. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu600062 India

ISBN: (纸本)9798350368413

The aim of fundus imaging is to inspect the irregularities corresponding to diseases that affect eye. The fundus image has a crucial role in detection and observation of diverse ophthalmic diseases. Existing researches have engaged on detection of single disease from the fundus image. However, simultaneous recognition of multi-disease (Md) from the fundus images is still confronting a major challenge. Therefore, this challenge can be addressed by devising a model to detect Md from the fundus imaging with an enhanced accuracy. Here, Skill Adam Optimization based deep Spiking neural network (SAO-deep SNN) is introduced for retinal Md classification using fundus images. Initially, considered fundus image is pre-processed to eliminate noises utilizing Median filter (MF). Thereafter, optic disc (Od) is segmented by deepJoint segmentation and next, artery and vein (A/V) classification is accomplished using sparking process. Then, features are extracted from Od segmented image and A/V classified image in feature extraction (FE) phase. Finally, retinal Md classification is done by deep Spiking Neural Network (deep SNN). However, deep SNN is trained utilizing Skill Adam Optimization (SAO) that is introduced by integrating Skill Optimization Algorithm (SOA) with Adam algorithm. Additionally, SAO-deep SNN achieved accuracy of 90.81%, sensitivity of 91.69% and specificity of 90.49%. © 2024 IEEE.

关键词： Median filters

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：