检索结果-内蒙古大学图书馆

Classification of Corn Leaf Images using Pre-Trained Deep Learning Schemes: A Study

Classification of Corn Leaf Images using Pre-Trained Deep Le...

2023 International Conference on Innovative Computing, Intelligent Communication and Smart electrical Systems, ICSES 2023

作者： Sangamithrai, K. Rajinikanth, V. Saveetha School of Engineering Division of Research and Innovation Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering TN Chennai602105 India

ISBN: (纸本)9798350319200

Automatic image classification using pre-trained deep learning (PDL) schemes are widely employed in several domains. This research aims to verify the classification performance of the chosen PDL schemes using the Corn Leaf Image (CLI) dataset. Stages existing in the proposed system include;(i) CLI collection, resizing and pre-processing with histogram equalization, (ii) feature extraction using chosen PDL scheme, (iii) SoftMax supported binary classification, and (iv) performance evaluation and verification. In this study, 3000 CLI images (1500 normal and 1500 rust instances) are examined. The experimental investigation of the study reveals that the VGG16 scheme exhibits superior classification accuracy on the chosen CLI dataset. Specifically, it achieves an accuracy of >93% when considering raw images and attains 100% accuracy when using pre-processed images. This research confirms that, in comparison to other models such as VGG19, ResNet variants, and DenseNet variants investigated in this study, VGG16 provides better result for the CLI dataset. © 2023 IEEE.

关键词： classification corn leaf data histogram equalization verification VGG16

来源：评论

学校读者我要写书评

暂无评论

Automated Traffic Management System Using Deep Learning Based Object Detection 21

Automated Traffic Management System Using Deep Learning Base...

引用

21st International Conference on Machine Learning and Cybernetics, ICMLC 2022

作者： Saini, Sumindar Kaur Singh Ghumman, Mankaran University Institute of Engineering and Technology Department of Computer Science Engineering Chandigarh India Department of Electrical Engineering Chandigarh India

ISBN: (数字)9781665488327

ISBN: (纸本)9781665488327

The traffic menace in India's metropolitan cities causes many travelers to suffer daily. In traffic control, simple and old forms of signal controllers, known as electro-mechanical signal controllers, are used till-date which use dial timers that have fixed, signalized intersection time plans. As the time is fixed, the people in the lane with the greatest number of vehicles must wait the most, leading to wastage of time, money, and natural resources such as petrol and diesel. The proposed system is a traffic light system with feedback in real-time. The vehicles present in a specific lane are detected using a camera and then the deep learning algorithm, YOLO (You Only Look Once) detects the total number of vehicles in a lane which is used for feedback control of the lights. The traffic lights controller changes its parameters in response to traffic length in a lane, optimizing the road use and the signal timing of an intersection will benefit from being adapted to the dominant flows changing over the time of the day. The experiment analysis reveals that response time for green light in real-time increases in the lane with a greater number of vehicles and is decreased for the lane with lesser number of vehicles keeping the total time the same, so effective in managing traffic. © 2022 IEEE.

关键词： Controllers

来源：评论

学校读者我要写书评

暂无评论

Development of Green Computing through Power Management in Wireless Networks using Machine Learning 7

Development of Green Computing through Power Management in W...

引用

7th International Conference on Inventive Computation Technologies, ICICT 2024

作者： Raja, S.R. Arya, Hemlata Ramya, D. Sivakumar, S. Arigela, Arun Kumar Venu, Nookala Saveetha Deemed University SIMATS Saveetha College of Liberal Arts And Science Department of Computer Science Chennai India Department of Computer Science & Engineering Madhya Pradesh Gwalior India Sathyabama Institute of Science And Technology Electrical And Electronics Engineering Rajiv Gandhi Salai Chennai India Vel Tech Rangarajan Dr. Sagunthala R And D Institute of Science And Technology Department of Electrical And Electronics Engineering Chennai Tamilnadu Avadi600062 India Department of Csit Telangana Hyderabad India Centre For IoT Madhya Pradesh Gwalior474 005 India

ISBN: (纸本)9798350359299

This study investigates the use of Support Vector Machines (SVM), Convolutional Neural Networks (CNN), and Recurrent Neural Networks (RNN) to improve power utilization in green data centers. The study examines each model's individual capabilities in addressing key concerns about energy efficiency and sustainability. SVM is extremely accurate in workload prediction and resource allocation, whereas CNN excels in real-time monitoring and cooling system efficiency. RNN contributes by anticipating fluctuations in energy use and adapting to dynamic workload changes over time. The research uses ten hypothetical trials to demonstrate the models' consistent performance across multiple measures. These results suggest that SVM, CNN, and RNN have transformative potential in the development of flexible, efficient, and sustainable green data centers. The study adds to the larger discussion about green computing by emphasizing the role of powerful machine learning models in shaping the future of ecologically responsible data center operations. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

POD: PCM-Based Computing Platform for Object Detection in Biomedical Imaging Application

POD: PCM-Based Computing Platform for Object Detection in Bi...

引用

IEEE Latin American Symposium on Circuits and Systems (LASCAS)

作者： Demeng Chen Amirali Amirsoleimani Mostafa Rahimi Azghadi Roman Genov Majid Ahmadi Department of Electrical and Computer Engineering University of Toronto Toronto Canada Department of Electrical Engineering and Computer Science York University Toronto Canada College of Science and Engineering James Cook University Townsville Australia Department of Electrical Engineering and Computer Science University of Windsor Windsor Canada

Recent advancements in image classification, object detection, and semantic segmentation have significantly acceler-ated medical image processing systems. However, for medical applications, these systems require exceptional performance to ensure reliability. High performance often entails increased computational load, power consumption, and system require-ments. In this paper, we investigate the potential of an efficient implementation of very deep object detection neural networks on Phase Change Memory (PCM)-based memristive crossbar circuits for MRI image labeling, aiming to reduce inference time and power consumption. The neural network model is developed from scratch, incorporating the latest breakthroughs in object detection, and is able to achieve up to 84.2%mAP performance on a standard brain tumor dataset containing 3064 T1-weighted contrast-inhanced images from 233 patients with meningioma, glioma, and pituitary tumor. We also discuss the design decisions, challenges, model performance on different model configurations, and issues that need to be addressed in future work.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diffusion Based Channel Gains Estimation in WSN Using Fractional Order Strategies

引用

computers, Materials & Continua 2022年第2期70卷 2209-2224页

作者： Nasir Mahmud Khokhar Muhammad Nadeem Majeed Syed Muslim Shah Department of Computer Engineering University of Engineering and TechnologyTaxila47050Pakistan Punjab University College of Information Technology University of PunjabLahore54000Pakistan Department of Electrical Engineering Capital University of Science and TechnologyIslamabad44000Pakistan

In this study,it is proposed that the diffusion least mean square(LMS)algorithm can be improved by applying the fractional order signal processing *** of Caputo’s fractional derivatives are considered in the optimization of cost *** is suggested to derive a fractional order variant of the diffusion LMS *** applicability is tested for the estimation of channel parameters in a distributed environment consisting of randomly distributed sensors communicating through wireless *** topology of the network is selected such that a smaller number of nodes are *** the network,a random sleep strategy is followed to conserve the transmission power at the *** proposed fractional ordermodified diffusionLMS algorithms are applied in the two configurations of combine-then-adapt and *** average squared error performance of the proposed algorithms along with its traditional counterparts are evaluated for the estimation of the Rayleigh channel *** proof of convergence is provided showing that the addition of the nonlinear term resulting from fractional derivatives helps adjusts the autocorrelation matrix in such a way that the spread of its eigenvalues *** increases the convergence as well as the steady state response even for the larger step *** results are shown for different number of nodes and fractional *** simulation results establish that the accuracy of the proposed scheme is far better than its classical counterparts,therefore,helps better solves the channel gains estimation problem in a distributed wireless *** algorithm has the potential to be applied in other applications related to learning and adaptation.

关键词： Diffusion strategies distributed channel gains fractional derivatives mean squared error

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Review Analysis of Distinct Tools Image Plagiarism Detection

A Comprehensive Review Analysis of Distinct Tools Image Plag...

引用

2024 International Conference on Artificial Intelligence and Emerging Technology, Global AI Summit 2024

作者： Naudiyal, Anjali Singh, Vineeta Joshi, Kapil Roka, Sanjay Mamoria, Pushpa Shakya, Rajeev Kumar School of Applied and Life Sciences Uttaranchal University Premnagar Dehradun India School of Engineering and Technology Chhatrapati Shahu Ji Maharaj University Department of Computer Science and Engineering Uttar Pradesh Kanpur208024 India Uttaranchal University Department of Computer Science & Engineering Dehradun India Graphic Era deemed to be university dehradun India School of Electrical Engineering and Computing Adama Science and Technology University Department of Electronics and Communication Engineering Adama Ethiopia

ISBN: (纸本)9798350379716

In the era of artificial intelligence, academic activities tend to use Chat GPT more frequently. A Chabot called Chat GPT is used for brainstorming, writing, and learning. Although most academicians use Chat GPT to their advantage when taking notes, it is detrimental to research. A few authors wrote the papers swiftly by using AI techniques. These days, chat GPT is employed in a wide range of tasks. It prepares any type of content for the internet. The likelihood of plagiarism is rising as a result of its use. At present, plagiarism is the biggest challenge in the field of research. Plagiarism occurs when an author uses this technology to modify another person's work and transmit it off as their own without providing a reference or credit. Plagiarism is a term used to describe when someone copies something from another source without providing credit to the original author. Google is working quickly in the image field, but at that point, it will be used to detect plagiarism that is generated with the aid of artificial intelligence. The less papers that are utilized in favor of online resources, the more academics are working to make the globe more environmentally friendly. In the presented paper, a few software applications are discussed and compare a number of different techniques to detect the plagiarism in academics field like scientific equations or cross-lingual or multilingual texts. Various applications are developed in research to identify instances of plagiarism in research papers, assignments, and source code. After reviewing the papers pertaining to various tools for detecting plagiarism, not much more work is done in the area of detecting plagiarism in images or in image text. The article that is being presented comes to the conclusion that no software tool has been developed to identify plagiarism in images or in the text associated with images. © 2024 IEEE.

关键词： Application programs

来源：评论

学校读者我要写书评

暂无评论

On the Identification of Isomorphic Graphs for Graph Neural Network using Multi-graph Approach 13

On the Identification of Isomorphic Graphs for Graph Neural ...

引用

13th IEEE Annual Information Technology, Electronics and Mobile Communication Conference, IEMCON 2022

作者： Njanko, Adrien Rawat, Danda B. Department of Electrical Engineering and Computer Science Howard University WashingtonDC United States

ISBN: (数字)9781665463164

ISBN: (纸本)9781665463164

The Graph Isomorphism problem regained interest with the rise of Graph Neural Networks (GNN). These GNN models have limited ability to distinguish between isomorphic graphs and hence their outputs are modified although the inputs remain the same. Bringing a mathematical way to determine the existing isomorphism between graphs will improve GNN performance. We proposed a multi-graph approach that allows us to extract the permutations to perform to recover one graph from the other. We construct a multi-graph from both input graphs and extract pairs of nodes that respect some properties we have defined. From simple and small graphs, we have been able to correctly extract the isomorphism or permutation matrix existing between both graphs. The extension to large graphs remains a challenge as it requires more computations to discard among a large number of possible candidates. © 2022 IEEE.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

engineering Framework for Smart Poultry Farming Using Internet of Things

Engineering Framework for Smart Poultry Farming Using Intern...

引用

2024 International Conference on Intelligent and Innovative Practices in engineering and Management, IIPEM 2024

作者： Manju, K. Dinesh, P.M. Deepa, K. Kathan, Karthik Lakshmi, G. Prasanna Alagarsamy, Manjunathan Sona College of Technology Department of Electronics and Communication Engineering Tamil Nadu Salem India SRM Institute of Science and Technology Faculty of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Tiruchirapalli India Kongunadu College of Engineering and Technology Department of Electrical and Electronics Engineering Tamil Nadu Trichy621215 India Sandip University School of Computer Science and Engineering Maharashtra Nashik India K.Ramakrishnan College of Technology Department of Electronics and Communication Engineering Tamil Nadu Trichy621112 India

ISBN: (纸本)9798350390049

Automation is more important now. This article focuses on automating chicken farms using mobile communication devices and wireless sensor networks. Chicken is the world's most popular food because it contains more protein, less fat, and less cholesterol than other poultry. Chicken's nutrition is another benefit. This project utilizes the Internet of Things to monitor and adjust chicken farm environmental conditions. Temperature, moisture, water level, ammonia gas, and waste level were considered. This research aimed to improve chicken farm chick growth. The individual also monitors chicken behavior and feeding. Another usage for the sensor module is water level management and monitoring. If all sensors are connected to the microcontroller, all sensor data may be gathered. After that, a Wi-Fi module uploads the data to a website. A computer or mobile device connected to the internet allows the poultry farm owner to examine its interior surroundings. This informs the owner on agricultural conditions. This system will maintain temperature, humidity, and water level without human intervention using a DC motor, ventilation window, and co-exhaust fan. This will be done without human intervention. Devices will activate as needed when threshold values are attained. Our method allows semi-automated chicken product production and bird behavior monitoring. This allows us to deliver nutritious chicken meat while reducing bird killing. © 2024 IEEE.

关键词： Humidity sensors

来源：评论

学校读者我要写书评

暂无评论

Edge Device Based Stress Detection for Older Adults with Cortisol Biomarker

Edge Device Based Stress Detection for Older Adults with Cor...

引用

2022 IEEE International Conference on Consumer Electronics, ICCE 2022

作者： Clark, Joseph Thapliyal, Himanshu University of Tennessee Department of Electrical Engineering and Computer Science KnoxvilleTN United States

ISBN: (纸本)9781665441544

Stress impairs human cognition and over long periods of time can cause severe negative health effects for older adults. Real-time stress detection can be a useful tool in stress mitigation strategies, but stress detection is often implemented with machine learning models too large to run on an edge device. This paper presents a stress detection framework for older adults which is designed to be executed with low latency by a wearable device or other embedded system. We use Galvanic Skin Response, Blood Volume Pulse, Interbeat Interval, and skin temperature data with cortisol as a stress biomarker to evaluate the performance of several machine learning models. The best performing model was a radial basis function-based SVC (Support Vector Machine). The model achieved a test data accuracy of 82% and a test data F1-Score of 0.70. Performance data indicates that the framework performs well and could be improved for use on a wearable device. © 2022 IEEE.

关键词： Cortisol

来源：评论

学校读者我要写书评

暂无评论

Subjective and Objective Quality Assessments of AI-Generated Images for Language E-Learning

引用

IEEE Access 2025年 13卷 100667-100682页

作者： Chibuike Onuoha Vu Hai Dang Nguyen Duc Nam Truong Thu Huong Pham Ngoc Nam Truong Cong Thang Department of Computer Science and Information Systems The University of Aizu Aizuwakamatsu Japan School of Electrical and Electronic Engineering Hanoi University of Science and Technology Hanoi Vietnam College of Engineering and Computer Science VinUniversity Hanoi Vietnam

AI-generated images (AIGIs) are becoming popular and can be employed in many applications, owing to Generative AI (GAI). Researchers have developed models that can be used to generate images for different scenarios. In addition, researchers have proposed datasets of natural scene images for language learning and different AIGI-quality datasets for general applications. For e-learning, particularly in the context of language learning, no AIGI dataset is currently available. To fill this gap, we first proposed an AIGI quality dataset for language learning. Both subjective and objective assessments have been conducted on the proposed dataset. The findings from subjective assessment show that higher perceptual quality also corresponds to a more substantial alignment. It also shows that the average MOS scores of images generated from Stability AI models are similar and lower than images generated by the Dall.E3 model. The results of the objective assessment indicate that the performance of off-the-shelf quality models is generally low. In addition, results from finetuning learning-based quality models show that significant gains and improvements can be achieved using the dataset. The results of the alignment evaluation show that the HPS model is the best, and realistic images in the dataset produced the best alignment correlation compared to the other styles in the dataset. The findings also show that multimodal large language models, such as vision-enabled GPT-4 (GPT-4V), still struggle to produce alignment scores that correlate with humans.

关键词： Electronic learning Visualization Text to image Quality of experience Quality assessment Diffusion models Training data Training Generators Generative AI

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：