检索结果-内蒙古大学图书馆

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Bano, Mehnaz Matta, Priya Chandel, Shivali Tula's Institute Department of Computer Science and Engineering Dehradun India Tula's Institute Department of Computer Applications Dehradun India

ISBN: (纸本)9798350387490

The Content Based Image Retrieval (CBIR) is basically used to extract images from the collection of images using several image matching and extraction methods. As it is now with the advancement and ongoing consistent technology and negligible cost of the electronic, digital and virtual sensors, a huge collection of image databases is processed by different types of applications. This type of database of images extends the requirement that we should provide effective search methods for the retrieval of images that can fulfill the demands of end-user. The texture, color, or shape of a picture is the most basic feature used to symbolize and index the images. These distinct elements of photographs are retrieved and used as a measure to find image similarities. A search procedure is initiated for relevant images that fulfill the user's information need using a sketch drawing or a query image given by the user that has similar features. The relevance feedback can be used as an optional step to retrieve and enhance the CBIR process. In this paper, after extracting semantic characteristics from photos, an analysis of the content of the images is performed with respect to features connected to the low level. In this paper, an overview of traditional CBIR methods (e.g.: Color histogram-based, texture based and shape based) are discussed. This paper's primary goal is to study the comprehensive details on the various computational techniques used for content-based image retrieval. To further enhance the efficiency of the image retrieval process, their limitations are also addressed. © 2024 IEEE.

关键词： Content based retrieval

来源：评论

学校读者我要写书评

暂无评论

Deep Learning based Approach for Cassava Leaf Disease Detection 8

Deep Learning based Approach for Cassava Leaf Disease Detect...

引用

8th International Conference on Electronics, Communication and Aerospace Technology, ICECA 2024

作者： Kalpana, T. Thamilselvan, R. Chitra, K. Kaviya, S. Kiruthiga, M. Mahesh, C. Kongu Engineering College Department of Computer Applications Erode India Kongu Engineering College Department of Computer Science and Engineering Erode India

ISBN: (纸本)9798350367904

Cassava is a vital staple crop in numerous tropical countries, to enhance plant disease detection using deep learning architecture including ResNet, EfficientNet, Incetion V3 and simple CNN. By levering these advance model significant improve accuracy compared to previous methods. This approach addresses the pressing issue of food insecurity by efficiently identifying diseases in crops. Types of Cassava disease are Cassava Mosaic Disease (CMD), Cassava Green Mottle (CGM), Cassava Brown Streak Disease (CBSD), and Cassava Bacterial Blight (CBB), along with the presence of Whitefly. The proposed work uses Convolution Neural Network (CNN) to identify the leaf diseases to quickly identify the specific disease that is affecting the crop. CNN can automatically detect important features without any human supervision. A vast collection of labelled cassava leaf photos comprising multiple disease classes is utilized for training the CNN model. To advance deep learning architectures, our research integrates techniques for data augmentation and transfer learning to further enchance model performance. © 2024 IEEE.

关键词： Plant diseases

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Solutions for Predictive Maintenance in Smart Transportation Systems

AI-Driven Solutions for Predictive Maintenance in Smart Tran...

引用

2025 IEEE International Conference on Computational, Communication and Information Technology, ICCCIT 2025

作者： Hundekari, Sheela Mittal, Tanusha Dutt, Amit Bhavana, Munugapati Kumar, Rakesh Nijhawan, Ginni School of Computer Applications Pimpri Chinchwad University Pune India Graphic Era Deemed to Be University Department of Computer Science & Engineering Dehradun India Lovely Professional University Phagwara India MLR Institute of Technology Department of Computer Science and Engineering Telangana Hyderabad India GLA University Department of Computer Engineering & Applications Mathura India

ISBN: (纸本)9798331512965

Predictive maintenance: A game changer in infrastructure and vehicle management, and able to cut maintenance expenses and downtime of smart transportation systems. This study explores ways in which smart transportation systems might use AI in order to plan maintenance schedules and forecast equipment breakdowns. Predictive algorithms, that can detect potential problems before raising to expensive repair or system breakdown, use real time sensor data from infrastructure and vehicles. Decision trees and neural networks are two of these models. By allowing AI driven solutions, transportation systems may transition from a reactive to a proactive maintenance practice which may support efficiency, safety, and reliability. Unsupervised learning methods are used to do anomaly detection for real time operations, and we examine the patterns in previous maintenance data with supervised learning approaches. The use of AI for predictive maintenance is also being studied for use in smart cities, where transportation networks are becoming more interconnected by IoT. The paper also considers challenges on data integration as well as the importance of scaling the algorithms and guaranteeing cybersecurity in these systems. Based on our research, smart transportation systems could benefit from AI to increase operational efficiency, reduce the cost of material and labor to maintain and repair equipment systems, and decrease the rate of disruptions. © 2025 IEEE.

关键词： Predictive maintenance

来源：评论

学校读者我要写书评

暂无评论

An Ontology Based Multilayer Perceptron for Object Detection

引用

computer Systems science & Engineering 2023年第3期44卷 2065-2080页

作者： P.D.Sheena Smart K.K.Thanammal S.S.Sujatha Department of Computer Science S.T.Hindu CollegeNagercoilAffiliated to Manonmaniam Sundaranar UniversityAbishekapattiTirunelveli627012TamilnaduIndia Department of Computer Science and Applications S.T.Hindu CollegeNagercoil629002India

In object detection,spatial knowledge assisted systems are *** detection is a main and challenging issue to analyze object-related *** existing object detection techniques were developed to consider the object detection problem as a classification problem to perform feature selection and *** these techniques still face,less computational efficiency and high time *** paper resolves the above limitations using the Fuzzy Tversky index Ontology-based Multi-Layer Perception method which improves the accuracy of object detection with minimum *** proposed method uses a multilayer forfinding the similarity score.A fuzzy membership function is used to validate the score for predicting the burned and non-burned *** assessment is performed with different factors such as classification rate,time complexity,error rate,space complexity,and precision by using the forestfire *** results show that this novel technique can help to improve the classification rate and reduce the time and space complexity as well as error rate than the conventional methods.

关键词： Object detection similarity score ontology deep learning fuzzy function perception

来源：评论

学校读者我要写书评

暂无评论

Enhancing sputum image clarity with multi-scale deep analysis and vector median filtering

引用

International Journal of Information Technology (Singapore) 2025年 1-8页

作者： Shiny, A. Amala Sivagami, B. Department of Computer Applications S.T. Hindu College Affiliated to Manonmaniam Sundaranar University Tirunelveli India Department of Computer Science and Applications S.T. Hindu College Affiliated to Manonmaniam Sundaranar University Tirunelveli India

Tuberculosis (TB) is a potentially fatal bacterial disease that mostly affects the lungs but has the potential to extend to other body parts. Noise in TB imaging databases can cause erroneous diagnosis results and misinterpretations. To overcome this a novel Sputum image denoise using multi-scale deep analysis model and vector medical filter (SD-MDAVM) has been proposed for denoising the image dataset. The input Sputum images are initially processed to Multi Scalar Image Generation and Noice pixel Detection. The Noise Pixel Detector identifies the noisy pixels in the image, whereas the Multi Scale Image Generation generates versions of the images at various scales. Then the noisy images from the multi-scale generation and the Noisy Pixel detection are given to a MultiScale Deep Analysis Model based Filter (MSDAMF) to reduce the image noise. Finally, the noise free images are gathered from the MSDAMF and the Vector Mediant Filter. For the KTI-DB database, the suggested approach achieves the lowest MSE values of 65.476, 83.192, and 78.358 for images KTI-DB-0, KTI-DB-1, and KTI-DB-2, respectively. The SD-MDAVM approach achieves the lowest time consumption across all databases with 3.52, 3.75, and 3.64 for ZNSM-DB, KTI-DB, and LCH-DB, respectively. © Bharati Vidyapeeth's Institute of computer applications and Management 2025.

关键词： Impulse noise Multi-scale analysis Salt and pepper Sputum image TB diagnosis Vector median filter

来源：评论

学校读者我要写书评

暂无评论

Design of Lightweight RNN for Human Activity Recognition on KU-HAR Dataset

Design of Lightweight RNN for Human Activity Recognition on ...

引用

International Health Informatics Conference, IHIC 2023

作者： Girdhar, Ashish Kait, Ramesh Kapur, Himani Department of Computer Science and Applications Kurukshetra University Kurukshetra India GGSSS Kaithal Kaithal India

ISBN: (纸本)9789819771899

With the world’s aged population increasing rapidly, an earnest need for recognition of human activities is sought after by the Healthcare units across the world. applications of Human Activity Recognition include surveillance, fitness among various others. This manuscript briefly discusses the approaches followed for recognising human activities in the literature. Additionally, in the present work a lightweight RNN (recurrent neural network) model having LSTM (long short term memory) cells is proposed for HAR on the dataset. This lightweight RNN model employs a feature extraction task. Feature extraction is done in three domains-Temporal, Spatial, and Spectral domains. Recently published dataset KU-HAR is used for the presented work and the proposed work performs fairly well over the dataset. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Copy Move Forgery Detection Using Novel Quadsort Moth Flame Light Gradient Boosting Machine

引用

computer Systems science & Engineering 2023年第5期45卷 1577-1593页

作者： R.Dhanya R.Kalaiselvi Department of Computer Applications Noorul Islam Centre for Higher EducationNagercoil629180India Department of Computer Science Engineering Noorul Islam Centre for Higher EducationNagercoil629180India

A severe problem in modern information systems is Digital media tampering along with fake *** though there is an enhancement in image development,image forgery,either by the photographer or via image manipulations,is also done in *** researches have been concentrated on how to identify such manipulated media or information manually along with automatically;thus conquering the complicated forgery methodologies with effortlessly obtainable technologically enhanced ***,high complexity affects the developed ***,it is complicated to resolve the issue of the speed-accuracy *** tackling these challenges,this article put forward a quick and effective Copy-Move Forgery Detection(CMFD)system utilizing a novel Quad-sort Moth Flame(QMF)Light Gradient Boosting Machine(QMF-Light GBM).Utilizing Borel Transform(BT)-based Wiener Filter(BWF)and resizing,the input images are initially pre-processed by eliminating the noise in the proposed *** that,by utilizing the Orientation Preserving Simple Linear Iterative Clustering(OPSLIC),the pre-processed images,partitioned into a number of grids,are ***,as of the segmented images,the significant features are extracted along with the feature’s distance is calculated and matched with the input ***,utilizing the Union Topological Measure of Pattern Diversity(UTMOPD)method,the false positive matches that took place throughout the matching process are *** that,utilizing the QMF-Light GBM visualization,the visualization of forged in conjunction with non-forged images is *** extensive experiments revealed that concerning detection accuracy,the proposed system could be extremely precise when contrasted to some top-notch approaches.

关键词： Borel transform based wiener filter(BWF) orientation preserving simple linear iterative clustering(OPSLIC) keypoint features block features outlier detection

来源：评论

学校读者我要写书评

暂无评论

Colossal pattern extraction using optimised length constraints based on differential evolutionary arithmetic optimisation algorithm

引用

International Journal of Information and Communication Technology 2024年第3期24卷 289-304页

作者： Reddy, T. Sreenivasula Sathya, R. Nuka, Mallikharjunarao Department of Computer Science and Engineering Faculty of Engineering and Technology Annamalai University Annamalai Nagar Tamil Nadu Chidambaram608002 India Department of Computer Science and Engineering Annamalai University Annamalai Nagar Tamil Nadu Chidambaram608002 India Department of Computer Applications Annamacharya Institute of Technology and Sciences YSR Kadapa Andhra Pradesh Rajampet516115 India

Extracting large amounts of information and knowledge from a large database is a trivial task. Existing bulk item mining algorithms for an extensive database are systematic and mathematically expensive and cannot be used for large-scale mining with interruptions. In this paper, the problem of mining the colossal patterns (CPs) is solved by using optimised length constraints (LCs). First, we describe the minimum LC and maximum LC problems and connect them to the optimal LC by identifying the optimal threshold values. Here, the differential evolutionary arithmetic optimisation algorithm (DAOA) is used to find the optimal threshold values of the constraints and extract the colossal patterns. The effectiveness of the proposed algorithm is proven by various experiments using different biological datasets. © 2024 Inderscience Enterprises Ltd.

关键词： Database systems

来源：评论

学校读者我要写书评

暂无评论

Experimental Approach to Identify the Optimal Deep CNN Models to Early Detection of Glaucoma from Fundus CT-Scan Images 7

Experimental Approach to Identify the Optimal Deep CNN Model...

引用

7th International Conference on Intelligent Computing and Control Systems, ICICCS 2023

作者： Sumitha, S. Gokila, S. Hindustan Institute of Technology & Science Master of Computer Applications Chennai India Hindustan Institute of Technology & Science Department of Computer Applications Chennai India

ISBN: (纸本)9798350397253

Glaucoma is an eye disorder that causes the optic nerve to be affected in glaucoma cause of improved Intraocular fluid Pressure (IOP) in the eye. The only way to prevent blindness is to detect glaucoma early, which can only be done through regular eye examinations. Additionally, earlier diagnosis of glaucoma is challenging to determine and requires several costly vision examination protocols and skillful ophthalmologists. The proposed work's goal is to detect Glaucoma using Convolution Neural Networks (CNNs) to speed up the diagnosis process for timely prevention. CNNs have proven effective in discovering even subtle changes produced by glaucoma. The experimental study using three different Deep Learning (DL) algorithms CNN, MobileNet, and ResNet are carried out to analyses the best model. All these models are pretrained on the image data generator for detecting and classifying glaucoma from the fundus photographs. A Gaussian filter is applied in order to remove noise from the images. Three different datasets ORIGA, SCES, and G1020, which contains images of both healthy and advanced glaucoma, are used to train the model. Also, these databases contain colored images of retina and retinal fundus images that are used for testing, and screening the glaucoma. The proposed method attained the best accuracy of 95% from the ResNet-50 algorithm. Also, each suggested model's performance has been evaluated with the results of each CNN model. Additionally, a custom web application has been developed with CNN-based models to classify Glaucoma. The outcomes show that the CNN algorithms have the ability to develop into a time-saving and cost-efficient tool for analyzing populations intended to prevent irreparable blindness caused by glaucoma. © 2023 IEEE.

关键词： Neural network models

来源：评论

学校读者我要写书评

暂无评论

Predicting Mental Health Disorders in the Technical Workplace: A Study on Feature Selection and Classification Algorithms 1

引用

8th International Conference on Data Management, Analytics and Innovation, ICDMAI 2024

作者： Mallick, Sumitra Panda, Mrutyunjaya Department of Computer Science Guru Nanak Institutions Technical Campus Telangana Hyderabad India Department of Computer Science and Applications Utkal University Odisha Bhubaneswar India

ISBN: (数字)9789819732425

ISBN: (纸本)9789819732418

Mental disorders are increasingly common among technical employees, posing significant challenges in the workplace due to high levels of stress. Recognizing and accurately predicting diverse situations is crucial for promoting mental health in healthcare settings. This study aims to predict mental health disorders using feature selection algorithms on the tech survey dataset, which consists of 61 features related to mental health attributes and frequency in the global technical workplace. Multiple machine learning classification algorithms were applied to the best features selected by RFECV, LASSO, and RFE. Performance metrics such as precision, accuracy, and recall were used to determine the optimal models. The results, discussed in an aggregated table, reveal the percentage of technical employees experiencing mental disorders. Our method performance in terms of classification accuracy has been proven to be much higher when compared with many competing feature selection strategies. The proposed research achieved a 79% accuracy rate by evaluating various classification algorithms alongside feature selection methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Feature Selection

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：