检索结果-内蒙古大学图书馆

An effective object detection and tracking using automated image annotation with inception based faster R-CNN model

International Journal of Cognitive Computing in engineering 2024年第1期5卷 343-356页

作者： Vijiyakumar, K. Govindasamy, V. Akila, V. Department of Computing Technologies School of computing SRM institute of Science and Technology Kattankulathur campus Tamilnadu Chengalpattu district India Department of Information Technology Pondicherry Engineering College Pondicherry India Department of Computer Science and Engineering Pondicherry Engineering College Pondicherry India

The present study advances object detection and tracking techniques by proposing a novel model combining Automated Image Annotation with Inception v2-based Faster RCNN (AIA-IFRCNN). The research methodology utilizes the DCF-CSRT model for image annotation, Faster RCNN for object detection, and the inception v2 model for feature extraction, followed by a softmax layer for image classification. The proposed AIA-IFRCNN model is evaluated on three benchmark datasets: Bird (dataset 1), UCSDped2 (dataset 2), and Under Water (dataset 3), to determine prediction accuracy, annotation time, Center Location Error (CLE), and Overlap Rate (OR). The experimental results indicate that the AIA-IFRCNN model outperformed existing models regarding detection accuracy and tracking performance. Notably, it achieved a maximum detection accuracy of 95.62 % on dataset 1, outperforming other models. Additionally, it achieved minimum average CLE values of 4.16, 5.78, and 3.54, and higher overlap rates of 0.92, 0.90, and 0.94 on the respective datasets (1, 2 and 3). Hence, this research work on object detection and tracking using the AIA-IFRCNN model is essential for improving system efficiency and fostering innovation in the field of computer vision and object tracking. © 2024

关键词： Image annotation

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning and Powerful Computational Framework for Brain Cancer MRI Image Recognition

引用

Journal of The Institution of Engineers (India): Series B 2024年第1期105卷 1-18页

作者： Kumar, Ankit Shukla, Santosh Kumar Prakash, Navin Yadav, Rakesh Kumar Department of Information Technology Babu Banarasi Das Institute of Technology and Management Lucknow India Department of Computer Science and Engineering Babu Banarasi Das Engineering College Lucknow India Department of Computer Science and Engineering MSOET Maharishi University of Information Technology Lucknow India

Brain tumors are one of the deadliest diseases and require quick and accurate methods of detection. Finding the optimum image for research goals is the first step in optimizing MRI images for pre- and post-processing. As a result, the mean grey-level approach was used to segment the MRI images using a threshold. In the second stage of statistical feature analysis, the picture features were extracted using the spatial gray-level dependency matrix using Hara lick's feature equations. As a consequence, the best features were picked and the tumor was placed in the appropriate location. In the third stage, an automated tool for classifying the photographs under assessment as having a tumor or not was created utilizing supervised learning and an artificially intelligent methodology. An efficient test of the network's performance yielded 97% of the desired results. © 2023, The Institution of Engineers (India).

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Compact 1D Self-Operational Neural Networks with Feature Injection for Global ECG Classification 4

Compact 1D Self-Operational Neural Networks with Feature Inj...

引用

4th International Conference on Innovative Practices in Technology and Management, ICIPTM 2024

作者： Sengottaiyan, N. Sathish Kumar, S. Sharma R, Rajesh Sungheetha, Akey Chinnaiyan, R. Hamsanandini, S. Alliance University Department of Computer Science and Engineering Bangalore India Adiyaman College of Engineering Department of It Hosur India Kongu Engineering College Department of Computer Science and Engineering Perundurai India

ISBN: (纸本)9798350307757

for solving problems in ECG classification readings for rhythm detection, a novel deep learning approach is presented in this paper. To capture important information about heart cycles like morphology and timing, a proposed technique integrates feature injection with a compact 1D Self-Operational Neural Network (Self-ONN). This allows for fluent and engaging data recording. With superior performance, the network surpasses current models in classification while maintaining minimal computational complexity. Its outstanding results are achieved through training with the MIT-BIH arrhythmias benchmark database. The network displays exceptional levels of accuracy, recall, and F1-score for normal segments (99%), supraventricular ectopic beats (82%), and ventricular ectopic beats (94%), demonstrating its remarkable capabilities. Here study demonstrates the applicability of the approach in wearable ECG sensors for self-monitoring and early detection of cardiovascular diseases. The paper offers comprehensive insights into network architecture, data processing stages, as well as comparisons with current algorithms. The suggested approach outperforms others in terms of F1-score, accuracy, sensitivity, specificity, and positive predictive value when applied to various beat types. The report contains a computational complex analysis that emphasizes the compactness of the model and its importance in reducing the difference in performance between patient-specific and global ECG classification techniques. © 2024 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

Number Plate Recognition Using OpenCV 6

Number Plate Recognition Using OpenCV

引用

6th IEEE International Conference on Emerging Smart Computing and Informatics, ESCI 2024

作者： Roopa Chandrika, R. Vanitha, K. Thahaseen, Aafiya Chandramma, R. Neerugatti, Vikram Mahesh, T.R. Faculty of Engineering Department of Computer Science and Engineering Coimbatore India Al-Ameen Engineering College Department of Computer Science and Engineering Erode India Bangalore India Faculty of Engineering and Technology Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350306613

The advancement of automated number plate recognition (ANPR) systems has garnered noteworthy attention in recent times owing to their diverse applications across multiple domains, including traffic management, parking management, and law enforcement. This paper presents an innovative ANPR method using OpenCV, an open-source computer vision library. Developing ANPR systems is a great fit for OpenCV since it offers a flexible platform for image processing and computer vision tasks. The suggested method effectively detects and recognizes number plates from images and video streams by utilizing OpenCV's capabilities for feature extraction, image preprocessing, and machine learning. Character segmentation, optical character recognitlon (OCR), and licence plate localization are important stages in the process. The ANPR system's accuracy and effectiveness are increased by using these strategies. A variety of real-world datasets, including different lighting conditions, camera angles, and vehicle types, are used in extensive experiments to assess the system's performance. The outcomes show how well the OpenCV-based ANPR system performs in tasks requiring license plate recognition, attaining high accuracy and resilience. Additionally, covered in the paper are possible uses for the ANPR system in security systems, vehicle tracking, and traffic monitoring. To make sure the system is workable in a variety of situations, scalability and real-time implementation are also taken into account. © 2024 IEEE.

关键词： machine learning number plate OpenCV recognition

来源：评论

学校读者我要写书评

暂无评论

Event Management System Using Spatial and Event Attribute Information

引用

SN computer science 2025年第3期6卷 1-9页

作者： Setia, Sonia Anjli, Km Bisht, Upasana Jyoti Raj, Dharm Department of Computer Science & Engineering Sharda School of Engineering & Technology Sharda University Uttar Pradesh Greater Noida India Department of Computer Science Institute of Innovation in Technology & Management Delhi Janakpuri India Department of Computer Science and Engineering ITS Engineering College Greater Noida India

The event management mechanism matches messages that have been subscribed to and events that have been published. To identify the subscriptions that correspond to the occurrence inside the category, it must first run a clustering operation on the subscription message data and determine the category to which the event belongs. In this work, we offer an on-the-fly publish-subscribe technique that can handle on-the-fly subscription changes and category modifications in a distributed environment, as well as the synchronization of spatial information and event attribute information. Additionally, without any prior information, clustering and matching processes can be carried out rapidly. The publish-subscribe method is implemented on a distributed system, and a load-balancing solution is proposed for the algorithm on the distributed system. We then constructed our cluster and used real data to empirically evaluate the suggested publish-subscribe technique. Experiments show that incorporating both similarity and relevance with frequency, compared to focusing on similarity alone, significantly decreases the number of categories which need to be matched for events. This leads to a 15.5% improvement in the speed of matching events and subscriptions. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2025.

关键词： Clustering algorithms Distributed systems Publish-and-subscribe systems

来源：评论

学校读者我要写书评

暂无评论

Conditional Generative Adversarial Network Approach for Autism Prediction

引用

computer Systems science & engineering 2023年第1期44卷 741-755页

作者： K.Chola Raja S.Kannimuthu Department of Computer Science and Engineering Sri Eshwar College of EngineeringCoimbatore641202TamilnaduIndia Department of Information Technology Karpagam College of EngineeringCoimbatore641032TamilnaduIndia

Autism Spectrum Disorder(ASD)requires a precise diagnosis in order to be managed and ***-invasive neuroimaging methods are disease markers that can be used to help diagnose *** majority of available techniques in the literature use functional magnetic resonance imaging(fMRI)to detect ASD with a small dataset,resulting in high accuracy but low *** supervised machine learning classification algorithms such as support vector machines function well with unstructured and semi structured data such as text,images,and videos,but their performance and robustness are restricted by the size of the accompanying training *** learning on the other hand creates an artificial neural network that can learn and make intelligent judgments on its own by layering *** takes use of plentiful low-cost computing and many approaches are focused with very big datasets that are concerned with creating far larger and more sophisticated neural *** modelling,also known as Generative Adversarial Networks(GANs),is an unsupervised deep learning task that entails automatically discovering and learning regularities or patterns in input data in order for the model to generate or output new examples that could have been drawn from the original *** are an exciting and rapidly changingfield that delivers on the promise of generative models in terms of their ability to generate realistic examples across a range of problem domains,most notably in image-to-image translation tasks and hasn't been explored much for Autism spectrum disorder prediction in the *** this paper,we present a novel conditional generative adversarial network,or cGAN for short,which is a form of GAN that uses a generator model to conditionally generate *** terms of prediction and accuracy,they outperform the standard *** pro-posed model is 74%more accurate than the traditional methods and takes only around 10 min for training even with a huge dat

关键词： Autism classification attributes imaging adversarial fMRI functional graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Identification of peak hour and active member on WhatsApp group using Python 5

Identification of peak hour and active member on WhatsApp gr...

引用

5th International Conference on Computational Intelligence and Communication Technologies, CCICT 2022

作者： Bajpai, Rishabh Sharma, Rahul Kumar Vashisht, Rohit ABES Engineering College Department of Computer Science Ghaziabad India

ISBN: (数字)9781665472241

ISBN: (纸本)9781665472241

As the internet came out of its infancy, the need for human conversation came out as the next part of its evolution process. With the rise of social media starting especially with the advent of Facebook, human interaction over the internet became instantaneous and smooth. One more addition to this was the development of WhatsApp, which was eventually bought by Facebook. This is a tool that analyses WhatsApp group user data to draw conclusions from it, presenting in the form of an easily understandable graphical representation. It is written in python using Jupiter notebook as a base format for writing the code, along with the use of some external libraries, matplot libraries (for plotting the graphs), and json (to read the json file for telegram group data). This project is coded with the help of a popular and open-source code editor VS - Code by Microsoft. As support to increase openness of the mega-corporations over the data policy, the code of the project is made open source, which can be found at (***) to enhance the peer review process and also to increase collaboration among the community, also it will help anyone if he/she wants to take a look at how the data is processed. © 2022 IEEE.

关键词： Python

来源：评论

学校读者我要写书评

暂无评论

Federated learning techniques in the healthcare area 4th

Federated learning techniques in the healthcare area

引用

4th International Conference on Computational Methods in science and Technology, ICCMST 2024

作者： Kumar, Sanjay Virk, Ishpreet Singh Puri, Renu Department of Computer Science and Engineering Chandigarh Engineering College-CGC Landran India

ISBN: (纸本)9781032911571

Federated understanding techniques have actually shown prospective, in the medical care sector allowing cooperation as well as information sharing while promoting personal privacy and also safety and security steps. This evaluation explores making uses of federated knowing in health care showcasing its capacity to boost results development medical study and also sustain tailored medication. The evaluation covers the advantages along with barriers of incorporating federated discovering in medical care together with opportunities for expedition as well as development in this area. Furthermore it deals with difficulties as well as chances for research study on medical care applications. The goal is to inspire a journey of linked expertise in health care contexts for it to come to be an approach for securing fragile professional information. The future pattern suggests an expanding fostering of linked knowing in setups, causing sophisticated procedures that focus on personal privacy and also safety and security while successfully using this innovation to resolve crucial problems within the medical care field. © 2025 the Author(s).

关键词：

来源：评论

学校读者我要写书评

暂无评论

RSSN at Multilingual Counterspeech Generation: Leveraging Lightweight Transformers for Efficient and Context-Aware Counter-Narrative Generation 1

RSSN at Multilingual Counterspeech Generation: Leveraging Li...

引用

1st Workshop on Multilingual Counterspeech Generation, MCG 2025 with Shared Task on Multilingual Counterspeech Generation

作者： Ravindran, V. Department of Computer Science and Engineering Sri Sivasubramaniya Nadar College of Engineering India

ISBN: (纸本)9798891762077

This paper presents our system for generating counter-speech (CN) in response to hate speech (HS), developed for the COLING 2025 shared task. We employ lightweight transformer-based models, DistilBART and T5-small, optimized for computational efficiency while maintaining competitive performance. Through comprehensive dataset analysis, we identify linguistic patterns, explore challenges, and propose enhancements. Our findings demonstrate the viability of lightweight models and highlight error patterns that can guide future research directions. We provide a detailed evaluation of results across multiple metrics, including BLEU, ROUGE, and BERTScore, and discuss strategies for enhancing contextual relevance in CNs. © 2025 Association for Computational Linguistics

关键词： Computational linguistics

来源：评论

学校读者我要写书评

暂无评论

Malicious Activities Prediction Over Online Social Networking Using Ensemble Model

引用

Intelligent Automation & Soft Computing 2023年第4期36卷 461-479页

作者： S.Sadhasivam P.Valarmathie K.Dinakaran Department of Computer Science and Engineering K.S.R College of EngineeringThiruchengodeIndia Centre for Artificial Intelligence Chennai Institute of TechnologyChennaiIndia Department of Computer Science and Engineering S.A.Engineering CollegeChennaiIndia

With the vast advancements in Information Technology,the emergence of Online Social Networking(OSN)has also hit its peak and captured the atten-tion of the young generation *** clone intends to replicate the users and inject massive malicious activities that pose a crucial security threat to the original ***,the attackers also target this height of OSN utilization,explicitly creating the clones of the user’s *** clone detection mechanisms are designed based on social-network *** instance,monitoring the occur-rence of clone edges is done to restrict the generation of clone ***,this assumption is unsuitable for a real-time environment and works optimally during the simulation *** research concentrates on modeling and efﬁ-cient clone prediction and avoidance methods to help the social network activists and the victims enhance the clone prediction *** model does not rely on ***,an ensemble Adaptive Random Subspace is used for clas-sifying the clone victims with k-Nearest Neighbour(k-NN)as a base classiﬁ*** weighted clone nodes are analysed using the weighted graph theory concept based on the classiﬁed *** the weighted node’s threshold value is high-er,the trust establishment is terminated,and the clones are ranked and sorted in the higher place for ***,the victims are alert to the clone propaga-tion over the online social networking end,and the validation is done using the MATLAB 2020a simulation *** model shows a better trade-off than existing approaches like Random Forest(RF),Naïve Bayes(NB),and the standard graph *** performance metrics like True Positive Rate(TPR),False Alarm Rate(FAR),Recall,Precision,F-measure,and ROC and run time analysis are evaluated to show the signiﬁcance of the model.

关键词： Online social network decision tree weighted measure clone attack predictive measures

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：