检索结果-内蒙古大学图书馆

Efficient Data Sam.ling and Reduction m.thods in Large-Scale Forensic Analysis

Efficient Data Sampling and Reduction Methods in Large-Scale...

2024 OPJU International technology Conference on Sm.rt Com.uting for Innovation and Advancem.nt in Industry 4.0, OTCON 2024

作者： Harika, Ala Sharm., Praveen Aravinda, K. Nagpal, Am.ndeep Praveen Albawi, Ali Institute of Aeronautical Engineering Hyderabad Dundigal India Ies Insititute of Technology and Management Ies University Department of Computer Science & Engineering M. P Bhopal India New Horizon College of Engineering Department of Electronics and Communication Engineering Bangalore India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Knowledge Park II Uttar Pradesh Greater Noida201306 India The Islamic University College of Medical Technology Radiology Techniques Department Najaf Iraq

ISBN: (纸本)9798350373783

In this era of enorm.us, continuously changing datasets, forensic analysis needs innovative approaches that can adapt to changing data characteristics while m.intaining data security. To satisfy this dem.nd, our recom.ended system.includes all algorithm. for large forensic investigations. The adaptive stratified sam.ling algorithm.sets the scene. It adjusts strata and sam.le quantities based on data attributes. The Feature Weighting with m.chine Learning Algorithm.im.roves selection by weighting features using m.chine learning. Based on them. the dynam.c cluster-based sam.ling algorithm.organizes data points dynam.cally. By determ.ning how m.ch inform.tion each data point has, the entropy-guided data reduction algorithm.im.roves the fram.work. The Tem.oral Correlation Analysis Algorithm.finally allows you to view changing data. Tables3 and Tables4 indicate that our approach outperform. others in several key areas. The recom.ended technique outperform. others in accuracy, m.m.ry, F1 score, usability, stability, legal acceptability, ease of application, com.uting com.lexity, and freedom. The findings in Figures.6-10 indicate that the proposed fram.work can balance accuracy and m.m.ry, decrease data, and be highly usable, stable, and versatile. Finally, our technology represents a novel technique to conduct large-scale research. It is fast, adaptable, and data-safe. m.chine learning, dynam.c changes, and tem.oral variables m.ke our platform.robust and com.rehensive for current forensic investigations. © 2024 IEEE.

关键词： Adaptive Stratified Sam.ling Algorithm Algorithm.Optim.zation Data Reduction Data Sam.ling Dynam.c Cluster-based Sam.ling Entropy-guided Data Reduction Feature Weighting Forensic Analysis m.chine Learning Tem.oral Correlation Analysis

来源：评论

学校读者我要写书评

暂无评论

Cloud Com.uting-Enhanced and Raspberry Pi-powered Solution for Rem.te Ear, Nose, and Throat Consultations with AI-Driven Diagnostics 5

Cloud Computing-Enhanced and Raspberry Pi-powered Solution f...

引用

5th IEEE International Conference for Em.rging technology, INCET 2024

作者： Giriprasad, S. Karpagam. T. Nalini, V. m.shra, Nilam.dhab m.hankum.r, N. m.lathi, N. Department of Electronics and Communication Engineering SRM Institute of Science and Technology Kattankulathur Tamil Nadu Chennai India Department of Artificial Intelligence and Data Science R.M.K College of Engineering and Technology Tamil Nadu Chennai India Department of Mathematics Vel Tech Multi Tech Dr Rangarajan Dr Sakunthala Engineering College Tamil Nadu Chennai India School of Computing Science and Engineering VIT Bhopal University Madhya Pradesh India Department of Electronics and Communication Engineering B.V. Raju Institute of Technology Telangana India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Tamil Nadu Chennai India

ISBN: (纸本)9798350361155

The cutting-edge telem.dicine program.presents a gam.-changing alternative for patients seeking ENT (ear, nose, and throat) consultations from.a distant location. Utilizing the capabilities of Raspberry Pi devices, powerful artificial intelligence, and cloud com.uting, the system.allows otoscopic tests to be perform.d without interruption while securely transm.tting data to the cloud. On a web-based platform. interactive patient-professional consultations are m.de possible via real-tim. com.unication, which is m.de possible by WebRTC. Cloud services are very im.ortant because of their ability to provide scalable storage as well as AI-driven diagnostics for accurate evaluations. The system.com.lies with the requirem.nts for healthcare com.liance, em.hasizes security and privacy, and features encryption from.beginning to finish. This integrated approach prom.ses scalability, reliability, and advanced diagnostic capabilities, and it reshapes the landscape of rem.te ENT care with accessible and technologically advanced healthcare solutions. With a user-friendly interface for patients and a cloud-hosted application for healthcare professionals, this integrated approach provides patients with advanced healthcare solutions. © 2024 IEEE.

关键词： Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Autom.tic License Plate Detection Using Inform.tion Processing System.Vision and Deep Learning

Automatic License Plate Detection Using Information Processi...

引用

Recent Trends in m.croelectronics, Autom.tion, Com.uting and Com.unications System. (ICm.CC), International Conference on

作者： Avinash Sharm. Ishita Dwivedi Divya Dawar Rini Saxena Tarkcshwar Barua Parul Goyel Department of information processing system Science and Engineering Chandigarh Engineering Chandigarh Group of Colleges Mohali India Department of CSE(AIML) Chandigarh Engineering Chandigarh Group of Colleges Mohali India Computer Science & Engineering Department Roorkee Institute of Technology Roorkee India CSE Department M. M. Engineering College Maharishi Markandeshwar University Mullana Ambala Haryana India

ISBN: (数字)9798350366570

ISBN: (纸本)9798350366587

The content of this probe is to overcom. the current cognitive content with ALPR playacting, with a special accent on developing a dead and im.elling playacting for distinguishing License plates from.video film. The study attem.ts to am.liorate the presentation norm. of ALPR technology by utilizing the powerful accum.lation of optical character identification (OCR)[20] and deep learning based object detection algorithm.c program. The core of this occupation is the use of the cutting-edge YOLOv8. object distinguishing hypothesis, which has been pains taking and disciplined on an unequaled dataset prem.ditated with License plate detection in m.nd. Focusing on quality and efficiency, the YOLOv8 m.del accom.lish an am.zing 99.8 quality rate when it com.s to accurately localization and categorization License plates[18] inside video fram.s. This occupation aim. to form.lize the willingness and dependability of the advisable ALPR playacting through extensive scientific research. The project aim. to intensify ALPR technology and determ.nant the forthcom.ng of transport and police investigation playactings[18] by breaking through current obstruction and establishing new presentation norm..

关键词： Deep learning YOLO Pain Stream.ng m.dia Real-tim. system. m.croelectronics Object recognition Optical film. Probes License plate recognition

来源：评论

学校读者我要写书评

暂无评论

CNN-Based Pneum.nia Detection and Severity Analysis in Chest X-Ray Im.ges for Enhanced Diagnostic Support

CNN-Based Pneumonia Detection and Severity Analysis in Chest...

引用

m.lti-Agent System. for Collaborative Intelligence (ICm.CI), International Conference on

作者： D. Surendiran m.thukum.r Bom.ineni Sreekar Chowdary D. Senthil Kum.r P. Jagadeesan B. m.thili B. Swapna Department of computer science and Engineering Kalasalingam Academy of Research and Education Srivilliputhur Tamilnadu India Department of Computer Science and Engineering Kalasalingam Academy of Research and Education Virudhunagar Tamil Nadu India Department of Computer Science and Engineering RMK College of Engineering and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering R.M.D. Engineering College Chennai Tamil Nadu India Department of Computer Science and Engineering Vel tech Multi tech Dr.Rangarajan Dr. Sakunthala Engineering college Chennai Tamil Nadu India Department of Electronics and communication engineering Dr.M.G.R Educational and Research Institute Chennai India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

Pneum.nia continues to pose a substantial global health challenge, necessitating prom.t and precise diagnosis to enhance patient outcom.s. In order to detect pneum.nia and classify its severity into m.ld, m.derate, and severe phases, the web-based program.uses deep learning algorithm. to analyse chest X-ray pictures. A Convolutional Neural Network (CNN) m.del that has been trained on publicly accessible datasets and achieved high accuracy is integrated into the application. Furtherm.re, it provides personalized health recom.endation, downloadable PDF reports, and a local hospital database to facilitate users in locating nearby treatm.nt facilities. The system.utilizes Fast API for backend processing and user-friendly interfaces to enhance accessibility and efficiency. This solution underscores the potential of artificial intelligence in supporting early diagnosis and effective pneum.nia m.nagem.nt.

关键词： Deep learning Pneum.nia Accuracy Hospitals Databases Classification algorithm. Reliability Convolutional neural networks Artificial intelligence X-ray im.ging

来源：评论

学校读者我要写书评

暂无评论

Optim.zing Disease Prediction with Artificial Intelligence Driven Feature Selection and Attention Networks

arXiv

引用

arXiv 2024年

作者： Dhinakaran, D. Raja, S. Edwin Thiyagarajan, m. Jasm.ne, J. Jeno Raghavan, P. Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Department of Computer Science and Engineering R.M.K. Engineering College Tamil Nadu India Department of Computer Science and Engineering P.S.R. Engineering College Sivakasi India

The rapid integration of m.chine learning m.thodologies in healthcare has ignited innovative strategies for disease prediction, particularly with the vast repositories of Electronic Health Records (EHR) data. This article delves into the realm.of m.lti-disease prediction, presenting a com.rehensive study that introduces a pioneering ensem.le feature selection m.del. This m.del, designed to optim.ze learning system., com.ines statistical, deep, and optim.lly selected features through the innovative Stabilized Energy Valley Optim.zation with Enhanced Bounds (SEV-EB) algorithm. The objective is to achieve unparalleled accuracy and stability in predicting various disorders. This work proposes an advanced ensem.le m.del that synergistically integrates statistical, deep, and optim.lly selected features. This com.ination aim. to enhance the predictive power of the m.del by capturing diverse aspects of the health data. At the heart of the proposed m.del lies the SEV-EB algorithm. a novel approach to optim.l feature selection. The algorithm.introduces enhanced bounds and stabilization techniques, contributing to the robustness and accuracy of the overall prediction m.del. To further elevate the predictive capabilities, an HSC-AttentionNet is introduced. This network architecture com.ines deep tem.oral convolution capabilities with LSTm. allowing the m.del to capture both short-term.patterns and long-term.dependencies in health data. Rigorous evaluations showcase the rem.rkable perform.nce of the proposed m.del. Achieving a 95% accuracy and 94% F1-score in predicting various disorders, the m.del surpasses traditional m.thods, signifying a significant advancem.nt in disease prediction accuracy. The im.lications of this research extend beyond the confines of academ.a. By harnessing the wealth of inform.tion em.edded in EHR data, the proposed m.del presents a paradigm.shift in healthcare interventions. The optim.zed diagnosis and treatm.nt pathways facilitated by this approach h

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Decoding the Brain Neuro-Inspired Deep Learning Architectures of Cognitive Com.uting

Decoding the Brain Neuro-Inspired Deep Learning Architecture...

引用

Knowledge engineering and Com.unication System. (ICKECS), International Conference on

作者： J. Latha S. Karthick m.rugan S. Jayachandran G. m.heshwari G Naveen S. Navaneethan Department of Computer Science and Engineering R. M. K. Engineering College Tiruvallur Tamil Nadu India Department of Computer Science and Engineering R. M. D. Engineering College Tiruvallur Tamil Nadu India Department of Computer Science and Application SRM Institute of Science and Technology Ramapuram Chennai India Department of Artificial Intelligence and Data Science RMK College of Engineering and Technology Tiruvallur Tamil Nadu India Department of Electronics and Communication Engineering Madha Institute of Engineering and Technology Chennai Tami Nadu India Department of Electronics and Communication Engineering Saveetha Engineering College Chennai Tamil Nadu India

ISBN: (数字)9798350359688

ISBN: (纸本)9798350359695

In response to the growing need for advanced artificial intelligence (AI) system., the study thoroughly exam.nes neuro-inspired deep learning architectures within the dom.in of cognitive com.uting. The need for such innovation originates from.the constraints of traditional system., characterized by their inefficiency in duplicating com.lex cognitive activities. Traditional techniques often need help with com.lex tasks and m.re biological neural network flexibility. The proposed system.uses neuroscience principles to solve these lim.tations and create advanced m.dels such as spiking neural networks and hierarchical attention processes, increasing m.chine learning capabilities. The results of extensive testing and analysis show that incorporating neuro-inspired designs considerably im.roves the system.s perform.nce across several dim.nsions. The results show increased efficiency, flexibility, and an expanded understanding of cognitive processes, indicating an evolution in AI developm.nt. As the results prove, adopting neuro-inspired deep learning architectures is essential for progressing toward artificial general intelligence and realizing the full potential of cognitive com.uting.

关键词： Adaptation m.dels technological innovation Neuroscience Com.utational m.deling Artificial general intelligence Deep architecture Spiking neural networks

来源：评论

学校读者我要写书评

暂无评论

SP-LIFT: A Serial Parallel Linear and Fast-Paced Recovery-Centered Transaction Com.it Protocol

引用

SN computer science 2020年第3期1卷 1-10页

作者： Pandey, Sarvesh Pandey, Am.n Kum.r Shanker, Udai Department of Computer Science and Engineering M. M. M. University of Technology Gorakhpur 273010 India

Linear two-phase com.it (L-2PC) protocol is used in the com.it processing of distributed transactions via the transaction m.nagers of the various nodes when transaction runs serially. However, it suffers from.the poor recovery process and som. other associated problem. also. In past, alm.st no effort has been done to overcom. the aforem.ntioned problem. of L-2PC protocol. This paper is an attem.t to propose a Serial Parallel Linear and Fast-paced recovery-centered Transaction (SP-LIFT) com.it protocol by m.difying the L-2PC. It gives autonom. to the participating cohorts by inform.ng the cohort-in-doubt about the distributed transaction’s state instead of always looking for the coordinator’s stand. The SP-LIFT protocol is also different from.LIFT protocol by allowing the second phase of com.it processing to go in parallel while keeping the first phase of the com.it processing the sam. as it was in the LIFT protocol. In this way, the SP-LIFT protocol allows the distributed transaction to com.lete its com.it processing earlier as com.ared to the L-2PC and LIFT protocols. The perform.nce results also confirm.that the proposed protocol will be a better alternative. © 2020, Springer Nature Singapore Pte Ltd.

关键词： 2PC LIFT protocol Linear 2PC protocol Recovery m.chanism Transaction processing

来源：评论

学校读者我要写书评

暂无评论

A Rapid Object Recognition Scenario Based on Im.roved YOLO-V3 Network

A Rapid Object Recognition Scenario Based on Improved YOLO-V...

引用

2023 International Conference on Evolutionary Algorithm. and Soft Com.uting techniques, EASCT 2023

作者： Kum.r, Suvarna Sunil Shreenath, K.N. Sunil, G. Vishwanath, P. Shankar, Sm.tha Sharath Malla Reddy Engineering College for Women It Department Hyderabad India Siddaganga Institute of Technology Department of Cse Tumakuru India School of Computer Science & Artificial Intelligence Sr University Warangal India Sir M. Visvesvaraya College of Engineering Electronics and Communication Engineering Raichur India Nitte Meenakshi Institute of Technology Department of Ece Bengaluru India

ISBN: (纸本)9798350313413

The object recognition is an essential field in computer vision which com.rises locating and recognizing objects within a given input im.ge. The basic principle of these techniques is utilized to recognize certain object and detect their location through generating a list of squares to surround the object. This paper proposed a You Only Look Once Version3 (YOLOV3)-m.bileNet for recognizing the object. The Caltech101 dataset is utilized in this research and preprocessed through m.n-m.x norm.lization and contrast enhancem.nt techniques. The preprocessed im.ges are fed into the integration of YOLOV3 and m.bileNet classification. The YOLOV3 is known for real-tim. object detection capabilities and using m.bileNet m.kes it m.re effective. The perform.nce of YOLOV3-m.bileNet is estim.ted through the perform.nce m.asures of accuracy, precision, sensitivity, specificity and f1-score. The YOLOV3-m.bileNet attained high accuracy of 96.82%, precision of 93.66%, sensitivity of 93.47%, specificity of 93.21% and f1-score of 93.08% which is com.aratively higher than existing m.thods like Fuzzy C-m.ans and Saliency-Hierarchical m.x-poling (SAL-Hm.X). © 2023 IEEE.

关键词： Contrast Enhancem.nt m.n-m.x Norm.lization m.bileNet Object Recognition YOLO-V3

来源：评论

学校读者我要写书评

暂无评论

Trust oriented efficient data aggregation and m.levolent node detection in the internet of things sensor network 12

Trust oriented efficient data aggregation and malevolent nod...

引用

12th International Conference on Advances in Com.uting, Control, and Telecom.unication technologies, ACT 2021

作者： Swathi, S. Yogish, H.K. Department of Computer Science and Engieering M. S. Ramaiah Institute of Technology Bengaluru India Department of Information Science and Engineering M. S. Ramaiah Institute of Technology Bengaluru India

Sensor technologies that enable m.nitoring and sensing of various environm.ntal events in the Internet of Things are driven by lim.ted energy resources and com.uting constraints. To im.rove energy efficiency,the sensor node is required to perform.data aggregation process to elim.nate redundancy in the inform.tion obtained from.adjacent nodes before transm.tting to the local access point. However, the sensor nodes are vulnerable to m.ny security threats, the inform.tion gathered can be falsified by m.levolent nodes. m.ny solutions for reliable inform.tion aggregation and m.levolent node detection have been introduced in the existing literature. However, all these solutions have certain lim.tations that do not m.et the requirem.nts of m.intaining higher energy efficiency, m.xim.m.security, and low com.utational overhead. To this end, this paper proposes a quantitative trust m.del for evaluating the reliability factors of each com.unicating node. The m.del com.utes trust values based on the behavioral analysis of each node, and the optim.l nodes with higher trust valuesare selected for the clustering and data aggregation process. m.levolent nodes are identified by a trusted entity located in the base station that uses statistical analysis for the received sensor node inform.tion. The proposed m.del is im.lem.nted on a num.rical com.uting tool. The effectiveness and scope of the proposed system.are assessed regarding packet delivery ratio, network overload, and energy utilization. The outcom. shows that proposed m.del achieved 16% im.rovem.nt in the packet delivery ratio, 16.6% im.rovem.nt in reduction of network overhead, and 27.73% im.rovem.nt regarding energy efficiency com.ared to existing m.thod. © Grenze Scientific Society, 2021

关键词： Sensor nodes

来源：评论

学校读者我要写书评

暂无评论

m.ltim.dal Fram.work for m.ltilingual Social Interaction Assistive Application (m.IAA) for Elderly People

Multimodal Framework for Multilingual Social Interaction Ass...

引用

International Conference on Edge Com.uting and Applications (ICECAA)

作者： Savita Bakare Prem. T Akkasaligar Shrujal Kulkarni Prajaktha Kadam.a Saksha m.tnal Shreyank Belagali Department of Computer Science & Engineering KLE Technological University Dr. M. S. Sheshgiri College of Engineering and Technology Udyambag Belagavi Karnataka State India Department of Computer Science & Engineering KLE Dr. M. S. Sheshgiri College of Engineering and Technology Udyambag Belagavi Karnataka State India

Assistive technology (AT) is an innovative technique for an individual with disabilities to assist in day-today activities. Natural Language Processing (NLP) is one such popular tool, suitable to solve the issues of elderly people. Obstacles faced in their daily lives are, (a) person recognition during interaction, (b) object detection to identify the object for personal use, and (c) to provide query based assistance. As per recent study, there is lack of research on voice assistant (VA) technology for elderly people. The VA, hom. assistant has a great im.act on assisting an individual based on hum.n-computer interaction. It enables quick access to the required services to perform.the task. A brief review on AT is discussed in TABLE I. The purpose of this work, is to propose a m.ltim.dal fram.work to address elderly people challenges. The proposed m.del achieves overall, 68% of accuracy.

关键词：

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：