检索结果-内蒙古大学图书馆

17th IEEE International Conference on Signal Processing, ICSP 2024

作者： Pan, Huichao Li, Cong Li, Xin Liu, Chunming Yang, Guodong Zhang, Chunjie Jinan Power Supply Company State Grid Shandong Electric Power Company Operation and Maintenance Department Jinan China Institute of Automation Chinese Academy of Sciences Cas Engineering Laboratory for Intelligent Industrial Vision Beijing China Beijing Jiaotong University School of Computer and Information Technology Beijing China

ISBN: (纸本)9798350387384

Power transmission lines are often subjected to wind-induced vibrations (also known as transmission line galloping). To alleviate this problem, quantitative transmission line galloping measurement is necessary. While it is costly and dangerous to install various types of sensors, it is more efficient to use contactless measurement methods (e.g. camera surveillance). In this paper, we propose a novel transmission line galloping measurement method using video analysis technique by spacer matching. First, we determine the spacers by template matching. Then we used matched spacers for the reconstruction of the movement of spacers. We also explore the intra-relationships of the movements of different spacers for accurate measurement. Finally, we synchronize the spacers of the whole line to simulate the galloping of transmission lines. Experiments on several transmission line galloping videos demonstrate the effectiveness of the proposed method. © 2024 IEEE.

关键词： Template matching

来源：评论

学校读者我要写书评

暂无评论

A Covid-19 Tracker for Medical Front-liners

A Covid-19 Tracker for Medical Front-liners

引用

2022 IEEE Pune Section International Conference, PuneCon 2022

作者： Ramesh, Rajeev Patil, Sandeep Jaiswal, Akshansh Banerjee, Vikramjit Shinde, Aman Kaswa, Manali School of Engineering and Applied Sciences University at Buffalo BuffaloNY United States International Institute of Information Technology Computer Engineering Department Pune India

ISBN: (纸本)9781665498975

The management of Covid-19 affected patients is a very difficult task. The current healthcare system of India is not able to cope with the enormous flow of patients and is in a dire need for improvement. This implementation paper provides a system which will manage all the affected patients right from the time they are Covid-19 positive till the time they are treated and discharged. This paper includes all the technical details of a fully implemented healthcare management system which is a significant improvement in the current system. The proposed system is a cross platform multi user web app which can be used by multiple stakeholders to carry out smooth management of the patients. It consists of a lot of key features like dynamic location-wise patient status, an accurate tracking system of ambulances, a statistical trend analysis of patients and categorical report generation of patients. This system aims to help the medical Front-liners in efficient management of Covid-19 patients, and it is a common site for all the different health workers like field workers and medical officers to work togetherand fight against this deadly disease affecting our country. © 2022 IEEE.

关键词： Ambulances

来源：评论

学校读者我要写书评

暂无评论

Spread Analysis and Prediction of Covid-19 in India using Machine Learning

Spread Analysis and Prediction of Covid-19 in India using Ma...

引用

Advancement in Computation & computer Technologies (InCACCT), International Conference on

作者： Anuradha Yenkikar C. Narendra Babu Department of Computer Science and Engineering indRamaiah University of Applied Sciences Bangalore Karnataka India Pune Institute of Computer Technology Pune India

Since its breakout, the coronavirus (covid-19) has wreaked devastation all over the world. There hasn’t been a nation that hasn’t been affected by it, and India is no exception. Finding a treatment for this sickness and stopping its spread is one of the hardest problems humanities has ever faced. World Health organization (WHO) figures show that the mortality rate and the number of people with covid-19 are both increased exponentially in some countries during the peak waves. In this study, we use machine learning approaches to forecast the number of covid-19 confirmations, recoveries, and mortality cases over a period of time and assess the coronavirus outbreak in India. The polynomial regression (PR), support vector regression (SVR), and an autoregressive integrated moving average (ARIMA) model are three techniques that are used. The findings demonstrate that, in terms of prediction outcomes, the ARIMA model provides the least Root Mean Squared Error (RMSE), closely followed by polynomial regression. SVR doesn’t perform well since predictions are either too low or too high. Overall, the proposed system can significantly aid in comprehending the pattern of spread in other nations and assist governmental bodies in taking action to lessen its effects in future.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Deep Learning Enabled Object Detection and Tracking Model for Big Data Environment

引用

computers, Materials & Continua 2022年第11期73卷 2541-2554页

作者： K.Vijaya Kumar E.Laxmi Lydia Ashit Kumar Dutta Velmurugan Subbiah Parvathy Gobi Ramasamy Irina V.Pustokhina Denis A.Pustokhin Department of Computer Science and Engineering Vignan’s Institute of Engineering for WomenVisakhapatnam530049India Department of Computer Science and Engineering Vignan’s Institute of Information TechnologyVisakhapatnam530049India Department of Computer Science and Information System College of Applied SciencesAlMaarefa UniversityRiyadh11597Kingdom of Saudi Arabia Department of Electronics and Communication Engineering Kalasalingam Academy of Research and EducationKrishnankoil626126TamilnaduIndia Department of Computer Science Christ UniversityBangalore560029India Department of Entrepreneurship and Logistics Plekhanov Russian University of Economics117997MoscowRussia Department of Logistics State University of ManagementMoscow109542Russia

Recently,big data becomes evitable due to massive increase in the generation of data in real time ***,object detection and tracking applications becomes popular among research communities and finds useful in different applications namely vehicle navigation,augmented reality,surveillance,*** paper introduces an effective deep learning based object tracker using Automated Image Annotation with Inception v2 based Faster RCNN(AIA-IFRCNN)model in big data *** AIA-IFRCNN model annotates the images by Discriminative Correlation Filter(DCF)with Channel and Spatial Reliability tracker(CSR),named DCF-CSRT *** AIA-IFRCNN technique employs Faster RCNN for object detection and tracking,which comprises region proposal network(RPN)and Fast *** addition,inception v2 model is applied as a shared convolution neural network(CNN)to generate the feature ***,softmax layer is applied to perform classification *** effectiveness of the AIA-IFRCNN method undergoes experimentation against a benchmark dataset and the results are assessed under diverse aspects with maximum detection accuracy of 97.77%.

关键词： Object detection tracking convolutional neural network inception v2 image annotation

来源：评论

学校读者我要写书评

暂无评论

Application of Augmented Reality and 3D Reconstruction Technologies in Power Scenarios 17

Application of Augmented Reality and 3D Reconstruction Techn...

引用

17th IEEE International Conference on Signal Processing, ICSP 2024

作者： Xu, Mingkai Li, Cong Liu, Chunming Li, Xin Yang, Guodong Yu, Dong Zhang, Chunjie Jinan Power Supply Company State Grid Shandong Electric Power Company Operation and Maintenance Department Jinan China Institute of Automation Chinese Academy of Sciences Cas Engineering Laboratory for Intelligent Industrial Vision Beijing China Beijing Jiaotong University School of Computer and Information Technology Beijing China

ISBN: (纸本)9798350387384

As the power system continues to develop, the application of augmented reality (AR) and 3D reconstruction technologies in power scenarios is becoming increasingly widespread. This paper proposes the integration of these two technologies for the detection, maintenance, and fault diagnosis of power equipment. Through real-time video segmentation and detection operations, AR technology can overlay key information onto the field view, helping engineers quickly identify equipment status and potential issues. Simultaneously, 3D reconstruction technology can generate precise models of power equipment and environments, providing comprehensive visual references and analytical tools that enhance maintenance efficiency and safety. The combined application of these technologies can significantly reduce the risks and costs associated with manual operations. © 2024 IEEE.

关键词： 3D Reconstruction Augmented reality Image Segment Objection detection

来源：评论

学校读者我要写书评

暂无评论

Application of Laplacian Teaching Learing Algorithm for contrained and unconstrained optimization problems 2

Application of Laplacian Teaching Learing Algorithm for cont...

引用

2nd IEEE International Conference on Measurement, Instrumentation, Control and Automation, ICMICA 2023

作者： Khurana, Rachna Singla, Shakuntla Garg, Vanita Mangla, Diksha Kumar, Sushil Pathak, Maheshwar Joshi, Pratibha P.I.E.T Department of Applied Sciences and Humanities Panipat India Mullana Department of Mathematics and Humanities Mullana India Amity University Noida Amity Institute of Applied Mathematics Noida India Nit Kurukshetra Department of Computer Engineering Haryana Kurukshetra India Sharda University Department of Mathematics Greater Noida India

ISBN: (纸本)9798350355048

Teaching Learning Based Optimization Algorithm, nature inspired optimization technique based on presence of constraints, TLBO can be used and adapted to solve constrained and unconstrained optimization problems. A brief introduction of using TLBO is illustrated through two different optimization problems. The complexity and the mathematical formulation of both the problems is given and the results are also provided using BBO and the comparative result is shown. © 2024 IEEE.

关键词： Optimization algorithms

来源：评论

学校读者我要写书评

暂无评论

A Review on the Role of Artificial Intelligence in Tourism 10

A Review on the Role of Artificial Intelligence in Tourism

引用

17th INDIACom;2023 10th International Conference on Computing for Sustainable Global Development, INDIACom 2023

作者： Dangwal, Aarti Kukreti, Mohit Angurala, Mohit Sarangal, Ruhi Mehta, Mankaj Chauhan, Prashant Chitkara Business School Chitkara University Punjab India University of Technology and Applied Sciences Cas Ibri Department of Business Administration Oman School of Computer Sc. and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9789380544472

The purpose of this study is to explore the role of Artificial Intelligence (AI) in enhancing customer service in the tourist industry by leveraging the synergy between AI and human emotions and cognition. A systematic review of the relevant literature was conducted to identify the existing research on AI in the service sector. The major findings suggest that AI can significantly improve the speed, creativity, and knowledge of service, leading to enhanced customer satisfaction. Additionally, the study highlights the increasing use of new AI technologies and techniques in the tourist trade. The interpretation of the findings suggests that the use of AI in the tourist industry is no longer limited to virtual interactions but extends to physical interactions as well. The study also emphasizes the importance of connectivity in the hospitality and tourist industry and highlights the need for further research and forecasting in this area. The implications of the study are that companies in the tourist industry need to focus on enhancing their customer service by leveraging the benefits of AI. They also need to adopt new AI technologies and techniques to stay ahead of the competition. Overall, the study provides a comprehensive understanding of the current state of AI in the service sector and its potential for improving customer service in the tourist industry. © 2023 Bharati Vidyapeeth, New Delhi.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Inception V3 Based Approach for the Recognition of Age-related macular degeneration Disease

Inception V3 Based Approach for the Recognition of Age-relat...

引用

2023 International Conference on Science, Engineering and Business for Sustainable Development Goals, SEB-SDG 2023

作者： Ogundokun, Roseline Oluwaseun Abdulahi, AbdulRahman Tosho Adenike, Ajiboye Raimot Babatunde, Akinbowale Nathaniel Babatunde, Ronke Seyi Landmark University Department of Computer Science Omu Aran Nigeria Kaunas University of Technology Department of Multimedia Engineering Nigeria Sdg 11. Sustainable Cities and Communities Landmark University Omu Aran Nigeria Institute of Information and Communication Technology Kwara State Polytechnic Department of Computer Science Nigeria Institute of Applied Sciences Kwara State Polytechnic Department of Statistics Nigeria Kwara State University Department of Computer Science Malete Nigeria

ISBN: (纸本)9798350324785

Millions of people around the world are infected with age-related macular degeneration (AMD) disease. It is not easily detected in the intermediate stage, as it is typically asymptomatic. Moreover, the ideal learning trends for AMD professional advice are identifying those who are at this stage of the condition, instructing them on ways to screen the early diagnosis of the choroidal neovascular level before significant vision loss is incurred, and encouraging them to think about taking nutritional supplements that may lessen the likelihood that the condition will extend from the intermediate to the mature phase. However, conventional identification of this disease can be time-intensive and necessitates knowledgeably competent individuals to carry out the task. Since retinal fundus images have proven beneficial in detecting AMD, automated methods for AMD detection from retina fundus images can be developed by applying a novel application of deep transfer learning (DTL) to leverage on the artificial intelligence advances. In this investigation, deep convolutional neural networks (DCNN) specifically trained for automated AMD evaluation were contrasted with deep transfer learning (DTL), a different deep learning (DL) technique that included common characteristics with a diagnostic grader. In order to differentiate between the age-related macular degeneration (AMD) stage and the Normal stage, automated identification was used on a 2-class classification issue. The study proposed using deep learning (DL) models, and compared them to the DTL model. The proposed DTL model with transfer learning approach yielded an accuracy of96.41%, area under receiver operator characteristics curve (AUC) of 0.9633, precision of 94.24%, specificity of 94.82% and false positive rate (FPR) of 0.0518 on the test dataset, which specified a considerable agreement with the gold standard Age-related Eye Disease investigation data set. Implementing an automatic DTL-founded AMD evaluation from fundu

关键词： Statistical tests

来源：评论

学校读者我要写书评

暂无评论

PROTOTYPE CONTRASTIVE CONSISTENCY LEARNING FOR SEMI-SUPERVISED MEDICAL IMAGE SEGMENTATION

arXiv

引用

arXiv 2025年

作者： He, Shihuan Lai, Zhihui Wang, Ruxin Kong, Heng Shenzhen Institutes of Advanced Technology Chinese Academy of Sciences China Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University China Department of Breast and Thyroid Surgery Baoan Central Hospital of Shenzhen China

Medical image segmentation is a crucial task in medical image analysis, but it can be very challenging especially when there are less labeled data but with large unlabeled data. Contrastive learning has proven to be effective for medical image segmentation in semi-supervised learning by constructing contrastive samples from partial pixels. However, although previous contrastive learning methods can mine semantic information from partial pixels within images, they ignore the whole context information of unlabeled images, which is very important to precise segmentation. In order to solve this problem, we propose a novel prototype contrastive learning method called Prototype Contrastive Consistency Segmentation (PCCS) for semi-supervised medical image segmentation. The core idea is to enforce the prototypes of the same semantic class to be closer and push the prototypes in different semantic classes far away from each other. Specifically, we construct a signed distance map and an uncertainty map from unlabeled images. The signed distance map is used to construct prototypes for contrastive learning, and then we estimate the prototype uncertainty from the uncertainty map as tradeoff among prototypes. In order to obtain better prototypes, based on the student-teacher architecture, a new mechanism named prototype updating prototype is designed to assist in updating the prototypes for contrastive learning. In addition, we propose an uncertainty-consistency loss to mine more reliable information from unlabeled data. Extensive experiments on medical image segmentation demonstrate that PCCS achieves better segmentation performance than the state-of-the-art methods. The code is available at https://***/comphsh/PCCS. © 2025, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Addressing the Rising Challenge of Malware Innovative Detection and Mitigation Techniques

Addressing the Rising Challenge of Malware Innovative Detect...

引用

2024 International Conference on Communication, computer sciences and Engineering, IC3SE 2024

作者： Balaram, A. Umashankari, E. Dutt, Amit Bharadwaj, Garima Revathi, V. Albawi, Ali Mlr Institute Of Technology Department Of Computer Science And Engineering Telangana Hyderabad India Institute Of Aeronautical Engineering Department Of Computer Science And Engineering Telangana Hyderabad India Lovely Professional University Phagwara India Amity Business School Amity University Greater Noida India New Horizon College Of Engineering Department Of Applied Sciences Bangalore India College Of Medical Technology The Islamic University Radiology Techniques Department Najaf Iraq

ISBN: (纸本)9798350366846

This research talks about Hybrid Anomaly Detection (HAD), a complex technology for finding and stopping malware. There are four different methods to apply the approach. The following are a few examples: EDR, DBA, TIS, and EML. The goal of the ablation specialists is to enhance the HAD structure in whatever way possible. With a success rate of 99.5% and only one false positive, DBA starts monitoring the process the second it starts. EML makes the system more flexible and useful by finding malware using probability estimates and weighted voting. TIS protects against new threats and motivates people to work together by sharing and prioritizing threat information. EDR is all about computer security by evaluating and reducing risks. The ablation study focuses on how well each algorithm can identify things, how flexible it is, how well it can work with others, and how safe it keeps endpoints safe. Since these algorithms work well together, the HAD framework offers a complete answer that performs better than other approaches in many ways. This study suggests a good way for everyone to work together to fight modern computer risks, which will improve cybersecurity. © 2024 IEEE.

关键词： Malware

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：