检索结果-内蒙古大学图书馆

3rd International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2023

作者： Indumathi, N. Divyalakshmi, R.J. Stalin, J. Ramachandran, V. Rajaram, P. Srm Institute of Science and Technology Computer Science and Applications Chennai India Sethu Institute of Technology Computer Science and Business Systems Virudhunagar India Computer Science and Engineering Gitam School of Computing Bengaluru India

ISBN: (纸本)9798350399264

Implemented Image captioning is becoming a need. Deep neural network models enable integrated applications to generate and caption images. Image captioning describes an image. It requires identifying an image's main objects, properties, and relationships. It produces correct sentences. The creation of image caption generators, which examine the content of an image and offer pertinent descriptions, makes use of deep learning and computer vision techniques. One element of this method involves classifying objects in the image using English keywords derived from training datasets. The caption generator was created by combining LSTM and CNN. In this paper, we propose a deep-learning model that uses computer vision and machine translation to characterize images and generate captions. The model successfully recognizes and labels visual items and their relationships. Transfer Learning will be used to demonstrate the suggested experiment, coupled with the Flickr8k dataset and the Python3 programming language. This study will also look into the functions and construction of neural networks. The proposed model achieves a BELU Score of 69.8. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Analysis of Various Hyperparameters for Predicting Hypertension using Machine Learning Algorithms 8

Analysis of Various Hyperparameters for Predicting Hypertens...

引用

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

作者： Duggal, Shallu Sood, Shivani Singh, Amanpreet Singh, Harjeet Malarvel, Muthukumaran Lovely Professional University School of Computer Applications Phagwara144411 India Chitkara Institute of Engineering and Technology Chitkara University Punjab 140401 India Department of Computer Science and Engineering India

ISBN: (纸本)9798350367904

Predicting hypertension, or high blood pressure, is crucial because it's a risky condition that frequently doesn't exhibit any obvious symptoms or indicators until major problems arise. By using predictive models for early identification, the risk of uncontrolled hypertension-related cardiovascular events, strokes, and organ damage can be decreased to take quick action. The study aims to predict the diagnosis of hypertension using three machine learning techniques: Logistic Regression, Gaussian Naive Bayes, and Support Vector Machine(SVM). With the focus on improving accuracy and reliability, the various hyperparameters of each individual algorithm are tuned using the cross validation and grid search approaches. After extensive testing and parameter modification, the SVM algorithm was found to be the most accurate predictor, which achieved a significant accuracy of 9 7. 0 0 %. The best hyper-parameters achieved for SVM are c value 4 and kernel as 'rbf'. The models' performance is evaluated using accuracy, specificity, sensitivity, F1-score, or AUC (Area Under the Curve). This study facilitates proactive healthcare measures by offering insightful information to determine the best algorithms for the early prediction of hypertension. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Fake News Detection Review: Concepts, Tools, Research gaps, and Possible solutions 7

Fake News Detection Review: Concepts, Tools, Research gaps, ...

引用

7th International Conference on Internet applications, Protocols, and Services, NETAPPS 2024

作者： Yakkundi, Sapana Patil, Rudragoud Goudar, Swetha Indudhar Department of Computer Science and Engineering KLS Gogte Institute of Technology Karnataka Belagavi India Department. of Master of Computer Applications KLS Gogte Institute of Technology Karnataka Belagavi India

ISBN: (纸本)9798331519513

The increasing number of social platforms means that there is a rapid expansion of online data. However, not all of this data can be trusted, as some users intentionally manipulate information to spread false news for personal or political reasons. Fake news can significantly impact public perception and societal outcomes. Its widespread influence was especially noticeable during the 2016 United States election cycle, leading to heated discussions about its role and consequences. Given the changing nature of news, real-time data processing has become essential for effectively identifying and countering misinformation. This research provides a comprehensive examination of the datasets, tools, and techniques utilized for detecting and combating fake news. Many researchers have developed models based on specific datasets, limiting their scope to particular domains. A thorough review of advanced models for real-time fake news detection highlights existing research gaps. The analysis of the review reveals that numerous datasets used in the literature are outdated, and there is a methodological challenge associated with the use of traditional machine learning approaches. With the continuous evolution of news, there is an urgent demand for utilizing sophisticated deep learning models for the automated, real-time verification of misinformation. This research presents promising approaches to tackle the challenge of detecting fake news. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

The Prediction of Diabetes Using Machine Learning in the Healthcare System 5th

The Prediction of Diabetes Using Machine Learning in the Hea...

引用

5th International Conference on Trends in Computational and Cognitive engineering, TCCE 2023

作者： Deep, Ishaan Singh, Payaswini Senapati, Biswa Ranjan Swain, Rakesh Ranjan Nayak, Subrat Kumar Patra, Binaya Kumar University Odisha Bhubaneswar751030 India Department of Computer Science Engineering and Applications Indira Gandhi Institute of Technology Sarang Dhenkanal India

ISBN: (纸本)9789819719228

Diabetes has been increasing at an exponential rate in India in recent years, and it is expected to reach 537 million by 2030. Diabetes will also cause a large rise in a variety of other health issues. Many machine learning techniques are being employed to solve the problem of diabetes prediction. In this paper, the authors have considered two machine learning techniques, such as support vector machine (SVM) and logistic regression (LR) for diabetes prediction. The SVM accuracy was found to be 87% when eight independent parameters were used to predict it, whereas the logistic regression accuracy was 87.01%. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

IoT-Aided Charity-Redistribution of Excess Food 2

IoT-Aided Charity-Redistribution of Excess Food

引用

2nd International Conference on Emerging Trends in Information Technology and engineering, ic-ETITE 2024

作者： Yogananth, V.S. Balasubramani, M. Vellore Institute of Technology Department of Computer Applications Tamil Nadu Vellore India School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798350328202

The utilization of the Internet of Things (IOT) has shown significant potential in various aspects of daily life, yet its application in addressing social issues remains underdeveloped. India, with a substantial number of orphanages, faces challenges in efficiently distributing crucial information, hindering donors from obtaining accurate data on food reserves. This project proposes an IOT-based system to tackle this issue, using Node MCU IOT devices connected to sensors that relay data through a network, accessible and monitorable via web applications. The proposed system architecture aims to bridge the gap between those who waste food and those in poverty who desperately need it. We intend to facilitate food donations by implementing smart containers equipped with IOT technology. These containers can detect excess food waste and share this information via a GSM module with trusted charitable organizations. This application is designed to serve three main stakeholders: service providers, donors, and food recipients in need. By creating smart containers, we ensure that donated food reaches the right individuals. We prioritize collaborating with trusted charities to oversee the distribution process. Only authorized charity members can access and distribute the food stored in these containers, ensuring that it reaches those who need it most. © 2024 IEEE.

关键词： Containers

来源：评论

学校读者我要写书评

暂无评论

Inspired Detection Model For Clustering Based Surveillance System: A Non-Conventional Review

Inspired Detection Model For Clustering Based Surveillance S...

引用

2024 IEEE International Conference on Automation and Computation, AUTOCOM 2024

作者： Gupta, Anil Kumar Sharma, Rupak Ojha, Rudra Pratap Srm Institute of Science and Technology Department of Computer Science and Engineering NCR Campus Ghaziabad Uttar Pradesh Modinagar India Srm Institute of Science and Technology Department of Computer Applications NCR Campus Ghaziabad Uttar Pradesh Modinagar India Department of Computer Science and Engineering Uttar Pradesh Greater Noida India

ISBN: (纸本)9798350382723

in current years, there has been a growing hobby in growing superior surveillance systems for detecting and monitoring anomalous activities. Traditional surveillance systems depend upon handmade policies and features, which are frequently limited of their capacity to accurately become aware of complex anomalies. To conquer this problem, we suggest a better visible anomaly detection version for clustering-based surveillance structures the use of long brief-time period reminiscence (LSTM) Diffusion manner. The proposed version incorporates the temporal context of the CCTV photos with the aid of making use of the LSTM network, which has been proven to deal with sequential data effectively. The LSTM community is used to extract movement features from the video frames, which are then fed into the clustering set of rules. This allows for the identification of comparable styles of sports and grouping them into clusters. Furthermore, we combine the concept of the Diffusion technique into the LSTM version to decorate the clustering method. The Diffusion procedure entails the gradual propagation of information among nodes in a network, which is particularly beneficial in figuring out abrupt changes in activities. This permits the version to locate anomalies with better accuracy and decrease fake alarms. To assess the performance of our proposed version, we behavior experiments on a real-global surveillance dataset. The consequences display that our model outperforms current techniques in terms of accuracy and detection price. © 2024 IEEE.

关键词： Diffusion

来源：评论

学校读者我要写书评

暂无评论

Design of a Lightweight Compressed Video Stream-Based Patient Activity Monitoring System

引用

computers, Materials & Continua 2024年第1期78卷 1253-1274页

作者： Sangeeta Yadav Preeti Gulia Nasib Singh Gill Piyush Kumar Shukla Arfat Ahmad Khan Sultan Alharby Ahmed Alhussen Mohd Anul Haq Department of Computer Science&Applications Maharshi Dayanand UniversityRohtak124001India University Institute of Technology Rajiv Gandhi Proudyogiki VishwavidyalayaBhopal462033India Department of Computer Science College of ComputingKhon Kaen UniversityKhon Kaen40002Thailand Department of Computer Science College of Computer and Information SciencesMajmaah UniversityAl Majmaah11952Kingdom of Saudi Arabia Department of Computer Engineering College of Computer and Information SciencesMajmaah UniversityAl Majmaah11952Kingdom of Saudi Arabia

Inpatient falls from beds in hospitals are a common *** falls may result in severe *** problem can be addressed by continuous monitoring of patients using *** advancements in deep learning-based video analytics have made this task of fall detection more effective and *** with fall detection,monitoring of different activities of the patients is also of significant concern to assess the improvement in their *** computation-intensive models are required to monitor every action of the patient *** requirement limits the applicability of such ***,to keep the model lightweight,the already designed fall detection networks can be extended to monitor the general activities of the patients along with the fall *** by the same notion,we propose a novel,lightweight,and efficient patient activity monitoring system that broadly classifies the patients’activities into fall,activity,and rest classes based on their *** whole network comprises three sub-networks,namely a Convolutional Neural Networks(CNN)based video compression network,a Lightweight Pose Network(LPN)and a Residual Network(ResNet)Mixer block-based activity recognition *** compression network compresses the video streams using deep learning networks for efficient storage and retrieval;after that,LPN estimates human ***,the activity recognition network classifies the patients’activities based on their *** proposed system shows an overall accuracy of approx.99.7% over a standard dataset with 99.63% fall detection accuracy and efficiently monitors different events,which may help monitor the falls and improve the inpatients’health.

关键词： Fall detection activity recognition human pose estimation accuracy

来源：评论

学校读者我要写书评

暂无评论

mHAR: a novel convolutional recurrent model for recognizing motion-based human activity 12

mHAR: a novel convolutional recurrent model for recognizing ...

引用

12th International Young Scientists Conference in Computational science, YSC 2023

作者： Kumar, Prabhat Suresh, S. Department of Computer Science Institute of Science Banaras Hindu University Varanasi221 005 India Department of Computer Engineering & Applications GLA University Mathura281406 India Department of Computer Applications National Institute of Technology Kurukshetra136119 India

With sensors built into smartphones and wearable devices, Human Activity Recognition (HAR) makes it possible to identify regular activities. One of the challenges is to access the motion information from activity data and extract the features from this information. A general model trained without motion features may perform poorly while recognizing the contextual patterns in human activities. In this paper, we proposed the mHAR (motion HAR) model for recognizing static, gradual, and dynamic motion activity to address this challenge. We examine the impact of the proposed model against the general non-convolutional and convolutional recurrent networks in terms of accuracy rates and F1 score. As an experimental dataset, the publicly accessible WISDM was employed. Additionally, the findings of the experiments demonstrate that, in contrast to the unbalanced class problem, motion features play a significant role in activity recognition by achieving accuracy rates of 92.29% and an average F1 score of 83.33%. © 2023 The Authors. Published by Elsevier B.V.

关键词： Smartphones

来源：评论

学校读者我要写书评

暂无评论

GIS and ML Integrated Techniques for Detection of Landslide-Prone Areas 2

GIS and ML Integrated Techniques for Detection of Landslide-...

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Sul, Astha Patil, Sanjay Vellore Institute of Technology School of Computer Science and Engineering Vellore India Maharashtra Remote Sensing Applications Centre Maharashtra Pune India

ISBN: (纸本)9798350368413

Landslides are a common natural disaster that can result in substantial casualties. One of the region's most vulnerable to landslides in India is Western Ghats. The risk casualty is reduced with the use of the landslide susceptibility map (LSM) and prediction of landslide points. The aim of this research is to explore and compare the 4 ML algorithms (K-Nearest Neighbor (KNN), Random Forest (RF), Support Vector Machine (SVM), and Logistic Regression (LR)) for generating the most promising LSM. This study focuses on 12 Landslide conditioning factors (LCFs) such as Elevation, Slope, Lithology, LULC, Distance to Road, Topographic Wetness Index (TWI), Stream Power Index (SPI), Topographic Roughness Index (TRI), Drainage Networks, NDVI, Rainfall, Sediment Transport Index (STI). It has been found that the slope of the ground, the distance to the road, and the annual rainfall all have a significant impact on the occurrence of landslides. The models made using different approaches have been analysed and compared using the following metrics: prediction accuracy, precision, recall, F1-score, and True Skill Statistics (TSS). Overall accuracy for LR, SVM, KNN, RF are 82.30, 84.00, 82.50, 87.20 respectively. The findings of the study show that there are more landslide-prone locations in Bhor, Velhe, Ambegaon, and Junnar in Pune District, Maharashtra. © 2024 IEEE.

关键词： Landslides

来源：评论

学校读者我要写书评

暂无评论

Utilizing Artificial Intelligence for Advance Data science and Analysis 2

Utilizing Artificial Intelligence for Advance Data Science a...

引用

2nd International Conference on Disruptive Technologies, ICDT 2024

作者： Sharma, Deepak Chaudhary, Gaurav Rajput, Kapil Singhal, Amit Sharma, Tarun Kumar Srm Institute of Science and Technology Department of Computer Applications UPModinagar Delhi India Ajay Kumar Garg Engineering College Department of Information Technology UP Ghaziabad India Graphic Era Hill University Computer Science & Engineering Uttarakhand Dehradun India Graphic Era Hill University Computer Science & Engineering UP Ghaziabad India Abes Engineering College Department of Computer Applications UP Ghaziabad India

ISBN: (纸本)9798350371055

Data technology has experienced an explosion in popularity and scope over the past few years, inflicting several companies to try to capitalize on the sizeable possibilities the technology has to provide. Agencies are utilizing AI to develop records science studies, allowing them to go beyond conventional strategies and discover new insights and innovations within the discipline. With AI, statistics scientists can identify styles in massive datasets, optimize algorithms to clear up complicated issues and create predictive fashions to discover developments and correlations. In addition, AI may be used to automate specific components of fact processing, making data technological know-how simpler and quicker. To make the most of this generation, organizations should have personnel knowledgeable in the basics of facts science and AI and the knowledge to recognize the complexities of the algorithms and applications they use. With the right group and the proper equipment, AI may make data technological know-how studies extra effective and more beneficial than ever. © 2024 IEEE.

关键词： Algorithms Correlations Fundamentals Technology Understand

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：