检索结果-内蒙古大学图书馆

Sentiment Analysis and Deep Learning (ICSADL), International Conference on

作者： Ashin Ajay Naveen Kumar Ashok Gokul balajiram Abinesh Tamizhselvan Senthil Kumar Thangavel Somasundaram K M. Tech in Artificial Intelligence Amrita Vishwa Vidyapeetham Coimbatore India B. Tech in Computer Science and Engineering Amrita Vishwa Vidyapeetham Coimbatore India Department of Computer Science and Engineering Amrita School of Computing Coimbatore Amrita Vishwa Vidyapeetham Coimbatore India Department of Mathematics School of Physical Sciences Coimbatore Amrita Vishwa Vidyapeetham India

ISBN: (数字)9798331523923

ISBN: (纸本)9798331523930

Effective driver behavior monitoring is necessary due to the increase in traffic accidents caused by distracted driving. In order to identify distractions such as talking, drinking, napping, and using a phone, this research suggests a CNN-based methodology. The model uses facial characteristics such as eyes to detect and analyze these activities. Thousands of photos depicting various distracted driving postures are used to train it on a publicly accessible dataset. The strategy seeks to improve road safety by offering a reliable way to identify distractions.

关键词： Deep learning Sentiment analysis Transfer learning Road safety Real-time systems Reliability Convolutional neural networks Driver behavior Monitoring Vehicles

来源：评论

学校读者我要写书评

暂无评论

Method of Text Summarization Using Lsa and Sentence based Topic Modelling with bert

Method of Text Summarization Using Lsa and Sentence Based To...

引用

2021 International Conference on Artificial Intelligence and Smart Systems, ICAIS 2021

作者： Gupta, Hritvik Patel, Mayank Geetanjali Institute of Technical Studies 5th Sem B. Tech Computer Science and Engineering Udaipur Rajasthan India

ISBN: (纸本)9781728195377

Document summarization is one such task of the natural language processing which deals with the long textual data to make its concise and fluent summaries that contains all of document relevant information. The branch of NLP that deals with it, is automatic text summarizer. Automatic text summarizer does the task of converting the long textual document into short fluent summaries. There are generally two ways of summarizing text using automatic text summarizer, first is using extractive text summarizer and another abstractive text summarizer. This paper has demonstrated an experiment in contrast with the extractive text summarizer for summarizing the text. On the other hand topic modelling is a NLP task that extracts the relevant topic from the textual document. One such method is Latent semantic Analysis (LSA) using truncated SVD which extracts all the relevant topics from the text. This paper has demonstrated the experiment in which the proposed research work will be summarizing the long textual document using LSA topic modelling along with TFIDF keyword extractor for each sentence in a text document and also using bERT encoder model for encoding the sentences from textual document in order to retrieve the positional embedding of topics word vectors. The algorithm proposed algorithm in this paper is able to achieve the score greater than that of text summarization using Latent Dirichlet Allocation (LDA) topic modelling. © 2021 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Optimum Charging Scheduling of an EV PL Owning Smart Reservation System 11

Optimum Charging Scheduling of an EV PL Owning Smart Reserva...

引用

11th International Conference on Power Science and engineering, ICPSE 2022

作者： Gokcek, Tayfur Guner, Sitki Sadreddini, Jale Erdinc, Ozan Yildiz Tech. University Electrical Engineering Istanbul Turkey Eskişehir Tech. University Electrical-Electronics Eng Eskişehir Turkey Ericsson Research Er Networks Istanbul34469 Turkey Carleton University Department of Systems and Computer Engineering OttawaONK1S 5B6 Canada

ISBN: (数字)9781665451291

ISBN: (纸本)9781665451291

With increasing the penetration rate of electric vehicle (EV) usage, the challenge of finding an available parking slot has been turned into finding an available parking slot having EV charger in metropolitans. Smart charging reservation systems considering EV drivers' preferences can facilitate finding an available charging station as well as managing the charging load of EVs in a parking lot. In this study, a bi-level optimization model is defined for minimizing the parking price of EV users, maximizing the profit of EV parking lot (PL) operator and the last one minimizing total power losses of the distribution network. A smart charging reservation system is used to select the EVs which are accepted for giving charging service considering several parameters. This reservation system was generated using Analytical Hierarchy Process (AHP) from Multi-Criteria Decision Making (MCDM) techniques. A PV system on the roof the PL is modelled to support the charging load of EVs at the PL. A mixed-integer linear programming model is established for solving the generated optimization problem. © 2022 IEEE.

关键词： Electric vehicles

来源：评论

学校读者我要写书评

暂无评论

Cryptocurrency PricePrediction using LSTM

Cryptocurrency PricePrediction using LSTM

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Swaraj Deo Gaurav Kumar Swayam Soni Gurmeet Singh B.Tech III Year School of Computing Science and Engineering Galgotias University Greater Noida India School of Computer Science and Engineering Galgotias University Greater Noida India

This paper focuses on utilizing the Long Short-Term Memory (LSTM) algorithm to forecast the prices of cryptocurrencies. that is implemented through the model, which will allow us to keep tabs on the fluctuating prices of the various coins that are available. As various cryptocurrencies are available for trading and investment and they are regarded as a type of digital asset. because trading and investing should be done after the knowledge of the market and trends, So, to solve this problem there should be analysis before trading any pair. Our goal is to present accurate prediction based on the dataset of the selected cryptocurrency. Hence, the proposed model is built and it concentrate mostly on technical analysis of the crypto coins which is the major indicator and most suitable for the prediction models. The proposed LSTM model achieves a variance regression score of 0.95 on test data of the bitcoin which serves as a representative cryptocurrency that is used in the model.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Novel Study on Data Science for Data Security and Data Integrity with Enhanced Heuristic Scheduling in Cloud 2

A Novel Study on Data Science for Data Security and Data Int...

引用

2nd International Conference on Automation, Computing and Renewable Systems, ICACRS 2023

作者： Polireddi, Naga Simhadri Apparao Suryadevara, Manoj Venkata, Srinivas Rangineni, Sandeep Koduru, Surendra Kumar Reddy Agal, Sanjay IKON Tech Services LLC PhoenixAZ United States Walmart BentonvilleAR United States Teradata HoustonTX United States Pluto TV West HollywoodCA United States Information Technology Biopharmaceutical Industry United States Computer Engineering Dr. V. R. Godhania College of Engineering and Technology B/h Gujarat India

ISBN: (纸本)9798350340235

Recently, "cloud computing" has become an attractive paradigm for the administration and provisioning of internet-based services. This paradigm is known as "cloud computing." The promise of this being a reality has been around for a while, but cloud computing has risen to meet the shifting conditions of the IT industry. In this article, we introduce the trust model, the suffrage heuristic, the Heterogeneous Earliest Finish Time (HEFT) scheduling algorithm, and the trust value computation. The trust model has parameters that vary with values of sub parameters and the tasks they perform. These functions are regarded as a standard of durability and cannot be broken. The assumption that better mappings can be made by allocating a resource or machine whose expected time of completion will suffer if that machine is not allocated is the foundation around which a suffrage heuristic will be built. Due to its great performance and stability across a variety of graph topologies, the HEFT technique is a promising solution for the Directed Acyclic Graph (DAG) and associated scheduling problem on the heterogeneous systems. The average schedule length is longer in the suffrage without trust scenario compared to the HEFT without trust, suffrage with trust, and the HEFT with trust scenarios. It is possible that there is no algorithm that, given a scheduling problem, can produce a best solution in polynomial time. Utilising random variables to find solutions to scheduling issues calls for the application of a stochastic approach as well. In addition to swarm algorithms and evolutionary algorithms, these strategies made use of Simulated Annealing (SA). The initial goal of the effort was to use a GA, and then the Firefly Algorithm (FA), to optimise the cost and performance of workflow scheduling. Algorithms like the HEFT and the GA have been proposed in this work. For applications utilising a finite set of heterogeneous processors, this HEFT serves as the underlying algorithm. We can u

关键词： Cloud computing Directed Acyclic Graph (DAG) Genetic Algorithm Heterogeneous Earliest Finish Time (HEFT)

来源：评论

学校读者我要写书评

暂无评论

Judging the Psychological Impact of News Articles on Rehab Patients: A Deep Learning Approach

Judging the Psychological Impact of News Articles on Rehab P...

引用

Communication, Computing and Signal Processing (IICCCS), IEEE International Conference on

作者： Amit Khan Dipankar Majumdar bikromadittya Mondal Dept. of Information Technology RCC Institute of Information Technology Kolkata India Dept. of Computer Sc & Engineering RCC Institute of Information Technology Kolkata India Dept. of Computer Sc & Engineering B.P. Poddar Institute of Mgmt & Tech. Kolkata India

ISBN: (数字)9798350390759

ISBN: (纸本)9798350390766

Sentiment detection and analysis from review comments of products, blogs and other social media communication is a common practice. Lot of research work have been proposed and established in the domain. While the above may prove to be effective for sales and marketing challenges but the same effort for the sentiment analysis of news articles is scarce. but surprisingly, this can definitely establish as a potentially efficient instrument for medical domain judging the suitability of a news article for individuals with disturbed health condition like depression, heart diseases or mental retardation having risk of committing suicides. To address the same, this article presents a novel approach harnessing the potential of Machine Learning (ML) and Deep Learning (DL) to detect the sentiment of a news article so as to measure its impact on the individual readers. The proposed work uses various supervised ML algorithms such as SVM, Naïve bayes’, Logistic Regression, Random Forest and Ensemble Method for assessing the inherent sentiment of news articles. Additionally, DL based Transformer model specifically bERT has also been employed to enhance the performance. Obtained results with various performance metrics clearly depict our model’s excellent performance.

关键词： Deep learning Support vector machines Sentiment analysis Social networking (online) Reviews Computational modeling Signal processing algorithms Signal processing Transformers Telecommunication computing

来源：评论

学校读者我要写书评

暂无评论

Empowering Safety: Designing of an IoT based Women Protective System using Artificial Intelligence enabled Smart Sensors

Empowering Safety: Designing of an IoT based Women Protectiv...

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： R. Sonia T Rubesh Kumar G. Naresh S. Durga Devi N Juliet Department of Computer Applications B S Abdur Rahman Crescent Institute of Science and Technology Vandalur Chennai Department of Biomedical Engineering Rajalakshmi Engineering College Chennai Department of ECE Mohan Babu University (Erstwhile SreeVidyanikethan Engineering College) Tirupati Andhra Pradesh Department of CSE Vel Tech High Tech Dr. Rangarajan Dr. Sakunthala Engineering College Avadi Chennai Department of Master of Computer Applications S.A. Engineering College Chennai

ISBN: (数字)9798350389449

ISBN: (纸本)9798350389456

Worldwide, women endure a great deal of unethical forms of domestic violence. The lack of an efficient tracking mechanism is speeding this up. An AI-based system that provides protection to vulnerable women was the subject of this research. In critical situations, this framework can respond appropriately automatically and manually. No place is secured for women, but they are more at risk when venturing out on their own into remote areas and unfamiliar roads. After recognizing danger, current women’s handheld safety gadgets require human involvement to activate (e.g., pushing a button or shaking the device). We provide an approach that aims to provide women with false proof safety while also attempting to address the shortcomings of current systems. This system showcases an Arduino-powered wearable safety gadget designed specifically for women. This gadget is designed to protect ladies from harm in case they encounter any risk. The gadget is able to converse and deliver alerts using a wireless sensor network. The user’s precise whereabouts can be sent to designated authorities and stored contacts through the use of GPS and GSM. In the event of an emergency, the device’s switch can be used as a panic button to get a shock; when pressed, the buzzer and laser diode will both activate. This research presents a novel approach to women’s safety, the IoT Powered Women Protection (IoTPWP), and evaluates its efficacy by cross-validating it with the usual model, the bluetooth enabled Women Safety System (bWSS). We also believe that shows with built-in cameras that record electric shock and broadcasting real-time footage can have an effect on women’s lives through the medium of digital technology.

关键词： Wireless sensor networks technological innovation Electric shock Pressing Switches Watches Real-time systems

来源：评论

学校读者我要写书评

暂无评论

Enhancing Human-Robot Collaboration through 5G-Enabled Transformation and Image-Guided Control with TYOLOV5 Algorithms 7

Enhancing Human-Robot Collaboration through 5G-Enabled Trans...

引用

7th International Conference on Image Information Processing, ICIIP 2023

作者： Madasamy, Sridhar Ramesh, P.S. Roy, Priyanka Arun Raj, S.R. Yadav, Vinay Kumar balaram, Allam Cognizant Technology Solution 500 Frank W. Burr Boulevard TeaneckNJ07666 United States Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science And Technology Department of Computer Science And Engineering Tamilnadu Chennai India Vellore Institute of Technology Department of Electrical And Electronics Engineering Tamilnadu Vellore India U.B.D.T College of Engineering Department of Electronics & Communication Engineering Karnataka Davanagere577004 India Glocal University Glocal School of Science And Technology Uttar Pradesh India Mlr Institute of Technology Department of Computer Science And Engineering Hyderabad500043 India

ISBN: (纸本)9798350371406

Factories that prioritize digital transformation experience heightened production rates and gain a competitive advantage by enhancing control and operational efficiency. In this study, image processing techniques were employed to achieve digital transformation objectives, and the data obtained was transmitted via 5G communication to a collaborative robot arm, enabling remote control. The robot arm was fitted with a 3D-printed humanoid hand for bin picking, where each finger was controlled by five servo motors. To manipulate the fingers, a user donned a glove equipped with flex sensors, which conveyed the finger positions to the servo motors, facilitating precise pick and place operations. Additionally, image processing was utilized to accurately control the robot arm's position. The research involved the implementation of tuned YOLO V5 (TYOLOV5) algorithms, using Python software, for object detection within the user's gloves. by comparing this approach with other existing methods, the experiment achieved the highest detection accuracy, demonstrating the effectiveness of the proposed approach in achieving superior recognition and estimation compared to traditional and existing deep learning methods. To validate its efficacy, experiments were conducted in a laboratory setting, where a collaborative robot was deployed for a small part assembly task. The results conclusively highlight the potential of this approach to significantly enhance recognition and estimation capabilities, especially in the realm of human-robot collaboration. © 2023 IEEE.

关键词： Image enhancement

来源：评论

学校读者我要写书评

暂无评论

Cyber Security Challenges and Effective Security Measures for IOT-based Intelligent Healthcare Systems

引用

Recent Advances in Electrical and Electronic engineering 2025年第6期18卷 735-747页

作者： Somnathe, Abhijit T. Gopinath, N. Deena, G. Anandh, R. Kumar, Santosh Tiwari, Kanchan S. Electronics and Telecommunication Smt Kashibai Navale College of Engineering Savitribai Phule Pune University Pune India Computer Science and Engineering B.S. Abdur Rahman Crescent Institute of Science and Technology Chennai India Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai India Electrical and Electronics Engineering Gaya College of Engineering Bihar India Electronics and Telecommunication Modern Education Society’s Wadia College of Engineering Pune India

Aims and background: In order to keep up with the rapid development of technology, cities must enhance their offerings in the areas of public security, medical care, transportation, and citizen well-being. Healthcare systems rely heavily on patient care. Patients' life and the services offered by doctors, nurses, clinicians, pharmaceutical companies, and governments stand to benefit from the implementation of Healthcare IoT. There has been a change in the medical industry, marked by the widespread adoption of wireless healthcare-monitoring-systems (HMS) in hospitals. Methodology: However, the Internet-of-Things (IoT) concept frequently ignores security-privacy for linked things. Security and privacy protections must be implemented systematically throughout the entire healthcare and remote health monitoring system, from the creation of equipment to their interconnection, communication, storage, and eventual destruction. This research investigates the risks associated with using smart health devices and provides recommendations for addressing those risks. The present security and privacy of IoT devices in healthcare systems, as well as the difficulties in adopting security frameworks, are discussed, and recommendations for addressing these issues are offered. Results: This study also contributes in two ways to the ongoing effort to investigate securityprivacy concerns in the circumstance of smart cities for healthcare purposes. Conclusion: Moreover, this article provides a summary of the many Internet of Things applications and the cyber threats they face. On the other hand, thorough assessments of methods to reduce cyber threats to 60% are presented. © 2025 bentham Science Publishers.

关键词： Cyber attacks

来源：评论

学校读者我要写书评

暂无评论

Weather and Climate Forecasting System for Cultivation using Naive's Algorithm 2

Weather and Climate Forecasting System for Cultivation using...

引用

2nd International Conference on Computing and Information technology, ICCIT 2022

作者： Sheela, M. Sahaya banu, S. Shahar Rajendran, T. Raj, S. Saran Sreeja, b.P. Pavai College of Technology Department of Electronics and Communication Engineering Pachal Namakkal India B S Abdur Rahman Crescent Institute of Science and Technology Department of Computer Applications Vandalur Chennai India Tamilnadu Coimbatore India Vel Tech Rangarajan Dr. Sagunthala Rd Institute of Science and Technology Department of Computer Science and Engineering Chennai India Karpagam College of Engineering Department of Information Technology Coimbatore India

ISBN: (纸本)9781665436052

Agriculture based advisory services and climatic information are more considerable in providing assistance for pastoralists and small farmers to manage climatic changes and risks factors to be adopted during changes. Moreover, there is some gap in providing climatic information that significantly addresses the requirement of pastoralists and farmers. Huge farmers rely over indigenous knowledge where experiences and indicators are utilized to forecast and observe weather conditions. When this prediction is inbuilt and implemented by many farmers, documentations, coordinators and so on for predicting weather, it should be accurate and reliable manner. This work concentrates on building a weather predictor system for farmers to identify the velocity flow that is needed during farming. This model includes Naives equation for performing this velocity prediction. The outcomes demonstrate that pastoralists and farmers utilize combination of biological and meteorological indications to predict weather conditions. Henceforth, it seems to be more crucial in providing assistance to enhance access to climatic information in various regions of India in vulnerable and poor resource communities. © 2022 IEEE.

关键词： Cultivation

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：