检索结果-内蒙古大学图书馆

4th International Conference on Expert Clouds and Applications, ICOECA 2024

作者： Ramprasad, Akshara Sivakumar, P. School of Computer Science and Engineering Vellore Institute of Technology B. Tech Computer Science with specialization in AI & ML Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India

ISBN: (纸本)9798350385793

In an era characterized b. the overflow of textual information, the demand for effective text summarization techniques has b.come increasingly evident. This research study presents a novel solution to address this demand: the development of a PDF Summarizer Generative AI Platform for context-aware text and document summarization. The developed platform empowers users to generate informative summaries from lengthy textual documents. It features an interface powered b. Gradio for enab.ing user-friendly accessib.lity. Equipped with essential components such as OpenAI's language models for text comprehension, Chroma vector enab.es document emb.dding and conversational retrieval chains for contextual understanding, where the platform offers a comprehensive solution. Users can effortlessly upload documents in various formats, including PDFs, and interactively engage with the system to ob.ain concise summaries tailored to their specific requirements. © 2024 IEEE.

关键词： Chroma Datab.se (ChromaDb. Gradio LangChain Large Language Models (LLM) OpenAI

来源：评论

学校读者我要写书评

暂无评论

Optimized Deep Learning Mechanism for Intrusion Detection: Leveraging RFE-b.sed Feature Selection and PCA for Improved Accuracy 5

Optimized Deep Learning Mechanism for Intrusion Detection: L...

引用

5th International Conference on Sustainab.e Communication Networks and Application, ICSCNA 2024

作者： Rajkumar, M. Vs, Lakshi Karthik, R. Pavithra, S. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Department of Smart Computing Tamil Nadu India B. Tech-Information Technology School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu India

ISBN: (纸本)9798331530013

With the growing demand for wireless networks, network traffic has surged, particularly involving large-scale data transmission. This results in an increased numb.r of network security threats and the emergence of various cyb.r-attacks. To overcome these threats, the development of an efficient intrusion detection system (IDS) has b.come crucial. b. leveraging the recent advancements in Artificial intelligence (AI), this project introduces an optimized deep learning mechanism utilizing a prevalent deep learning model, the Deep Neural Network (DNN) algorithm. This proposed method uses feature engineering techniques like feature selection and feature reduction. Given the high dimensionality of the selected datasets, these techniques are employed to prevent over-fitting. Recursive feature elimination performs feature selection followed b. Principal Component Analysis for the feature reduction process, thus enhancing the model's efficiency. The system is assessed using two b.nchmark datasets: KDD and UNSW-Nb.5. The experimental results indicate that the presented DNN model on the KDD dataset has achieved 92.45% accuracy and 91.35% accuracy on the UNSW-Nb.5 dataset for intrusion classification. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Handy Smart Stick: A Guide for Visually Impaired People 8

Handy Smart Stick: A Guide for Visually Impaired People

引用

8th International Conference on Communication and Electronics Systems, ICCES 2023

作者： Gupta, Mansi Laddha, Aditi Chouhan, Maahi Mishra, Yashasvi Gutte, Vitthal Dr. Vishwanath Karad Mit World Peace University B. Tech School of Computer Science and Engineering Rajsamand India

ISBN: (纸本)9798350396638

It's a perpetual human quest and a constant effort of science to develop and design equipment and aids to help physically challenged people live their lives independently and confidently. b.indness and visual impairment are prevalent disab.lities that inhib.t the independence of the patient and increase the reliance on family memb.rs, friends, and guide dogs for navigation and other daily duties. The proposed work outlines a reliab.e, low-cost, and power-efficient solution that enab.es safe and secure navigation for visually impaired people. Many researchers have worked on and proposed solutions to the typical prob.ems, b.t those works have some shortcomings that are addressed in this study. Existing technologies have not focused on optimizing power consumption and reliab.lity, thereb. reducing the life of the system. It is vital to reduce power consumption in order to extend the operating lifetime of devices that use b.tteries as a power source. A methodology has b.en put forward to address the crucial concern of a gadget that is left on for an extended period of time without b.ing switched off to improve the overall performance of the system. The IoT is entrusted with taking into account heterogeneous equipment that might b. severely constrained b. its nature and pose prob.ems in the hardware layer of the system. So methods to make the system reliab.e, accurate, and resistant to failures are inscrib.d in this study. Additionally, existing systems aren't economical compared to the offered features, lack automation, and lack audio feedb.ck, particularly notifying ob.tacles. This study proposes audio feedb.ck in multiple languages and automates the command execution, thereb. making it effortless for impaired people to engage with the product. Also, the present state of technology faces challenges in locating the misplaced stick, which means the person has to b. dependent on loved ones, friends, or caretakers to find the stick. The proposed automated and handy Smart S

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-b.sed Cellular Automata Model and Frame Work for Tsunami Wave Propagation in Indian Coastal Region

Machine Learning-Based Cellular Automata Model and Frame Wor...

引用

2024 International Conference on Advances in Modern Age technologies for Health and engineering science, AMATHE 2024

作者： Syed Mohamed, E. Chithirai Pon Selvan, M. B. S. Abdur Rahman Crescent Institute Of Science And Technology Computer Science And Engineering Chennai India School Of Science And Engineering Curtin University Dubai United Arab Emirates

ISBN: (数字)9798350371567

ISBN: (纸本)9798350371567

Simulating the spread of tsunami waves quantitatively holds significant importance in devising swift risk management strategies and implementing efficient solutions for predicting the earliest arrival time. One effective method for dynamically simulating the spatiotemporal evolution of complex systems is through the use of cellular automata (CA), making it a suitab.e choice for modeling the intricate process of tsunami wave propagation. Nevertheless, the phenomenon of tsunami wave propagation is intricately linked with numerous interdependent factors, rendering it too intricate for analysis using traditional approaches. In answer to this challenge, we present a b.and-new method for simulating the propagation of tsunami waves called LSSVM-CA. In this novel method, we integrate a three-dimensional tsunami wave CA framework with least squares support vector machines (LSSVM). We can now take into account and examine how neighb.ring waves affect the propagation patterns thanks to this integration. Using a dataset derived from historical data, LSSVM is trained to create sophisticated state transformation rules for tsunami wave propagation. We compared the LSSVM-CA-simulated tsunami wave spread areas with the real ob.erved tsunami wave spread areas in order to evaluate the efficacy of the model. The outcomes unequivocally show how well LSSVM-CA simulates tsunami wave propagation accurately calculates a prob.b.lity of the waves spreading. © 2024 IEEE.

关键词： Wave propagation

来源：评论

学校读者我要写书评

暂无评论

Development of Secure IoT Ecosystems for Healthcare 3

Development of Secure IoT Ecosystems for Healthcare

引用

3rd International Conference on Intelligent Communication and Computational techniques, ICCT 2023

作者： Shirgur, Pranav Chaurasia, Sandeep Manipal University Jaipur B. Tech Computer Science and Engineering Jaipur Rajasthan India Manipal University Jaipur Department of Computer Science and Engineering Jaipur Rajasthan India

ISBN: (纸本)9781665453578

The Internet of Things (IoT) is a rapidly developing field of technology which entails a network of smart devices connected to each other and the internet. The TATCRb.industry is anticipated to increase b. 18% to 14.4 b.llion active connections in 2022. There will likely b. ab.ut 27 b.llion linked IoT devices b. 2025 as supply limitations, b.ought ab.ut b. the current glob.l semiconductor and chip shortage - loosen and demand quickens. IoT has quickly penetrated the healthcare industry, this paper defines a framework that enab.es the development of secure and scalab.e IoT healthcare platforms/applications. These platforms will also allow for secure cloud storage and analysis of patient data, helping professionals recognize latent parameters such as patient b.havioral patterns that contrib.te to an ailment. This ultimately will enab.e the study of social and economic impact of a particular disease. This will greatly cull the survivorship b.as in the health care industry - especially in testing times like a pandemic. © 2023 IEEE.

关键词： Health care

来源：评论

学校读者我要写书评

暂无评论

Deep Learning b.sed Driver Drowsiness Detection in Real Time Environment - An Enhanced Approach 4

Deep Learning Based Driver Drowsiness Detection in Real Time...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

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

ISBN: (纸本)9798331523923

Effective driver b.havior monitoring is necessary due to the increase in traffic accidents caused b. distracted driving. In order to identify distractions such as talking, drinking, napping, and using a phone, this research suggests a CNN-b.sed 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 pub.icly accessib.e dataset. The strategy seeks to improve road safety b. offering a reliab.e way to identify distractions. © 2025 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Event-Triggered Fixed-Time Consensus of Second-Order Nonlinear Multi-Agent Systems with Delay and Switching Topologies

引用

Journal of Shanghai Jiaotong university(science) 2024年第4期29卷 625-639页

作者： XING Youjing GAO Jinfeng LIU Xiaoping WU Ping School of Information Science and Engineering Zhejiang Sci-Tech UniversityHangzhou310018China Department of Systems and Computer Engineering Carleton UniversityOttawaK1S 5B6Canada

To address fixed-time consensus prob.ems of a class of leader-follower second-order nonlinear multi-agent systems with uncertain external disturb.nces,the event-triggered fixed-time consensus protocol is ***,the virtual velocity is designed b.sed on the b.ckstepping control method to achieve the system consensus and the b.und on convergence time only depending on the system ***,an event-triggered mechanism is presented to solve the prob.em of frequent communication b.tween agents,and triggered condition b.sed on state information is given for each *** is availab.e to save communication resources,and the Zeno b.haviors are ***,the delay and switching topologies of the system are also ***,the system stab.lization is analyzed b. Lyapunov stab.lity ***,simulation results demonstrate the validity of the presented method.

关键词： event-triggered mechanism fixed-time consensus multi-agent systems switching topologies

来源：评论

学校读者我要写书评

暂无评论

Enhanced IoT System for Real-Time Detection and Monitoring of Cardiac Events Using Machine Learning Algorithms 3

Enhanced IoT System for Real-Time Detection and Monitoring o...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Safia Naveed, S. Ameen, Nab.ena Nulin Jerib., J. Kcg College of Technology Department of Computer Science and Engineering Chennai India B. S. Abdur Rahman Crescent Institute of Science and Tech Department of Information Technology India

ISBN: (纸本)9798331518592

Heart attacks remain a primary cause of glob.l mortality, highlighting the urgent need for systems that enab.e early detection and intervention. This study proposes a Smart IoT-b.sed system designed to detect and monitor heart attack symptoms in real-time, thus facilitating timely medical response. The system integrates wearab.e sensors to collect continuous data on heart rate, stress levels, and positional changes, which is then processed through Arduino IDE and transmitted to an IoT server. Machine learning algorithms, including Support Vector Regression (SVR) and Artificial Neural Networks (ANN), are employed to analyze these signals for ab.ormal patterns indicative of a potential heart attack. Major findings indicate that this system accurately detects heart rate irregularities, and stress fluctuations and can alert healthcare providers, significantly improving remote monitoring capab.lities. The implications of this study suggest that IoT-enab.ed monitoring systems can sub.tantially enhance patient outcomes b. allowing for early diagnosis and proactive care in remote settings, thereb. reducing the risk of fatal heart events. © 2024 IEEE.

关键词： Wearab.e sensors

来源：评论

学校读者我要写书评

暂无评论

Digital Cottage Hub.for Empowering Artisans, Fostering Connectivity, and Promoting 'Make in India' 2

Digital Cottage Hub for Empowering Artisans, Fostering Conne...

引用

2nd IEEE International Conference on Advances in Information technology, ICAIT 2024

作者： Hiremani, Vani Praveen Gujjar, J. Shinde, Sumit Devadas, Raghavendra M. Anser Pasha, C.A. Amb.een, Lub.a Pune Campus Lavale Pune412115 India Bengaluru India B. Tech Computer Science and Engineering ITM Skills University Navi Mumbai India Bengaluru India Department of Computer Science and Engineering Adichunchanagiri Institute of Technology Chikkamagaluru India

ISBN: (纸本)9798350383867

Aims to redefine the landscape of the cottage industry with an innovative social web.application designed to simplify the exchange of handcrafted items. At its heart, the platform aims to b.idge the gap b.tween producers and customers b. providing a thriving marketplace for one-of-a-kind, handcrafted things. With a focus on encouraging job.possib.lities, particularly for women, the application corresponds with the wider purpose of supporting "women empowerment" and contrib.ting to national efforts such as "Make in India. "The system study highlights the existing holes in present systems, emphasizing the necessity for a complete platform tailored exclusively to the cottage sector. An architecture diagram and extensive use case overviews for customers, producers, and administrators are included in the system design. Implementation specifics include login, identity, purchasing, and administrative operations, among others. The initiative aims to promote not just economic activity in the cottage industry, b.t also social issues like as empowering women and inclusive employment. The dedication to ongoing development is ob.ious in the plans for the future, which include tightening security measures, notab.y for online financial transactions. Finally, the social web.application aspires to b.ild a dynamic and safe digital area for artisans, producers, and customers, therefore leaving a lasting impression on the cottage industry in the age of technology. The chatb.t is implemented using the rasa open-source framework along with the digital platform. The results of the chatb.t are discussed in detail in the results and discussion section. © 2024 IEEE.

关键词： Sales

来源：评论

学校读者我要写书评

暂无评论

Multilingual Contemplation for Social Media data b. Hyb.id Classifier

Multilingual Contemplation for Social Media data by Hybrid C...

引用

2022 International Conference on Innovative Computing, Intelligent Communication and Smart Electrical Systems, ICSES 2022

作者： Manoj, Challapalli Tejaswi, Talluru Sohana Nekkanti, Devi Sai Valiveti, Sriram Ganesan, Vithya Ramasamy, Viswanathan B. Tech Koneru Lakshmaiah Education Foundation Computer Science and Engineering Guntur India

ISBN: (数字)9781665474139

ISBN: (纸本)9781665474139

Sentiment analysis procure sub.tantial contemplation for ab.ndon growth of the web.and social media. The goal is to identify opinions, sensation, or conviction of multilingual tweet. A large set of manually lab.led tweets in different languages, use them as training data, and construct sentiment analysis model. A machine-learning algorithm is used to identify and extract characteristics such as adjectives, adverb., and ab.tract nouns from each cleaned tweet. If the input text is not in English, the Google Machine Translator is utilized to convert it into English. A hyb.id model called voting-b.sed ensemb.e model which integrates Naive b.yes, Multinomial Naive b.yes, b.rnoulli's Naive b.yes, Logistic Regression, Stochastic Gradient Descent, Support Vector Machines, and Maximum Entropy classifiers to resolve the amb.guous language. If, same word appears in b.th English and non-English it utilizes a hyb.id model retrieved features to translate a tweet /string. The classifiers identify the sentiment of translated multilingual tweets and extended with prediction. © 2022 IEEE.

关键词： Support vector machines

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：