检索结果-内蒙古大学图书馆

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

Data-driven visual analytics of Human Mob.lity data and green cover using Image Processing for Smart Cities 3

Data-driven visual analytics of Human Mobility data and gree...

引用

3rd IEEE International Conference on Intelligent tech.ologies, CONIT 2023

作者： Ramanathan, Sivasub.amanian Syed, Kulsoom Chavan, Tejaswini B. Tech Computer Science & Business Systems SVKMs NMIMS Navi Mumbai Mumbai India School of Technology Management & Engineering SVKMs NMIMS Navi Mumbai Mumbai India

ISBN: (纸本)9798350338607

This research paper presents an approach to data-driven visual analytics of human mob.lity data using Kernel Density Estimation visualized through heatmaps, highlighting the need for exploration of forecasting methods and intuitive visualizations using the ARIMA model. A specific geographic area is chosen for the demonstration of the scope of the proposed system. The system is a web.application developed using Streamlit, an open-source python framework. To effectively implement the smart city concept, it is crucial to integrate diverse IoT systems, data sources, data streams, and analytical tools into a unified and seamless platform that facilitates the collection, analysis and presentation of information related to urb.n systems and sub.ystems. We propose taking into consideration several attrib.tes when analyzing human mob.lity patterns, such as vehicle/traffic density, modes of transport, transport data, demographics, latitude, and longitude. Additionally, the system utilizes image processing as an efficient method for calculating urb.n green cover using morphological operations that are computationally cheaper and easy to use as compared to traditional surveys that are time and resource intensive. This information is used to develop smart plans to sustain or increase green cover in select areas, leading to the creation of sustainab.e and green smart cities. © 2023 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

b.ain Tumor Detection using MRI Image Processing tech.iques

Brain Tumor Detection using MRI Image Processing Techniques

引用

2024 IEEE International Conference on Innovation and Novelty in engineering and tech.ology, INNOVA 2024

作者： Jadhav, Amb.ji S. Pawar, Rashmi Hattaraki, Sunilkumar M. b.gali, Shwetha Patil, Rajeshwari S. Patil, b.agyashree Department of Elecrtical and Electronics Engineering B.L.D.E. A’s V.P. Dr. P.G.H. College of Engg. and Tech. Vijayapura India Department of Electronics and Communication Engineering B.L.D.E. A’s V.P. Dr. P.G.H. College of Engg. and Tech. Vijayapura India Department of Computer Science and Engineering Sri Krishna Institute of Technology Bengaluru India

ISBN: (纸本)9798331505134

Medical image processing is highly developed and critical in the medical field, encompassing methods like X-rays, MRI, and CT scans. These tech.iques help to identify minute defects in the human b.dy. b.ain tumors, which disrupt normal b.ain function, are detected through MRI using segmentation, feature extraction, and classification, processes that are time-consuming and depend on the expertise of clinical professionals. computer-aided tech.ology addresses these challenges. This work aims to diagnose b.ain tumors accurately and quickly using MRI images. Image preprocessing is done using CLAHE and median filter to enhance contrast and eliminate noise. Thresholding is used for segmentation and a lightweight U-net is used for tumor segmentation, achieving high accuracy and efficiency without extensive training data. Finally, an MSD-CNN classifies the tumor, capturing b.th local and glob.l features for b.tter image recognition. Our proposed model outperforms over existing methods in terms of accuracy, rob.stness, and efficiency in b.ain tumor detection. © 2024 IEEE.

关键词： Median filters

来源：评论

学校读者我要写书评

暂无评论

Unified dimensionality reduction tech.iques in chronic liver disease detection

arXiv

引用

arXiv 2024年

作者： Karna, Anand Khan, Naina Rauniyar, Rahul Shamb.arkar, Prashant Giridhar B. Tech Student Computer Engineering Department Delhi Technological University India Computer Engineering Department Delhi Technological University India

Glob.lly, chronic liver disease continues to b. a major health concern that requires precise predictive models for prompt detection and treatment. Using the Indian Liver Patient Dataset (ILPD) from the University of California at Irvine’s UCI Machine Learning Repository, a numb.r of machine learning algorithms are investigated in this study. The main focus of our research is this dataset, which includes the medical records of 583 patients, 416 of whom have b.en diagnosed with liver disease and 167 of whom have not. There are several aspects to this work, including feature extraction and dimensionality reduction methods like Linear Discriminant Analysis (LDA), Factor Analysis (FA), t-distrib.ted Stochastic Neighb.ur Emb.dding (t-SNE), and Uniform Manifold Approximation and Projection (UMAP). The purpose of the study is to investigate how well these approaches work for converting high-dimensional datasets and improving prediction accuracy. To assess the prediction ab.lity of the improved models, a numb.r of classification methods were used, such as Multi-layer Perceptron, Random Forest, K-nearest neighb.urs, and Logistic Regression. Remarkab.y, the improved models performed admirab.y, with Random Forest having the highest accuracy of 98.31% in 10-fold cross-validation and 95.79% in train-test split evaluation. Findings offer important new perspectives on the choice and use of customized feature extraction and dimensionality reduction methods, which improve predictive models for patients with chronic liver disease. © 2024, CC b..

关键词： Dimensionality reduction

来源：评论

学校读者我要写书评

暂无评论

Prevention from gas devastation

Prevention from gas devastation

引用

2020 International Online Conference on engineering Response to COVID-19, IOCER-COVID-19 2020

作者： Datta, Sanghita Sah, Ankita Gautam, Sidharth Das, Upamita Maity, Saikat B. Tech Computer Science Engineering JIS University India

LPG leakages are the most common issues found in household and gas plants. This issue is life threatening not only for the humans in the vicinity b.t also for the surrounding areas. The idea b.hind our project is to save the lives of those innocents who can get affected due to the carelessness of certain people. So, as soon as the gas gets detected b. the system, the concerned people around will receive messages as well as the alarm rings. © 2021 Institute of Physics Pub.ishing. All rights reserved.

关键词： Gas plants

来源：评论

学校读者我要写书评

暂无评论

Decoding Water Hyacinth Growth Stages with Deep Learning

Decoding Water Hyacinth Growth Stages with Deep Learning

引用

Next Generation Communication & Information Processing (INCIP), International Conference on

作者： Maheswari L. Patil Vidhan Mehta Sumith Sigtia Gyanendra Pandey Shivani Kumari Department of Artificial Intelligence and Machine Learning The Oxford College of Engineering Bangalore India B. Tech Artificial Intelligence and Machine Learning The Oxford College of Engineering Bangalore India B. Tech Computer Science and Engineering Dr. B R Ambedkar NIT Jalandhar Punjab India B. Tech Industrial and Production Engineers Dr B R Ambedkar NIT Jalandhar Punjab India

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

Eichhornia crassipes, commonly referred to as water hyacinth and thought to b. one of the most aggressive aquatic macrophytes, is an emerging threat to b.th ecosystems and economies. The potential for rapid proliferation induces b.ockage of waterways, decreased b.odiversity, degraded water quality, and reduced fishery and recreational values; it demands advanced monitoring and management tech.iques. Our research proposes a b.tter approach for identification of water hyacinth growth stages with greater accuracy b. applying the latest deep-learning models so as to take more stringent control measures. We enhanced our dataset b. incorporating high-resolution images from diverse aquatic environments, including Kaikondrahalli Lake in b.ngalore and Anasagar Lake in Ajmer, adding to existing images sourced from Kaggle. Three pre-trained CNN models b.sed on transfer learning, namely ResNet50, VGG16, and InceptionV3,have b.en taken into consideration and evaluated with great care for their efficacy in classification. Among them, InceptionV3outperformed, with training accuracy of 98.43% and testing accuracy of 99.80%. These models were further integrated into a custom SimpleCNN architecture improving the rob.stness in classification through Ensemb.e Learning. The performance ob.ained from the current study notab.y surpassed the b.nchmark accuracy of 86.2% set b. Dyrmann et al. in their CNN-b.sed multi-class classification study.

关键词： Training Deep learning Accuracy Invasive species b.ological system modeling Computational modeling Lakes b.nchmark testing Convolutional neural networks Residual neural networks

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

Handy Smart Stick: A Guide for Visually Impaired People

引用

International Conference on Communication and Electronics Systems (ICCES)

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

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 tech.ologies 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 tech.ology 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：

来源：评论

学校读者我要写书评

暂无评论

Context-Aware Summarization for PDF Documents using Large Language Models

Context-Aware Summarization for PDF Documents using Large La...

引用

Expert Clouds and Applications (ICOECA), International Conference on

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

ISBN: (数字)9798350385793

ISBN: (纸本)9798350385809

In an era characterized b. the overflow of textual information, the demand for effective text summarization tech.iques 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.

关键词： Generative AI Datab.ses Large language models Text summarization Portab.e document format Vectors Context modeling

来源：评论

学校读者我要写书评

暂无评论

Development of Secure IoT Ecosystems for Healthcare

Development of Secure IoT Ecosystems for Healthcare

引用

International Conference on Intelligent Communication and Computational tech.iques (ICCT)

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

The Internet of Things (IoT) is a rapidly developing field of tech.ology 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.

关键词： Industries Economics Cloud computing Ecosystems Medical services b.havioral sciences Internet of Things

来源：评论

学校读者我要写书评

暂无评论

Automated Handwriting Machine

Automated Handwriting Machine

引用

International Conference for Convergence of tech.ology (I2CT)

作者： KG Deekshitha Chaitanya Patange M Harshitha Pavitra Y.J B. Tech. Electronics and Communication Engineering PES University Bangalore Karnataka India Department of Electronics and Communication Engineering PES University Bangalore Karnataka India

The Automatic Writing Machine is a device used to automate the process of writing b. eliminating the necessity of human aid for a physically challenged person. The proposed work aims to design a user-friendly automated writing machine with computer numerical control (CNC) along with Arduino and Raspb.rry Pi. The user input(image/text/audio) signal is converted into handwriting using Python programming to generate coordinates and drive your CNC machine through Arduino. The proposed work is a stand-alone system eliminating the requirement of high-end machines to process the coordinate data. The proposed work also eliminates the need of software such as b.n-b.x and G-code which restrict the user input to only images. The proposed work has increased the efficiency in handling user input over the work reported in literature along with reduced hardware and software requirements.

关键词： Program processors Costs Computational modeling Writing Programming Software Hardware

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：