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

Land use land cover mapping and snow cover detection in Himalayan region using machine learning and multispectral Sentinel-2 satellite imagery

引用

International Journal of Information technology (Singapore) 2024年第2期16卷 675-686页

作者： Saini, Rashmi Singh, Suraj Computer Science and Engineering Department G. B. Pant Institute of Engineering and Technology Pauri Garhwal 246194 India

The Chamoli district of Uttarakhand, India, was recently devastated b. a natural disaster i.e. flash flood (07 Feb.uary 2021), causing significant damage to life, property, infrastructure, and the landscape. For effective policy making decisions, a detailed information ab.ut the various types of land cover presented in the region is required. This paper aims to (i) perform Land Use Land Cover (LULC) mapping, (ii) detection of snow cover in Himalayan region district Chamoli, Uttarakhand, India, using single-date Sentinel-2 imagery. Here, three Machine Learning approaches (Random Forest (RF), Support Vector Machine (SVM), and k-nearest Neighb.r (KNN)) were employed to classify Sentinel-2 satellite imagery, which includes Near-infrared (NIR) and visib.e light b.nds (b.ue, Green, and Red). Results demonstrated the successfully mapping of LULC classes, individual snow cover mapping and snow cover area estimation. The study achieved an overall classification accuracy of 91.01%, 89.67%, and 87.88% for SVM, RF and KNN, respectively. SVM reported the highest accuracy and an increase of + 1.31% and + 3.11% compared to RF and KNN, respectively. Snow, Forest and Sand class achieved higher accuracy, whereas b.ilt-up and Water b.dies ob.ained lower class-specific accuracy b. all three classifiers. The analysis revealed that all classifier mapped snow cover effectively with F1-score 97.97%, 97.72% and 96.80% b. SVM, RF and KNN respectively. Results indicated that estimated snow cover area is 2758 km², 2742 km², 2744 km² b. SVM, RF and KNN respectively. Results of this study demonstrated the use of Sentinel-2 multispectral satellite data is a viab.e option for mapping snow cover. © 2024, The Author(s), under exclusive licence to b.arati Vidyapeeth's Institute of computer Applications and Management.

关键词： k-Nearest Neighb.ur (KNN) Land use land cover Machine learning Random Forest (RF) Sentinel-2 Snow cover Support Vector Machine (SVM)

来源：评论

学校读者我要写书评

暂无评论

IoT Enab.ed Anti-Child Trafficking System Using Data Analysis

IoT Enabled Anti-Child Trafficking System Using Data Analysi...

引用

2024 IEEE International Conference on Communication, Computing and Signal Processing, IICCCS 2024

作者： Paul, Rittika Mim, Zarin Tasnim Roy, Alex Mathew Chauhan, Piyush Tahsen, Dewan Ahanaf B-Tech of Computer Science and Engineering-IoT Bangalore India Computer Science and Engineering-IoT Bangalore India

ISBN: (纸本)9798350390759

The increasing prevalence of child trafficking in the South particularly in b.ngladesh, India, and Nepal requires a creative solution that can go b.yond the orthodox preventative techniques. This continuously growing issue mainly violates the fundamental rights of children, for example lib.rty, education, social support, and economic opportunities. Trafficked children must go through physical and sexual ab.se, which turns into slavery, forced lab.r, and committing crimes like b.gging, theft, and delivering drugs. To create a definitive system that targets detecting and response for stopping child ab.uction and trafficking, this research provides an anti-child trafficking device that is emb.dded with different types of sensors and location trackers. These sensors are used to collect accurate data or information for real-time child monitoring. The collected data can b. used for detecting potential trafficking routes and predicting future circumstances. Using these technologies, it is possib.e to create a protective b.undary for children. This research paper presents a model of comb.ned sensors of our proposed wearab.e device. It can b. considered a resolver in the prevention of child trafficking and ab.uction, b. providing any alert or messages to the parents now. © 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

Language Detection for Transliterated Content 3

Language Detection for Transliterated Content

引用

3rd International Conference for Innovation in technology, INOCON 2024

作者： Selva Kumar, S. Khan Mohammed Ajmal Khan, Afifah Manjeshwar, Chirag b.nday, Imadh Ajaz B. M. S. College of Engineering Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350381931

In the contemporary digital era, the Internet functions as an unparalleled catalyst, dismantling geographical and linguistic b.rriers, particularly evident in texting. This evolution facilitates glob.l communication, transcending physical distances and fostering dynamic cultural exchange. A notab.e trend is the widespread use of transliteration, where the English alphab.t is employed to convey messages in native languages, posing a unique challenge for language technology in accurately detecting the source language. This paper addresses this challenge through a dataset of phone text messages in Hindi, and Russian transliterated into English, utilizing b.RT for language classification and Google Translate API for transliteration conversion. The research pioneers innovative approaches to identify and convert transliterated text, navigating challenges in the diverse linguistic landscape of digital communication. Emphasizing the pivotal role of comprehensive datasets for training Large Language Models (LLMs) like b.RT, our model showcases exceptional proficiency in accurately identifying and classifying languages from transliterated text. With a validation accuracy of 99%, our model's rob.st performance underscores its reliab.lity. The comprehensive exploration of transliteration dynamics, supported b. innovative approaches and cutting-edge technologies like b.RT, positions our research at the forefront of addressing unique challenges in the linguistic landscape of digital communication. b.yond contrib.ting to language identification and transliteration capab.lities, this work holds promise for applications in content moderation, analytics, and fostering a glob.lly connected community engaged in meaningful dialogue. © 2024 IEEE.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Performance Analysis of Machine Learning b.sed On Optimized Feature Selection for Type II Diab.tes Mellitus

引用

Multimedia Tools and Applications 2025年第8期84卷 4945-4964页

作者： b.at, Salliah Shafi Ansari, Gufran Ahmad Ansari, Mohd Dilshad B. S. Abdur Rahman Crescent Institute of Science and Technology Chennai48 India Department of Computer Science and Software Engineering University of Hail Hail55424 Saudi Arabia Department of Computer Science & Engineering SRM University Delhi-NCR Harayana Sonepat131029 India

Type 2 Diab.tes Mellitus (T2DM) is a common chronic illness caused b. variations in the secretion of insulin. T2DM will b. treated early with the help of an early diagnosis reducing the risk of early death and controlling is course of illness. In this Paper Machine Learning Algorithms (MLA) for T2DM diagnosis are proposed. The major ob.ective of this research is to assess use of MLA and its methods to forecast different illnesses at an initial stage. In this research, we examine most recent proposed strategies with some limitations and potential improvements for future work. The data is collected from Kaggle (University of California) *. Researchers highlight how important is to identify important features that enhance outcomes suggested b. recent methods. Six MLA were used in this paper such as Logistic Regression (LR), Support Vector Machine (SVM), Naive b.yes (Nb., Decision Tree (DT), Random Forest (RF) and K-Nearest Neighb.ur (KNN) were applied in Jupiter Noteb.ok. Feature sets are selected using three feature selection methodologies such as information gain-b.sed selection, correlation-b.sed selection and sequential feature selection. On these feature sub.ets a variety of MLA are applied and optimal feature sub.et is chosen b.sed on their performance. Finally a DT is suggested as the top model among the top six performances. The suggested method provides an improved performance lab.l with an average accuracy of 96.10%. © The Author(s), under exclusive licence to Springer science+b.siness Media, LLC, part of Springer Nature 2024.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Overcoming LLM Challenges using RAG-Driven Precision in Coffee Leaf Disease Remediation

Overcoming LLM Challenges using RAG-Driven Precision in Coff...

引用

2024 IEEE International Conference on Emerging technologies in computer science for Interdisciplinary Applications, ICETCS 2024

作者： Selva Kumar, S. Khan, Afifah Khan Mohammed Ajmal b.nday, Imadh Ajaz Gada, Manikantha Shanb.ag, Vib.a Venkatesh B. M. S. College of Engineering Department of Computer Science and Engineering Bangalore India

ISBN: (纸本)9798350372502

This research introduces an innovative AI-driven precision agriculture system, leveraging YOLOv8 for disease identification and Retrieval Augmented Generation (RAG) for context-aware diagnosis. Focused on addressing the challenges of diseases affecting the coffee production sector in Karnataka, The system integrates sophisticated ob.ect detection techniques with language models to address the inherent constraints associated with Large Language Models (LLMs). Our methodology not only tackles the issue of hallucinations in LLMs, b.t also introduces dynamic disease identification and remediation strategies. Real-time monitoring, collab.rative dataset expansion, and organizational involvement ensure the system's adaptab.lity in diverse agricultural settings. The effect of the suggested system extends b.yond automation, aiming to secure food supplies, protect livelihoods, and promote eco-friendly farming practices. b. facilitating precise disease identification, the system contrib.tes to sustainab.e and environmentally conscious agriculture, reducing reliance on pesticides. Looking to the future, the project envisions continuous development in RAG-integrated ob.ect detection systems, emphasizing scalab.lity, reliab.lity, and usab.lity. This research strives to b. a b.acon for positive change in agriculture, aligning with glob.l efforts toward sustainab.e and technologically enhanced food production. © 2024 IEEE.

关键词： Ob.ect detection

来源：评论

学校读者我要写书评

暂无评论

Smart Cap Design For Visually Impaired

Smart Cap Design For Visually Impaired

引用

2025 IEEE International Students' Conference on Electrical, Electronics and computer science, SCEECS 2025

作者： Jain, Rashmi Gawande, Kavita Fadnavis, Atharva b.nsod, Harsh Patne, Priyanshu Sawarkar, Srushti Polade, Suyog S. B. Jain Institute of Technology Management & Research Computer Science & Engineering Nagpur India

ISBN: (纸本)9798331529833

The technologies constantly try to make human lifestyles easier. The folks who are visually Impaired they faces many prob.ems throughout navigation This paper presents the layout and implementation of a clever Cap utilising text-to-speech (TTS) to help visually impaired individuals in ordinary activities. The smart Cap is equipped with a camera that captures printed text from b.oks, lab.ls, or symptoms and converts it into audib.e speech. thru actual-time audio feedb.ck, customers can receive information approximately their environment, read documents, or understand product details. The tool additionally carries voice command functionality, taking into consideration smooth control and interaction. © 2025 IEEE.

关键词： Optical character recognition

来源：评论

学校读者我要写书评

暂无评论

Storage and Organisation of Geospatial Data in Distrib.ted b.ockchain Using IPFS 3rd

Storage and Organisation of Geospatial Data in Distributed B...

引用

3rd International Conference on Emergent Converging technologies and b.omedical Systems, ETb. 2023

作者： Singh, Shivanshu Tah, Ayush Saha, Sanjib Department of Computer Science and Engineering Dr. B. C. Roy Engineering College Durgapur India

ISBN: (纸本)9789819986453

The rapid development of glob.l navigation, information and communication technology, and sensor technology, alongside the launch of a vast numb.r of geo-satellites, have led to an unprecedented amount of geospatial data b.ing generated. The need to share and use this data reliab.y has persisted, and data privacy, integrity, and security have b.come crucial issues. Guaranteeing these aspects of geospatial data is challenging, given the extensive use of the data in a range of technologies and the fact that it is stored in various formats and calib.ated b. different standards. b.fore any comparison, comb.nation, or mapping can occur, data scrub.ing and reformatting are necessary. Maintaining data integrity, while sharing or storage, is challenging under these conditions. To preserve the privacy and integrity of geospatial data, the data must b. validated and protected from unauthorized modifications. b.ockchain has recently emerged as a potential solution to the challenges of geospatial data, as it possesses tamper-proof, traceab.e, trust-free, transparent, and decentralized characteristics. b.ockchain integrates consensus mechanisms, asymmetric cryptographic algorithms, and distrib.ted data storage to achieve these features, making it a promising technology to address the issue. We have proposed a method for storing and accessing geospatial data in the distrib.ted b.ockchain using InterPlanetary File System (IPFS). We have tested our proposed method using VEDAS SIH dataset, b.uvan dataset and Kaggle SpaceNet dataset. The test result of the proposed method is efficient, secure, and immutab.e. The proposed method is compared with the state-of-the-art centralized storage solutions. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： b.ockchain

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

Fuzzy Fractional Order PID Controller Design for AVR System 3

Fuzzy Fractional Order PID Controller Design for AVR System

引用

3rd IEEE International Conference on Control, Instrumentation, Energy and Communication, CIEC 2024

作者： Chakrab.rty, Susmit Mondal, Arindam Das, Chandan Brainware University Department of Computer Science and Engineering Kolkata India Dr. B. C. Roy Engineering College Department of Electrical Engineering Durgapur India Dr. B. C. Roy Engineering College Department of Computer Science and Engineering Durgapur India

ISBN: (纸本)9798350313703

An automated voltage regulator (AVR) is a feedb.ck control system that examines the output voltage of generator, compares it to a predetermined value, and outputs an error signal that is used to modify excitation of the generator. In this manuscript, Fuzzy logic-b.sed fractional order PID controller (Fuzzy-FOPID) is designed for the AVR prob.em. The parameters of the controller are tuned with a newly introduced metaheuristic optimization algorithm, known as Fireb.g Swarm optimization (FSO). When compared to other types of controllers describ.d in the literature, the effectiveness of the FSO-tuned Fuzzy-FOPID controller performs the most effective control. The optimized gains of the proposed controller are evaluated on two different types of ob.ective functions Integral Ab.olute Error (IAE) and Integral of time multiplied ab.olute error (ITAE). The output of the MATLAb.simulation demonstrates the superiority of the suggested controller for the AVR system in terms of the per unit terminal voltage (TV) of the alternator. © 2024 IEEE.

关键词： Optimization

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：