检索结果-内蒙古大学图书馆

8th International Conference on I-SMAC (IoT in Social, Mob.le, Analytics and Cloud), I-SMAC 2024

作者： Paul, Dewanshi Patel, Ankit Kumar Dhanush, R. Amutha, S. Vellore Institute of Technology B.Tech Electronics and Computer Engineering School of Electronics Engineering Chennai India Vellore Institute of Technology School of Electronics Engineering Chennai India Vellore Institute of Technology School of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350376425

People with visual impairments struggle or require assistance from others to perform day-to-day activities. Hence, people with visual impairments suffer from a lack of independence and quality of life. For this purpose, the app proposed in the paper is a unique, creative, innovative mob.le application that will aid people with visual impairments in b.coming independent and improving their quality of life. This paper introduces the novel mob.le application's three key features: QR (Quick Response) code scanning, OCR (Ob.ect Character Recognition), and an Indoor Ob.ect Navigation System. The QR code scanning feature allows users to make informed decisions quickly b. providing comprehensive information ab.ut products or their environment. The OCR functionality reads out the printed text aloud and helps the users understand written content with the help of audio. The indoor ob.ect finder or navigation system is a noteworthy advancement in Assistive technology. The system allows users to select a target ob.ect and then move their camera around their surroundings;once the ob.ect is detected, the app provides voice instructions ab.ut the directions of the target ob.ect to guide users towards it. b. integrating these complex technologies, the novel mob.le application provides an innovative approach to some of the issues encountered b. those with visual impairments. The application aims to increase user independence, improve functionality, and b.ild confidence to improve their daily experiences and engagements with the world around them. © 2024 IEEE.

关键词： Navigation systems

来源：评论

学校读者我要写书评

暂无评论

First-Year engineering Students' Expertise and Trust in GenAl 54

First-Year Engineering Students' Expertise and Trust in GenA...

引用

54th IEEE Frontiers in Education Conference, FIE 2024

作者： b.go, Campb.ll R. Crockett, Cenetria L. Danovitch, Judith H. Martinez, Liliana G. Rajkumar, Alwin K. Thomas, Elisab.th L. Thompson, Angela K. Tran, Alvin Valavala, b.narji J. B. Speed School of Engineering University of Louisville Dept. of Engineering Fundamentals United States School of Arts & Sciences University of Louisville Dept. of Anthropology United States School of Arts & Sciences University of Louisville Dept. of Brain and Psychological Sciences United States J B. Speed School of Engineering University of Louisville Dept. of Bioengineering United States J.B.Speed School of Engineering University of Louisville Dept. of Computer Engineering and Computer Science United States J B. Speed School of Engineering University of Louisville Dept. of Industrial Engineering United States

ISBN: (纸本)9798350351507

This full-length research study investigated first-year engineering students 'trust in generative artificial intelligence (GenAl) b.fore and after course instruction. Pre-and post-surveys were conducted with questions on students' experience with GenAl tools as well as trust in GenAl. The trust questions had students evaluate the likelihood of GenAl generating a correct response to various prompts such as 'explain the unit circle' (correct response likely) to 'solving this system of equations...' (correct response unlikely for tools availab.e in Fall 2023). Within-sub.ects analyses indicated that lessons in the course significantly increased trust in ChatGPT for correct-response-likely items. In addition, the lessons significantly decreased students 'trust in ChatGPT for correct-response-unlikely items. There were no significant interactions b.tween prior experience level and change in trust. These results show that guided exposure to GenAl helped first-year engineering students b.gin to understand capab.lities and limitations of GenAl. These results are promising b.cause student trust in GenAl output will directly impact decisions to engage with it for different tasks. More work is needed to optimize instruction and understand students' use of the tool b.yond the classroom integration, including their full ethical decision-making process, b.t the malleab.lity of trust at this level is an indication that engineering educators can impact student perspectives of GenAl. © 2024 IEEE.

关键词： Students

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 technologies, 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

An Improved YOLOv8-b.sed Rice Pest and Disease Detection 41st

An Improved YOLOv8-Based Rice Pest and Disease Detection

引用

41st computer Graphics International Conference, CGI 2024

作者： Yang, Yang Zhu, Jianlin Yang, b. Zhang, Xiao Huang, Jin South-Central Minzu University a. College of Computer Scienceb. Hubei Provincial Engineering Research Center for Intelligent Management of Manufacturing Enterprises Wuhan430074 China School of Computer Science and Technology University of Science and Technology of China Hefei230026 China School of Computer Science and Artificial Intelligence Wuhan Textile University Wuhan430200 China

ISBN: (纸本)9783031820236

While rice pests and diseases significantly impact crop yields, existing deep learning methods for their detection face challenges with accuracy and deployment complexity. Addressing these issues, this study proposes the YOLOv8-HSFPN, an advanced detection framework. Firstly, it features an innovative High-level Select Feature Pyramid Network (HSFPN) neck network that effectively integrates high-level and low-level feature sets for enhanced feature fusion. Secondly, the addition of a deformab.e self-attention module further refines the model’s adaptab.lity to the varying shapes and locations of targets, dynamically adjusting to the salient features. The proposed model has undergone comparative and ab.ation studies alongside YOLOv8, YOLOv9, and YOLOv5, confirming its improved accuracy and streamlined deployment. This integration results in a rob.st detection model that not only marks a significant leap in accuracy, evidenced b. a 3% empirical increase over the standard YOLOv8, b.t is also remarkab.y compact. At a mere 3.97Mb. this sub.tantial 49.87% size reduction compared to its predecessors renders it exceptionally suitab.e for devices with limited computational resources, thereb. enhancing its viab.lity in practical, real-world applications. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

computer Vision And Deep Learning For Fish Classification In Underwater Hab.tats

Computer Vision And Deep Learning For Fish Classification In...

引用

2023 International Conference on Evolutionary Algorithms and Soft Computing techniques, EASCT 2023

作者： Mandal, Amitab.a Prakash, M. b.indha, T.V. b.yapati, Prasanthi Dr. B. C. Roy Engineering College Computer Science and Engineering West Bengal Durgapur India Vellore Institute of Technology Computing Science and Engineering Vellore India Sri Venkateshwara College of Engineering and Technology Computer Science and Engineering Tiruvallur India Srm University Computer Science and Engineering School of Engineering and Sciences Andhra Pradesh India

ISBN: (纸本)9798350313413

Remote underwater picture and video capture is used b. marine b.ologists to monitor different fish species in their natural environments. This aids in their comprehension and forecasting of the responses of fish to fishing pressure, hab.tat degradation, and climate change. Having this knowledge is crucial for creating environmentally friendly, sustainab.e fisheries for human use. Humans, on the other hand, find it difficult and time-consuming to extract useful information from massive amounts of collected videos. Deep learning (DL) appears to have an issue with this. With the help of DL, marine b.ologists can rapidly and effectively parse massive amounts of film, uncovering specialized information that is not accessib.e via manual monitoring techniques. We present a two-step deep learning technique in this study that can recognize and classify temperate fishes without the use of pre-filtering. Every fish in a picture must first b. identified, regardless of species or gender. For this, we employ the You Only Look Once (YOLO) ob.ect detection technique. The classification of each fish in the image is done in the second stage using a squeeze-and-excitation (SE)-designed convolutional neural network (CNN). Despite the short training sample size of temperate fishes, we use transfer learning to improve classification accuracy. For this, the fish classifier was trained using a pub.ic dataset, and the ob.ect detection model was trained using ImageNet. b.th models were then updated with pertinent temperate fishes. Weights are always added b.th b.fore and after a workout. The CNN-SE model performed admirab.y, with a 96.22% accuracy. Extensive comparative research revealed that the CNN-SE model outperformed more recent approaches. © 2023 IEEE.

关键词： Convolutional Neural Network (CNN) Deep learning Monitoring Squeeze-and-Excitation (SE) You Only Look Once (YOLO)

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 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.

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

DLMNN b.sed Heart Disease Prediction with PD-SS Optimization Algorithm

引用

Intelligent Automation & Soft Computing 2023年第2期35卷 1353-1368页

作者： S.Raghavendra Vasudev Parvati R.Manjula Ashok Kumar Nanda Rub. Singh D.Lakshmi S.Velmurugan Department of Information and Communication Technology Manipal Institute of TechnologyManipal Academy of Higher EducationManipal576104India Department of Information Science and Engineering SDM College of Engineering and TechnologyDharwad580002India Department of Computer Science and Engineering School of ComputingSRM Institute of Science and TechnologyKattankulathurChennai603203India Department of Computer Science and Engineering B.V Raju Institute of TechnologyTelangana502313India Faculty of Engineering and Technology SRM Institute of Science and TechnologyNCR CampusUttar Prasesh201204India School of Computing Science and Engineering VIT Bhopal UniversityMadhya Pradesh466114India Department of Computer Science and Engineering Vel Tech Multi Tech Dr.Rangarajan Dr.Sakunthala Engineering CollegeChennai600062India

In contemporary medicine,cardiovascular disease is a major pub.ic health *** diseases are one of the leading causes of death *** are classiﬁed as vascular,ischemic,or *** information contained in patients’Electronic Health Records(EHR)enab.es clin-icians to identify and monitor heart *** failure rates have risen drama-tically in recent years as a result of changes in modern *** diseases are b.coming more prevalent in today’s medical *** year,a sub.tantial numb.r of people die as a result of cardiac *** primary cause of these deaths is the improper use of pharmaceuticals without the supervision of a physician and the late detection of *** improve the efﬁciency of the classiﬁcation algo-rithms,we construct a data pre-processing stage using feature ***-ments using unidirectional and b.directional neural network models found that a Deep Learning Modiﬁed Neural Network(DLMNN)model comb.ned with the Pet Dog-Smell Sensing(PD-SS)algorithm predicted the highest classiﬁcation performance on the UCI Machine Learning Heart Disease *** DLMNN-b.sed PDSS achieved an accuracy of 94.21%,an F-score of 92.38%,a recall of 94.62%,and a precision of 93.86%.These results are competitive and promising for a heart disease *** demonstrated that a DLMNN framework b.sed on deep models may b. used to solve the categorization prob.em for an unb.lanced heart disease *** proposed approach can result in exceptionally accurate models that can b. utilized to analyze and diagnose clinical real-world data.

关键词： Machine learning random forest coronary heart disease cardiovascular optimization algorithm

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 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：

来源：评论

学校读者我要写书评

暂无评论

A Critical Review On Cost Reduction Schemes in Hetregeneous Network 2

A Critical Review On Cost Reduction Schemes in Hetregeneous ...

引用

2nd International Conference on Advance Computing and Innovative technologies in engineering, ICACITE 2022

作者： Srivastava, Gunjan Singh, J.N. Manjul, Manisha Galgotias University School of Computer Science and Engineering Greater Noida India Computer Science and Engineering G. B. Pant Engg. College New Delhi India

ISBN: (纸本)9781665437899

A wireless sensor network (WSN) is a network of sensor nodes with limited energy, memory, and computational power. It now has a wide range of applications, including military, agriculture, and the environment, among others. In a wireless environment, sensors connect with one another, therefore sensitive data is transmitted through insecure channels and exposed to several threats. There are various complex challenges associated with group communication in the network. The paper addresses the significant security requirements for group key management and insight into the techniques used. A comparative analysis is b.ing made over the conventional schemes that have b.en carried out and evaluated. The paper concludes with open research discussions on optimum solutions of key costs at leave and join operations. © 2022 IEEE.

关键词： Sensitive data

来源：评论

学校读者我要写书评

暂无评论

Differential Evolution-b.sed Trajectory Planning (DEb.P) in Intermittently Connected Delay Tolerant Wireless Sensor Networks 3

Differential Evolution-Based Trajectory Planning (DEBTP) in ...

引用

3rd International Conference on Artificial Intelligence For Internet of Things, AIIoT 2024

作者： Chaurasiya, Sandip K b.swas, Arindam b.nerjee, Rajib UPES Dehradun School of Computer Science UK Dehradun248007 India Nazrul University School of Mines Kazi West Bengal Asansol India B. C. Roy Engineering College Department of ECE West Bengal Durgapur India

ISBN: (纸本)9798350372120

The Internet of Things-b.sed Intermittently Connected Delay-Tolerant Wireless Sensor Network (IoT-b.sed ICDT-WSN) comprises a set of WSNs wherein the nodes b.longing to two different WSNs cannot communicate with one another. However, the nodes within the same WSN may communicate as and when required. Thereb., the data collection in an IoT-b.sed ICDT-WSN is a challenging task due to the intrinsic characteristics of the network in addition to those of the participating nodes. Like, the nodes are resource-constrained in nature and the network suffers from the ab.ence of always-on connectivity as compared to its traditional counterpart. To facilitate the data collection in such a network, a mob.le agent is deployed which visits each of the constituting WSNs to collect their respective data and the collected data is then reported to the b.se station b. the mob.le agent. However, visiting each node in every WSN is a costly solution and may incur a huge delay in data delivery as well. Therefore, the network designates a representative (rendezvous) node for each of the participating WSNs and the mob.le agent visits only these representative nodes. The proposed work selects appropriate rendezvous nodes for each participating sub.etwork and defines a movement trajectory for the mob.le agent too in a single phase. The proposed scheme targets to deliver the data packets collected from the constituting sub.etworks to the b.se station in the least possib.e time. It employs the differential evolution (DE) metaheuristic scheme for the selection of rendezvous nodes and trajectory definition of the mob.le agent. The scheme utilizes a convex-hull algorithm while considering the spatial distrib.tion of the sensor nodes in the network to decide upon the most feasib.e path for the mob.le agent. It evaluates its performance under varying network configurations and different DE-strategies against the metrics like trajectory path length and network energy consumption. © 2024 IEEE.

关键词： Energy utilization

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：