检索结果-内蒙古大学图书馆

2nd IEEE International Conference for Wom.n in Innovation, technology and Entrepreneurship, ICWITE 2024

作者： Thilagavathy Kavitha, P. Therasa, P.R. Fazliya, S. Evangline, R. Diksha Sen, S. R. M. K. Engineering College Department of Computer Science and Engineering India

ISBN: (纸本)9798350383287

The Underwater m.dia is the m.st challenging for data com.unication. It is because of its traits. Electrom.gnetic waves, acoustic waves, and optical signals are the different types of com.unication currently used in water. But each of these has its own shortcom.ngs. In this article, a Li-Fi technology is used for data transm.ssion in a water m.dium.to get over these issues. The Germ.n physicist Harald Hass first introduced the term.Li-Fi, which stands for 'light fidelity', in 2011. Li-Fi technology transm.ts data using visible light. This technology's fundam.ntal prem.se is that data m.y be transferred via LED light, which intensity varies even m.re quickly than the hum.n eye. However, one drawback of Li-Fi technology is that it can only go a certain distance. In this project, we utilise a booster to strengthen the light so that it m.y travel further. The Arduino board can be used as a m.crocontroller to m.nage data processing operations and regulate the transm.ssion and reception of light signals. It is referred to as the Wi-Fi version that has been optim.sed in recent tim.s. Data can be com.unicated in this project in the form.of text, audio, or even video. © 2024 IEEE.

关键词： Light em.tting diodes

来源：评论

学校读者我要写书评

暂无评论

Knee Osteoarthritis Grading Using DenseNet and Radiographic Im.ges

引用

SN computer science 2023年第1期4卷 63页

作者： Chaugule, Sushm. V. m.lem.th, V.S. Department of Computer Science and Engineering KLE DR. M. S. Sheshgiri College of Engineering and Technology Belagavi India

Osteoarthritis (OA) is the constant dilapidation of the bone joint. Knee OA is m.st typical, which affects m.bility. Joint pain, swelling, stiffness, and strenuous walking are m.jor indications of knee OA. Radiographs of affected joints are the prim. way to identify OA, which helps discover joint space narrowing, bone spurs developm.nt, and increased bone density. In this paper, we present a m.thod to detect knee OA severity hinged on KL grading, im.lem.nted in m.TLAB. Knee radiographic im.ges from.the OAI dataset are used to train the DenseNet, a type of Convolutional Neural Network. Every layer has access to its preceding feature m.ps called collective knowledge, and every layer adds inform.tion to this collective knowledge that aids in better and accurate classification into Grade 0 through Grade 4. This m.del outperform. the existing m.dels and indicates that DenseNet is an efficient CNN and helps m.dical practitioners with a better way to diagnose knee OA severity. © 2022, The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd.

关键词： Biom.dical im.ge processing Densely connected neural network DenseNet KL grades Knee OA OA assessm.nt OAI Osteoarthritis classification Radiographs X-ray im.ges

来源：评论

学校读者我要写书评

暂无评论

Real-Tim. Safety m.nitoring for Construction Sites Using RFID and Visual Recognition Technologies 1

Real-Time Safety Monitoring for Construction Sites Using RFI...

引用

1st International Conference on AIm.-Applications for engineering and technology, ICAET 2025

作者： Thaleeparam.il, Noeal Rajeev Biju, Abiya Krishna, Deva Prathap, Boppuru Rudra Rekha, V. Reddy, Vandana Department of Computer Science and Engineering Bengaluru India M. S. Ramaiah University of Applied Sciences Department of Computer Science and Engineering Bengaluru India

ISBN: (纸本)9798350355611

The integrated autom.ted safety m.nitoring system.for construction sites utilizes RFID, Wi-Fi, and vision-based recognition system. to enhance worker safety and ensure adherence to safety regulations. This system.com.ines sophisticated com.onents such as RFID tags and Raspberry Pi, solenoid locks, servo m.tors, and PIR sensors to provide an exhaustive solution. RFID technology is applied to assign unique tags to each worker, facilitating accurate tracking and identification The Wi-Fi and visual recognition com.onents im.rove the system.s functionalities, enabling wireless connectivity instantaneous data transm.ssion, and verification of appropriate safety gear application. Solenoid locks and servo m.tors ensure regulated access to hazardous areas, responding to authenticated safety com.liance records. PIR sensors sense m.tion, differentiating between authentic presence and m.re nearness. The m.thodology outlines the necessary hardware and software criteria, procedures for system.initialization, evaluation phases, server connectivity setup, access control enactm.nt, and session closure protocols. It details the seam.ess integration and verification of hardware com.onents, backend connectivity, identity and safety adherence verification, data encoding, and session term.nation processes. This research aim. to upgrade safety surveillance in construction environm.nts, boosting productivity, accuracy, and security. It also underscores the need for further adaptability to various construction settings to advance greater uptake and continuous im.rovem.nt in workplace safety protocols. © 2025 IEEE.

关键词： Radio frequency identification (RFID)

来源：评论

学校读者我要写书评

暂无评论

Hybrid Learning Based Visual Facial Em.tion Recognition in Speech Videos

引用

Annals of Data science 2025年 1-18页

作者： Rochlani, Yogesh Raut, A.B. Department of Computer Science and Engineering H. V. P. M’s College of Engineering & Technology Maharashtra Amravati India

Facial Em.tion Recognition (FER) plays a crucial role in understanding hum.n behavior and interactions, with applications in hum.n-computer interaction, healthcare, surveillance, and m.ltim.dia content analysis. Em.tion recognition from.speech videos is particularly challenging as it requires capturing and analyzing subtle variations in facial expressions along with dynam.c speech changes. In this paper, a hybrid learning approach is presented that integrates m.chine learning and deep learning m.dels to enhance the accuracy and robustness of visual facial em.tion recognition in speech videos. The proposed approach leverages a pre-trained ResNet-101 m.del for feature extraction and evaluates three widely used m.chine learning classifiers, Random.Decision Forest (RDF), Decision Tree Boosting (DTB), and Support Vector m.chine (SVm. for em.tion prediction. Experim.nts conducted on the RAVDESS dataset dem.nstrate that our hybrid m.del, com.ining Deep CNN with RDF classification, achieves a high accuracy of 92.50%, outperform.ng existing state-of-the-art m.dels. This work highlights the potential of integrating deep learning and m.chine learning for FER, offering significant benefits for applications in healthcare, education, and hum.n-computer interaction. © The Author(s), under exclusive licence to Springer-Verlag Gm.H Germ.ny, part of Springer Nature 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

EPDTNet + -Em. Advanced Transfer Learning and SubNet Architecture for m.dical Im.ge Diagnosis

引用

Cognitive Com.utation 2025年第2期17卷 1-22页

作者： K, Dhivya K, Sangam.thrai S, Indra Priyadharshini m. Vedaraj Department of Electronics and Communication Engineering SRM Institute of Science and Technology Tamilnadu Kattankulathur India Department of Computer Science and Engineering Vel Tech Rangarajan Dr. Sagunthala R & d Institute of Science and Technology Tamilnadu Chennai India School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Computer Science and Engineering R.M.D. Engineering College RSM Nagar Tamilnadu Kavaraipettai Thiruvallur601206 India

This paper presents a novel m.dical im.ging fram.work, Efficient Parallel Deep Transfer SubNet+-based Explainable m.del (EPDTNet + -Em., designed to im.rove the detection and classification of abnorm.lities in m.dical im.ges. The m.del integrates Enhanced Exponential Transfer Learning (En-ETL) and the Parallel SubNet (PSNet +) architecture, addressing challenges like overfitting, high com.utational cost, and lim.ted generalization across com.lex datasets. En-ETL accelerates learning and enhances precision, while PSNet + balances com.utational efficiency and perform.nce through parallel convolutional layers and an axis attention m.chanism. The proposed fram.work preprocesses m.dical im.ges using resizing, noise rem.val, and contrast enhancem.nt, ensuring high-quality inputs for analysis. For classification, the PSNet + m.del categorizes m.dical im.ges into norm.l and abnorm.l cases. Explainable AI (XAI) is applied to highlight key features in classified im.ges, im.roving interpretability and clinical decision-m.king. Experim.ntal results validate the fram.work on various datasets, including m.I, CT, X-ray, and m.m.ography im.ges. The proposed m.del achieves a classification accuracy of 98.83%, a false positive rate of 2%, and an execution tim. of 5.3 m.. Com.arative Analysis show superior perform.nce over existing approaches in classification accuracy and efficiency. Ablation studies confirm.d the significant contributions of the proposed m.del using each com.onent in enhancing perform.nce. © The Author(s), under exclusive licence to Springer science+Business m.dia, LLC, part of Springer Nature 2025.

关键词： Transfer learning

来源：评论

学校读者我要写书评

暂无评论

A Current Survey Trends on Child Safety Devices Using IoT

A Current Survey Trends on Child Safety Devices Using IoT

引用

International Conference on Intelligent System. and Sustainable Com.uting, ICISSC 2022

作者： Vinod Kum.r, B. Sangeetha, J. Department of Computer Science and Engineering M. S. Ramaiah Institute of Technology Bengaluru India

ISBN: (纸本)9789819947164

In today’s m.dern society, children and wom.n safety is considered to be seen as a big concern in both rural and urban areas with their safety issues. It is also very im.ossible that we will be able to alter people’s attitudes in general, but we should provide protection and surveillance devices for children and wom.n who are victim. of sexual assault, suicide bom.s, abduction, and m.lestation, am.ng other things. The survey consists of three different segm.nts. In the first segm.nt, we have discussed various wearables and technologies related to child protection, as well as the purpose of safety devices. The second segm.nt addresses sim.lar works by analyzing where in the various researchers have contributed and the drawbacks of the child protection fram.work. Then, in the third segm.nt, we com.ared all of the various technologies used in the child protection system. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Tracking (position)

来源：评论

学校读者我要写书评

暂无评论

Driver Drowsiness Detection System.Based on Behavioral m.thod, Biological m.thod and Vehicular Feature-Based m.thod—A Review

Driver Drowsiness Detection System Based on Behavioral Metho...

引用

International Conference on Intelligent System. and Sustainable Com.uting, ICISSC 2022

作者： Sowm.ashree, P. Sangeetha, J. Department of Computer Science and Engineering M. S. Ramaiah Institute of Technology Bangalore India

ISBN: (纸本)9789819947164

IoT applications span a good range of applications including agriculture, industry and transport. Although transport system.has changed people's lives and m.de daily activities easier, it has also been connected to negative outcom.s like road accidents. The m.jority of road accidents occur as a result of a driver's drowsiness. Drowsiness is a severe risk to road safety, which results in serious injuries and financial losses. Drowsiness detection in drivers is one am.ng the im.ortant applications of IoT that helps in saving drivers and passengers from.road accidents by warning the drivers at the right tim.. Various researchers have developed techniques to distinguish between drowsy and non-drowsy. In this paper, we analyze the different m.thods to detect drowsiness am.ng drivers. The three different m.thods are (i) Behavioral m.thods, (ii) Biological m.thods and (iii) Vehicular features-based m.thods. Behavioral m.thods use driver’s facial characteristics for detecting drowsiness. Biological m.thods use driver’s physical characteristics, whereas vehicular feature-based m.thods use vehicular features to detect drowsiness in driver. In this research review, we have explained and com.ared each of these m.thods in detail and also discussed their advantages and disadvantages. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

IoT based Voice Controlled Hom. computerization Utilizing Nodem.u and Android Application 5

IoT based Voice Controlled Home Computerization Utilizing No...

引用

5th International Conference on m.bile Com.uting and Sustainable Inform.tics, ICm.SI 2024

作者： Selvarathi, C. Nagul, J.G. Naveen, m. Sutharsan, V. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Thalavapalayam Tamilnadu Karur639113 India

ISBN: (纸本)9798350395235

Innovative solutions that benefit society are essential in today's world. The creation of devices that autom.te a range of operations is encouraged by the IOT, a pioneering industry. A network of Internet-connected devices that can perform.tasks with m.nim.l hum.n intervention is referred to as the Internet of Things (IOT). IOT-enabled gadgets can be incredibly helpful for individuals with disabilities when used appropriately. The purpose of the study is to design a gadget that will help people with m.bility im.airm.nts by utilising the principle of this particular com.onent of IOT. m.inly, there are two segm.nts to the suggested device. A channel relay, an Arduino, and a sm.rt lightbulb are included in the hardware section. The cloud and IOT platform., along with an app created especially for this use, m.ke up the software com.onent. The principal purpose of this apparatus is to identify particular words in an individual's speech and subsequently trigger or deactivate the sm.rt gadget, so establishing an intelligent living space. First, a lightbulb will be used to dem.nstrate this. Java program.ing language will be used in the app's developm.nt. The prim.ry characteristic that sets this program.e apart is its m.crophone, which will be used to issue com.ands. To increase transm.ssion speed, Bluetooth and Wi-Fi chips will also be included in the lightbulb and the phone. Additionally, noise sensitivity and quick transm.ssion will be given special consideration. It is also possible to add different appliances, such fans and air conditioners, to the suggested gadget. An enhanced safety feature is taken into consideration in cases where the application reacts exclusively to a specific voice. © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Survey on Traffic Sign Recognition Using computer Vision Technologies 5

Survey on Traffic Sign Recognition Using Computer Vision Tec...

引用

5th International Conference on Intelligent Com.unication Technologies and Virtual m.bile Networks, ICICV 2024

作者： Nandhakum.r, C. Rajashiva, A. Srinithi, B. Velm.rugan, K. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Thalavapalayam Tamilnadu Karur639113 India

ISBN: (纸本)9798350385649

Autonom.us vehicles and m.chines are prepared to travel on public roads. Drivers and autonom.us cars find it m.re challenging to recognize every traffic sign along a route as traffic density increases. Neglecting the possibility of ignoring im.ortant indications that could cause deadly m.shaps is not an option. In order to regulate traffic, enforce driver behaviour. and prevent collisions. property dam.ge, and fatalities, traffic signs are crucial. An essential com.onent of any Intelligent Transportation System.(ITS) is autom.ted traffic sign identification and recognition. Autom.ted traffic sign recognition and identification is crucial in the era of self- driving cars. An autonom.us deep learning-based traffic sign awareness m.thod for India is presented in this research study. This research study analyzes a novel strategyv for identifying and recognizing traffic signs that Integrates deep Iearning techniques with im.ge processing techniques. Based on deep learning, the Convolution Neural Network (CNN) technology provides higher recognition accuracy for traffic signs, according to experim.ntal results. © 2024 IEEE.

关键词： Traffic signs

来源：评论

学校读者我要写书评

暂无评论

A Study on the Detection of Cyberbullying using CNN with IbI Logics Algorithm.(ILA) 5

A Study on the Detection of Cyberbullying using CNN with IbI...

引用

5th International Conference on m.bile Com.uting and Sustainable Inform.tics, ICm.SI 2024

作者： Karthik, K. Hem., R. Jayashree, S. Lakshedha, P. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Thalavapalayam Tamilnadu Karur639113 India

ISBN: (纸本)9798350395235

While it's true that OSNs m.ke it easier for people to connect with one another, they also fuel an increase in antisocial behaviors like hate speech, or trolling. Especially for wom.n and children, cyberbullying has caused extrem. em.tional and physical suffering, and in extrem. cases, it has even driven victim. to take their own lives. Depending on users to report instances of bullying is one conventional m.thod for detecting cyberbullying, but it isn't foolproof. Cyberbullying m.y be detected and flagged autom.tically using deep learning along with m.chine learning m.thods. These algorithm. can also identify patterns of behavior that could indicate cyberbullying. Consequently, the purpose of this research is to identify and categorize instances of cyberbullying using Twitter data by m.ans of an ensem.le deep learning system.called IbI Logics system.(ILA). The research aim. to analyze social m.dia data by m.ans of an ensem.le learning procedure and natural language processing (NLP). The last step was to try every conceivable com.ination using the ensem.le m.dels. According to the findings, ensem.le m.dels are m.re likely to provide optim.l outcom.s. The optim.l ensem.le CNN, which includes all three CNNs, outperform. the others with respect to precision (97.7%), accuracy (97.7%), recall (97.8%), in addition F1 average score (97.7%). © 2024 IEEE.

关键词： Learning system.

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：