检索结果-内蒙古大学图书馆

5th International Conference on IoT Based Control Networks and Intelligent System., ICICNIS 2024

作者： Ram.a Shri, G. Aathika Erfana, S. Devadharshini, A. Harinika, A. Keerthana, G. M. Kumarasamy College of Engineering Thalavapalayam Department of Computer Science and Engineering Tamil Nadu Karur639113 India

ISBN: (数字)9798331518097

ISBN: (纸本)9798331518097

This project deals with issues and risks that the drivers face especially while overtaking big vehicles in the way. While facing this challenge, a solution aim.d at enhancing the safety on roads. Our technology uses a wireless cam.ra m.unted at the front side of the autom.bile and transm.ts live feed onto a screen at the rear side of the vehicle and achieves the see-through effect. This would ensure the passing of the car with a view to oncom.ng traffic, thus reducing accidents and collisions through sudden braking or unsafe overtaking. This project designed a prototype in which the vehicle is controlled through Bluetooth using an Android application for controlling a vehicle. The four gear m.tors connected to the m.crocontroller on the receiver side enable the vehicle to m.ve. © 2024 IEEE.

关键词： Liquid crystal displays

来源：评论

学校读者我要写书评

暂无评论

Recurrent Neural Network Analysis of Optom.try Data

Recurrent Neural Network Analysis of Optometry Data

引用

2024 IEEE International Conference on Intelligent Com.uting and Em.rging Com.unication technologies, ICEC 2024

作者： Sharm., Avinash Barua, Tarkeshwar Saxena, Rini Goswam., m.nish Goyel, Parul Chandigarh Group of Colleges Chandigarh Engineering Department of Computer Science and Engineering 140307 India Roorkeee Institute of Technology Department of Computer Science and Engineering Roorkee India Chandigarh Pharmacy College Chandigarh Group of Colleges 140307 India M. M. Engineering College Maharishi Markandeshwar Mullana Computer Science & Engineering Haryana Ambala1307 India

ISBN: (纸本)9798331508432

This survey explores the potential of recurrent neural networks (RNNs) for analyse eye-trailling data, generally data obtained from.Optom.try system.. RNNs stand out at distinguishing patterns in consecutive data, m.king them.appropriate for tasks like foretell future gaze, distinguishing areas of interest, and detecting anom.lousness in gaze patterns. The abstract synopsis the process of probing Optom.try data using RNNs. It highlights data pre-processing steps like cleaning, form.tting, and norm.lization. The assortm.nt of an LSTm.network edifice and hyperparam.ter tuning for optim.l execution are discussed. breeding and evaluation operation are explained[12], including using separate breeding, validation, and testing sets. Finally, the abstract m.ntions potential computer applications of the analysis, including hum.n-computer interaction(HCI) (HCI) optim.zation and individual behavior understanding. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

QR Code with Block Chain technology for m.dical Device Ownership 9

QR Code with Block Chain Technology for Medical Device Owner...

引用

9th International Conference on Advanced Com.uting and Com.unication System., ICACCS 2023

作者： m.kanyadevi, K. Rithika, S. Biratheep, S. Subanki, S. M. Kumarasamy College of Engineering Department of Computer Science and Engineering Tamilnadu Karur India

ISBN: (纸本)9798350397376

m.dical device quality and safety are im.ortant because they affect people's lives and health, and society has placed a high value on these factors. Healthcare supply chain has been m.jorly intruded for fake m.dical devices and technologies. Products that are counterfeited are frequently created to reach profit from.the original product's lower price. Because of its high risk, a traceability system.m.st be set up. m.st businesses are m.king greater efforts to prevent counterfeiting. The QR code system.presented in this project is application-, security-and privacy-focused. The existing system.uses non-fungible token (NFT) based solution that enhances the tokenization protocols. In our paper we propose the usage of QR technology. It is easy and affordable to create a QR code for a m.dical device's identification. Because QR codes are sim.le to use. This system.stores the inform.tion in decentralized storage of the Blockchain technology system.to verify the legitim.cy of m.dical equipm.nt, ensuring that users are not dependent on outside apps. Blockchain which is defined as the distributed ledger system.that is based upon apowerful cryptographic technique and is used to capture and preserve inform.tion about m.dical devices, m.king it difficult for anybody to tam.er with them. Along with Blockchain, the usage of decentralized system.m.kes the privacy of the data m.re effective. The paper also allows the custom.r end to view and verify the m.dical device ownership. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

tech-Enabled Altruism. Harnessing technology in Social m.dia for Food Waste Reduction 3

Tech-Enabled Altruism: Harnessing Technology in Social Media...

引用

3rd IEEE Delhi Section Flagship Conference, DELCON 2024

作者： Sujatha, E. Jayanthi, m. Sandeepa, N. Raju, D. Naveen Nagaraj, S. Department of Computer Science and Engineering Chennai India Rajalakshmi Engineering College Department of Computer Science and Business Systems Chennai India R. M. K. Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798331518592

Altruistic Connections is a pioneering social m.dia platform.that am.lgam.tes the functionalities of popular networking applications with a unique em.hasis on fostering altruistic endeavors. Drawing inspiration from.established platform. like Instagram. this project introduces a distinct dim.nsion by enabling users not only to share their stories and experiences but also to engage in philanthropic activities seam.essly. The platform.facilitates direct com.unication through m.ssaging, creating a com.unitydriven space where users can connect over shared values and altruistic initiatives. Users can post, like, save, and com.ent on content while also exploring and participating in a m.rketplace specifically designed for charitablecontributions. The technical architecture of 'Altruistic Connections' ensures a secure and user-friendly experience. Robust m.ssaging features, seam.ess posting m.chanism., and an integrated altruistic m.rketplace form.the core of the platform. Em.hasis is placed on privacy and data security, aligning with the trust users place in the com.unity. Strategies for user acquisition involve collaborations with philanthropic influencers, engagem.nt with altruistic com.unities, and partnerships to expand the platform.s reach. The project's financial sustainability is achieved through potential collaborations with philanthropic organizations and businesses that align with the spirit of altruism. Addressing potential challenges related to the verification of charitable activities, transaction security, and content m.deration, the platform.im.lem.nts rigorous m.asures to create a trustworthy and fulfilling environm.nt. The abstract concludes by em.hasizing the com.itm.nt of 'Altruistic Connections' to redefine social m.dia engagem.nt through technology, altruism. and the power of com.unity. An altruistic m.rketplace form. the core of the platform. Em.hasis is placed on privacy and data security, aligning with the trust users place in the com.unity. © 2024

关键词： m.rketplaces

来源：评论

学校读者我要写书评

暂无评论

Resilient Kannada Scene Text Detection: CRAFT-YOLOv8 Fusion 18

Resilient Kannada Scene Text Detection: CRAFT-YOLOv8 Fusion

引用

18th INDIAcom.11th International Conference on Com.uting for Sustainable Global Developm.nt, INDIACom.2024

作者： Paul, Anoshor B. Vikrant, G. Sai Um.devi, V. B. M. S. College of Engineering Dept. of Computer Science Bengaluru India

ISBN: (纸本)9789380544519

The extraction of text from.natural scene im.ges is an increasingly vital task in computer vision, with applications spanning num.rous dom.ins. This study introduces a sim.le and effective m.thod tailored for detecting Kannada text in com.lex scene im.ges, extendable to use in any Indian language. This paper presents a novel approach for Kannada scene text detection that com.ines the CRAFT (Character Region Awareness for Text Detection) algorithm.for text annotation generation with the YOLOv8 (You Only Look Once) m.del for text detection. The paper details a sim.le im.lem.ntation of the aforem.ntioned algorithm. addressing challenges such as varying text sizes, orientations, and com.lex backgrounds. The dataset annotation process was stream.ined and optim.zed, saving significant tim. com.ared to traditional m.thods. To com.ensate for the scarcity of Kannada text datasets, a custom.Kannada scene im.ge dataset was curated. This dataset offers diverse real-world scenarios for testing the m.del. The m.del achieved an accuracy of 85.30% m.P at a 0.6 Intersection Over Union (IoU) threshold on the training-validation dataset and a com.endable 80.10% m.P across a diverse set of Kannada test im.ges. The prim.ry objective of this paper is to furnish researchers with an accessible m.thodology for detecting local Indian languages in scene im.ges and to further extend this research to the developm.nt of m.re sophisticated text extraction tools, benefiting a diverse range of digital applications. © 2024 Bharati Vidyapeeth, New Delhi.

关键词： CRAFT Detection Kannada Scene Text YOLO

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 Novel Ensem.le Classifier Fram.work to Preprocess, Learn and Predict Im.alanced Heterogeneous Drifted Data Stream 2

A Novel Ensemble Classifier Framework to Preprocess, Learn a...

引用

2nd International Conference on Electrical, Electronics, Inform.tion and Com.unication technologies, ICEEICT 2023

作者： Paulraj, D. Vigilson Prem. m. R. M. K. Engineering College Department of Computer Science and Engineering Chennai India R. M. K. College of Engineering and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350397635

Organizations nowadays are producing huge size of data stream. whose velocity is extra-ordinary, at a rapid speed. m.ning data on stream.data is a topic of great interest to the research com.unity and has a great effect of a different types of applications. These applications include banking, com.unication technologies, field of learning, estim.tion of forthcom.ng weather, sensors, social m.dia, and so on. However, Internet of Things (IoT) and sm.rt devices generates enorm.us volum. of data stream. that are entirely heterogeneous in nature. The size, rapidity, pattern and category of these data stream. are all non-stationary and highly vulnerable to concept drift. It is a significant problem. considering the realm.of data m.ning in stream.data. However, one significant and challenging issue in stream.data m.ning is how to deal with the concept drifts, to the sam. degree, sudden, gradual and increm.ntal drifts, which happens explosively. Additionally, the problem.of stream.ng data classification of nonlinear data stream.can only be partially solved by the current m.thodologies. m.st of the works consider fixed size blocks, chunks or windows of hom.geneous data stream.to address the issues of the concept drift. Thus, a novel ensem.le classifier is therefore necessary in order to accurately classify heterogeneous stream.of data while swiftly changing to different sorts of concept drifts. This works proposes a novel m.thod, Ensem.le Classifier Fram.work for the detection and learning of concept-drift in addition to the classification in heterogeneous data stream. This work further presents a solution to deal with dynam.c occurrence of concept drift. © 2023 IEEE.

关键词： Classification (of inform.tion)

来源：评论

学校读者我要写书评

暂无评论

Stirring Squeeze of Alum.nium.Alloy m.tal m.trix com.osites using optim.l prediction process

引用

m.terials Today: Proceedings 2022年 69卷 1425-1430页

作者： Swathi, D. Kalpana, V. Selvarathi, C. Rajendran, Sasikum.r Department of Computer Science and Engineering K.Ramakrishnan College of Engineering Trichy India Department of Computer Science and Engineering M. Kumarasamy College of Engineering Karur India

Alum.num.is regarded as a widely used m.terial for m.nufacturing com.onents in the industrial and other m.nufacturing sectors due to the necessity for lightweight and strong m.terials. But over the years, alum.nium.m.terials have been studied in an effort to im.rove their m.chanical characteristics. Due to the incorporation of reinforcem.nts, hybrid m.trix com.osites are thus introduced to enhance the m.chanical properties. In this study, nanoscale reinforcing particles are used to prepare an alum.nium.hybrid m.tal m.trix com.osite. Alum.num.is regarded as an effective m.nufacturing m.terial, and m.tal production involves m.ltiple levels of hybridization. In the current study, titanium.carbide, alum.nium.oxide, and silicon nitride nanoparticles hybridise with alum.nium.alloy 2219 with 94 % of the original m.terial. The proposed reinforced m.terial is produced using the stirring-squeeze casting process, an innovative type of casting that is used to construct the reinforcem.nts. The benefit of this squeeze casting m.thod is that it has a lower defect rate than traditional casting m.thods. After fabrication, m.chanical testing is done to check the m.nufactured specim.ns' qualities under loading circum.tances. With an intender ball of 5 m. diam.ter and a 250 kg loading condition, the m.terial's tensile strength and hardness are tested on a universal testing equipm.nt. One of the sim.lest ways to determ.ne the error rate of a result from.experim.nts using m.chine learning is to use the statistical approach of analysis. So, in order to im.rove the m.chanical properties, this research develops a statistical analytic m.thod for optim.sing the process param.ters. For optim.sing the stirring-squeeze casting process's process param.ters, the m.ta-heuristic m.thod is proposed. Finally, the com.arison of experim.ntal and expected results brings the result to a close. According to the com.arison's findings, the suggested m.terial com.osition has the highest level of m.chanical qu

关键词： Taguchi m.thods

来源：评论

学校读者我要写书评

暂无评论

Autom.ted Sem.ntic Interpretations in Web Applications via Cloud Com.uting Aspects

Automated Semantic Interpretations in Web Applications via C...

引用

2024 International Conference on Com.unication, computer sciences and engineering, IC3SE 2024

作者： Preethi, D. m.hta, Poornim. Sood, Devendra Department Of Computer Science And Information Technology Bangalore India Noida Institute Of Engineering And Technology Department Of It And M. Tech Integrated Uttar Pradesh Greater Noida India Tula's Institute Department Of Computer Science And Engineering Dehradun India

ISBN: (纸本)9798350366846

The creation and execution of applications in several disciplines have been greatly aided by the integration of cloud com.uting and sem.ntic web technologies. Although they are independent entities, they m.y also be com.ined in m.ny ways to provide answers - a subject that has been thoroughly researched lately. The num.er of 'new cloud providers, applications, facilities, m.nagem.nt system., and data' has significantly increased in recent years. The com.lexity that has resulted from.this expansion em.hasises the need for new technology in order to efficiently m.nage and support these varied and m.ny services and resources. As a result, difficulties with 'cloud services and resources' transferability, com.atibility, security, choice, negotiation, identity, and specification m.ght arise. Sem.ntic technologies are a vital tool for reassessing these issues because of their enorm.us 'cloud com.uting' capacity. This study uses a variety of sources to exam.ne and evaluate the im.act of 'Sem.ntic-Web technology' in the cloud. m.reover, a cloud-based engagem.nt strategy shows how we m.y leverage the features and advantages of cloud com.uting to build the sem.ntic web and provide autom.tic sem.ntic annotations to online applications on a large scale. © 2024 IEEE.

关键词： Sem.ntic Web

来源：评论

学校读者我要写书评

暂无评论

A Survey on Recom.endation System.for Future Researchers using Classifiers 6

A Survey on Recommendation System for Future Researchers usi...

引用

6th International Conference on Inventive Com.utation technologies, ICICT 2023

作者： m.rugesan, m. Nandhakrishnan, G. Saran, S. Venis, C. Department of Computer Science and Engineering M. Kumarasamy College of Engineering Thalavapalayam Tamilnadu Karur639113 India Department of Computer Science and Engineering M. Kumarasamy College of N. Engineering Thalavapalayam Tamilnadu Karur639113 India

ISBN: (纸本)9798350398496

Recom.endation system.has revolutionized how users and websites com.unicate, becom.ng m.re and m.re vital. There are num.rous uses for recom.ender system. in a variety of industries, including the econom.cs, education, and science. The am.unt of digital inform.tion is growing swiftly due to the quick growth of inform.tion technology. Using big data analysis techniques, researchers use search engines like Google and Bing to find and filter m.terial such as m.vies, m.sic, and articles. To assist these academ.cs, digital libraries like Pubm.d, DBLP, and arXiv offer sophisticated search interfaces;however, users m.st initiate the search process them.elves. Therefore, taking into account the general trends of com.unities and specific interests, a tool is very helpful to actively discover and recom.end the m.st intriguing research articles. The problem.of locating the m.st relevant research publications for a specific academ.c is looked into. Existing solutions are unable to adequately address the suggestions of new publications since there is a dearth of previous data. As a result, this study on recom.endation algorithm. include algorithm. for collaborative filtering. Additionally, a hybrid recom.endation algorithm.is created to incorporate real-tim. sm.leys, ratings, reviews, and tem.oral considerations. © 2023 IEEE.

关键词： Recom.ender 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：