检索结果-内蒙古大学图书馆

2022 International Conference on Advancements in Smart, Secure and Intelligent Computing, ASSIC 2022

作者： Pandian, Saran Chaurasia, Uttkarsh Ranjan, Shudhanshu Saxena, Shefali Daiict Data Science Gandhinagar India Nit Dept. of Computer Science and Engineering Hamirpur India Presidency University Dept. of Computer Science and Engineering Banglore India Nit Dept. of Electronics and Communication Hamirpur India

ISBN: (纸本)9781665461092

Graph neural networks(GNN) are a special variant of neural networks which help in dealing with unstructured data such as graph data. The advent of the GNN has helped in dealing with problems in different domains, especially in the domain of Natural Language Processing(NLP). In NLP, GNNs are used to implement tasks such as text classification which has a wide variety of applications. There are two ways to represent the text data using GNN namely, Inductive and transductive. In this paper, we apply the approach of the inductive model using different variants of GNN. We observed that the GAT variant gave better performance compared to other variants. Moreover, we observed that the complexity of the model and the dataset size influences the entropy of the output. © 2022 IEEE.

关键词： Entropy

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Mobile Application for Intelligent Attendance Tracking 1

Design and Implementation of a Mobile Application for Intell...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Kaushik, Priyanka Nadhiya, S. Jain, Deepak Verma, Anupama Kumar, Saurabh Bhavadharani, S. Chandigarh University Dept. of Computer Science Engineering Chandigarh India Dhanalakshmi Srinivasan College Dept. of AI & Data Science Coimbatore India IIM Indore Dept. of Management Indore India Usha Martin University Dept. of Business Management & Comm Jharkhand India Mangalayatan University Dept. of Business Management & Commerce Aligarh India A.H. Edu. & Research Dept. of Commerce Meenakshi Chennai India

ISBN: (纸本)9798350356816

Taking attendance is an important task in schools, universities, and other institutions. However, traditional attendance taking methods such as paper-based attendance sheets or manual entry into an electronic system are time-consuming and prone to errors. In recent years, the emergence of facial recognition technology has opened up new possibilities for attendance management systems. This research paper discusses the development and implementation of a Smart Attendance System using Facial Recognition technology using OpenCV in educational institutions. The study explores the benefits, limitations, and ethical considerations associated with this technology and its implications for the future of attendance management systems. This model takes use of LBPH and gja, exfilaface recognition to increase accuracy over conventional models. After this, the connection of recognized faces is compared with the kdatabase containing student's faces. This model will be an effective method for controlling student attendance. © 2024 IEEE.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Smart City Solutions Leveraging Internet of Things (IoT) Technology 1

Smart City Solutions Leveraging Internet of Things (IoT) Tec...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Kumawat, Bhawesh Shalini, E. Tomar, Vinay Upadhyay, Rajesh Kumar Gupta, Divyanshu Geetha, P.V. Madhav University Dept. of CSE Pindwara India Meenakshi A.H. Edu. & Research Dept. of Computer Science Chennai India Jiwaji University Dept. of Chemistry Gwalior India Usha Martin University Dept. of EEE Jharkhand India J.S. University Dept. Electronics & Comm. Engineering Shikohabad India Dhanalakshmi Srinivasan College Dept. of AI & Data Science Coimbatore India

ISBN: (纸本)9798350356816

The widespread adoption of the Internet of Things (IoT) is facilitating the development of Smart City initiatives globally. Everyday objects are increasingly equipped with electronic gadgets and connected through various protocol suites, becoming part of a vast network. According to a recent Gartner study, by 2020, smart cities are projected to deploy 50 billion connected devices. This advancement is expected to make urban environments more adaptive and resilient to future changes. This paper explores current and future trends in smart cities and IoT, highlighting the technologies and applications driving their growth. We examine how the expansion of IoT directly impacts the evolution of smart cities and discuss the interplay between the two, as well as the factors motivating their development. Smart cities have the potential to reduce manual labor, mitigate disaster risks, and streamline daily life. Lastly, we address some of the challenges associated with IoT in the context of smart cities and propose potential solutions to these issues. © 2024 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

Next Generation Intelligent Traffic Signal Control: Empowering Electronics Consumers with Edge-AIoT Capabilities

引用

IEEE Transactions on Consumer Electronics 2025年第1期71卷 1926-1934页

作者： Chavhan, Suresh Doswada, Rohit Gupta, Deepak Gunjal, Saymam Rodrigues, Joel J.P.C. School of Data Sciences Indian Institute of Science Education and Research Kerala Thiruvananthapuram India C-DoT Karnataka Bangalore India Dept. of Computer Science and Engineering Maharaja Agrasen Institute of Technology Delhi India Centre for Research Impact and Outcome Institute of Engineering and Technology Chitkara University Punjab India Department of Computer Science and Engineering University of Visvesvaraya College of Engineering Karnataka Bangalore India Federal University of Piaui PI Teresina Brazil

Traffic congestion has become a major issue that is being faced by the majority of road users. The increasing vehicle usage, and the lack of space and funds to construct new transport infrastructure, further complicates the issue. In this scenario, it is important to come up with an intelligent and economical solution that improves the quality of road users' service. The problem with the traffic handling framework is signal timings are fixed which is not adaptive to the density of vehicles. To address this issue we propose an Edge-Augument Artificial Intelligence of Things (AIoT) road user cooperation for traffic management. The proposed system efficiently utilizes electronic devices to learn and adapt to changing traffic conditions in real-time. By optimizing the traffic signal timings based on the actual traffic conditions, adaptive systems reduce delay, improve traffic flow, reduce fuel consumption and pollution, and improve the electronics consumers' and road users' experiences. The proposed system has been tested with real-time experiments by integrating Electronic devices like cameras, smartphones, and AGX Xavier (edge device) with Cloud (ThingSpeak). The proposed system is verified by simulating the proposed system in the SUMO traffic simulator and its reliability is concluded by comparing the waiting time, depart delay, running, and halt time with the existing traditional method. © 2025 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

A Framework for Identifying Emotions in Text through Machine Learning and Natural Language Processing Methods 1

A Framework for Identifying Emotions in Text through Machine...

引用

1st IEEE International Conference on Advances in Computing, Communication and Networking, ICAC2N 2024

作者： Kaushik, P. Damodaran, B. Reshma, P. Ganguli, Ranjan Shyamu Kajla, Amar Chandigarh University Dept of CSE AIML-CSE Chandigarh India Meenakshi A.H.E.R Dept. of Psychology Chennai India Dhanalakshmi Srinivasan College of Engineering Dept. of AI & Data Science Coimbatore India Usha Martin University Dept. of CSE Jharkhand India J.S. University Dept. of Computer Science Shikohabad India Chandigarh University India Dept. of CSE Chandigarh India

ISBN: (纸本)9798350356816

This research introduces an innovative approach that leverages machine learning and natural language processing (NLP) techniques to detect emotions in text. The proposed system, equipped with a Google Chrome extension, allows users to easily and rapidly evaluate the emotional content of the websites they browse. By employing various NLP methods, including keyword extraction and tokenization, the system effectively extracts relevant features from the text. These features are then used to train a machine learning model capable of accurately predicting the emotional tone of new text. The system demonstrates exceptional accuracy across several benchmark datasets and proves its practical utility in real-world applications. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Advanced Deep Learning Approaches for Content-Based Image Retrieval System in Skin Cancer Diagnostics

Advanced Deep Learning Approaches for Content-Based Image Re...

引用

2024 International Conference on Intelligent Computing and Sustainable Innovations in Technology, IC-SIT 2024

作者： Margret, Issac Neha Kasetty, Sai Bhargav Sudha, Nuthalapati Ojha, Rajesh Kumar Madhuri, K. Sai Rajakumar, K. V.I.T University SCOPE Tamilnadu Vellore India CYS VNR VJIET Dept. of CSE - DS AI&DS Telangana Hyderabad India Silicon University Dept. of Computer Science & Engineering Odisha Bhubaneswar India BVRIT Dept. of CSE - Data Science Telangana Narsapur Hyderabad India

ISBN: (纸本)9798350369175

The objective of this paper is to develop and assess the performance of a deep learning model-based content skin cancer detection image retrieval system. In this regard, CNN, VGGNet, ResNet, DenseNet, InceptionNet, and MobileNet were tested on recall, accuracy, mean average precision, F1, and precision metrics. VGGNet performed best among them, with an accuracy of 92.3%, outperforming all other models in precision, F1-score, and recall. CNN also gave the best performance with 91.5% accuracy. The CBIR system retrieved relevant images for the given lesions, especially melanoma lesions, which were relevant and high in precision within the top 5 retrieved images. These results also confirm the efficiency of CNN and VGGNet in enhancing accuracy during the retrieval of skin cancer diagnosis images. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

FedERA: Framework for Federated Learning with Diversified Edge Resource Allocation 2

FedERA: Framework for Federated Learning with Diversified Ed...

引用

2nd IEEE International Conference on Federated Learning Technologies and Applications, FLTA 2024

作者： Borthakur, Anupam Kasliwal, Aditya Manna, Asim Dewan, Dipyan Sheet, Debdoot Centre of Excellence in Artificial Intelligence Indian Institute of Technology Kharagpur West Bengal India Dept. of Data Science and Computer Application Manipal Institute of Technology Karnataka Manipal India

ISBN: (纸本)9798350354812

Federated Learning (FL) is a distributed machine learning (ML) approach that allows multiple devices to train a model while keeping training data private on edge devices. However, existing FL libraries are incapable of: (i) supporting a wide range of existing FL algorithms, (ii) handling diverse public as well as custom datasets, (iii) discarding unreliable updates from malicious edge devices, (iv) facilitating edge-device training, and (v) implementing model compression to reduce communication overhead. With the rapid progression in AI, there is an increment in the computation power while training the models on edge devices which results in more carbon emission (CE). However, in most of the existing FL frameworks, there is no module for estimating CE. In this paper, we present FedERA, a modular and fully customizable open-source FL framework aiming to address these issues especially also by offering extensive support on heterogeneous edge devices and by incorporating both standalone and distributed training approaches. The integration of new software modules unforeseen in existing FL frameworks not only amplifies the scope of its usability but also fosters environment-friendly FL. We believe that FedERA will be a valuable tool for researchers and practitioners working in FL. ©2024 IEEE.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition Using Multi-Block Deep CNN 5

Facial Expression Recognition Using Multi-Block Deep CNN

引用

5th International Conference on Circuits, Control, Communication and Computing, I4C 2024

作者： Priyadarshini, V. Srinivasulu Reddy, U. Reddy Chirra, Venkata Rami Mrudula, M. Suneetha, M. National Institute of Technology Dept. of Computer Science & Engineering Andhra Pradesh India Machine Learning & Data Analytics Lab National Institute of Technology Dept. of Computer Applications Tiruchirappalli India School of Computer Science & Engineering VIT-AP University Amaravathi India Malla Reddy College of Engineering Department of CSE Telangana India Independent Researcher Amaravati India

ISBN: (纸本)9798331528539

Emotions play a crucial role in decision-making, moral judgments, and other cognitive processes. The goal of this work is to identify people's facial emotions from face images. Facial expression recognition (FER), a highly diverse field with many commonalities between classes, is a challenging problem. The capabilities of current FER systems are limited in this regard. In this work, a multi-block Deep Convolutional Neural Networks (DCNN) model was proposed to identify facial expressions. Five blocks with different computational components were defined in a multi-block DCNN to extract the unique characteristics from input images. The second model (DCNN-SVM) is developed with an ensemble of SVM classifier to improve predictability and stability. The third model (DCNN-MV) is based on the majority voting with 4 classifiers SVM, KNN, Random Forest, and Decision Tree. The CK+ dataset was utilized and expanded via image data augmentation to enhance model performance and generalization. By adjusting hyperparameters, the suggested DCNN model's accuracy was investigated. The DCNN model reports an accuracy score of 97.71%. Both DCNN-SVM and DCNN-MV models achieved 97.79% accuracy. On the CK+ dataset, the proposed models demonstrated good accuracy in identifying facial expressions. When compared to existing models, the proposed model outperformed existing models in terms of accuracy. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Smart framework for enhancing security of IoT linked devices in Healthcare Systems 5

Smart framework for enhancing security of IoT linked devices...

引用

5th International Conference on Information Management and Machine Intelligence, ICIMMI 2023

作者： Duvey, Anurag Anand Rahi, Pankaj Gowri Ganesh, N.S. Basa, Santi Swarup Dept. of Artificial Intelligence & Data Science Poornima Institute of Engineering and Technology Jaipur India Health Information Technology Management Indian Institute of Health Management Research Bangalore India Dept. of Artificial Intelligence & Data Science Saveetha Engineering College Chennai India Dept. of Computer Science Maharaja Sriram Chandra Bhanja Deo University Odisha Baripada India

ISBN: (纸本)9798400709418

The adoption of blockchain technology is widespread across diverse industries due to its rapid advancement and high level of innovation. The technology in question is widely acknowledged for its ability to adapt and be utilized in diverse domains, thereby enabling the storage of data in interconnected fields through peer-to-peer networks. Blockchain technology demonstrates high performance in the storage of transactions that have minimal digital traces, as well as in situations where there is a need for immutability and transparency. The utilization of blockchain technology can potentially offer advantages in various domains such as supply chain management, the maintenance of dynamic patient authorization for data use, and the verification of patient, provider, or supplier identification in certain situations. The main objective of this research study is to investigate the application of blockchain technology in improving the security of Internet of Things (IoT) systems, particularly in the context of remote patient monitoring and its linked EHR system. This article explores the advantages of incorporating Internet of Things (IoT) devices into the remote patient monitoring practice, as well as the practical challenges that may arise during the installation phase. The proposed concept utilizes sophisticated and effective cryptographic methodologies, particularly the Advanced Encryption Standard (AES) scheme, to guarantee dependable data transmission across networks and safeguarded storage within cloud environments. © 2023 ACM.

关键词： Smart contract

来源：评论

学校读者我要写书评

暂无评论

Cascading Effects: Analyzing Project Failure Impact in the Maven Central Ecosystem

Cascading Effects: Analyzing Project Failure Impact in the M...

引用

International Mining Software Repositories, MSR

作者： Mina Shehata Saidmakhmud Makhkamjonoov Mahad Syed Esteban Parra Dept. of Math Computer Science and Data Science Belmont University Nashville TN USA

ISBN: (数字)9798331501839

ISBN: (纸本)9798331501846

This study examines failure propagation within the Maven Central ecosystem, a critical software dependency repository, through a comprehensive analysis of dependency networks using the Goblin framework. Our dual-sampling methodology, investigating both top dependencies and random libraries, revealed two distinct failure propagation patterns that pose significant risks to ecosystem stability. Core infrastructure failures, particularly evident in cases like the AWS SDK family, can create immediate and widespread disruption. These libraries have many direct dependents - averaging 20,402 projects that would break immediately if the library fails. Furthermore, these core libraries themselves have extensive dependencies, with the AWS SDK family depending on 377 other libraries itself. The impact of failures spreads deeply through the ecosystem, with dependency chains reaching an average of 90.80 levels. Our analysis of peripheral projects reveals their significant cascading effects, with higher average dependency dept.s of 54.25 levels and chain lengths extending to 116.74 levels, as exemplified by cases like ***:camel-swagger-java, which demonstrated a maximum chain length of 647 levels. Our findings highlight specific vulnerabilities in dependency network structures, showing that ecosystem resilience requires both protecting core infrastructure and managing dependency complexity.

关键词： Software maintenance Ecosystems Power system protection Focusing Libraries Stability analysis Complexity theory Protection Power system faults Resilience

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：