检索结果-内蒙古大学图书馆

2023 International Conference on System, Computation, Automation and Networking, ICSCAN 2023

作者： Sofia, R. Murali, R. Sambathkumar, R. Navinkumar, B. Sivaraj, K. Manakula Vinayagar Institute of Technology Department of Electronic and Communication Engineering Puducherry India

ISBN: (纸本)9798350315127

Diabetes is a chronic disease that affects millions of people worldwide. Machine learning techniques have been used to predict diabetes with high accuracy using clinical and lifestyle data. In this study, we propose a low-cost diabetes level prediction system using machine learning. The system will use a dataset of clinical and lifestyle data to train and test machine learning algorithms, including decision tree, random forest, and neural network. The proposed system aims to achieve high accuracy in diabetes prediction while minimizing the cost of implementation. The system will be implemented as a smart web application that can be accessed by healthcare professionals and patients. The results of this study will contribute to the development of low-cost and accessible diabetes prediction systems that can improve the quality of life of patients with diabetes. (Abstract) © 2023 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Elevated-temperature dry sliding wear behaviors of dual-cathode HiPIMS TiN and TiZrN films

引用

Emerging Materials Research 2025年第1期14卷 98-106页

作者： Lin, Yu-Tse Liu, Wen-Chung Kuo, Chin-Chiuan Department of Power Mechanical Engineering National Formosa University Huwei Yunlin County Taiwan Department of Mechanical and Computer Aided Engineering National Formosa University Huwei Yunlin County Taiwan Graduate Institute of Aeronautical and Electronic Engineering National Formosa University Huwei Yunlin County Taiwan

Titanium–zirconium nitride films with three Zr/Ti ratios (16/35, 22/29, and 25/26) were deposited using Ti and Zr dual-cathode reactive high-power impulse closed-field magnetron sputtering by adjusting the average power ratio of two cathode materials. The sliding wear resistances of the obtained TiZrN films at different temperatures were compared. The results revealed that the ternary TiZrN film exhibited a higher hardness (approximately 35 GPa) and lower elastic modulus (approximately 360–380 GPa) than those of the binary TiN film. This contributed to the lower friction coefficient and wear resistance at room temperature. However, the addition of Zr became disadvantageous with an increase in wear temperature. Above 4008C, the surface hardness of the TiZrN film decreased dramatically with an increase in the Zr fraction. This is attributed to the increased vulnerability of the film to oxidation. Structural discontinuity induced by the inhomogeneous oxidation (a multilayer structure with voids, embedded oxides, and oxynitrides formed in the surface layer) roughened the film surface and reduced the surface strength, which accelerated the wear of TiZrN films at elevated temperature in an ambient atmosphere. Such ternary nitride coatings should not be applied in oxidative high temperature environments without obstructing the oxidation through designed composition and structure. © 2025 Emerald Publishing Limited: All rights reserved.

关键词： Vacuum deposited coatings

来源：评论

学校读者我要写书评

暂无评论

IoT-Assisted AI Framework for Preserving Biodiversity: Monitoring Rare Trees in Dynamic Forest Ecosystems

IoT-Assisted AI Framework for Preserving Biodiversity: Monit...

引用

2025 International Conference on Multi-Agent Systems for Collaborative Intelligence, ICMSCI 2025

作者： Rajan, K. Palanivel Raj, J. Relin Francis Krishnan, R. Santhana Balamuralikrishnan, G. Vidyasree, G. Jothi, J. Nirmal Psna College of Engineering and Technology Department of Electrical and Electronics Engineering Dindigul India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Velammal College of Engineering and Technology Department of Computer Science and Engineering Madurai India Sri Sai Ranganathan Engineering College Department of Computer Science and Engineering Coimbatore India Vel Tech Rangarajan Dr. Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Avadi India

ISBN: (纸本)9798331509828

The preservation of biodiversity, particularly the monitoring of rare tree species in dynamic forest ecosystems, presents significant challenges due to the complexities in detecting and analyzing forest changes. This research introduces a novel IoT -assisted AI framework, termed FoLiA-Net (Forest Lightweight Adaptive Network), designed to improve the efficiency and accuracy of monitoring rare trees. The proposed algorithm combines IoT sensor data with machine learning techniques to adaptively detect, classify, and track rare tree species across large and dynamically changing forest areas. The framework utilizes a lightweight neural network structure to ensure real-time processing while minimizing computational resources, making it suitable for deployment in resource-constrained environments. Simulation experiments were conducted to evaluate the performance of FoLiA-Net in comparison with existing algorithms, including Faster R-CNN (F-R-CNN), Random Forest Classifier (RFC), and Gradient Boosting Machines (GBM). The evaluation was based on several key performance metrics such as accuracy, latency and detection efficiency. The results revealed that FoLiA-Net outperformed the existing algorithms in terms of accuracy and computational efficiency, demonstrating a notable improvement in the monitoring of rare tree species in diverse forest ecosystems. The proposed framework is particularly effective in large-scale forest monitoring, providing a valuable tool for biodiversity conservation efforts © 2025 IEEE.

关键词： Biodiversity Forest Ecosystems Machine Learning Rare Trees Simulation Sustainability

来源：评论

学校读者我要写书评

暂无评论

Hybrid Deep Learning for International Trading: Integrating LSTM and Transformer Models 4

Hybrid Deep Learning for International Trading: Integrating ...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Akhila, T.S. Relin Francis Raj, J. Kani Jesintha, D. Santhana Krishnan, R. Vinoth Kumar, V. Sundaravadivel, P. Dhanalakshmi College of Engineering Department of Electronics and Communication Engineering Chennai India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Electronics and Communication Engineering Chennai India Scad College of Engineering and Technology Department of Computer Science and Engineering Cheranmahadevi India Scad College of Engineering and Technology Department of Electronics and Communication Engineering Cheranmahadevi India Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Electronics and Communication Engineering Chennai India Saveetha Engineering College Department of Artificial Intelligence and Machine Learning Chennai India

ISBN: (纸本)9798331523923

This research proposes a hybrid deep learning model combining Long Short-Term Memory (LSTM) networks and Transformers to enhance decision-making in international trading. The model leverages advanced techniques such as RoBERTa for text tokenization, FinBERT for sentiment analysis, and XLM-Roberta for multilingual language processing. LSTM is employed to analyze sequential numerical data like historical prices and trading volumes, providing accurate price and volatility forecasts. The Transformer component processes textual data to extract sentiment classifications and event-driven market impacts, facilitating a comprehensive understanding of market conditions. A fully connected fusion layer integrates insights from both components, enabling the model to classify market conditions holistically. The optimization process utilizes the Adam optimizer with learning rate scheduling to ensure efficient and effective training. Loss functions like Mean Squared Error (MSE) and Cross-Entropy Loss are employed to optimize numerical predictions and categorical outcomes, respectively. By combining temporal analysis with sentiment-driven insights, this hybrid model offers improved price forecasting, advanced multilingual sentiment analysis, and event-driven market condition predictions. The proposed approach aims to provide traders with actionable insights, enabling more informed decision-making in the highly dynamic and multilingual environment of international trading. © 2025 IEEE.

关键词： Costs

来源：评论

学校读者我要写书评

暂无评论

Next-Gen SDN Security: Quantum Keying Meets AI Analytics

Next-Gen SDN Security: Quantum Keying Meets AI Analytics

引用

2024 International Conference on Distributed Systems, computer Networks and Cybersecurity, ICDSCNC 2024

作者： Virushabadoss, S. Anithaashri, T.P. Nivedha, M. Krishnan, S. Hari Karuppannan, Anand Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Dept. of Computer Science and Engineering Chennai India Arasu Engineering College Department of Electronics and Communication and Engineering Kumbakonam India Sanskrithi School of Engineering Department of Electronics and Communication and Engineering Puttaparthi India Gnanamani College of Technology Department of Electronics and Communication and Engineering Namakkal India

ISBN: (纸本)9798350375442

This paper suggests a complete security architecture that blends quantum key distribution (QKD) with cutting-edge machine learning methods to improve the Software-Defined Networking (SDN) control plane. By creating secure channels of communication through QKD, the framework ensures integrity and secrecy of control messages between the SDN controller and network devices. Furthermore, network traffic is continuously monitored and analyzed using machine learning techniques, enabling the detection of unusual behaviors that might be warning signs of upcoming security problems. Tests utilizing Mininet as the network interface and Open Daylight as the SDN controller proved the efficacy of the suggested method. The outcomes revealed a minimal computational overhead, exceptional detection accuracy up to 98.1%, and low false positive rates, substantiating the system's ability to effectively manage varied network conditions and traffic volumes. These results underscore the potential of integrating QKD with robust machine learning strategies to secure the SDN control plane against sophisticated threats. © 2024 IEEE.

关键词： Quantum cryptography

来源：评论

学校读者我要写书评

暂无评论

Enhancing Security in IoT Networks Through RDAD for Attack Detection in RPL-Enabled Environments

引用

SN computer Science 2024年第7期5卷 864页

作者： Sridhar, K. Kumar, B. Anjanee Devi, S. Anjali Raju, Vadali Pitchi Soni, Anita Singh, Pallavi Deore, Shailesh Shivaji Department of Mechanical Engineering Lendi Institute of Engineering and Technology Andhra Pradesh Vizianagaram India Department of Electronic and Communication Engineering Dadi Institute of Engineering and Technology Gavarapalem Andhra Pradesh Anakapalle India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram Andhra Pradesh Guntur India Indur Institute of Engg. & amp Tech Siddipet India IES University Bhopal India Department of ECE Hindustan Institute of Technology and Science TN Chennai India Department of Computer Engineering SSVPS B S DEORE College of Engineering Maharashtra Dhule India

The “Internet of Things” (IoT) revolutionizes technology integration, enabling interconnected devices to communicate both among themselves and with the online realm. These smart gadgets collect valuable data, facilitating remote sharing via networked connections. Yet, their constrained memory, power, and computational capacities pose challenges. Within IoT, devices vary in functionality, from fully capable to limited subsets. These communication methods are integral to IoT's existence. Security is paramount when deploying IoT applications due to the inevitability of routing attacks aiming to intercept data in transit. To thwart such unauthorized access, Rank Decreased Attack Detection (RDAD) emerges as a crucial solution. Developed with IoT in mind, the Routing Protocol for Low-Power and Lossy Networks (RPL) serves as an anticipatory routing protocol. In an IoT environment, routing flaws can obscure data, thus highlighting the significance of RPL's topology-building process, which prioritizes nodes based on a ranking measure. RDAD proposes a mechanism that considers a parent node's Packet Delivery Ratio (PDR) to select trustworthy routing paths for data packets. Comparative analysis reveals RDAD's superiority over existing detection methods, significantly enhancing packet delivery rates and minimizing losses. With a detection rate of nearly 96.5% for RDA attacks, RDAD emerges as a potent safeguard for IoT routing security. © The Author(s), under exclusive licence to Springer Nature Singapore Pte Ltd. 2024.

关键词： INTI IoT PDR RDAD RPL

来源：评论

学校读者我要写书评

暂无评论

R-SLR: Real-Time Sign Language Recognition System 3

R-SLR: Real-Time Sign Language Recognition System

引用

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

作者： Ghosh, Monalisa De, Debjani Anand, Lovely Baraha, Satyakam Institute Of Engineering and Management Department of Computer Science Kolkata India Sri Sivasubramaniya Nadar College of Engineering Department of Electronics and Communication Chennai India

ISBN: (纸本)9798350372120

Sign language is the main medium of communication for people with hearing impairments. This language is mostly based on hand expressions complemented by non-manual gestures. It facilitates harmonious integration of the disabled into our society. In this paper, we present R-SLR, a sign language recognition system that can recognize the signs in real-time. R-SLR identifies the hand in a video stream and extracts the region of interest. We create our dataset by collecting the frames and pre-process them to enhance the frame quality and reduce noise. R-SLR detects sign language using Convolutional Neural Network. We extract the features from the pre-processed frames and classify the signs using the pre-trained DenseNet 201 model. The model performance is tested and it achieves 96.5% accuracy. The R-SLR then translates the identified sign language gesture into text or speech. Our designed R-SLR is an efficient and non-intrusive system. © 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

Intelligent Decision-Making in Cybersecurity Using Machine Learning 12th

Intelligent Decision-Making in Cybersecurity Using Machine L...

引用

12th International Conference on Frontiers of Intelligent Computing: Theory and Applications, FICTA 2024

作者： Sakhare, Nitin N. Maruthi Shankar, B. Kalnawat, Aarti Sharma, Abha Rege, P.R. Wagh, Kapil Adhar Department of Computer Engineering BRACT’s Vishwakarma Institute of Information Technology Maharashtra Pune India Department of Electronics and Communication Engineering Sri Krishna College of Engineering and Technology Tamil Nadu Coimbatore India Pune India Electronics and Communication Engineering Arya College of Engineering Rajasthan Jaipur India Department of Computer Engineering Vishwakarma Institute of Information Technology Maharashtra Pune India Nutan Maharashtra Institute of Engineering and Technology Maharashtra Pune India

ISBN: (纸本)9789819601462

In the constantly changing field of cybersecurity, the need for advanced decision-making tools is more crucial than ever. This study explores machine learning in order to introduce an innovative method for strengthening cybersecurity protocols. The methodology involves combining Random Forests (RF) and Support Vector Machines (SVM) using the AdaBoost algorithm in an ensemble framework. The ensemble model is intricately crafted to address the complexities of intrusion detection, utilizing the combined capabilities of Random Forest’s data handling and Support Vector Machine’s pattern discrimination. AdaBoost enhances the ensemble’s predictive abilities by iteratively adjusting weights to focus more on misclassified instances. This adaptive learning process enables the model to constantly develop and adjust to new cyber threats. Validation against benchmark datasets demonstrates an impressive accuracy rate of 97.78%, highlighting the strength of the ensemble methodology. The True Positive Rate (TPR) of 98.33% demonstrates the ensemble’s effectiveness in accurately detecting and responding to potential cyber threats. The results demonstrate the superior performance of the proposed ensemble method and highlight its ability to achieve a balance between accuracy and adaptability. This research significantly advances intelligent decision-making in cybersecurity by introducing a potent ensemble approach that smoothly integrates various machine learning algorithms. The method’s proven accuracy and sensitivity make it a powerful tool in combating the increasing complexity of cyber threats. The combination of RF, SVM, and AdaBoost sets a standard for future research in strengthening digital defenses and ensuring the resilience of critical information systems. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of a Decentralized Voting System Using Volta Blockchain 5

Design and Implementation of a Decentralized Voting System U...

引用

5th IEEE International Women in Technology Conference, WINTECHCON 2024

作者： Arthi, M. Suganthi Evangeline, C. Bharadwaj, Rohit Avrit, M. Jaswant, Gogineni Siranjeevi, G.P. School of Computer Science and Engineering Vellore Institute of Technology Chennai India Department of Electronics and Communication Engineering Sri Eshwar College of Engineering Coimbatore India

ISBN: (纸本)9798350374070

The drive for secure, open, and easily accessible voting systems has spurred the advance of decentralized blockchain-powered voting systems. This paper outlines the design and implementation of a decentralized voting system that utilizes the Hardhat Ether for testing and deployment, the Volta blockchain, Solidity smart contracts, and MetaMask for user interaction. Our approach ensures the confidentiality and integrity of votes by harnessing the irreversible and transparent properties of blockchain technology, enabling participation from any location with internet connectivity. Users can safely cast their ballots straight from their web browsers thanks to the inclusion of MetaMask, improving accessibility and usability. Furthermore, the application of Hardhat Ether simplifies the development process, enabling reliable deployment and testing protocols. This paper discusses the architecture, functionality, and security considerations of our decentralized voting system, highlighting its potential to revolutionize democratic processes worldwide. © 2024 IEEE.

关键词： Voting machines

来源：评论

学校读者我要写书评

暂无评论

An Adaptive Machine Learning Approach for Electrical Fault Detection and Minimization 2

An Adaptive Machine Learning Approach for Electrical Fault D...

引用

2nd International Conference on Information and communication Technology, ICICT 2024

作者： Biswas, Md. Emran Ahamed, Md Sayem Rafi, Md. Abid Hasan Haque, Md Dulal Department of Electronics and Communication Engineering HSTU Bangladesh Department of Computer Science and Engineering Engineering UIU Bangladesh Shanghai Institute of Technical Physics Chinese Academy of Science China

ISBN: (纸本)9798331508227

In the field of electrical power systems, effective fault detection, and minimization are crucial for maintaining system reliability and operational efficiency. This paper introduces machine learning based Adaptive Fault Reduction Algorithm (AFRA), a novel performance optimization approach designed to reduce fault occurrences significantly of electrical power systems. We used a binary classification dataset with a total of 12,001 data samples for this research. Random Forest (RF) model was used for fault detection and compared its performance against the Artificial Neural Network (ANN) model. RF model demonstrated accuracy, precision, and recall, with scores of 99.79%, 99.64%, and 99.91% respectively, compared to the ANN’s 99.54%, 99.54%, and 99.45%. By integrating AFRA, we reduced the number of fault events from 5,496 to just 6, achieving a 99.89% reduction. Our approach highlights the importance of optimization in fault detection and minimization methodologies, offering a robust framework for improving system reliability. The promising results achieved by AFRA suggest significant potential for its application in real-time monitoring and dynamic fault detection and minimization in power systems. ©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

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：