检索结果-内蒙古大学图书馆

2024 International Conference on System, Computation, Automation and Networking, ICSCAN 2024

作者： Mohanapriya, D. Indumathi, R. Priyatharsini, S. Arounesh, A. Kumar, V.Kishore Kamalan, R. Manakula Vinayagar Institute of Technology Department of Computer Science and Engineering Puducherry India Karpagam Academy of Higher Education Department of Electronics and Communication Engineering Coimbatore India Manakula Vinayagar Institute of Technology Department of Computer Science and Engineering India

ISBN: (纸本)9798331510022

This AI-based route optimizing system has put its focal point on only efficient travel routes based on real-time traffic. It focuses on calculating the shortest distance to source, along with destination and via points, distance, time-based traffic details, in order to arrive at the most optimal route for any journey. Advanced AI techniques in optimizing systems continuously adjust the route according to live traffic patterns so that users may experience the least delay possible. The system integrates with fuel consumption estimations provided the traveler through inputting vehicle mileage, enabling travelers to make better plans for their trips by considering time and fuel efficiency. This would save one time spent traveling, saves fuel, thus saving money while keeping the environment free from pollution. By such smart decisions on making routes, the system increases drivers' overall driving experience, especially in crowded areas or where there is heavy traffic. Since the system is inherently real-time, it's therefore very adaptive to the changing nature of road conditions, thus travel stream lined for the users. © 2024 IEEE.

关键词： Transportation routes

来源：评论

学校读者我要写书评

暂无评论

Streamlined Data Pipeline for Real-Time Threat Detection and Model Inference 17

Streamlined Data Pipeline for Real-Time Threat Detection and...

引用

17th International Conference on COMmunication Systems and NETworkS, COMSNETS 2025

作者： Singh, Rajkanwar Aravindan, V. Mishra, Sanket Singh, Sunil Kumar VIT-AP University School of Computer Science & Engineering Andhra Pradesh Amaravati India Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Department of Computer Science and Engineering Karnataka Manipal India

ISBN: (纸本)9798331531195

Real-time threat detection in streaming data is crucial yet challenging due to varying data volumes and speeds. This paper presents an architecture designed to manage large-scale, high-speed data streams using deep learning and machine learning models. The system utilizes Apache Kafka for high-throughput data transfer and a publish-subscribe model to facilitate continuous threat detection. Various machine learning techniques, including XGBoost, Random Forest, and LightGBM, are evaluated to identify the best model for classification. The ExtraTrees model achieves exceptional performance with accuracy, precision, recall, and F1 score all reaching 99% using the SensorNetGuard dataset within this architecture. The PyFlink framework, with its parallel processing capabilities, supports real-time training and adaptation of these models. The system calculates prediction metrics every 2, 000 data points, ensuring efficient and accurate real-time threat detection. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

WPIML: Web Page Indexing Using Heterogeneous Multi-source Knowledge and Reasoning by Fact Driven Learning 15th

WPIML: Web Page Indexing Using Heterogeneous Multi-source Kn...

引用

15th International Conference on Soft Computing and Pattern Recognition, SoCPaR 2023 and 14th World Congress on Nature and Biologically Inspired Computing, NaBIC 2023

作者： Jayanth, M.K.V. Deepak, Gerard Santhanavijayan, A. Department of Computer Science and Engineering JNTU GV College of Engineering Vizianagaram Vizianagaram India Department of Computer Science and Engineering Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal India Department of Computer Science and Engineering National Institute of Technology Tiruchirappalli Tiruchirappalli India

ISBN: (纸本)9783031889912

The epoch of Web 3.0, there arises a necessity for a strategic framework that focuses on a knowledge-centric strategy for indexing web pages. Existing web page indexing frameworks predominantly rely on either keywords or clustering mechanisms. The current demand is for a knowledge-centric model that incorporates learning and reasoning. This paper introduces a statistical model for web page indexing, which not only involves various sources of knowledge but also contributes significantly to web page indexing. The framework's operational process involves the extraction of URLs and descriptions from the dataset. Furthermore, keywords from the URLs are extracted, and an RDF generation paradigm is implemented. This is coupled with ontology generation and knowledge incorporation, utilizing knowledge stores like Wikidata and YAGO. The substantial augmentation of knowledge is accomplished through an ingenious metadata generation strategy. To categorize the metadata, a deep learning Convolutional Neural Network (CNN) classifier is integrated. Additionally, a XGBoost classifier is employed for web page indexing, with the selection of features being driven by Shannon's entropy mechanism. The model facilitates strategic reasoning via normalized Google distance and Renkonen index, employing differential ratios of step deviance measures. The optimization prowess of the artificial algae algorithm is harnessed for effective solutions. This optimization aids in achieving the finest instances for web page indexing, thereby narrowing the cognitive gap between the existing worldwide web and the incorporated knowledge of Web 3.0. The proposed framework's performance is remarkable, boasting an average precision of 96.45%, an average recall of 97.19%, and an impressive F-measure of 387.27%. The framework also achieves the lowest value of False Discovery Rate (FDR) at a mere 0.04%. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Indexing (materials working)

来源：评论

学校读者我要写书评

暂无评论

A versatile framework for analyzing galaxy image data by incorporating Human-in-the-loop in a large vision model

引用

Chinese Physics C 2024年第9期48卷 176-187页

作者： Ming-Xiang Fu Yu Song Jia-Meng Lv Liang Cao Peng Jia Nan Li Xiang-Ru Li Ji-Feng Liu A-Li Luo Bo Qiu Shi-Yin Shen Liang-Ping Tu Li-Li Wang Shou-Lin Wei Hai-Feng Yang Zhen-Ping Yi Zhi-Qiang Zou National Astronomical Observatories Chinese Academy of SciencesBeijing 100101China College of Electronic Information and Optical Engineering Taiyuan University of TechnologyTaiyuan 030024China School of Astronomy and Space Science University of Chinese Academy of SciencesBeijing 101408China Key lab of Space Astronomy and Technology National Astronomical ObservatoriesBeijing 100101China School of Computer Science South China Normal UniversityGuangzhou 510631China CAS Key Laboratory of Optical Astronomy National Astronomical ObservatoriesBeijing 100101China University of Chinese Academy of Sciences NanjingNanjing 211135China University of Science and Technology Beijing Beijing 100083China Shanghai Astronomical Observatory Chinese Academy of SciencesShanghai 200030China School of Computer and Information Dezhou UniversityDezhou 253023China Faculty of Information Engineering and Automation Kunming University of Science and TechnologyKunming 650500China School of Computer Science and Technology Taiyuan University of Science and TechnologyTaiyuan 30024China School of Mechanical Electrical and Information EngineeringShandong UniversityWeihai 264209China Nanjing University of Posts&Telecommunications Nanjing 210023China School of Science University of Science and Technology LiaoningAnshan 114051China

The exponential growth of astronomical datasets provides an unprecedented opportunity for humans to gain insight into the ***,effectively analyzing this vast amount of data poses a significant *** response,astronomers are turning to deep learning techniques,but these methods are limited by their specific training sets,leading to considerable duplicate *** overcome this issue,we built a framework for the general analysis of galaxy images based on a large vision model(LVM)plus downstream tasks(DST),including galaxy morphological classification,image restoration object detection,parameter extraction,and *** the low signal-to-noise ratios of galaxy images and the imbalanced distribution of galaxy categories,we designed our LVM to incorporate a Human-in-the-loop(HITL)module,which leverages human knowledge to enhance the reliability and interpretability of processing galaxy images *** proposed framework exhibits notable fewshot learning capabilities and versatile adaptability for all the abovementioned tasks on galaxy images in the DESI Legacy Imaging *** particular,for the object detection task,which was trained using 1000 data points,our DST in the LVM achieved an accuracy of 96.7%,while ResNet50 plus Mask R-CNN reached an accuracy of 93.1%.For morphological classification,to obtain an area under the curve(AUC)of~0.9,LVM plus DST and HITL only requested 1/50 of the training sets that ResNet18 *** addition,multimodal data can be integrated,which creates possibilities for conducting joint analyses with datasets spanning diverse domains in the era of multi-messenger astronomy.

关键词： artificial intelligence large vision model human-in-the-loop astronomy galaxies

来源：评论

学校读者我要写书评

暂无评论

Stratification of Depressed and Non-Depressed Texts from Social Media using LSTM and its Variants 2

Stratification of Depressed and Non-Depressed Texts from Soc...

引用

2nd International Conference on Machine Learning and Data engineering, ICMLDE 2023

作者： Kumar, Keerthan G.T. Anoop, R. Koolagudi, Shashidhar G. Rao, Trupthi Kodipalli, Ashwini Department of Information Science and Engineering Siddaganga Institute of Technology Tumkur India Department of Artificial Intelligence and Data Science Global academy of Technology Bengaluru India Department of Computer Science and Engineering National Institute of Technology Karnataka Surathkal India

This work examines the performance of various LSTM (long short-term memory) variants on social media text data. This study evaluates the performance of LSTM models with different architectures, namely, classic LSTM, Bidirectional LSTM, Stacked LSTM, gated recurrent unit (GRU), and bidirectional GRU, on a social network dataset comprising texts extracted from multiple social media platforms. We aim to identify the most effective LSTM variant of the five considered LSTM models for text analysis through a comparative study of the models' precision, recall, F1-score, and accuracy. The research findings show that the Classic LSTM and the GRU model perform better than the other models in accuracy. In contrast, the bidirectional models (Bidirectional LSTM and Bidirectional GRU) provide better precision scores than their respective primitive models. This research has significant implications for developing more efficient models for natural language processing applications. It offers beneficial insights into the implications involving the scrutiny of depression on social media platforms through text data analysis. © 2024 Elsevier B.V.. All rights reserved.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

The Future of Online Shopping: Blockchain- Powered E-Commerce Platforms

The Future of Online Shopping: Blockchain- Powered E-Commerc...

引用

2024 International Conference on Signal Processing, Computation, Electronics, Power and Telecommunication, IConSCEPT 2024

作者： Kiran, Ajmeera Sri, Nemani Divya Ayyasamy, Ramesh Kumar Chinnasamy, P. Vellanki, Sreelakshmi Vujwala, Maddula MLR Institute of Technology Department of Computer Science and Engineering Hyderabad India Faculty of Information and Communication Technology Kampar Malaysia School of Computing Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamilnadu India

ISBN: (纸本)9798331540685

A cutting-edge online marketplace that uses blockchain technology to transform how we purchase and sell goods and services is known as a blockchain- powered e-commerce platform. This platform uses a decentralized network of computers, also known as nodes, to maintain a transparent and impenetrable record of all transactions instead of depending on a central authority like a bank or a company. A blockchain-based e-commerce platform is a secure, transparent, and trusted online marketplace. It does away with the need for intermediaries, improves security, and provides a world market where users can confidently conduct peer-to-peer transactions. This novel strategy could change how online commerce and shopping are performed. © 2024 IEEE.

关键词： Marketplaces

来源：评论

学校读者我要写书评

暂无评论

An ensemble framework of decision trees for class imbalance using partitioning

引用

International Journal of Innovative Computing and Applications 2024年第1期15卷 1-13页

作者： Kadappa, Vijayakumar Guggari, Shankru Veerabhaskar, Rajeshwari Devi Doddapoojari Department of Computer Applications B.M.S. College of Engineering Bengaluru560019 India School of Computer Science and Engineering KLE Technological University Hubballi580031 India Department of Electronics and Communication Engineering Global Academy of Technology Bengaluru560098 India

Decision tree classifiers are widely used in machine learning and data mining due to their intuitiveness. However, they do not perform well for class-imbalanced data due to bias creation towards the majority class. Therefore, handling class-imbalanced data is an active research area in many applications of machine learning. Feature set partitioning paradigm is proven to be effective for classification by many researchers. In this paper, we extend the ideas of partitioning to propose a decision tree ensemble to overcome class-imbalance issues. The framework consists of balancing the data, partitioning the feature set, building local decision trees, then combining decisions. Some instances of the proposed framework (e.g., Ferrer diagram-based approach) are used to validate the performance of the framework. An empirical study is carried out using University of California Irvine (UCI), Knowledge Extraction Evolutionary Learning (KEEL), and other datasets. The performance of the instances of the proposed framework demonstrates improved performance compared to other benchmark machine learning approaches. Copyright © 2024 Inderscience Enterprises Ltd.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

CLEAN: Cloud-enabled Scalable Blockchain Outsourcing System Using Dynamic Programming 6

CLEAN: Cloud-enabled Scalable Blockchain Outsourcing System ...

引用

6th ACM International Symposium on Blockchain and Secure Critical Infrastructure, BSCI 2024

作者： Chan, Weilin Wei, Yihang Jiang, Peng Xu, Lei Zhu, Liehuang Yu, Jing School of Computer Science and Technology Beijing Institute of Technology Beijing China Institute of Information Engineering Chinese Academy of Sciences Beijing China

ISBN: (纸本)9798400706387

Blockchain technology has garnered significant attention in academic and industrial domains due to its ability to establish a secure and trustworthy environment. As blockchain techniques continue to advance, there is a growing demand for computing resources in dimensions like storage, data processing, and network bandwidth. To meet this demand, leveraging cloud computing as an off-chain resource for scalable on-chain services has emerged as a viable solution. However, allocating cloud resources in heterogeneous cloud computing environments presents challenges due to their inherent complexity. Native cloud environments encompass diverse cloud service providers with varying capabilities, pricing models, and performance characteristics. Given the cloud's capacity to scale resources based on demand, this paper introduces a novel approach called the Cloud-enabled Scalable Blockchain (CLEAN) outsourcing model. The CLEAN model aims to develop a scalable blockchain system that minimizes costs and enhances performance. We propose a dynamic programming algorithm considering influential factors such as cloud service costs, availability, and execution time. The algorithm aims to minimize expenses while ensuring efficient resource allocation. Experimental evaluations involving rigorous analysis have been conducted to assess the effectiveness of the proposed approach. The results indicate that CLEAN outperforms the Greedy Algorithm and Genetic Algorithm (GA) by maintaining relatively low latency across all the CLEAN settings. Additionally, CLEAN demonstrates lower energy consumption compared to the Greedy Algorithm and GA, with up to a 50% and 30% reduction, respectively, as the number of transactions increases. Furthermore, the experiments determine the optimal number of orderers for the three settings to balance the trade-off between time cost and performance. Moreover, the findings also reveal that simply increasing the number of orderers in the cloud does not guarantee improv

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Analyzing Cyberbullying Word Distribution Across Social Media to Develop Lexicon Dictionary 2

Analyzing Cyberbullying Word Distribution Across Social Medi...

引用

2nd IEEE International Conference on Networks, Multimedia and Information technology, NMITCON 2024

作者： Sahana, V. Anil Kumar, K.M. Jss Academy of Technical Education Dept. of Information Science and Engineering Bengaluru560060 India Jss Science and Technology University Dept. of Computer Science and Engineering Mysuru570006 India

ISBN: (纸本)9798350372892

Social media platforms have become essential tools for communication, collaboration, and exchanging information, ideas, and knowledge among users worldwide. Despite their benefits, the anonymity offered by these platforms has unfortunately led to a rise in hate speech and cyberbullying, causing concern across the globe. This issue has drawn the attention of researchers and scholars now focused on devising methods for automatically detecting cyberaggression and hate speech. The goal is to mitigate these harmful behaviors and create safer online environments [1]. This study specifically aims to identify and analyze the usage of cyberbullying language within the English Tweet corpus, focusing on distinguishing between bullying and non-bullying language. This research contributes to developing more effective cyberbullying detection models by examining the frequency and patterns of cyberbullying words. These findings are vital for enhancing the efficacy of cyberbullying detection on social networks in future research efforts. The conclusions of the experiments indicate that the SVM achieved the highest average accuracy, approximately 84 %. © 2024 IEEE.

关键词： Anonymity

来源：评论

学校读者我要写书评

暂无评论

Cyber Security Threat Detection in Internet of Things Using Optimized Deep Learning Technique 3

Cyber Security Threat Detection in Internet of Things Using ...

引用

3rd IEEE Asian Conference on Innovation in technology, ASIANCON 2023

作者： Mariappan, Umasree Balakrishnan, D. Rajendran, S. Alagusundar, Nanditha Sheriff, A. Ashiq Aadith, K. Sri Vidya College of Engineering and Technology Department of Computer Science and Engineering Tamil Nadu Virudhunagar626001 India Kalasalingam Academy of Research and Education Department of Computer Science and Engineering Tamil Nadu Krishnankoil626126 India Kalasalingam Academy of Research and Education Department of Electrical and Electronics Engineering Tami lNadu Krishnankoil626126 India

ISBN: (纸本)9798350302288

Cybersecurity threat detection in the Internet of Things (IoT) refers to the process of identifying and addressing potential security risks and attacks within IoT systems and devices. It involves monitoring IoT networks and devices for abnormal behavior, detecting intrusions or unauthorized access attempts, ensuring the integrity of data, managing vulnerabilities, analyzing behavioral patterns, and staying informed about emerging threats. This ongoing process aims to maintain the security and integrity of IoT infrastructure by proactively identifying and mitigating potential security threats. Recent studies have demonstrated that deep learning algorithms are highly efficient and offer numerous advantages compared to earlier methods when it comes to conducting security assessments of IoT devices. Dual Channel Convolution Neural Network with Spider Monkey Optimization (DCCNN-SMO), a deep learning technique which visualized colored images for finding harmful intrusions in IoT network. Here, DCCNN used two channels of CNN and combined in fully connected layer for detecting intrusions in IoT network. The hyper parameters of DCCNN were fine tune by SMO which enhance the performance of DCCNN. In this paper, the convergence speed and effectively fine tuning the hyper parameters of DCCNN an Adapted SMO (ASMO) is introduced for better detection of intrusions in IoT network. The position update equation of the basic SMO algorithm is modified by incorporating a dual seek scheme. This approach, employed in the local leader (LL) phase, global leader (GL) phase, and LL decision phase, facilitates the acquisition of fresh outcomes, representing best hyper parameters of DCCNN for better detection of intrusion in IoT network. The performance of the proposed DCCNN-ASMO is demonstrated to be superior in terms of accuracy, precision, and recall, as evidenced by the experimental results. © 2023 IEEE.

关键词： Internet of things

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：