检索结果-内蒙古大学图书馆

5th International Conference on Advances in Distributed Computing and Machine Learning, ICADCml 2024

作者： Ganesan, P. Leo Joseph, L.M.I. Sivakumar, V.G. Thulasi Prasad, S. Sathish, B.S. Sajiv, G. Department of Electronics and Communication Engineering Vidya Jyothi Institute of Technology Hyderabad India Department of Electronics and Communication Engineering SR University Telangana Warangal India Department of Computer Science Engineering AI Sri Venkateshwara College of Engineering Bengaluru India Saveetha School of Engineering SIMATS Chennai India

ISBN: (纸本)9789819718405

The identification of vehicles is indispensable task in this fast moving world where attentiveness is most important than ever before. The suggested methodology explains the effectiveness of fuzzy clustering algorithms for unsupervised vehicle recognition and segmentation in infrared thermography. The method takes use of the natural temperature variations that exist between moving objects and their environment, allowing for precise border delineation. Fuzzy clustering has shown to be a flexible method that offers a framework to organize pixels with comparable properties. By taking into account the uncertainty present in thermal imaging, fuzzy clustering presents a viable solution in the context of vehicle recognition and segmentation. Infrared thermography is more effective in challenging scenarios such as darkness, smoke, or dust. It is also well-suited for real-time scenarios due to fast thermal response. The proposed methodology finds applications in transportation management, security systems, industrial monitoring, and various thermal inspections. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Fuzzy clustering

来源：评论

学校读者我要写书评

暂无评论

Biometric-Based Access Control Systems with Robust Facial Recognition in IoT Environments 3

Biometric-Based Access Control Systems with Robust Facial Re...

引用

3rd IEEE International Conference on Intelligent Techniques in Control, Optimization and Signal Processing, INCOS 2024

作者： Satish Babu, B.V. Manoranjini, J. Changala, Ravindra Aarif, Mohd Mary, S. Suma Christal Raj, I Infant Prasad v Potluri Siddhartha Institute of Technology Department of It Vijayawada India Chaitanya Bharathi Institute of Technology Department of Ai & Ml Hyderabad India Guru Nanak Institutions Technical Campus Department of Information Technology Hyderabad India Associate Editor-Publishing Global Research Network Noida India Panimalar Engineering College Department of Information Technology Poonamalle Chennai India K. Ramakrishnan College of Engineering Department of Computer Science and Engineering Tamil Nadu Trichy India

ISBN: (纸本)9798350361186

The integration of biometric-based access control systems with robust facial recognition technology within Internet of Things (IoT) environments holds paramount significance in addressing contemporary security challenges. The novelty of the research endeavours to contribute to this critical area by investigating and implementing a novel approach, employing Convolutional Neural Networks (CNN) for facial classification within the biometric framework. The significance of this study lies in its potential to enhance security measures in IoT environments, ensuring reliable and efficient access control. Previous attempts at integrating facial recognition into IoT have encountered notable challenges, including suboptimal accuracy, vulnerability to adversarial attacks, and scalability issues. This research builds upon these prior issues by introducing CNN for facial classification, leveraging its capabilities in image processing and pattern recognition to achieve enhanced accuracy and resilience against potential security threats. The novelty of the study is underscored by the application of CNN within the biometric context of IoT, offering a cutting-edge solution tailored to the intricacies of interconnected devices. Experiments conducted on benchmark datasets showcase the promising capabilities of the proposed system, with face recognition accuracies reaching an impressive 98%. These results underscore the potential of this research to significantly advance the state-of-the-art in biometric-based access control, particularly within the context of IoT environments. The utilization of CNN introduces a pioneering element, contributing to the evolution of secure and efficient access control solutions in the era of IoT. © 2024 IEEE.

关键词： Biometrics

来源：评论

学校读者我要写书评

暂无评论

Improving Gloss-free Sign Language Translation by Reducing Representation Density 38

Improving Gloss-free Sign Language Translation by Reducing R...

引用

38th Conference on Neural Information Processing Systems, NeurIPS 2024

作者： Ye, Jinhui Wang, Xing Jiao, Wenxiang Liang, Junwei Xiong, Hui Guangzhou China Department of Computer Science and Engineering HKUST Hong Kong Guangzhou HKUST Fok Ying Tung Research Institute Hong Kong Tencent AI Lab China

Gloss-free sign language translation (SLT) aims to develop well-performing SLT systems with no requirement for the costly gloss annotations, but currently still lags behind gloss-based approaches significantly. In this paper, we identify a representation density problem that could be a bottleneck in restricting the performance of gloss-free SLT. Specifically, the representation density problem describes that the visual representations of semantically distinct sign gestures tend to be closely packed together in feature space, which makes gloss-free methods struggle with distinguishing different sign gestures and suffer from a sharp performance drop. To address the representation density problem, we introduce a simple but effective contrastive learning strategy, namely SignCL, which encourages gloss-free models to learn more discriminative feature representation in a self-supervised manner. Our experiments demonstrate that the proposed SignCL can significantly reduce the representation density and improve performance across various translation frameworks. Specifically, SignCL achieves a significant improvement in BLEU score for the Sign Language Transformer and GFSLT-VLP on the CSL-Daily dataset by 39% and 46%, respectively, without any increase of model parameters. Compared to Sign2GPT, a state-of-the-art method based on large-scale pre-trained vision and language models, SignCL achieves better performance with only 35% of its parameters. Implementation and Checkpoints are available at https://***/JinhuiYE/SignCL. © 2024 Neural information processing systems foundation. All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Machine learning tool for exploring sentiment analysis on twitter data

引用

Materials Today: Proceedings 2022年 56卷 1927-1934页

作者： Biradar, Shanta H. Gorabal, J.V. Gupta, Gaurav Department of Information Science & Engineering Sir M Visvesvaraya Institute of Technology Bengaluru562157 India Department of Computer Science & Engineering ATME College of Engineering Mysore570028 India Yogananda School of AI Computing and Data Science Shoolini University Himachal Pradesh Solan India

In social media, micro-blogging is a common routine of most people around the world. Social media analytics gathering structure and unstructured Big-Data from various social sites and analyzing to make business decisions using Apache Hadoop and Apache Hive respectively. The objective of the research work was to develop big data technology used for gathering and handling large unstructured data from real time social media for sentiment analysis for identifying the brand and services. The methodology devised an algorithm based on sentimental analysis using customers review classification, which dealt with prepossessing the datasets, clustering of the data based on the specific domains, feature vector using n-gram models and tf-idf vectors extracts synonyms and classification sentiment analysis. The result shows that applied sentimental analysis with unsupervised clustering of data into specific domains and supervised machine learning techniques handle large amounts of twitter data in an efficient way. The developed tool 1.5 times faster than that of traditional database to Hadoop cluster and also the accuracy is nearly 80 %, which helps the user in computing, analyzing and interpreting interaction and associations between people, topics and ideas. © 2021

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Mobile edge fog, Blockchain Networking and Computing-A survey 1

Mobile edge fog, Blockchain Networking and Computing-A surve...

引用

1st International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2023

作者： Salama, Ramiz Al-Turjman, Fadi Bhatla, Shruti Mishra, Divya Ai and Robotics Institute Research Center for Ai and IoT Near East University Nicosia Department of Computer Engineering Mersin10 Turkey Ai and Robotics Institute Near East University Artificial Intelligence Engineering Dept. Mersin Nicosia10 Turkey University of Kyrenia Research Center for Ai and IoT Faculty of Engineering Kyrenia Mersin10 Turkey Graphic Era Hill University Department of Computer Science and Engineering Dehradun India Abes Engineering College Ghaziabad India

ISBN: (纸本)9798350338027

Mobile edge computing (MEC) and blockchain technology are two rapidly evolving areas in computer science that have the potential to significantly impact the design and operation of distributed systems. MEC involves the deployment of computing resources and services at the edge of the network, closer to the end users, enabling lowlatency, high-bandwidth applications such as augmented reality and machine learning. Blockchain technology, on the other hand, is a distributed database that allows for secure, transparent, and immutable record-keeping, with potential applications in a wide range of industries. In this project, we explore the integration of MEC and blockchain technology for the management of distributed computing resources at the edge of the network. We review the state of the art in these two areas, including existing projects and prototypes, and describe our materials and method for evaluating their potential for integration. Our results show that the combination of MEC and blockchain has the potential to enable new applications and services that require both low latency and secure, decentralized data management. We conclude by summarizing the main contributions of our work and discussing future directions for research in this area. Our findings have implications for the design and operation of distributed systems, and have the potential to enable new applications and services in a wide range of industries. © 2023 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Network security, trust & privacy in a wiredwireless Environments-An Overview 1

Network security, trust & privacy in a wiredwireless Environ...

引用

1st International Conference on Computational Intelligence, Communication Technology and Networking, CICTN 2023

作者： Salama, Ramiz Al-Turjman, Fadi Bhatla, Shruti Gautam, Devendra Ai and Robotics Institute Research Center for Ai and IoT Near East University Nicosia Department of Computer Engineering Mersin10 Turkey Ai and Robotics Institute Near East University Artificial Intelligence Engineering Dept. Mersin Nicosia10 Turkey University of Kyrenia Research Center for Ai and IoT Faculty of Engineering Kyrenia Mersin10 Turkey Graphic Era Hill University Department of Computer Science and Engineering Dehradun India Abes Engineering College Ghaziabad India

ISBN: (纸本)9798350338027

In this report, we explore the key challenges and threats facing network security in wired and wireless environments, as well as the technologies and best practices for addressing these challenges. We provide an overview of the key concepts and terminology related to network security, trust, and privacy, and discuss the role of encryption in maintaining trust and privacy in these environments. We also examine common attack vectors and countermeasures and offer some recommendations for best practices in the realm of network security. © 2023 IEEE.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Approach of CNN and GRU Models for Network and Server Intrusion

An Ensemble Approach of CNN and GRU Models for Network and S...

引用

Emerging Technology (INCET), International Conference for

作者： Aniketh Reddy Adireddy Vishnu Kurnala Sindu Patlolla Gagandeep Arora Artificial Intelligence & Machine Learning Vardhaman College of Engineering Hyderabad India Computer Science & Engineering (AI&ML) Vardhaman College of Engineering Hyderabad India

ISBN: (数字)9798350361155

ISBN: (纸本)9798350361162

This research paper delves into the realm of cybersecurity by proposing an innovative ensemble model that blends Gated Recurrent Units (GRU) and Convolutional Neural Networks (CNN) for network and server intrusion detection. CNNs excel in spatial feature extraction, particularly suited for analyzing network traffic patterns, while GRUs are adept at capturing temporal dependencies within sequential data. The integration of these models aims to leverage their complementary strengths, enhancing the overall robustness of intrusion detection systems. Through comprehensive training and evaluation on diverse datasets, the ensemble model showcases promising results, demonstrating improved accuracy and resilience against adversarial attacks compared to standalone CNN and GRU models. In addition to making a significant contribution to the rapidly developing field of deep learning in cybersecurity, this research offers practical implications for the development of more secure network and server environments in the face of dynamic cyber threats.

关键词： Training Intrusion detection Telecommunication traffic Logic gates Feature extraction Robustness Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

An IoT-based Deep Belief Network in Intrusion Detection System using Butterfly Optimization 10

An IoT-based Deep Belief Network in Intrusion Detection Syst...

引用

10th International Conference on Communication and Signal Processing, ICCSP 2024

作者： Cherian, Aswathy K. Vaidhehi, M. Arshey, M. Simpson, Serin V. Briskilal, J. Singh, Astitva Srm Institute of Science and Technology Department of Computing Technologies Chennai Kattankulathur India Scms School of Engineering and Technology Department of Ai & Ds Kerala Ernakulam India Madanapalle Institute of Technology & Science Department of Computer Science and Technology Chittoor Andhra Pradesh Madanapalle India

ISBN: (纸本)9798350353068

Rapid technological advancements in the communication and internet industries have led to a huge increase in network scale and data volume. Network security is having a hard time identifying attacks as new threats are being created. Additionally, you can't overlook the possibility of unauthorized users trying to attack the network in various methods. Numerous technologies, such as an intrusion detection system, can be utilized to protect the network from potential threats (IDS). The collecting and dissemination of data by Internet-connected devices is referred to as the 'Internet of Things' (IoT). There are now more privacy and security problems due to the proliferation of Internet connections and the introduction of new technologies like the Internet of Things (IoT). IoT incursions are becoming increasingly complex and numerous as a result of the proliferation of connected devices. Companies are boosting their investment in research and development in order to better detect these threats. In this research, Deep Belief Network (DBN) and Butterfly Optimization Algorithm (BOA) Intrusion Detection Systems (IDS) are proposed for detecting Io T network assaults. In order to minimize information leakage on the test data, the UNSW-NB15 dataset was normalized using the Absolute Maximum Scaling (AMS) approach in the first stage of this study process. This dataset contains a mixture of current assaults and typical network traffic, categorized into nine different attack types. The next step was to use Principal Component Analysis to reduce the dimensionality (PCA). Last but not least, results showed that DBN-BOA was superior to other IoT intrusion detection systems in terms of accuracy and speed. © 2024 IEEE.

关键词： Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

GoT: Effective Graph-of-Thought Reasoning in Language Models

GoT: Effective Graph-of-Thought Reasoning in Language Models

引用

2024 Findings of the Association for Computational Linguistics: NAACL 2024

作者： Yao, Yao Li, Zuchao Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China MoE Key Lab of Artificial Intelligence AI Institute Shanghai Jiao Tong University China National Engineering Research Center for Multimedia Software School of Computer Science Wuhan University Wuhan430072 China

ISBN: (纸本)9798891761193

With the widespread use of language models (LMs) in NLP tasks, researchers have discovered the potential of Chain-of-thought (CoT) to assist LMs in accomplishing complex reasoning tasks by generating intermediate steps. However, human thought processes are often non-linear, rather than simply sequential chains of thoughts. Therefore, we propose Graph-of-Thought (GoT) reasoning, which models human thought processes not only as a chain but also as a graph. By representing thought units as nodes and connections between them as edges, our approach captures the non-sequential nature of human thinking and allows for a more realistic modeling of thought processes. GoT adopts a two-stage framework with an additional GoT encoder for thought graph representation and fuses the graph representation with the original input representation through a gated fusion mechanism. We evaluate GoT's performance on a text-only reasoning task (AQUA-RAT) and a multimodal reasoning task (scienceQA). Our model achieves significant improvement over the strong CoT baseline on the AQUA-RAT test set and boosts accuracy from 85.19% to 87.59% using the T5-base model over the state-of-the-art Multimodal-CoT (Zhang et al., 2023) on the scienceQA test set. Our code is publicly available at https://***/Zoeyyao27/Graphof-Thought. © 2024 Association for Computational Linguistics.

关键词： Rats

来源：评论

学校读者我要写书评

暂无评论

An Approach to Detect and Classify Potentially Suspicious Activity from Real-Time Log Data using Anomaly Detection Methods

An Approach to Detect and Classify Potentially Suspicious Ac...

引用

Innovation in Technology (INOCON), IEEE International Conference for

作者： Arnab Sengupta Akash Kundu aishi Mukhopadhyay Computer Science & Engineering (AI/ML) Heritage Institute of Technology Kolkata India Computer Science & Engineering Heritage Institute of Technology Kolkata India Electronics & Communication Engineering Heritage Institute of Technology Kolkata India

This paper aims to propose an intricate yet streamlined approach to incorporate Machine Learning into Cybersecurity by employing anomaly detection techniques to screen real-time log data and identify as well as classify suspicious activity. Our research focuses on avoiding misclassification with particular emphasis on minimising permissivity to ensure that threats with greater risk are not misclassified to a lesser priority. The paper explores a two-tiered strategy comprising an initial model dedicated to the identification of potentially suspicious log data through anomaly detection methods, serving as a preliminary filter. Subsequently, a secondary model is tasked with the responsibility of classifying the identified threats into distinct priority levels based on anomalous features. This approach sets groundwork for a robust framework that prioritises minimising vulnerability while maximising accuracy.

关键词：

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：