检索结果-内蒙古大学图书馆

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Zeyu Xiong Daizong Liu Pan Zhou Jiahao Zhu Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wangxuan Institute of Computer Technology Peking University

Temporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video. Most existing methods extract frame-grained features or object-grained features by 3D ConvNet or detection network under a conventional TSG framework, failing to capture the subtle differences between frames or to model the spatio-temporal behavior of core persons/objects. In this paper, we introduce a new perspective to address the TSG task by tracking pivotal objects and activities to learn more fine-grained spatio-temporal behaviors. Specifically, we propose a novel Temporal Sentence Tracking Network (TSTNet), which contains (A) a Cross-modal Targets Generator to generate multi-modal templates and search space, filtering objects and activities, and (B) a Temporal Sentence Tracker to track multi-modal targets for modeling the targets’ behavior and to predict query-related segment. Extensive experiments and comparisons with state-of-the-arts are conducted on challenging benchmarks: Charades-STA and TACoS. And our TSTNet achieves the leading performance with a considerable real-time speed.

关键词： Solid modeling Target tracking Three-dimensional displays Grounding Benchmark testing Signal processing Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Anomaly Detection in Social Networks using Improved Local Outlier Factor

Anomaly Detection in Social Networks using Improved Local Ou...

引用

Intelligent Systems and Computational Networks (ICISCN), International Conference on

作者： Rana Veer Samara Sihman Bharattej R Muntader Mhsnhasan Sowmya M Prabhakaran M V K. Ghamya Department of Computer Science Saint Leo University FL USA Department of Computers Techniques Engineering College of Technical Engineering The Islamic University of Al Diwaniyah Al Diwaniyah Iraq Department of Artificial Intelligence and Data Science Nitte Meenakshi Institute of Technology Bengaluru India Department of Computer Science and Engineering (Cyber Security) Dhanalakshmi Srinivasan College of Engineering and Technology Mamallapuram India Department of Computer Science and Engineering (AI&ML) Mohan Babu University Tirupati India

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

In the present era, Anomaly Detection (AD) aims to identify malicious activities in social networks. Even though previous researchers suggest effective methods for AD still there are limitations such as a lack of labeled data and struggled to handle high dimensional data. In this research, Improved Local Outlier Factor (ILOF) is proposed to detect anomalies and effectively handles the high dimensional data by using distance metric to calculate local density. Primarily, the data is collected from CERT insider threat and then preprocessed with truncation to remove extreme values for effective feature extraction. After that, the Principal Component Analysis (PCA) is incorporated to extract most informative features such as principal components to identify anomalies as data points. Finally, the extracted features are fed into proposed ILOF uses density-based approach to calculate the local density effectively for detecting anomalies in social networks. From the results, proposed ILOF model attained better outcomes compared to existing Bidirectional Long Short-Term Memory (BiLSTM) in terms of accuracy, precision, recall and F1-score as 98.50%, 97.08%, 98.25% and 97.66% respectively.

关键词： Measurement Accuracy Social networking (online) High dimensional data Transfer learning Feature extraction Real-time systems Intelligent systems Anomaly detection Principal component analysis

来源：评论

学校读者我要写书评

暂无评论

Empirical Evaluation of Real-Time Diabetic Retinopathy Disease Detection using IoT Enabled Medical Imaging Processing Strategy

Empirical Evaluation of Real-Time Diabetic Retinopathy Disea...

引用

Electronics and Renewable Systems (ICEARS), International Conference on

作者： S. Agnes Shifani N. Saraswathy Margaret Clemencia. A G.B. Santhi Jayant Giri Mohammad Rasmi Al-Mousa Department of ECE Saveetha School of Engineering Saveetha Institute of Science and Technology (SIMATS) Saveetha University Chennai Department of Chemistry Parisutham Institute of Technology and Science(Autonomous) Thanjavur Department of Computer Science and Engineering New Prince Shri Bhavani College of Engineering and Technology Chennai Department of Mechanical Engineering Yeshwantrao Chavan College of Engineering Nagpur India Department of Cyber Security College of Information Technology Zarqa University Zarqa Jordan

ISBN: (数字)9798331509675

ISBN: (纸本)9798331509682

Diabetic Retinopathy (DR) poses a significant risk to vision among diabetic patients, necessitating early and accurate detection for effective intervention. This research introduced a novel methodology to detect the diabetic retinopathy in an efficient way. In contrast to the existing technique called Convolutional Neural Network (CNN), the proposed approach called Hybrid Learning assisted Diabetic Retinopathy Predictor (HLDRP) allows for easy and quick implementation and offers patients direct access to diagnostic equipment. By leveraging a hybrid learning model that incorporates both supervised and unsupervised learning techniques, HLDRP enhances the accuracy and reliability of DR diagnosis. The IoT component facilitates continuous monitoring and data acquisition from patients, while the hybrid learning model analyzes this data to detect early signs of DR and predict disease progression. Experimental results indicate that HLDRP offers superior diagnostic performance compared to traditional methods, with increased sensitivity and specificity. This integrated approach not only improves early detection but also enables personalized treatment planning, potentially transforming the management of diabetic retinopathy through innovative technology and advanced analytics. Through comprehensive evaluation using a diverse dataset of retinal images, HLDRP demonstrates significant improvements in diagnostic performance, including increased sensitivity and specificity compared to traditional detection methods. The results underscore HLDRP's potential to facilitate early intervention and personalized treatment, providing a valuable tool for healthcare professionals in managing and preventing diabetic retinopathy.

关键词： Diabetic retinopathy Accuracy Image processing Sensitivity and specificity Predictive models Real-time systems Internet of Things Hybrid learning Reliability Diseases

来源：评论

学校读者我要写书评

暂无评论

Track the Answer: Extending TextVQA from Image to Video with Spatio-Temporal Clues 39

Track the Answer: Extending TextVQA from Image to Video with...

引用

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Zhang, Yan Zeng, Gangyan Shen, Huawen Wu, Daiqing Zhou, Yu Ma, Can Institute of Information Engineering Chinese Academy of Sciences China VCIP & TMCC & DISSec College of Computer Science Nankai University China School of Cyber Security University of Chinese Academy of Sciences China School of Cyber Science and Engineering Nanjing University of Science and Technology China

ISBN: (纸本)157735897X

Video text-based visual question answering (Video TextVQA) is a practical task that aims to answer questions by jointly reasoning textual and visual information in a given video. Inspired by the development of TextVQA in image domain, existing Video TextVQA approaches leverage a language model (e.g. T5) to process text-rich multiple frames and generate answers auto-regressively. Nevertheless, the spatio-temporal relationships among visual entities (including scene text and objects) will be disrupted and models are susceptible to interference from unrelated information, resulting in irrational reasoning and inaccurate answering. To tackle these challenges, we propose the TEA (stands for "Track thE Answer") method that better extends the generative TextVQA framework from image to video. TEA recovers the spatio-temporal relationships in a complementary way and incorporates OCR-aware clues to enhance the quality of reasoning questions. Extensive experiments on several public Video TextVQA datasets validate the effectiveness and generalization of our framework. TEA outperforms existing TextVQA methods, video-language pretraining methods and video large language models by great margins. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection of Thyroid Disease Through Machine Learning Technique 25

Detection of Thyroid Disease Through Machine Learning Techni...

引用

25th International Arab Conference on Information technology, ACIT 2024

作者： Almomani, Mutaz Al-Qerem, Ahmad Nashwan, Shadi Jebreen, Issam Rajab, Mohammed Alauthman, Mohammad Jeadi, Mohammad Elrashidi, Ali Zarqa University Faculty of Information Technology Computer Science Department Zarqa13110 Jordan Middle East University Faculty of Information Technology Cybersecurity Department Amman11831 Jordan University Headquarter University of Anbar Ramadi Iraq University of Petra Department of Information Security Amman11196 Jordan University of Business and Technology Department of Electrical Engineering Jeddah21432 Saudi Arabia

ISBN: (纸本)9798331540012

Thyroid disease, one of the most common endocrine disorders, requires prompt diagnosis to effectively treat it. To improve diagnostic precision and expedite medical procedures, this paper explores the use of Machine Learning (ML) approaches for the early identification and categorization of thyroid diseasees. Sophisticated machine learning methods, including support vector machines, neural networks, and decision trees, are used to leverage a variety of datasets. These models outperform traditional diagnostic techniques in their capacity to identify complex patterns and minute variations in thyroid function parameters. The application of machine learning to the diagnosis of thyroid disease not only increases diagnostic accuracy but also makes preventive healthcare approaches possible. Personalized risk assessments are made possible by ML models, which analyze a wide range of patient-specific characteristics and help to improve the targeting of therapies. Furthermore, decision-making procedures are accelerated by the real-time processing powers of machine learning systems, which may shorten the interval between diagnosis and the start of therapy. this paper emphasizes how machine learning has revolutionized the diagnosis of thyroid disease and how it has the potential to completely change clinical procedures. The integration of sophisticated algorithms and extensive datasets presents opportunities for enhanced precision, effectiveness, and customization of diagnostic methods, which might eventually lead to better patient outcomes and more efficient use of healthcare resources for thyroid condition treatment. In this paper, the results were as follows: Two classifiers performed the best: LMT and LogitBoost. The Trees and Meta-learning strategy performed the best learning strategy, while the CorrelationAttributeEval and InfoGainAttributeEval methods performed the best feature selection. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A secure quantum homomorphic encryption ciphertext retrieval scheme

引用

Soft Computing 2025年第3期29卷 1497-1509页

作者： Cheng, Zhen-Wen Chen, Xiu-Bo Xu, Gang Chang, Yan Miao, Li-Hua Yang, Yi-Xian Wang, Ya-Lan School of Data and Computer Science Shandong Women’s University Jinan250300 China Information Security Center State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China School of Information Science and Technology North China University of Technology Beijing100144 China School of Cybersecurity Chengdu University of Information Technology Chengdu610225 China Huawei Technologies Co. Ltd Shenzhen518129 China Department of Computer Science Faculty of Engineering and Physical Sciences University of Surrey Surrey GuildfordGU2 7XH United Kingdom

In a recent paper (Gong et al. Quantum Inf Process 19:3, 2020), a novel ciphertext retrieval scheme based on the Grover algorithm and quantum homomorphic encryption was presented. In this scheme, when the server performs the operation of marking the solution on the user’s encrypted state in the Grover iteration, it needs to remove many gate-errors generated in the homomorphic evaluation of the T gate. And the server could judge this specific solution from the quantum circuit of marking the solution. It makes this scheme unable to achieve the low-cost and secure ciphertext retrieval. Therefore, we improve the Gong et al.’s scheme and propose a secure quantum homomorphic encryption ciphertext retrieval scheme. In our scheme, the trusted third party is introduced to cooperate with the server to execute the Grover algorithm. In each Grover iteration, the trusted third party can quickly mark the solution on the plaintext state, encrypt the marked state, and transmit it to the server. Then the server performs the remaining operations of this Grover iteration on the encrypted state. The trusted third party finally decrypts the iterated state. This cooperative approach ensures that the number of auxiliary qubits required and extra quantum gates executed in our scheme are lower than the Gong et al.’s scheme. By analyzing the security of our scheme, we confirm that the server and the trusted third party will not be informed of this solution. Thus, our scheme realizes the secure ciphertext retrieval with low computational overhead. We utilize IBM’s Qiskit framework to simulate our scheme, and the experimental result shows that our scheme is correct. It is worth noting that the low-cost and secure ciphertext retrieval will play a crucial role in modern information security and privacy protection. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2025.

关键词： Ciphertext

来源：评论

学校读者我要写书评

暂无评论

Enhancing Image security Using Novel Scrambling and Chaotic Techniques with ChaCha20 Algorithm

Enhancing Image Security Using Novel Scrambling and Chaotic ...

引用

International Conference on Computing and Networking technology (ICCNT)

作者： Datta Sai Manikanta Narayana Karun Kumar Enaganti P Mathivanan Department of Computer Science and Engineering(Cyber Security) Amrita School of Computing Amrita Vishwa Vidyapeetham Chennai India Department of Electronics and Communication Engineering Amrita School of Engineering Amrita Vishwa Vidyapeetham Chennai India

ISBN: (数字)9798350370249

ISBN: (纸本)9798350370270

The importance of protecting the privacy and security of shared data has increased along with the popularity of image-sharing services. In this paper, we propose a method to improve image transmission security through the use of encryption. Our process has two steps: scrambling, which causes uncertainty, and encryption, which causes information to spread. To create confusion, the image is split into matrices and rotated recursively during the scrambling phase. Furthermore, the security of the image is improved by employing a distinctive scrambling technique to encrypt the pixel coordinates. In the encryption stage, a chaotic map is constructed to produce a key, which is subsequently encrypted with the ChaCha20 stream cipher. The results show that our technology is better at protecting images than other encryption methods. By protecting images from manipulation and illegal access, technology also improves their authenticity and integrity throughout transmission.

关键词： Data privacy Ciphers Uncertainty Chaotic communication Image communication Streaming media Encryption

来源：评论

学校读者我要写书评

暂无评论

A Survey on Semantic Communication Networks: Architecture, security, and Privacy

引用

IEEE Communications Surveys and Tutorials 2024年

作者： Guo, Shaolong Wang, Yuntao Zhang, Ning Su, Zhou Luan, Tom H. Tian, Zhiyi Shen, Xuemin Xi'An Jiaotong University School of Cyber Science and Engineering Xi'an China University of Windsor Department of Electrical and Computer Engineering Windsor Canada University of Technology Sydney School of Computer Science Sydney Australia University of Waterloo Department of Electrical and Computer Engineering Waterloo Canada

With the rapid advancement and deployment of intelligent agents and artificial general intelligence (AGI), a fundamental challenge for future networks is enabling efficient communications among agents. Unlike traditional human-centric, data-driven communication networks, the primary goal of agent-based communication is to facilitate coordination among agents. Therefore, task comprehension and collaboration become the key objectives of communications, rather than data synchronization. Semantic communication (SemCom) aims to align information and knowledge among agents to expedite task comprehension. While significant research has been conducted on SemCom for two-agent systems, the development of semantic communication networks (SemComNet) for multi-agent systems remains largely unexplored. In this paper, we provide a comprehensive and up-to-date survey of SemComNet, focusing on their fundamentals, security, and privacy aspects. We introduce a novel three-layer architecture for multi-agent interaction, comprising the control layer, semantic transmission layer, and cognitive sensing layer. We explore working modes and enabling technologies, and present a taxonomy of security and privacy threats, along with state-of-the-art defense mechanisms. Finally, we outline future research directions, paving the way toward intelligent, robust, and energy-efficient SemComNet. This survey represents the first comprehensive analysis of SemComNet, offering detailed insights into its core principles as well as associated security and privacy challenges. © 2024 IEEE.

关键词： Differential privacy

来源：评论

学校读者我要写书评

暂无评论

Successive Interference Cancellation Approach to Estimated Outage and Coverage Probability for UDN B5G Network

Successive Interference Cancellation Approach to Estimated O...

引用

IEEE International Conference on Artificial Intelligence in engineering and technology (IICAIET)

作者： Faizan Qamar Anand Gachhadar Syed Hussain Ali Kazmi Rosilah Hassan Faculty of Information Science and Technology Center for Cyber Security Universiti Kebangsaan Malaysia (UKM) Selangor Malaysia Department of Electronics and Computer Engineering Institute of Engineering Tribhuvan University Kathmandu Nepal

The rapid evolution of wireless communication technologies has led to the emergence of Ultra-Dense Networks (UDNs) in Beyond 5G (B5G) systems, providing unprecedented connectivity and capacity. However, the dense deployment of base stations in UDNs results in severe interference, leading to considerable performance challenges. To tackle this issue, the Successive Interference Cancellation (SIC) approach has gained attention as a promising technique to enhance system performance. This research article explores the potential of SIC implementation in 5G UDN. The primary contribution of this work is summarized as follows. Firstly, an improved SIC technique is developed to validate the theoretical study of SIC in a multi-tier 5G UDN. This technique enhances the accuracy of outage probability and coverage probability calculations by employing a stochastic geometry model that accurately represents the real-world scenario, considering the random distribution of both users and base stations within the UDN. Secondly, numerical simulations are conducted to demonstrate the effectiveness of the proposed SIC technique, surpassing traditional methods. The simulation results are compared with Zero Forcing (ZF) to assess the validity and applicability of the concept and validate the theoretical findings. This research contributes to advancing the understanding and practical implementation of SIC in UDN, paving the way for improved network performance and capacity in future wireless communication systems.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Empowering Small and Medium Enterprises with Data Analytics for Enhanced Competitiveness 13

Empowering Small and Medium Enterprises with Data Analytics ...

引用

13th IEEE International Conference on Control System, Computing and engineering, ICCSCE 2023

作者： Mosbah, Aissa Ali, Musab A. M. Tahir, Nooritawati Md Dhofar University College of Commerce and Business Administration Salalah Oman University of Technology and Applied Sciences Ibri Oman International Information Technology University Department of Computer Engineering and Information Security Almaty Kazakhstan Universiti Teknologi Mara School of Electrical Engineering College of Engineering Malaysia Malaysia

ISBN: (纸本)9798350323184

In today's competitive landscape, Small and Medium-sized Enterprises (SMEs) are increasingly embracing business data analytics to gain valuable insights and make informed decisions. However, the true essence of big data lies not only in its volume but also in the analysis process and the derived insights that aid managers in making effective business choices. Despite this, limited knowledge exists regarding SMEs' utilization of data analytics and its potential in facilitating informed decision-making. Therefore, this paper aims to elucidate the concept of business data analytics within the context of SMEs and outline the essential requirements for its effective implementation, enabling SMEs to leverage data analytics for enhanced competitiveness. It is proposed that the foundation of a successful data analytics system for SMEs should encompass four key elements: data, people, technology, and process. The degree to which data analytics contributes to a firm's competitiveness is largely influenced by four factors: data quality, well-defined objectives, the caliber of analytic tools and techniques, and analytical skills. Data generates information and insights, which in turn foster knowledge that ultimately leads to wisdom. However, due to limited resources, SMEs may be less inclined to engage in advanced predictive and prescriptive analytics compared to larger firms. © 2023 IEEE.

关键词： Decision making

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：