检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Tang, Duoxun Cao, Yuxin Xiao, Xi Wang, Derui Wen, Sheng Zhu, Tianqing The College of Science Sichuan Agricultural University Ya’an China The School of Computing National University of Singapore Singapore The Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen China The Cybersecurity and Quantum Systems Group CSIRO’s Data61 Australia The School of Science Computing and Engineering Technologies Swinburne University of Technology MelbourneVIC Australia The Faculty of Data Science City University of Macau China

Video classification systems based on Deep Neural Networks (DNNs) have demonstrated excellent performance in accurately verifying video content. However, recent studies have shown that DNNs are highly vulnerable to adversarial examples. Therefore, a deep understanding of adversarial attacks can better respond to emergency situations. In order to improve attack performance, many style-transfer-based attacks and patch-based attacks have been proposed. However, the global perturbation of the former will bring unnatural global color, while the latter is difficult to achieve success in targeted attacks due to the limited perturbation space. Moreover, compared to a plethora of methods targeting image classifiers, video adversarial attacks are still not that popular. Therefore, to generate adversarial examples with a low budget and to provide them with a higher verisimilitude, we propose a novel black-box video attack framework, called Stylized Logo Attack (SLA). SLA is conducted through three steps. The first step involves building a style references set for logos, which can not only make the generated examples more natural, but also carry more target class features in the targeted attacks. Then, reinforcement learning (RL) is employed to determine the style reference and position parameters of the logo within the video, which ensures that the stylized logo is placed in the video with optimal attributes. Finally, perturbation optimization is designed to optimize perturbations to improve the fooling rate in a step-by-step manner. Sufficient experimental results indicate that, SLA can achieve better performance than state-of-the-art methods and still maintain good deception effects when facing various defense methods. We believe that the proposed SLA can raise awareness among the security community about the reliability and security of video classification systems and serve as a memorandum of possible attack methods for the future. Copyright © 2024, The Authors. All rights

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Assistive Technical Communication of Montenegrin eServices: a Case Study 27

Assistive Technical Communication of Montenegrin eServices: ...

引用

27th International Conference on Information Technology, IT 2023

作者： Simon, Aniko Lakovic, Luka Kovacevic, Pavle Kara, Peter A. Ognjanovic, Ivana Sendelj, Ramo Reich, Christoph Roganovic, Milovan Mantas, John Bokor, Laszlo Sigma Technology Budapest1093 Hungary University of Donja Gorica Faculty for Information Systems and Technologies Podgorica81000 Montenegro Budapest University of Technology and Economics Faculty of Electrical Engineering and Informatics Department of Networked Systems and Services Budapest1111 Hungary Kingston University Wireless Multimedia and Networking Research Group Department of Computer Science School of Computer Science and Mathematics Faculty of Science Engineering and Computing LondonKT1 2EE United Kingdom University of Donja Gorica Humanistic Studies Podgorica81000 Montenegro Furtwangen University Institute of Data Science Cloud Computing and It Security Furtwangen78120 Germany Clinical Centre of Montenegro Clinic for Neurology Podgorica81000 Montenegro National and Kapodistrian University of Athens Faculty of Nursing School of Health Sciences Goudi 11527 Greece

ISBN: (纸本)9798350397512

With the advancement of information technology in the recent decades, digital and online services have become essential components of everyday life in Europe. Montenegro is no different in this regard. However, as digital literacy in the country is still in a developing phase in comparison with most countries of the EU, a higher portion of its citizens may rely on assistive technical communication. In this paper, we provide a case study on the assistive technical communication of Montenegrin eServices. The work addresses the sectors of online banking, healthcare services, higher education, national administrative services, and utilities. Our findings highlight the diversity in terms of implemented assistive technical communication, and distinguish usage contexts on the level of adequacy. Yet as the functionalities of Montenegrin eServices are expected to gradually expand in the upcoming years, assistive technical communication must aim to handle the higher extents of service complexity. © 2023 IEEE.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Visible Light Positioning Method for Indoor Line-of-Sight Scene Based on Time Series Coding 9

Visible Light Positioning Method for Indoor Line-of-Sight Sc...

引用

9th IEEE International Conference on data science in Cyberspace, DSC 2024

作者： Yu, Yonghao Guo, Yongde Zhao, Dawei Fu, Kexue Tang, Yongwei Wang, Qinyuan City University of Macau Faculty of Data Science China Qilu University of Technology Shandong Academy of Sciences Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center National Supercomputer Center in Jinan Jinan China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Shandong University School of Mechanical Engineering Key Laboratory of High Efficiency and Clean Mechanical Manufacture Ministry of Education Jinan China

ISBN: (纸本)9798350391367

Existing indoor visible light positioning methods, such as those based on fingerprint database algorithms, are complex to construct and consume significant resources. In response to this issue, the text proposes an end-to-end indoor visible light positioning method that samples continuous signals at a small number of random coordinate positions in indoor environments. Through a deep learning method based on attention mechanism, a nonlinear mapping between the received signal and spatial position coordinates is constructed, and the time series properties in the received signal are encoded as a feature in the data. The method is further improved by combining residual networks to improve accuracy. Through simulation experiments, it has been verified that the deep learning based localization method described in this article can achieve sub meter level accuracy on small sample datasets, and it has been proven that time series features have a significant impact on localization accuracy in indoor visible light positioning algorithms based on deep learning. © 2024 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Optimizing Patient Satisfaction Surveys and Feedback with Cloud computing and NLP Techniques 8

Optimizing Patient Satisfaction Surveys and Feedback with Cl...

引用

8th International Conference on I-SMAC (IoT in Social, Mobile, Analytics and Cloud), I-SMAC 2024

作者： Jayanthi, L.N. Shanmugam, Kannan Suma, Challapalli Sagar, B.S. Maniraj, S.P. Ganeshbabu, T.R. Saveetha College of Liberal Arts and Sciences Department of Commerce Tamil Nadu Chennai India Vit Bhopal University School of Computing Science and Engineering Department of Gaming Technology Madhapradesh Bhopal India Department of Computer Science and Engineering Andhra Pradesh Bhimavaram India Reva University Department of Electrical and Electronics Engineering Karnataka Bengaluru India Faculty of Engineering & Technology Department of Data Science and Business Systems Chennai Tamil Nadu Kattankulathur India Department of Electronics and Communication Tamil Nadu Namakkal India

ISBN: (纸本)9798350376425

Healthcare quality assessment and identification of opportunities for improvement are crucially facilitated by patient satisfaction surveys. Traditional approaches sometimes face difficulties in handling substantial amounts of written comments and obtaining real useful data. It presents a new method that combines cloud computing with Natural Language Processing (NLP) approaches to enhance the analysis of patient satisfaction data. By using cloud platforms, it can effectively manage large datasets and provide scalable, cost-efficient processing. The use of NLP methods, such as text mining and sentiment analysis, enables the conversion of unstructured input into structured insights, thereby uncovering the fundamental patient feelings and patterns. This connection enables the analysis of data in real-time also improving the accuracy of interpreting feedback and facilitating fast enhancements in healthcare services. Future research will prioritise the improvement of NLP algorithms and the investigation of supplementary cloud-based technologies to enhance the accuracy and efficiency of patient satisfaction analysis to improved patient care and experience. © 2024 IEEE.

关键词： Sentiment analysis

来源：评论

学校读者我要写书评

暂无评论

Descriptor: Egocentric Action Recognition for Bengali Sign Language Detection dataset (Ego-SLD)

IEEE Data Descriptions

引用

IEEE data Descriptions 2025年 2卷 102-112页

作者： Asfak Ali Bibek Das Ahmad Sami Al-Shamayleh Sujatro Sarkar Chinmoyee Ray Sayoni Mandal Saifuddin Sk Adnan Akhunzada Department of Electronics and Telecommunication Engineering Jadavpur University Kolkata India Department of Data Science and Artificial Intelligence Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan Department of Electrical Engineering Jadavpur University Kolkata India College of Computing and Information Technology University of Doha for Science and Technology Doha Qatar

Sign language recognition integrates computer vision and natural language processing to automatically interpret hand gestures and translate them into spoken or written Bengali. The primary goal is to bridge the communication gap between sign language users and non-users by recognizing gestures, movements, postures, and facial expressions that correspond to spoken language elements. Since hand gestures are the cornerstone of sign language communication, they play a pivotal role in improving the accuracy of sign language recognition systems. This article introduces Ego-SLD, a video dataset specifically designed for egocentric action recognition of Bangla sign language used in daily life situations. The dataset contains videos of 16 commonly used words, collected from 12 individuals (ten males and two females) aged between 16 and 42 years. Each participant provided two samples of each word in an indoor environment with standard lighting conditions. Ego-SLD is a crucial resource for the automatic recognition of Bangla sign language and holds significant potential to benefit the deaf community. Moreover, it serves as a valuable dataset for researchers focusing on vision-based sign language detection, hand gesture recognition, and egocentric action recognition. IEEE SOCIETY/COUNCIL Computer Society data TYPE/LOCATION Video; Jadavpur University, Kolkata, West Bengal, India data DOI/PID https://***/10.21227/kbeg-fa06

关键词： Sign language Hands Recording Annotations Machine learning Accuracy Lighting Face recognition Cleaning Training

来源：评论

学校读者我要写书评

暂无评论

AI-based Framework for Discriminating Human-authored and AI-generated Text

IEEE Transactions on Artificial Intelligence

引用

IEEE Transactions on Artificial Intelligence 2024年

作者： Wani, Mudasir Ahmad Abd El-Latif, Ahmed A. Elaffendi, Mohammad Hussain, Amir Prince Sultan University EIAS Data Science Lab College of Computer and Information Sciences Center of Excellence in Quantum and Intelligent Computing Riyadh11586 Saudi Arabia Menoufia University Department of Mathematics and Computer Science Faculty of Science Shebin El-Koom32511 Egypt Edinburgh Napier University School of Computing Merchiston Campus EdinburghEH10 5DT United Kingdom

Deep learning techniques are increasingly adept at distinguishing between human-written and AI-generated text. This study presents a deep learning-based text classification system to discern the source of text - whether it's generated by AI or authored by a human. We compiled a comprehensive and diverse dataset incorporating existing datasets, real-time tweets, and synthetic data generated by cutting-edge AI models such as Google Bard and OpenAI's ChatGPT. Seven deep learning techniques including Convolutional Neural Networks (CNN), Artificial Neural Networks (ANN), Recurrent Neural Networks (RNN), Long Short-Term Memory networks (LSTM), Gated Recurrent Unit (GRU), Bidirectional LSTM (BiLSTM), and Bidirectional RNN (BiRNN) and four text embedding techniques namely One-hot, Word2Vec, TF-IDF, and BERT, are employed to perform 28 experiments (4∗7). Our findings exhibit outstanding performance across all models. BERT-based models notably outshine the others, with BERT-CNN achieving the highest accuracy of 98.87%, an MCC of 0.9742, and an F1 measure of 0.9916. Following closely, Bert-BiLSTM attained an accuracy, MCC, and F1 score of 98.77%, 0.9720, and 0.9909, respectively. This paper demonstrates the effectiveness of deep learning approaches in distinguishing between human and AI-generated text, with potential applications in automated content moderation, detection of AI-generated spam, and safeguarding the authenticity of user-generated content. © 2020 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Phase transition to chaos in complex ecosystems with non-reciprocal species-resource interactions

arXiv

引用

arXiv 2023年

作者： Blumenthal, Emmy Rocks, Jason W. Mehta, Pankaj Department of Physics Boston University BostonMA02215 United States Faculty of Computing and Data Science Boston University BostonMA02215 United States

Non-reciprocal interactions between microscopic constituents can profoundly shape the large-scale properties of complex systems. Here, we investigate the effects of non-reciprocity in the context of theoretical ecology by analyzing a generalization of MacArthur’s consumer-resource model with asymmetric interactions between species and resources. Using a mixture of analytic cavity calculations and numerical simulations, we show that such ecosystems generically undergo a phase transition to chaotic dynamics as the amount of non-reciprocity is increased. We analytically construct the phase diagram for this model and show that the emergence of chaos is controlled by a single quantity: the ratio of surviving species to surviving resources. We also numerically calculate the Lyapunov exponents in the chaotic phase and carefully analyze finite-size effects. Our findings show how non-reciprocal interactions can give rise to complex and unpredictable dynamical behaviors even in the simplest ecological consumer-resource models. © 2023, CC BY.

关键词： Lyapunov methods

来源：评论

学校读者我要写书评

暂无评论

Generative Adversarial Networks for Spatio-Spectral Compression of Hyperspectral Images

Generative Adversarial Networks for Spatio-Spectral Compress...

引用

Workshop on Hyperspectral Image and Signal Processing: Evolution in Remote Sensing, WHISPERS

作者： Martin Hermann Paul Fuchs Akshara Preethy Byju Alisa Walda Behnood Rasti Begüm Demir Faculty of Electrical Engineering and Computer Science Technische Universität Berlin Germany Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India BIFOLD - Berlin Institute for the Foundations of Learning and Data Germany

ISBN: (数字)9798331513139

ISBN: (纸本)9798331513146

Deep learning-based hyperspectral image (HSI) compression has recently attracted great attention in remote sensing due to the growth of hyperspectral data archives. Most of the existing models achieve either spectral or spatial compression and do not jointly consider the spatio-spectral redundancies present in HSIs. To address this problem, in this paper, we propose High Fidelity Compression (HiFiC)-based models for spatio-spectral compression of HSIs. In detail, we introduce two new models: i) HiFiC using Squeeze and Excitation (SE) blocks (denoted as HiFiCs E ); and ii) HiFiC with 3D convolutions (denoted as HiFiC 3D ) in the framework of compression of HSIs. We analyze the effectiveness of HiFiCs E and HiFiC 3D in compressing the spatio-spectral redundancies with channel attention and inter-dependency analysis. Experimental results show the efficacy of the proposed models in performing spatio-spectral compression, while reconstructing images at reduced bitrates with higher reconstruction quality. The code of the proposed models is publicly available at https://***/rsim/HSI-SSC.

关键词： Convolutional codes Solid modeling Image coding Three-dimensional displays Convolution Redundancy Bit rate Transform coding Image reconstruction Hyperspectral imaging

来源：评论

学校读者我要写书评

暂无评论

Remote Sensing data-Based Satellite Image Analysis in Water Quality Detection for Public Health data Modelling

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 532-541页

作者： Balakrishnan, S. Preetam Raj, P Michael Somasekar, J. Kumar, Kambala Vijaya Amutha, S. Sangeetha, A. Department of Computer Science and Engineering Aarupadai Veedu Institute of Technology (AVIT) Vinayaka Mission’s Research Foundation (Deemed to be University) Chennai India Department of Computer Science and Engineering MLR Institute of Technology Telangana Dundigal Hyderabad 500043 India Department of Computer Science and Engineering Faculty of Engineering and Technology JAIN (Deemed-to-be-University) Karnataka Bengaluru 562112 India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation Vaddeswaram AP India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R & amp D Institute of Science and Technology Tamilnadu Chennai India Department of Artificial Intelligence and Data Science Kongunadu College of Engineering and Technology TamilNadu Tholurpatti India

One of the most important aspects of environmental sustainability is water quality monitoring. The ecology is impacted by poor water quality in addition to aquatic life. With the volume of data being collected from satellite systems, the issue of effectively and automatically extracting water bodies is growing more pressing. One of the most important things to do for managing and safeguarding water resources is to conduct extensive monitoring of water quality parameters, or WQPs. It is still difficult to monitor optically inactive WQPs in inland waters, such as total nitrogen (TN), ammoniacal nitrogen (AN), and total phosphorus (TP). Water quality (WQ) classification and prediction can be greatly enhanced with the use of artificial intelligence (AI). This research proposes novel method in healthcare detection by water quality analysis based on classification utilising ML model. Input is collected as healthcare dataset based on water quality as well as processed for noise removal and normalisation. The processed data features are extracted and classified utilising reinforcement Gaussian stacked layer network with variational fuzzy Markov basis neural network. In order to suggest best course of action for the water bodies, it is imperative that any study look into the spatiotemporal changes of the dominant water quality parameters (WQPs). WQP concentrations have typically been determined by extensive fieldwork. These findings could help identify and regulate non-point source pollution, offer a large-scale spatial picture of the water quality, and pinpoint vulnerable locations and times of water pollution. Experimental analysis is carried out for various water sample dataset in terms of detection accuracy, mean precision, recall, F-1 score and AUC. The proposed technique obtained 97% of detection accuracy, 95% of recall, 91% of F-1 score, 96% of AUC, and 94% of MAP. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Classification Fuzzy Markov basis Healthcare detection Machine learning model Water quality analysis

来源：评论

学校读者我要写书评

暂无评论

A Behavioural Network Traffic Novelty Detection for the Internet of Things Infrastructures 1

引用

11th International Symposium on Parallel Architectures, Algorithms and Programming, PAAP 2020

作者： Hamad, Salma Abdalla Sheng, Quan Z. Tran, Dai Hoang Zhang, Wei Emma Nepal, Surya Department of Computing Faculty of Science and Engineering Macquarie University Sydney Australia School of Computer Science The University of Adelaide Adelaide Australia Data61 CSIRO Sydney Australia

ISBN: (数字)9789811600104

ISBN: (纸本)9789811600098

The Internet of Things (IoT) applied solutions are changing the way the world perceives technology. IoT devices are now being used in a wide range of applications to transfer or share relevant information, hence reducing human interventions. With such widespread IoT solutions, security becomes a significant concern. Many of the IoT devices are vulnerable due to several reasons, including in-secure implementations, poor life cycle management, and inappropriate configurations, leading to an increase in the risk of these devices getting exposed and attacked. However, the current security approaches for detecting compromised IoT devices are inefficient, especially for zero-day attacks. Since no one knows how a new attack would look like, it will be useful to monitor and detect anomalies using accurate detection techniques. This work probes the possibility of detecting IoT network traffic anomalies using novelty detection techniques;thus, it can detect compromised IoT devices. One of this work’s main contributions is developing an IoT anomaly detection system named Behavioural Novelty Detection for IoT Infrastructure (BND-IoT). BND-IoT trains a neural network with novel selected behavioural features extracted from benign traffic only and then uses the novelty techniques to detect any unusual traffic patterns. We show that the presented approach effectively detects anomalies within IoT devices’ network traffic with a robust average F1-score of 96.7% and a low false rejection rate of 7%. © 2021, Springer Nature Singapore Pte Ltd.

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：