检索结果-内蒙古大学图书馆

IEEE Workshop on Applications of computer Vision (WACV)

作者： Alberto Presta Enzo Tartaglione Attilio Fiandrotti Marco Grangetto Pamela Cosman University of Turin Italy LTCI Télécom Paris Institut Polytechnique de Paris Dept. of Electrical and Computer Engineering UC San Diego CA USA

ISBN: (数字)9798331510831

ISBN: (纸本)9798331510848

Learned progressive image compression is gaining momentum as it allows improved image reconstruction as more bits are decoded at the receiver. We propose a progressive image compression method in which an image is first represented as a pair of base-quality and top-quality latent representations. Next, a residual latent representation is encoded as the element-wise difference between the top and base representations. Our scheme enables progressive image compression with element-wise granularity by introducing a masking system that ranks each element of the residual latent representation from most to least important, dividing it into complementary components, which can be transmitted separately to the decoder in order to obtain different reconstruction quality. The masking system does not add further parameters or complexity. At the receiver, any elements of the top latent representation excluded from the transmitted components can be independently replaced with the mean predicted by the hyperprior architecture, ensuring reliable reconstructions at any intermediate quality level. We also in-troduced Rate Enhancement Modules (REMs), which refine the estimation of entropy parameters using already decoded components. We obtain results competitive with state-of-the-art competitors, while significantly reducing computational complexity, decoding time, and number of parameters.

关键词： computer vision Image coding Estimation Receivers computer architecture Entropy Decoding Reliability Computational complexity Image reconstruction

来源：评论

学校读者我要写书评

暂无评论

A Study on Traceable Group Signature Scheme for Blockchain

A Study on Traceable Group Signature Scheme for Blockchain

引用

Information and Network Technologies (ICINT), International Conference on

作者： Hyo-Jin Song Im-Yeong Lee Dept. of Software Convergence Soonchunhyang Univ. Asan-si 31538 Republic of Korea Dept. of Computer Software Engineering Soonchunhyang Univ. Asan-si 31538 Republic of Korea

A blockchain is a decentralized database system in which a ledger containing transactions is stored and maintained identically by all through consensus among network participants without a central server. Instead of having a central server, network participants make sure that everyone stores and maintains the same ledger containing transactions through consensus. Integrity and reliability of the data stored in the blockchain are guaranteed, but on the other hand, privacy issues may arise. The pseudonymity of the public key reused in transactions causes a privacy invasion of the user’s behavioral pattern, asset size, and offline identity. Therefore, instead of assigning unique public keys to everyone, they are provided through a single signature in a blockchain environment. It can also be described as a method for ensuring anonymity by having members of the same group use the same public key in a transaction while employing the group signature, which has been studied in this paper. This paper defines the key used for group signature is defined as a composition of a “group private key” and a “partial key”. Mainly among them, we consider the leakage of the partial key. In the proposed scheme, it is possible to trace the leaker and the signer from the signature generated by the outsider with the leaked partial key. In this paper, we provide a secure traceable group signature scheme to cope with the leakage of the group signing key.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Security and Threat Detection through Cloud-Based Wazuh Deployment

Security and Threat Detection through Cloud-Based Wazuh Depl...

引用

Humanitarian Technology Conference (KHI-HTC), IEEE Karachi Section

作者： Syed Moiz Abdul Majid Abdul Basit Mansoor Ebrahim Abdul Ahad Abro Mehwish Naeem Dept. of Computer Science Iqra University Karachi Pakistan Dept. of Cyber Security Institute of Business Administration (IBA-CICT) Karachi Pakistan Dept. of Computer Science Indus University Karachi Pakistan Dept. of Software Engineering Iqra University Karachi Pakistan University Libre de Bruxelles Brussels Belgium

In today's interconnected business landscape, security is the cornerstone of all organizations, irrespective of their size or industry. This research emphasizes the critical need to safeguard organizational assets from cyber threats and highlights the pivotal role that firewalls play in fortifying network and cyber systems. The challenge lies in maintaining updated firewall defenses to prevent server downtime and the circumvention of security measures. To address these concerns, this study introduces a novel approach by integrating Cloud Wazuh, a user-friendly solution tailored for non-technical personnel, providing streamlined deployment and customizable security rules. Leveraging Wazuh suite of tools, particularly the Host-Based Intrusion Detection System (HIDS), the research detects and mitigates potential threats, including patterns associated with attacks such as Port Scanning, Denial of Service (DoS), and Metasploit. Additionally, Wazuh offers a range of features, from Security Analytics to File Integrity Monitoring, to comprehensively protect against cyber threats. While implementing Cloud Wazuh may entail initial costs, it proves cost-effective compared to maintaining a dedicated IT security team. This research underscores how Cloud Wazuh deployment serves as a pivotal tool for organizations looking to strengthen their security measures, safeguard their data, and ensure uninterrupted operations in an increasingly digital and interconnected world.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Macula Swelling Detection using Retinal Fundus Images

Macula Swelling Detection using Retinal Fundus Images

引用

IEEE International Workshop on Imaging Systems and Techniques (IST)

作者： Rukham Mumtaz Khan Fazal Saadat Ali Khan Fauzia Khan Rafia Hassan Dept. of Computer Engineering National University of Sciences and Technology Islamabad Pakistan Dept. of Information Security National University of Sciences and Technology Islamabad Pakistan Dept. of Computer Science University of Tartu Tartu Estonia Dept. of Software Engineering Bahria University Islamabad Pakistan

Diabetic Macular Edema (DME) is an advanced symptom of Diabetic Retinopathy (DR) and can lead to irreversible vision loss. Macular Edema (ME) is the swelling of the macula, the part of the eye accountable for thorough central vision. The utilization of image processing in the detection of diabetic macular edema (DME) plays a crucial role in the field of medical imaging, effectively reducing the time and manual effort required by medical specialists to identify this disease. In this paper, we proposed a method that uses digital fundus images to analyze the swelling of the macula. The proposed algorithm consists of four steps, i.e., (i) retinal image dataset collection, (ii) retinal image pre-processing, (iii) feature extraction, and (iv) classification to categorize the disease into three different stages, i.e., normal, stage 1 (mild) and stage 2 (severe). The proposed method is tested on three databases, i.e., MESSIDOR, DMED, and the local dataset AFIO obtained from the local hospital in Pakistan. We use three parameters to check the validity of the proposed algorithm, i.e., visual inspection, accuracy, and area under calculation time. Our method achieves an average accuracy of 96.07 % with a sensitivity of 93.74 % and specificity of 97.32%. We also compare our results with other proposed methods, which shows our method performs better.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid ConvLSTM with Attention for Precise Driver Behavior Classification

Hybrid ConvLSTM with Attention for Precise Driver Behavior C...

引用

Artificial Intelligence and Knowledge engineering (AIKE)

作者： Ghulam Mustafa Seong-Je Cho Youngsup Hwang Dept. of Computer Engineering Sun Moon University Asan-si South Korea Dept. of Software Science Dankook University Yongin South Korea

Driving behavior classification plays an important role in many real-world applications, including traffic accident prevention, driver safety, usage-based insurance, and optimizing ridesharing services. In this research, we introduce a novel approach called Hybrid ConvLSTM with Attention for Driver Behavior Classification (HCLA-DBC), designed to achieve precise and reliable driver behavior classification. Our main focus is to distinguish three fundamental driving behavior classes: normal, drowsy, and aggressive, which play a vital role in supporting advanced driver-assistance systems (ADAS). To evaluate the performance of our proposed models, we conducted experiments using the publicly available UAH-DriveSet dataset. The evaluation comprised six distinct models, encompassing two machine learning models (SVM and Gradient Boosting) and four deep learning models (CNN, MLP, LSTM, and HCLADBC). Our HCLA-DBC model outperformed all other models and previous results on the same data. On the test data, it achieved an accuracy of 94.12%, precision of 94.24%, recall score of 94.12%, F1-score of 94.12%, and a macro-average ROC AUC of 98.83. These exceptional outcomes underscore the efficacy of our hybridized approach and its potential to significantly enhance driver behavior classification. The HCLA-DBC model not only promises new possibilities for driver behavior analysis but also paves the way for elevated ADAS capabilities and safer driving experiences.

关键词：

来源：评论

学校读者我要写书评

暂无评论

On the Importance of Performing App Analysis Within Peer Groups

arXiv

引用

arXiv 2022年

作者： Hassan, Safwat Li, Heng Hassan, Ahmed E. Dept. of Engineering Thompson Rivers University KamloopsBC Canada Dept. of Computer and Software Engineering Polytechnique Montréal MontréalQC Canada Queen's University KingstonON Canada

The competing nature of the app market motivates us to shift our focus on apps that provide similar functionalities and directly compete with each other (i.e., peer apps). In this work, we study the ratings and the review text of 100 Android apps across 10 peer app groups. We highlight the importance of performing peer-app analysis by showing that it can provide a unique perspective over performing a global analysis of apps (i.e., mixing apps from multiple categories). First, we observe that comparing user ratings within peer groups can provide very different results from comparing user ratings from a global perspective. Then, we show that peer-app analysis provides a different perspective to spot the dominant topics in the user reviews, and to understand the impact of the topics on user ratings. Our findings suggest that future efforts may pay more attention to performing and supporting app analysis from a peer group context. For example, app store owners may consider an additional rating mechanism that normalizes app ratings within peer groups, and future research may help developers understand the characteristics of specific peer groups and prioritize their efforts. © 2022, CC BY-NC-ND.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Malware Detection and Classification for Internet of Things Using Self-Attention Based Long Short-Term Memory 3

Malware Detection and Classification for Internet of Things ...

引用

3rd IEEE International Conference on Distributed Computing and Electrical Circuits and Electronics, ICDCECE 2024

作者： Sudhakar, K. Husain, Saif O. Babu, D. Raja Kumar, M. Ashok Dineshkumar, R. Nitte Meenakshi Institute Of Technology Dept. Of Ai & Ds Bengaluru India College Of Technical Engineering The Islamic University Department Of Computers Techniques Engineering Najaf Iraq Sr University Department Of Electrical And Electronics Engineering Warangal India Skyline University Nigeria Department Of Computer Science Software Engineering And Cyber Security Kano State Nigeria Saveetha School Of Engineering Saveetha Institute Of Medical And Technical Sciences Saveetha University Department Of Electronics And Communication Engineering Chennai India

ISBN: (纸本)9798350318609

The Internet of Things (IoT) connects numerous intelligent devices providing security features that interact with default settings accessed through applications. Additionally, Deep Learning (DL)-based mechanisms was involved for malware detection to identify and mitigate attacks. The Adaptive Synthetic Sampling (ADASYN) technique addresses class imbalances, especially when splitter class instances are distributed data in complex patterns. The proposed Self-Attention based Long Short-Term Memory (LSTM) classification method facilitates the handling of long-range dependencies in transferred data sequences offering high flexibility and adaptability to varying input lengths. For feature selection Particle Swarm Optimization (PSO) is utilized iteratively optimizes a solution in a high-dimensional space although it may have a low convergence rate due to its iterative process. The obtained results demonstrate the proposed Self-Attention based LSTM model achieves better accuracy reaching 98.05% on the NSL-KDD dataset and 99.01 % on the UNSW-NB15 dataset. These results ensure accurate classification compared to other existing methods, such as Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN). © 2024 IEEE.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Towards Motor Imagery Classification of Finger Tapping by Both Hands for Controlling a Finger-Arm Bionic Robot

Towards Motor Imagery Classification of Finger Tapping by Bo...

引用

International Winter Workshop on Brain-computer Interface (BCI)

作者： Seong-Hyun Yu Young-Min Go Hyeong-Yeong Park Seo-Jin Lee Minji Lee Ji-Hoon Jeong Dept. Computer Science Chungbuk National University Cheongju Republic of Korea School of Computer Science Chungbuk National University Cheongju Republic of Korea Dept. Biomedical Software Engineering The Catholic University of Korea Bucheon South Korea

In motor imagery, the greatest attention was paid to decoding signals from large muscles. However, there is a missing piece in helping people with finger issues or paralysis. This study investigates the potential advancements in neurorehabilitation by exploring the discriminative capabilities of electroencephalography (EEG) based classification in finger tapping. To improve neurorehabilitation strategies, we performed a comparative analysis of finger tapping classification during motor imagery and execution tasks. Using EEG signals, we employed machine learning and deep learning techniques, including support vector machines (SVM), linear discriminant analysis (LDA) and EEGNet. Our results indicate promising differences in EEG signatures between the two paradigms, with SVM, LDA, and EEGNet demonstrating varying degrees of efficacy in classification. These findings suggest potential implications for customized neurorehabilitation interventions. The study contributes to the affirmative possibility of effective rehabilitation strategies and is of particular relevance for patients with impaired motor function.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Performance Evaluation of Popular Deep Neural Networks for Neural Machine Translation 20

Performance Evaluation of Popular Deep Neural Networks for N...

引用

20th International Conference on Frontiers of Information Technology, FIT 2023

作者： Naeem, Muhammad Siddique, Abu Bakar Ali, Raja Hashim Arshad, Usama Abideen, Zain Ul Ali Khan, Talha Shah, Muhammad Huzaifa Zeeshan Ijaz, Ali Ali, Nisar Gik Institute of Engg. Sciences & Technology Faculty of Computer Science & Engineering Topi Pakistan University of Europe for Applied Sciences Dept. of Technology & Software Engineering Berlin Germany BCMaterials Basque Center for Materials Applications & Nanostructure Basque Country Leioa Spain University of Regina Faculty of Electronic Systems Engineering Regina Canada

ISBN: (纸本)9798350395785

The field of Neural Machine Translation (NMT) has shown impressive performance for quick and easy communication in various languages spoken all over the world. NMT helps us by improving communication between different languages. For this purpose, different sequential models are used such as Recurrent Neural Network (RNN), Long Short Term Memory (LSTM), and Gated Recurrent Units (GRU). Analysis among these different models are important for making language translation better and choose the best model for the right job. This research investigates the performance of these models on two distinct language datasets, English-to-German and English-to-Urdu. Based on accuracy metrics, the findings reveal that GRU having test accuracy (88.22% ) outperforms RNN (87.21% ), and LSTM (85.70% )demonstrating the highest translation accuracy, followed by RNN and LSTM exhibiting comparatively lower accuracy levels. © 2023 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Robust Phishing URL Classification Using FastText Character Embeddings and Hybrid Deep Learning

Robust Phishing URL Classification Using FastText Character ...

引用

Robotics, Automation, Artificial-intelligence and Internet-of-Things (RAAICON), 2019 IEEE International Conference on

作者： Abdullah Al-Sakib Zishad Hossain Limon Anamul Sakib Md Nuruzzaman Pranto Md Ariful Islam Shayma Sultana Md. Redwan Ahmed Shafiur Rahman Dept. of Information Technology Westcliff University CA USA Dept. of Computer Science Westcliff University CA USA Dept. of Business Administration International American University CA USA Dept. of Management Information System International American University CA USA Dept. of Computer Science and Engineering East West University Dhaka Bangladesh Dept. of Software Engineering Daffodil International University Dhaka Bangladesh

ISBN: (数字)9798331534400

ISBN: (纸本)9798331534417

Phishing attacks are a major cybersecurity threat that resulted in over 1.2 million incidents in the first half of 2020. These attacks caused substantial financial losses and posed risks to individuals and organizations. Being able to identify fraudulent websites is crucial in order to effectively address these potential risks. This study introduces a novel method for detecting phishing URLs by using word and character embeddings to capture complex URL patterns. We used a dataset of 80,000 URLs, including 50,000 legitimate ones and 30,000 phishing instances, and applied thorough preprocessing techniques. We utilized word embeddings in FastText to handle unseen words, with the added advantage of n-gram representations. Additionally, we captured character-level features through dense character embeddings. We trained several machine learning and deep learning models, and one model, the Convolutional Bidirectional LSTM (CBiLSTM), stood out with an accuracy of 99.01% and an F1-score of 99.08%. Furthermore, we made a thorough comparison with the most advanced techniques available, and our findings demonstrated clear superiority over previous research. This study presents an effective approach for classifying phishing URLs, providing a valuable tool to combat fraud and protect against identity theft, thereby helping to minimize the financial and emotional harm experienced by victims.

关键词： Deep learning Uniform resource locators Training Adaptation models Phishing Prevention and mitigation Encoding Tokenization Real-time systems Robots

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：