检索结果-内蒙古大学图书馆

arXiv 2022年

作者： Jiang, Wei Li, Gang Wang, Yibo Zhang, Lijun Yang, Tianbao National Key Laboratory for Novel Software Technology Nanjing University Nanjing China Department of Computer Science the University of Iowa Iowa City United States Department of Computer Science and Engineering Texas A&M University College Station United States

Variance reduction techniques such as SPIDER/SARAH/STORM have been extensively studied to improve the convergence rates of stochastic non-convex optimization, which usually maintain and update a sequence of estimators for a single function across iterations. What if we need to track multiple functional mappings across iterations but only with access to stochastic samples of O(1) functional mappings at each iteration? There is an important application in solving an emerging family of coupled compositional optimization problems in the form of Pmi=1 fi(gi(w)), where gi is accessible through a stochastic oracle. The key issue is to track and estimate a sequence of g(w) = (g1(w), . . ., gm(w)) across iterations, where g(w) has m blocks and it is only allowed to probe O(1) blocks to attain their stochastic values and Jacobians. To improve the complexity for solving these problems, we propose a novel stochastic method named Multi-block-Single-probe Variance Reduced (MSVR) estimator to track the sequence of g(w). It is inspired by STORM but introduces a customized error correction term to alleviate the noise not only in stochastic samples for the selected blocks but also in those blocks that are not sampled. With the help of the MSVR estimator, we develop several algorithms for solving the aforementioned compositional problems with improved complexities across a spectrum of settings with non-convex/convex/strongly convex/Polyak-Lojasiewicz (PL) objectives. Our results improve upon prior ones in several aspects, including the order of sample complexities and dependence on the strong convexity parameter. Empirical studies on multi-task deep AUC maximization demonstrate the better performance of using the new estimator. Copyright © 2022, The Authors. All rights reserved.

关键词： Error correction

来源：评论

学校读者我要写书评

暂无评论

Joint Admission Control and Resource Allocation of Virtual Network Embedding via Hierarchical Deep Reinforcement Learning

arXiv

引用

arXiv 2024年

作者： Wang, Tianfu Shen, Li Fan, Qilin Xu, Tong Liu, Tongliang Xiong, Hui Anhui Province Key Laboratory of Big Data Analysis and Application School of Computer Science University of Science and Technology of China Hefei230027 China The School of Big Data and Software Engineering Chongqing University ChinaScience Chongqing401331 China JD Explore Academy The UBTECH Sydney Artificial Intelligence Centre The School of Information Technologies Faculty of Engineering and Information Technologies The University of Sydney DarlingtonNSW2008 Australia Thrust of Artificial Intelligence Nansha Guangdong Guangzhou511400 China The Hong Kong University of Science and Technology Department of Computer Science and Engineering Hong Kong

As an essential resource management problem in network virtualization, virtual network embedding (VNE) aims to allocate the finite resources of physical network to sequentially arriving virtual network requests (VNRs) with different resource demands. Since this is an NP-hard combinatorial optimization problem, many efforts have been made to provide viable solutions. However, most existing approaches have either ignored the admission control of VNRs, which has a potential impact on long-term performances, or not fully exploited the temporal and topological features of the physical network and VNRs. In this paper, we propose a deep Hierarchical Reinforcement Learning approach to learn a joint Admission Control and Resource Allocation policy for VNE, named HRL-ACRA. Specifically, the whole VNE process is decomposed into an upper-level policy for deciding whether to admit the arriving VNR or not and a lower-level policy for allocating resources of the physical network to meet the requirement of VNR through the HRL approach. Considering the proximal policy optimization as the basic training algorithm, we also adopt the average reward method to address the infinite horizon problem of the upper-level agent and design a customized multi-objective intrinsic reward to alleviate the sparse reward issue of the lower-level agent. Moreover, we develop a deep feature-aware graph neural network to capture the features of VNR and physical network and exploit a sequence-to-sequence model to generate embedding actions iteratively. Finally, extensive experiments are conducted in various settings, and show that HRL-ACRA outperforms state-of-the-art baselines in terms of both the acceptance ratio and long-term average revenue. Our code is available at https://***/GeminiLight/hrl-acra. Copyright © 2024, The Authors. All rights reserved.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

On the Privacy of Mental Health Apps: An Empirical Investigation and its Implications for Apps Development

arXiv

引用

arXiv 2022年

作者： Iwaya, Leonardo Horn Ali Babar, M. Rashid, Awais Wijayarathna, Chamila Centre for Research on Engineering Software Technologies The University of Adelaide AdelaideSA5005 Australia Australia Department of Mathematics and Computer Science Karlstad University Karlstad Sweden Bristol Cyber Security Group Department of Computer Science University of Bristol United Kingdom

An increasing number of mental health services are offered through mobile systems, a paradigm called mHealth. Although there is an unprecedented growth in the adoption of mHealth systems, partly due to the COVID-19 pandemic, concerns about data privacy risks due to security breaches are also increasing. Whilst some studies have analyzed mHealth apps from different angles, including security, there is relatively little evidence for data privacy issues that may exist in mHealth apps used for mental health services, whose recipients can be particularly vulnerable. This paper reports an empirical study aimed at systematically identifying and understanding data privacy incorporated in mental health apps. We analyzed 27 top-ranked mental health apps from Google Play Store. Our methodology enabled us to perform an in-depth privacy analysis of the apps, covering static and dynamic analysis, data sharing behaviour, server-side tests, privacy impact assessment requests, and privacy policy evaluation. Furthermore, we mapped the findings to the LINDDUN threat taxonomy, describing how threats manifest on the studied apps. The findings reveal important data privacy issues such as unnecessary permissions, insecure cryptography implementations, and leaks of personal data and credentials in logs and web requests. There is also a high risk of user profiling as the apps' development do not provide foolproof mechanisms against linkability, detectability and identifiability. Data sharing among third parties and advertisers in the current apps' ecosystem aggravates this situation. Based on the empirical findings of this study, we provide recommendations to be considered by different stakeholders of mHealth apps in general and apps developers in particular. We conclude that while developers ought to be more knowledgeable in considering and addressing privacy issues, users and health professionals can also play a role by demanding privacy-friendly apps. Copyright © 2022, The Authors. All r

关键词： Data privacy

来源：评论

学校读者我要写书评

暂无评论

Scenario-Assisted Deep Reinforcement Learning

arXiv

引用

arXiv 2022年

作者： Yerushalmi, Raz Amir, Guy Elyasaf, Achiya Harel, David Katz, Guy Marron, Assaf Department of Computer Science and Applied Mathematics Weizmann Institute of Science Rehovot76100 Israel School of Computer Science and Engineering The Hebrew University of Jerusalem Givat Ram Jerusalem91904 Israel Software and Information Systems Engineering Ben-Gurion University of the Negev Beer-Sheva8410501 Israel

Deep reinforcement learning has proven remarkably useful in training agents from unstructured data. However, the opacity of the produced agents makes it difficult to ensure that they adhere to various requirements posed by human engineers. In this work-in-progress report, we propose a technique for enhancing the reinforcement learning training process (specifically, its reward calculation), in a way that allows human engineers to directly contribute their expert knowledge, making the agent under training more likely to comply with various relevant constraints. Moreover, our proposed approach allows formulating these constraints using advanced model engineering techniques, such as scenario-based modeling. This mix of black-box learning-based tools with classical modeling approaches could produce systems that are effective and efficient, but are also more transparent and maintainable. We evaluated our technique using a case-study from the domain of internet congestion control, obtaining promising results. Copyright © 2022, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Application of Neural Networks for Network Traffic Monitoring and Analysis

Application of Neural Networks for Network Traffic Monitorin...

引用

International Symposium on Multidisciplinary Studies and Innovative Technologies (ISMSIT)

作者： Oleksandr Kushnerov Pierre Murr Serhii Herasymov Stanislav Milevskyi Marharyta Melnyk Sergii Golovashych Department of Economic Cybernetics Sumy State University Sumy Ukraine Computer Engineering Department International University of Science and Technology in Kuwait Kuwait Kuwait Cybersecurity department National Technical University “Kharkiv polytechnic institute” Kharkiv Ukraine Department of Cyber Security and information protection SET University Kyiv Ukraine Department of Software Engineering and Management Intelligent Technologies National Technical University “Kharkiv polytechnic institute” Kharkiv Ukraine

ISBN: (数字)9798350354423

ISBN: (纸本)9798350354430

Monitoring and analyzing network traffic are critically important tasks in the context of increasing cyber threats. Traditional data processing methods often struggle to handle the large volumes and complexity of modern network traffic, necessitating the use of advanced technologies such as neural networks and machine learning. This article demonstrates the application of neural networks for monitoring and analyzing network traffic, highlighting their ability to learn from large datasets to detect complex patterns and anomalies. Using TensorFlow, we developed a neural network model based on an autoencoder that effectively identifies and classifies anomalies in network traffic. The model's effectiveness was validated using a synthetic dataset from Kaggle, showing high accuracy on both training and testing data. Our approach significantly improves the efficiency and accuracy of threat detection compared to traditional methods, making it a valuable tool for enhancing cybersecurity.

关键词： Training Accuracy Neural networks Telecommunication traffic Machine learning Data models Threat assessment computer security Monitoring Testing

来源：评论

学校读者我要写书评

暂无评论

Effects of term weighting approach with and without stop words removing on Arabic text classification

Effects of term weighting approach with and without stop wor...

引用

International Conference on Optimization and Applications (ICOA)

作者： Esra’a Alhenawi Ruba Abu Khurma Pedro A. Castillo Maribel G. Arenas Ayat Mahmoud Al-Hinawi Department of Software Engineering Faculty of Information Technology Al-Ahliyya Amman University Amman Jordan Department of Computer Science MEU Research Unit Faculty of Information Technology Middle East University Amman Jordan University of Granada Granada Spain Department of Allied Engineering Sciences Hashemite University Zarqa Jordan

Text classification is a technique for grouping articles into pre-defined categories. Prior to categorization, text documents have to be set up and organised in a form that is compatible with the data mining techniques. That has produced many term weighting techniques have been developed in the literature to improve the functionality of text categorization systems. This paper compares techniques for text classification based on when stop words are eliminated from the documents once and when they are not. We used an Arabic data set of 322 papers grouped into six subjects (health, politics, science, education, agriculture and finance) to research which is the influence of prior weighting of features approaches on classification outcomes with regard to accuracy, recall, precision, and F-measure values. Each document subset includes 50 documents, except the health one that includes 61. We carried out four experiments and checked results getting that only for precision, the term frequency feature weighting approach with stop word removal are more or less the same than for binary method. Moreover the conclusion for accuracy, recall and F-measure is that Feature weighting approach with stop word outperforms the Binary one. Additionally, if the phrase for weighting is the same for both methods, to remove stop word increases classification accuracy for all the experiments.

关键词：

来源：评论

学校读者我要写书评

暂无评论

AdvMask: A Sparse Adversarial Attack Based Data Augmentation Method for Image Classification

arXiv

引用

arXiv 2022年

作者： Yang, Suorong Li, Jinqiao Zhao, Jian Shen, Furao State Key Laboratory for Novel Software Technology Department of Computer Science and Technology Nanjing University Nanjing210023 China The State Key Laboratory for Novel Software Technology School of Electronic Science and Engineering Nanjing University Nanjing210023 China

Data augmentation is a widely used technique for enhancing the generalization ability of convolutional neural networks (CNNs) in image classification tasks. Occlusion is a critical factor that affects on the generalization ability of image classification models. In order to generate new samples, existing data augmentation methods based on information deletion simulate occluded samples by randomly removing some areas in the images. However, those methods cannot delete areas of the images according to their structural features of the images. To solve those problems, we propose a novel data augmentation method, AdvMask, for image classification tasks. Instead of randomly removing areas in the images, AdvMask obtains the key points that have the greatest influence on the classification results via an end-to-end sparse adversarial attack module. Therefore, we can find the most sensitive points of the classification results without considering the diversity of various image appearance and shapes of the object of interest. In addition, a data augmentation module is employed to generate structured masks based on the key points, thus forcing the CNN classification models to seek other relevant content when the most discriminative content is hidden. AdvMask can effectively improve the performance of classification models in the testing process. The experimental results on various datasets and CNN models verify that the proposed method outperforms other previous data augmentation methods in image classification tasks. Copyright © 2022, The Authors. All rights reserved.

关键词： Image classification

来源：评论

学校读者我要写书评

暂无评论

Transformers for 1D signals in Parkinson's disease detection from gait

arXiv

引用

arXiv 2022年

作者： Nguyen, Duc Minh Dimitri Miah, Mehdi Bilodeau, Guillaume-Alexandre Bouachir, Wassim Litiv Laboratory Dept. of Computer Engineering and Software Engineering Polytechnique Montréal Montréal Canada Téluq University Department of Science and Technology Montréal Canada

This paper focuses on the detection of Parkinson's disease based on the analysis of a patient's gait. The growing popularity and success of Transformer networks in natural language processing and image recognition motivated us to develop a novel method for this problem based on an automatic features extraction via Transformers. The use of Transformers in 1D signal is not really widespread yet, but we show in this paper that they are effective in extracting relevant features from 1D signals. As Transformers require a lot of memory, we decoupled temporal and spatial information to make the model smaller. Our architecture used temporal Transformers, dimension reduction layers to reduce the dimension of the data, a spatial Transformer, two fully connected layers and an output layer for the final prediction. Our model outperforms the current state-of-the-art algorithm with 95.2% accuracy in distinguishing a Parkinsonian patient from a healthy one on the Physionet dataset. A key learning from this work is that Transformers allow for greater stability in results. The source code and pre-trained models are released in https://***/DucMinhDimitriNguyen. Copyright © 2022, The Authors. All rights reserved.

关键词： Image recognition

来源：评论

学校读者我要写书评

暂无评论

Backpropagation on Dynamical Networks

arXiv

引用

arXiv 2022年

作者： Tan, Eugene Corrêa, Dèbora Stemler, Thomas Small, Michael The Department of Mathematics & Statistics The University of Western Australia CrawleyWA6009 Australia The Department of Computer Science & Software Engineering The University of Western Australia Crawley WA6009 Australia

Dynamical networks are versatile models that describe a variety of behaviours such as synchronisation and feedback. However, applying these models in real systems is difficult as prior information of the connectivity structure or local dynamics is often unknown and must be inferred from observations of network states. Additionally, the influence of coupling interactions further complicates the isolation of local node dynamics. Given the architectural similarities between dynamical networks and recurrent neural network (RNNs), we propose a network inference method based on the backpropagation through time algorithm used to train RNNs. This method aims to simultaneously infer both the connectivity structure and local node dynamics from node state observations. An approximation of local node dynamics is first constructed using a neural network. This is alternated with an adapted BPTT algorithm to regress corresponding network weights by minimising prediction errors of the network based on the previously constructed local models until convergence. This method was found to be successful in identifying the connectivity structure for coupled networks of chaotic oscillators. Freerun prediction performance with the resulting local models and weights was comparable to the true system with noisy initial conditions. The method is also extended to asymmetric negative coupling. © 2022, CC BY.

关键词： Backpropagation

来源：评论

学校读者我要写书评

暂无评论

Extracting and Classifying 3D Medical Image Texture Characteristics using GLCM and LBP-Based Techniques

Extracting and Classifying 3D Medical Image Texture Characte...

引用

Data science, Agents & Artificial Intelligence (ICDSAAI), International Conference on

作者： R. Srinath R. Sharmila N. Raghavendran M. C. Babu K. Ramanan R. Saravanakumar Department of Computer Applications Karpagam Academy of Higher Education Coimbatore Tamil Nadu India Department of Artificial Intelligence and Date Science RMK College of Engineering and Technology Chennai Tamil Nadu India Department of Artificial Intelligence and Data Sciences Chennai Institute of Technology Chennai Tamil Nadu India Iconix Software Solution Tirunelveli Tamil Nadu India

ISBN: (数字)9798331537555

ISBN: (纸本)9798331537562

Recent advances in 3D sensor technology have advanced 3D imaging systems. This sparks interest in 3D picture feature extraction and categorization. According to the literature, textural content is essential to visuals. In this case, we extract texture characteristics from three-dimensional photos to improve feature differentiation. Category of volumetric data with texture is possible using this method. We employ feature vectors from Local Binary Patterns (LBP) and Gray-Level Co-occurrence Matrix methods to achieve this. The visual pattern and volumetric data contrast, homogeneity, and local anisotropy are described. The proposed approach was tested using a publicly accessible dataset of modified volumetric textured pictures. Generative Adversarial Networks (GAN) and recurrent Neural Networks (RNN) are classified. Our solution outperforms manually constructed techniques for extracting texture characteristics from 3D and 2D data and standard deep-learning networks. Even with few photographs per class, the recommended method improves class distinction and yields good results. Show exceptional accuracy. Integrating the Gray Level Co-occurrence Matrix (GLCM) with Local Binary Patterns (LBP) improved classification performance. The GLCM approach, which captures spatial relationships, and the LBP method, which depicts local texture, was advantageous. This hybrid method improved feature extraction and classification, notably for complex 3D medical pictures with subtle texture changes.

关键词： Deep learning Visualization Three-dimensional displays Machine learning algorithms Recurrent neural networks Liver Feature extraction Generative adversarial networks Classification algorithms Tumors

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：