检索结果-内蒙古大学图书馆

31st Euromicro International Conference on Parallel, distributed and network-Based processing, PDP 2023

作者： Crampon, Kevin Giorkallos, Alexis Baud, Stephanie Steffenel, Luiz Angelo Atos Se Center for Excellence in Advanced Computing Echirolles France Université de Reims Champagne-Ardenne Cnrs MEDyC Reims France Université de Reims Champagne-Ardenne Reims France

ISBN: (纸本)9798350337631

Deep learning use is growing in many numerical simulation fields, and drug discovery does not escape this trend. Indeed, before proceeding with in vitro and then in vivo experiments, drug discovery now relies on in silico techniques such as molecular docking to narrow the number of experiments and identify the best candidates. This method explores the receptor surface and the ligand's conformational space, providing numerous ligand-receptor poses. All these poses are then scored and ranked by a scoring function allowing to predict the best poses among all, then compare different ligands regarding a given receptor or different targets regarding a given ligand. Since the 2010s, numerous deep learning methods have been used to tackle this problem. Nowadays, there are two significant trends in deep learning for molecular docking: (i) the augmentation of available structural data and (ii) the use of a new kind of neural network: the graph convolutional neural networks (GCNs). In this paper, we propose the study of training scalability of a GCN-a molecular complex scoring function-on an increasing number of GPUs and with a variety of batch sizes. After a hyperparameter analysis, we achieve an 80% reduction in the training time, but this improvement sometimes involves a performance metrics degradation that the final users must ponder. © 2023 IEEE.

关键词： Ligands

来源：评论

学校读者我要写书评

暂无评论

Event camera simulator design for modeling attention-based inference architectures

引用

JOURNAL OF REAL-TIME IMAGE processing 2022年第2期19卷 363-374页

作者： Pantho, Md Jubaer Hossain Mbongue, Joel Mandebi Bhowmik, Pankaj Bobda, Christophe Univ Florida Gainesville FL 32611 USA

In recent years, there has been a growing interest in realizing methodologies to integrate more and more computation at the level of the image sensor. The rising trend has seen an increased research interest in developing novel event cameras that can facilitate CNN computation directly in the sensor. However, event-based cameras ca be expensive, limiting performance exploration on high-level models and algorithms. This paper presents an event camera simulator that can be a potent tool for hardware design prototyping, parameter optimization, attention-based innovative algorithm development, and benchmarking. The proposed simulator implements a distributed computation model to identify relevant regions in an image frame. Our simulator's relevance computation model is realized as a collection of modules and performs computations in parallel. The distributed computation model is configurable, making it highly useful for design space exploration. The Rendering engine of the simulator samples frame-regions only when there is a new event. The simulator closely emulates an image processing pipeline similar to that of physical cameras. Our experimental results show that the simulator can effectively emulate event vision with low overheads

关键词： Simulator Convolutional neural network Embedded vision Pixel processing

来源：评论

学校读者我要写书评

暂无评论

Acceleration in distributed Sparse Regression 36

Acceleration in Distributed Sparse Regression

引用

36th Conference on neural Information processing Systems (NeurIPS)

作者： Maros, Marie Scutari, Gesualdo Purdue Univ Sch Ind Engn W Lafayette IN 47907 USA

ISBN: (纸本)9781713871088

We study acceleration for distributed sparse regression in high-dimensions, which allows the parameter size to exceed and grow faster than the sample size. When applicable, existing distributed algorithms employing acceleration perform poorly in this setting, theoretically and numerically. We propose a new accelerated distributed algorithm suitable for high-dimensions. The method couples a suitable instance of accelerated Nesterov's proximal gradient with consensus and gradient-tracking mechanisms, aiming at estimating locally the gradient of the empirical loss while enforcing agreement on the local estimates. Under standard assumptions on the statistical model and tuning parameters, the proposed method is proved to globally converge at linear rate to an estimate that is within the statistical precision of the model. The iteration complexity scales as O(root kappa), while the communications per iteration are at most (O) over tilde (log m/(1-rho)), where kappa is the restricted condition number of the empirical loss, m is the number of agents, and rho is an element of[0,1) measures the network connectivity. As by-product of our design, we also report an accelerated method for high-dimensional estimations over master-worker architectures, which is of independent interest and compares favorably with existing works.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Democratic Learning: A distributed Machine Learning Framework with Collaborative Voting and Model Pruning for Privacy and Security

Democratic Learning: A Distributed Machine Learning Framewor...

引用

International Joint Conference on neural networks (IJCNN)

作者： Lv, Mingyang Zhang, Hong Wang, Miao Wang, Liqiang Wu, Peng Hebei Univ Sch Cyber Secur & Comp Baoding Peoples R China Univ Cent Florida Dept Comp Sci Orlando FL 32816 USA

ISBN: (纸本)9798350359329;9798350359312

With the rapid evolution of the Internet of Things (IoT), there is a noticeable surge in both the proliferation of edge devices and the voluminous data they generate. These edge devices are progressively furnished with AI processors, harnessing the power of deep learning to augment their data processing capabilities. However, in edge environments, traditional federated learning methods typically send multiple models to a central server for aggregation, which gives rise to several tough challenges such as low data transmission efficiency, privacy concerns, and the threat of model poisoning attacks. In this paper, we introduce a distributed machine learning framework with an innovative collaborative voting mechanism to integrate the results of adaptive pruned models on various end devices for edge computing. The main goals of this framework are to mitigate the risk of data privacy and strengthen the system's resilience against model poisoning attacks. Additionally, an adaptive model pruning mechanism is implemented to tailor diverse models according to the limited computational resources available on end devices for enhancing training efficiency. Experiments reveal that our framework can effectively mitigate the impact of poisoning attacks, but also provide superior efficiency and accuracy for edge computing compared with other prevalent federated learning methods.

关键词： Edge computing Security and Privacy Poisoning Attack Federated Learning Model Pruning

来源：评论

学校读者我要写书评

暂无评论

Prediction of N6-methyladenosine sites using convolution neural network model based on distributed feature representations

引用

neural networkS 2020年 129卷 385-391页

作者： Tahir, Muhammad Hayat, Maqsood Chong, Kil To Abdul Wali Khan Univ Mardan Dept Comp Sci Mardan 23200 KP Pakistan Chonbuk Natl Univ Dept Elect & Informat Engn Jeonju 54896 South Korea Chonbuk Natl Univ Adv Elect & Informat Res Ctr Jeonju 54896 South Korea

N-6-methyladenosine (m(6)A) is a well-studied and most common interior messenger RNA (mRNA) modification that plays an important function in cell development. N(6)A is found in all kingdoms of life and many other cellular processes such as RNA splicing, immune tolerance, regulatory functions, RNA processing, and cancer. Despite the crucial role of m(6)A in cells, it was targeted computationally, but unfortunately, the obtained results were unsatisfactory. It is imperative to develop an efficient computational model that can truly represent m(6)A sites. In this regard, an intelligent and highly discriminative computational model namely: m6A-word2vec is introduced for the discrimination of m(6)A sites. Here, a concept of natural language processing in the form of word2vec is used to represent the motif of the target class automatically. These motifs (numerical descriptors) are automatically targeted from the human genome without any clear definition. Further, the extracted feature space is then forwarded to the convolution neural network model as input for prediction. The developed computational model obtained 83.17%, 92.69%, and 90.50% accuracy for benchmark datasets S-1, S-2, and S-3, respectively, using a 10-fold cross-validation test. The predictive outcomes validate that the developed intelligent computational model showed better performance compared to existing computational models. It is thus greatly estimated that the introduced computational model "m6A-word2vec" may be a supportive and practical tool for elementary and pharmaceutical research such as in drug design along with academia. (C) 2020 Elsevier Ltd. All rights reserved.

关键词： CNN Natural language processing word2vec 10-fold cross-validation

来源：评论

学校读者我要写书评

暂无评论

Detecting Android Botnet Applications Using Convolution neural network

引用

Computers, Materials & Continua 2023年第11期77卷 2123-2135页

作者： Mamona Arshad Ahmad Karim Salman Naseer Shafiq Ahmad Mejdal Alqahtani Akber Abid Gardezi Muhammad Shafiq Jin-Ghoo Choi Department of Information Technology Bahauddin Zakariya UniversityMultan60000Pakistan Department of Information Technology University of the Punjab Gujranwala CampusGujranwala52250Pakistan Industrial Engineering Department College of EngineeringKing Saud UniversityP.O.Box 800Riyadh11421Saudi Arabia Department of Computer Science COMSATS University IslamabadIslamabad45550Pakistan Department of Information and Communication Engineering Yeungnam UniversityGyeongsan38541Korea

The exponential growth in the development of smartphones and handheld devices is permeated due to everyday activities i.e.,games applications,entertainment,online banking,social network sites,etc.,and also allow the end users to perform a variety of *** of activities,mobile devices attract cybercriminals to initiate an attack over a diverse range of malicious activities such as theft of unauthorized information,phishing,spamming,distributed Denial of Services(DDoS),and malware *** applications are a type of harmful attack that can be used to launch malicious activities and has become a significant threat in the research area.A botnet is a collection of infected devices that are managed by a botmaster and communicate with each other via a command server in order to carry out malicious *** the rise in malicious attacks,detecting botnet applications has become more ***,it is essential to investigate mobile botnet attacks to uncover the security issues in severe financial and ethical damages caused by a massive coordinated command *** state of the art,various solutions were provided for the detection of botnet applications,but in general,the researchers suffer various techniques of machine learning-based methods with static features which are usually ineffective when obfuscation techniques are used for the detection of botnet *** this paper,we propose an approach by exploring the concept of a deep learning-based method and present a well-defined Convolutional neural network(CNN)*** the visualization approach,we obtain the colored images through byte code files of applications and perform an *** analysis of the results of an experiment,we differentiate the performance of the model from other existing research ***,our method outperforms with 94.34%accuracy,92.9%of precision,and 92%of recall.

关键词： CNN botnet applications machine learning image processing

来源：评论

学校读者我要写书评

暂无评论

GNN-Aided distributed GAN with Partially Observable Social Graph 25

GNN-Aided Distributed GAN with Partially Observable Social G...

引用

IEEE Wireless Communications and networking Conference (IEEE WCNC)

作者： Chen, Ming Wang, Shangshang Zhang, Tianyi Shao, Ziyu Yang, Yang ShanghaiTech Univ Sch Informat Sci & Technol Shanghai Peoples R China Hong Kong Univ Sci & Technol Guangzhou Guangzhou Peoples R China

ISBN: (纸本)9798350303582;9798350303599

The proliferation of edge computing has facilitated the edge-based artificial intelligence-generated content (AIGC) for ubiquitous and distributed end devices. To exemplify, we focus on the distributed implementation of one established instance, generative adversarial network (GAN), yielding the distributed GAN task. Practically speaking, this task usually is impeded by concerns including the unknown latency (of processing and transmission), the fairness requirement induced by heterogeneous distributed data and the limited energy budget of end devices. Besides, an often neglected factor is how to exploit feedback from networked end devices among which social ties indicate the flow of shared information. In practice, such social ties are partially observable to lack of exact knowledge of users, e.g., resulted from scarce historical data and privacy issues. Under this setting, we propose an online algorithm via integration of 1) online learning aided by graph neural network (GNN), aiming to recover social ties with GNN-based edge prediction, for accelerated learning of uncertainty and 2) online control to adaptively guarantee the constraints. We theoretically show that it not only achieves a sub-linear regret with guaranteed energy consumption and fairness but also leads to a superior global GAN. We also conduct simulations to justify its outperformance over online baselines.

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

distributed neural network with TensorFlow on Human Activity Recognition Over Multicore TPU

Distributed Neural Network with TensorFlow on Human Activity...

引用

IEEE International Symposium on Embedded Multicore Socs (MCSoC)

作者： Haklin Kimm Incheon Paik East Stroudsburg University East Stroudsburg PA USA School of Computer Science and Engineering University of Aizu Aizu-Wakamatsu City Fukushima Japan

ISBN: (纸本)9781728187525

There have been increasing interests and success of applying deep learning neural networks to their big data platforms and workflows, say distributed Deep Learning. In this paper, we present distributed long short-term memory (dLSTM) neural network model using TensorFlow over multicore Tensor processing Unit (TPU) on Google Cloud. LSTM is a variant of the recurrent neural network (RNN), which is more suitable for processing temporal sequences. This model could extract human activity features automatically and classify them with a few model parameters. In the proposed model, the raw data collected by mobile sensors was fed into distributed multi-layer LSTM layers. Human activity recognition data from UCI machine-learning library have been applied to the proposed distributed LSTM (dLSTM) model to compare the efficiency of TensorFlow over CPU and TPU based on execution time, and evaluation metrics: accuracy, precision, recall and F1 score along with the use of Google Colab Notebook.

关键词： Deep learning Measurement Tensors Recurrent neural networks Multicore processing distributed databases Activity recognition

来源：评论

学校读者我要写书评

暂无评论

FaLa: feature-augmented location-aware transformer network for graph representation learning

引用

neural Computing and Applications 2025年 1-28页

作者： Morshed, Md Golam Sultana, Tangina Lee, Young-Koo Computer Science and Engineering Kyung Hee University Yongin17104 Korea Republic of Computer Science and Engineering International University of Business Agriculture and Technology Dhaka1230 Bangladesh Electronics and Communication Engineering Hajee Mohammad Danesh Science & Technology University Dinajpur5200 Bangladesh

Data augmentation is a technique that improves the ability of neural networks to make accurate predictions by increasing the size of the training dataset. However, it is still uncertain how to properly use data augmentation on graph data in order to boost the performance of graph neural networks (GNNs). While the majority of current graph regularizers primarily concentrate on modifying the topological structures of graphs by adding or deleting nodes and edges, we propose a technique to augment node and edge features in order to improve efficiency. More precisely, we use cosine similarity to perform cross-functions on the existing features. This allows us to generate new graph features, such as node and edge attributes, as well as new graph structures. We then merge these new features together to provide specific pairs of inputs for graph transformer networks. We next propose feature-augmented location-aware transformer (FaLa) networks that generalize well across several graph learning problems by combining the positional and structural encoding of nodes. Additionally, in order to avoid collecting duplicate data from other features, we apply a disparity restriction during training on these latent node embeddings. Experimental findings across eleven real-world datasets demonstrate that our methodology enhances node classification accuracy by a significant margin of 2.8% to 22.7%, link prediction by 1.6% to 8.5%, and graph classification by 7.0% to 39.8% compared to the state-of-the-art graph convolutional network (GCN) and graph transformer (GT) models. This clearly shows the importance of augmenting graph features and location encoding for efficient graph representation learning. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Graph neural networks

来源：评论

学校读者我要写书评

暂无评论

Deep Convolutional neural network-Based High-Precision and Speed DDOS Detection in SDN Environments 21

Deep Convolutional Neural Network-Based High-Precision and S...

引用

21st International Computer Conference on Wavelet Active Media Technology and Information processing, ICCWAMTIP 2024

作者： Madoune, Sid Ali Senouci, Sarra Dingde, Jiang Senouci, Abdelkader School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu611731 China School of Mechanical and Electronic Engineering University of Electronic Science and Technology of China Chengdu611731 China Northumbria University Faculty of Engineering and Environment NewcastleNEI 8ST United Kingdom

ISBN: (纸本)9798331519254

The rapid expansion of interconnected infrastructures has dramatically increased the volume of network devices and traffic, introducing significant security vulnerabilities in Software-Defined networking (SDN) environments. distributed Denial-of-Service (DDoS) attacks exploit the centralized control plane characteristic of SDN, underscoring the need for adaptive, efficient detection mechanisms. In response, we present a novel hybrid framework that leverages Principal Component Analysis (PCA) for dimensionality reduction and a supervised Deep Convolutional neural network (DCNN) for high-precision classification of normal and malicious events. Rigorous evaluation on a real-world SDN dataset, comprising both categorical and numerical features, demonstrates that the proposed model achieves an exceptional detection accuracy of 99.97% and a swift detection time of only 3 seconds-making it well-suited for real-time applications in SDN. These results affirm the efficacy of our model in enhancing both security and scalability, contributing a robust solution for mitigating DDoS threats in dynamic SDN environments. © 2024 IEEE.

关键词： Convolutional neural networks

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：