Filters








1,093 Hits in 4.7 sec

Distributed Map Classification using Local Observations [article]

Guangyi Liu, Arash Amini, Martin Takáč, Héctor Muñoz-Avila, Nader Motee
2021 arXiv   pre-print
Using a graph decomposition technique, we proposed an offline learning structure that makes every robot capable of communicating with and fusing information from its neighbors to plan its next move towards  ...  Our approach is particularly useful for fast map classification in large environments using a large number of communicating robots.  ...  Both models are trained with = 5, and = 15 on the clouded map dataset. As shown in Table.  ... 
arXiv:2012.10480v2 fatcat:t3cvmmezwnhfxnsxseyyefucc4

Slack Squeeze Coded Computing for Adaptive Straggler Mitigation [article]

Krishna Giri Narra, Zhifeng Lin, Mehrdad Kiamari, Salman Avestimehr, Murali Annavaram
2019 arXiv   pre-print
., overhead) that is built into the coded computing frameworks by efficiently assigning work for all fast and slow nodes according to their speeds and without needing to re-distribute data.  ...  While performing distributed computations in today's cloud-based platforms, execution speed variations among compute nodes can significantly reduce the performance and create bottlenecks like stragglers  ...  ACKNOWLEDGEMENTS We sincerely thank all the reviewers for their time and constructive comments. We thank Daniel Wong for his valuable feedback on the SC '19, November 17-22, 2019, Denver, CO, USA K.  ... 
arXiv:1904.07098v2 fatcat:6mj2ox3a5jezlpl2zt2vweehfi

Mind reading of the proteins: Deep-learning to forecast molecular dynamics [article]

Chitrak Gupta, John Kevin Cava, Daipayan Sarkar, Eric A Wilson, John Vant, Steven Murray, Abhishek Singharoy, Shubhra Kanti Karmaker
2020 bioRxiv   pre-print
to predict conformational transitions on two different biological systems.  ...  Here, we utilize LSTMs in order to predict future molecular dynamics from current and previous timesteps, and examine how this physics-guided learning can benefit researchers in computational biophysics  ...  This so-called Kirchhoff decomposition scheme boosted the performance of LSTM significantly. ADK Vs 100-alanine: We report RMSD of each simulated system, i.e., ADK and SMD ( Figs. 2A and 4B ).  ... 
doi:10.1101/2020.07.28.225490 fatcat:uraxa3rt3zbbnkewf5ichlzqxe

Using Microservice Architecture as a Load Prediction Strategy for Management System of University Public Service

Liming Huang, Man-Ying Lee, Xiaojie Chen, Hsien-Wei Tseng, Cheng-Fu Yang, Shun-Fa Lee
2021 Sensors and materials  
We used the management system of a university's public service as basic data in the microservice architecture and the Spring Cloud package as the experimental platform.  ...  Keywords: load prediction, spring boot, microservice architecture, neural network, long short-term memory (LSTM) The microservice architecture is widely adopted in cloud computing and the applications  ...  Conclusions We proposed an improved load prediction strategy based on the neural network LSTM method and its revised GRU model.  ... 
doi:10.18494/sam.2021.3048 fatcat:4ykxyqfonjhq5bapqlrwftnhrm

Resource allocation optimization using artificial intelligence methods in various computing paradigms: A Review [article]

Javad Hassannataj Joloudari, Roohallah Alizadehsani, Issa Nodehi, Sanaz Mojrian, Fatemeh Fazl, Sahar Khanjani Shirkharkolaie, H M Dipu Kabir, Ru-San Tan, U Rajendra Acharya
2022 arXiv   pre-print
The review ends with a discussion on open research directions and a conclusion.  ...  With the advent of smart devices, the demand for various computational paradigms such as the Internet of Things, fog, and cloud computing has increased.  ...  cost by 40% compared to methods based on symmetric cost minimization of prediction error N/A Cloud resource allocation LSTM Eramo [98] Variant of multiobjective evolutionary algorithm based on decomposition  ... 
arXiv:2203.12315v1 fatcat:43mouwxwene6xllnw3gsmdh6hy

A Survey on Machine Learning for Geo-Distributed Cloud Data Center Management [article]

Ninad Hogade, Sudeep Pasricha
2022 arXiv   pre-print
But these techniques are difficult to scale to geo-distributed problem sizes and have limited applicability in dynamic heterogeneous system environments, forcing cloud service providers to explore intelligent  ...  We examine the challenges and the issues in current research focused on ML for cloud management and explore strategies for addressing these issues.  ...  ACKNOWLEDGMENTS This work is supported by the National Science Foundation (NSF) under grant CCF-1302693.  ... 
arXiv:2205.08072v1 fatcat:nz3vvmdrard6hgydagnsadrnpm

Deep Learning in Mobile and Wireless Networking: A Survey

Chaoyun Zhang, Paul Patras, Hamed Haddadi
2019 IEEE Communications Surveys and Tutorials  
Subsequently, we provide an encyclopedic review of mobile and wireless networking research based on deep learning, which we categorize by different domains.  ...  The rapid uptake of mobile devices and the rising popularity of mobile applications and services pose unprecedented demands on mobile and wireless networking infrastructure.  ...  This permits fast implementation of deep NNs on both cloud and fog services.  ... 
doi:10.1109/comst.2019.2904897 fatcat:xmmrndjbsfdetpa5ef5e3v4xda

Guest Editorial: Introduction to the Special Section on Machine Learning-Based Internet of Vehicles: Theory, Methodology, and Applications

Jun Guo, Sunwoo Kim, Henk Wymeersch, Walid Saad, Wei Chen
2019 IEEE Transactions on Vehicular Technology  
Vehicular Cloud Network (VCN) is a hybrid technology that has a remarkable impact on IoV by instantly using vehicular resources.  ...  SQL injection attack is one of the most common attacks in intelligent transportation system. It has characteristics like various types, fast mutations, hidden attacks, and great harm.  ... 
doi:10.1109/tvt.2019.2914747 fatcat:rrpckr7cczfdzmqy7nkbcnsdua

Deep Learning in Mobile and Wireless Networking: A Survey [article]

Chaoyun Zhang, Paul Patras, Hamed Haddadi
2019 arXiv   pre-print
Subsequently, we provide an encyclopedic review of mobile and wireless networking research based on deep learning, which we categorize by different domains.  ...  The rapid uptake of mobile devices and the rising popularity of mobile applications and services pose unprecedented demands on mobile and wireless networking infrastructure.  ...  This permits fast implementation of deep NNs on both cloud and fog services.  ... 
arXiv:1803.04311v3 fatcat:awuvyviarvbr5kd5ilqndpfsde

AI Augmented Edge and Fog Computing: Trends and Challenges [article]

Shreshth Tuli and Fatemeh Mirhakimi and Samodha Pallewatta and Syed Zawad and Giuliano Casale and Bahman Javadi and Feng Yan and Rajkumar Buyya and Nicholas R. Jennings
2022 arXiv   pre-print
Edge, Fog, Cloud, and Serverless.  ...  This survey reviews the evolution of data-driven AI-augmented technologies and their impact on computing systems.  ...  Acknowledgments This work is supported by the the President's Ph.D. Scholarship at Imperial College London and Australian Research Council Discovery Project.  ... 
arXiv:2208.00761v1 fatcat:tfrhvlenyvbg7kidoydjzqejai

Multi-Tier Cellular Handover with Multi-Access Edge Computing and Deep Learning

Percy Kapadia, Boon-Chong Seet
2021 Telecom  
Although the proposed scheme may increase the number of handovers, it is effective in reducing the handover failure (HOF) and ping-pong rates by 30% and 86%, respectively, compared to the current 3GPP  ...  A variant of artificial neural networks called a long short-term memory (LSTM) network is used in conjunction with a look-up table (LUT) as part of the proposed solution.  ...  The proposal is to optimize these inefficiencies through ML and data mining techniques by developing a clustering algorithm based on shapelets and wavelet decompositions at the cell's edge.  ... 
doi:10.3390/telecom2040026 fatcat:fj7tqjc6mjdudl4wkrmkrw2hgy

Spatial-Temporal Genetic-based Attention Networks for Short-Term Photovoltaic Power Forecasting

Tao Fan, Tao Sun, Hu Liu, Xiangying Xie, Zhixiong Na
2021 IEEE Access  
mechanism, while CNNs have the advantage of fast training and can achieve parallel training process by stacking convolutional layers.  ...  [35] constructed a hybrid deep learning model combining wavelet packet decomposition (WPD) and LSTM networks for one-hour-ahead PV power forecasting. Kushwaha et al.  ... 
doi:10.1109/access.2021.3108453 fatcat:2lp3ax5fmvhbtgkxyslgqdlnna

Symmetry-Adapted Machine Learning for Information Security

Jong Hyuk Park
2020 Symmetry  
It offers the identification of unknown and new attack patterns by extracting hidden data patterns in next-generation ICT systems.  ...  The symmetry-adapted machine-learning approach can support an effective way to deal with the dynamic nature of security attacks by the extraction and analysis of data to identify hidden patterns of data  ...  [6] propose a scalable and hybrid intrusion detection system (IDS) based on a two-stage ID system using Spark machine learning and a convolutional LSTM network (Conv-LSTM).  ... 
doi:10.3390/sym12061044 fatcat:dury4tukzre7hblsusdxcg4zee

A Unified FPGA Virtualization Framework for General-Purpose Deep Neural Networks in the Cloud

Shulin Zeng, Guohao Dai, Hanbo Sun, Jun Liu, Shiyao Li, Guangjun Ge, Kai Zhong, Kaiyuan Guo, Yu Wang, Huazhong Yang
2022 ACM Transactions on Reconfigurable Technology and Systems  
On the other hand, to overcome the heavy re-compilation overheads, a tiling-based instruction frame package design and a two-stage static-dynamic compilation, are proposed.  ...  On the other hand, current cloud-based DNN accelerators have excessive compilation overhead, especially when scaling out to multi-FPGA systems for multi-tenant sharing, leading to unacceptable compilation  ...  Therefore, this article focuses on exploring a fast and general compilation framework for the virtualized ISA-based DNN accelerators, which can be deployed on both public and private cloud scenarios.  ... 
doi:10.1145/3480170 fatcat:kgrhiohisvcdxm635l3wykgdri

A Fall Detection Network by 2D/3D Spatio-temporal Joint Models with Tensor Compression on Edge

Shuwei Li, Changhai Man, Ao Shen, Ziyi Guan, Wei Mao, Shaobo Luo, Rumin Zhang, Hao Yu
2022 ACM Transactions on Embedded Computing Systems  
We propose to apply tensor train decomposition on the model to reduce storage and computational consumption, so that the deployment on edge devices can to realized.  ...  Instead of detecting fall motion by the traditional CNNs, we propose a Long Short-Term Memory (LSTM) model based on time-series joint-point features extracted from a pose extractor .  ...  CONCLUSION This paper has proposed an accurate and fast video fall detection system based on a spatio-temporal joint-point model, which performs both 2D or 3D pose estimation and fall detection.  ... 
doi:10.1145/3531004 fatcat:7lwqa7bze5b5vki24gjpza47la
« Previous Showing results 1 — 15 out of 1,093 results