PyTorchKR Papers

최신 논문

총 561편
태그·기간 등 상세 필터

카테고리 탐색

로그인 후 이 태그 구독

논문 ID: publication/3276026

Arrhythmia Detection Using Deep Convolutional Neural Network With Long Duration ECG Signals

This article presents a new deep learning approach for cardiac arrhythmia (17 classes) detection based on long-duration electrocardiography (ECG) signal analysis. Cardiovascular disease prevention is one of the most important tasks of any health care system as about 50 million people are at risk of heart disease in the world. Although automatic analysis of the ECG signal is very popular, current methods are not satisfactory. The goal of our research was to design a new method based on deep learning to efficiently and quickly classify cardiac arrhythmias. Described research is based on 1000 ECG signal fragments from the MIT - BIH Arrhythmia database for one lead (MLII) from 45 persons. Approach based on the analysis of 10-s ECG signal fragments (not a single QRS complex) is applied (on average, 13 times less classifications/analysis). A complete end-to-end structure was designed instead of the hand-crafted feature extraction and selection used in traditional methods. Our main contribution is to design a new 1D-Convolutional Neural Network model (1D-CNN). Proposed method is 1) efficient, 2) fast (real-time classification) 3) non-complex and 4) simple to use (combined feature extraction and selection, and classification in one stage). Deep 1D-CNN achieved a recognition overall accuracy of 17 cardiac arrhythmia disorders (classes) at a level of 91.33% and classification time per single sample of 0.015 sec. Compared to the current research, our results are one of the best results to date, and our solution can be implemented in mobile devices and cloud computing.

arXiv:2005.04680

Optimizing Deep Learning Recommender Systems' Training On CPU Cluster Architectures

During the last two years, the goal of many researchers has been to squeeze the last bit of performance out of HPC system for AI tasks. Often this discussion is held in the context of how fast ResNet50 can be trained. Unfortunately, ResNet50 is no longer a representative workload in 2020. Thus, we focus on Recommender Systems which account for most of the AI cycles in cloud computing centers. More specifically, we focus on Facebook's DLRM benchmark. By enabling it to run on latest CPU hardware and software tailored for HPC, we are able to achieve more than two-orders of magnitude improvement in performance (110x) on a single socket compared to the reference CPU implementation, and high scaling efficiency up to 64 sockets, while fitting ultra-large datasets. This paper discusses the optimization techniques for the various operators in DLRM and which component of the systems are stressed by these different operators. The presented techniques are applicable to a broader set of DL workloads that pose the same scaling challenges/characteristics as DLRM.

arXiv:2005.03135

Catch Me If You Can: Using Power Analysis to Identify HPC Activity

Monitoring users on large computing platforms such as high performance computing (HPC) and cloud computing systems is non-trivial. Utilities such as process viewers provide limited insight into what users are running, due to granularity limitation, and other sources of data, such as system call tracing, can impose significant operational overhead. However, despite technical and procedural measures, instances of users abusing valuable HPC resources for personal gains have been documented in the past \cite{hpcbitmine}, and systems that are open to large numbers of loosely-verified users from around the world are at risk of abuse. In this paper, we show how electrical power consumption data from an HPC platform can be used to identify what programs are executed. The intuition is that during execution, programs exhibit various patterns of CPU and memory activity. These patterns are reflected in the power consumption of the system and can be used to identify programs running. We test our approach on an HPC rack at Lawrence Berkeley National Laboratory using a variety of scientific benchmarks. Among other interesting observations, our results show that by monitoring the power consumption of an HPC rack, it is possible to identify if particular programs are running with precision up to and recall of 95\% even in noisy scenarios.

arXiv:2004.12059

SAIA: Split Artificial Intelligence Architecture for Mobile Healthcare System

As the advancement of deep learning (DL), the Internet of Things and cloud computing techniques for biomedical and healthcare problems, mobile healthcare systems have received unprecedented attention. Since DL techniques usually require enormous amount of computation, most of them cannot be directly deployed on the resource-constrained mobile and IoT devices. Hence, most of the mobile healthcare systems leverage the cloud computing infrastructure, where the data collected by the mobile and IoT devices would be transmitted to the cloud computing platforms for analysis. However, in the contested environments, relying on the cloud might not be practical at all times. For instance, the satellite communication might be denied or disrupted. We propose SAIA, a Split Artificial Intelligence Architecture for mobile healthcare systems. Unlike traditional approaches for artificial intelligence (AI) which solely exploits the computational power of the cloud server, SAIA could not only relies on the cloud computing infrastructure while the wireless communication is available, but also utilizes the lightweight AI solutions that work locally on the client side, hence, it can work even when the communication is impeded. In SAIA, we propose a meta-information based decision unit, that could tune whether a sample captured by the client should be operated by the embedded AI (i.e., keeping on the client) or the networked AI (i.e., sending to the server), under different conditions. In our experimental evaluation, extensive experiments have been conducted on two popular healthcare datasets. Our results show that SAIA consistently outperforms its baselines in terms of both effectiveness and efficiency.

arXiv:2004.11842

A Mobile Cloud-Based eHealth Scheme

Mobile cloud computing is an emerging field that is gaining popularity across borders at a rapid pace. Similarly, the field of health informatics is also considered as an extremely important field. This work observes the collaboration between these two fields to solve the traditional problem of extracting Electrocardiogram signals from trace reports and then performing analysis. The developed system has two front ends, the first dedicated for the user to perform the photographing of the trace report. Once the photographing is complete, mobile computing is used to extract the signal. Once the signal is extracted, it is uploaded into the server and further analysis is performed on the signal in the cloud. Once this is done, the second interface, intended for the use of the physician, can download and view the trace from the cloud. The data is securely held using a password-based authentication method. The system presented here is one of the first attempts at delivering the total solution, and after further upgrades, it will be possible to deploy the system in a commercial setting.

arXiv:2004.10968

ArchNet: Data Hiding Model in Distributed Machine Learning System

Integrating idle embedded devices into cloud computing is a promising approach to support distributed machine learning. In this paper, we approach to address the data hiding problem in such distributed machine learning systems. For the purpose of the data encryption in the distributed machine learning systems, we propose the Tripartite Asymmetric Encryption theorem and give mathematical proof. Based on the theorem, we design a general image encryption scheme ArchNet.The scheme has been implemented on MNIST, Fashion-MNIST and Cifar-10 datasets to simulate real situation. We use different base models on the encrypted datasets and compare the results with the RC4 algorithm and differential privacy policy. Experiment results evaluated the efficiency of the proposed design. Specifically, our design can improve the accuracy on MNIST up to 97.26% compared with RC4.The accuracies on the datasets encrypted by ArchNet are 97.26%, 84.15% and 79.80%, and they are 97.31%, 82.31% and 80.22% on the original datasets, which shows that the encrypted accuracy of ArchNet has the same performance as the base model. It also shows that ArchNet can be deployed on the distributed system with embedded devices.

arXiv:2004.10497

Distributed Learning and Inference with Compressed Images

Modern computer vision requires processing large amounts of data, both while training the model and/or during inference, once the model is deployed. Scenarios where images are captured and processed in physically separated locations are increasingly common (e.g. autonomous vehicles, cloud computing). In addition, many devices suffer from limited resources to store or transmit data (e.g. storage space, channel capacity). In these scenarios, lossy image compression plays a crucial role to effectively increase the number of images collected under such constraints. However, lossy compression entails some undesired degradation of the data that may harm the performance of the downstream analysis task at hand, since important semantic information may be lost in the process. Moreover, we may only have compressed images at training time but are able to use original images at inference time, or vice versa, and in such a case, the downstream model suffers from covariate shift. In this paper, we analyze this phenomenon, with a special focus on vision-based perception for autonomous driving as a paradigmatic scenario. We see that loss of semantic information and covariate shift do indeed exist, resulting in a drop in performance that depends on the compression rate. In order to address the problem, we propose dataset restoration, based on image restoration with generative adversarial networks (GANs). Our method is agnostic to both the particular image compression method and the downstream task; and has the advantage of not adding additional cost to the deployed models, which is particularly important in resource-limited devices. The presented experiments focus on semantic segmentation as a challenging use case, cover a broad range of compression rates and diverse datasets, and show how our method is able to significantly alleviate the negative effects of compression on the downstream visual task.

arXiv:1807.11659

Serverless computing provides on-demand high performance computing for biomedical research

Cloud computing offers on-demand, scalable computing and storage, and has become an essential resource for the analyses of big biomedical data. The usual approach to cloud computing requires users to reserve and provision virtual servers. An emerging alternative is to have the provider allocate machine resources dynamically. This type of serverless computing has tremendous potential for biomedical research in terms of ease-of-use, instantaneous scalability and cost effectiveness. In our proof of concept example, we demonstrate how serverless computing provides low cost access to hundreds of CPUs, on demand, with little or no setup. In particular, we illustrate that the all-against-all pairwise comparison among all unique human proteins can be accomplished in approximately 2 minutes, at a cost of less than $1, using Amazon Web Services Lambda. This is a 250x speedup compared to running the same task on a typical laptop computer.

arXiv:2004.02315

Multi-agent Reinforcement Learning for Resource Allocation in IoT networks with Edge Computing

To support popular Internet of Things (IoT) applications such as virtual reality, mobile games and wearable devices, edge computing provides a front-end distributed computing archetype of centralized cloud computing with low latency. However, it's challenging for end users to offload computation due to their massive requirements on spectrum and computation resources and frequent requests on Radio Access Technology (RAT). In this paper, we investigate computation offloading mechanism with resource allocation in IoT edge computing networks by formulating it as a stochastic game. Here, each end user is a learning agent observing its local environment to learn optimal decisions on either local computing or edge computing with the goal of minimizing long term system cost by choosing its transmit power level, RAT and sub-channel without knowing any information of the other end users. Therefore, a multi-agent reinforcement learning framework is developed to solve the stochastic game with a proposed independent learners based multi-agent Q-learning (IL-based MA-Q) algorithm. Simulations demonstrate that the proposed IL-based MA-Q algorithm is feasible to solve the formulated problem and is more energy efficient without extra cost on channel estimation at the centralized gateway compared to the other two benchmark algorithms.

arXiv:2003.12141

Scalable Deployment of AI Time-series Models for IoT

IBM Research Castor, a cloud-native system for managing and deploying large numbers of AI time-series models in IoT applications, is described. Modelling code templates, in Python and R, following a typical machine-learning workflow are supported. A knowledge-based approach to managing model and time-series data allows the use of general semantic concepts for expressing feature engineering tasks. Model templates can be programmatically deployed against specific instances of semantic concepts, thus supporting model reuse and automated replication as the IoT application grows. Deployed models are automatically executed in parallel leveraging a serverless cloud computing framework. The complete history of trained model versions and rolling-horizon predictions is persisted, thus enabling full model lineage and traceability. Results from deployments in real-world smart-grid live forecasting applications are reported. Scalability of executing up to tens of thousands of AI modelling tasks is also evaluated.

arXiv:2003.09876

HierTrain: Fast Hierarchical Edge AI Learning with Hybrid Parallelism in Mobile-Edge-Cloud Computing

Nowadays, deep neural networks (DNNs) are the core enablers for many emerging edge AI applications. Conventional approaches to training DNNs are generally implemented at central servers or cloud centers for centralized learning, which is typically time-consuming and resource-demanding due to the transmission of a large amount of data samples from the device to the remote cloud. To overcome these disadvantages, we consider accelerating the learning process of DNNs on the Mobile-Edge-Cloud Computing (MECC) paradigm. In this paper, we propose HierTrain, a hierarchical edge AI learning framework, which efficiently deploys the DNN training task over the hierarchical MECC architecture. We develop a novel \textit{hybrid parallelism} method, which is the key to HierTrain, to adaptively assign the DNN model layers and the data samples across the three levels of edge device, edge server and cloud center. We then formulate the problem of scheduling the DNN training tasks at both layer-granularity and sample-granularity. Solving this optimization problem enables us to achieve the minimum training time. We further implement a hardware prototype consisting of an edge device, an edge server and a cloud server, and conduct extensive experiments on it. Experimental results demonstrate that HierTrain can achieve up to 6.9x speedup compared to the cloud-based hierarchical training approach.

arXiv:2002.10619

Three Approaches for Personalization with Applications to Federated Learning

The standard objective in machine learning is to train a single model for all users. However, in many learning scenarios, such as cloud computing and federated learning, it is possible to learn a personalized model per user. In this work, we present a systematic learning-theoretic study of personalization. We propose and analyze three approaches: user clustering, data interpolation, and model interpolation. For all three approaches, we provide learning-theoretic guarantees and efficient algorithms for which we also demonstrate the performance empirically. All of our algorithms are model-agnostic and work for any hypothesis class.

arXiv:2002.10294

Semantic, Efficient, and Secure Search over Encrypted Cloud Data

Companies and individuals demand more and more storage space and computing power. For this purpose, several new technologies have been designed and implemented, such as the cloud computing. This technology provides its users with storage space and computing power according to their needs in a flexible and personalized way. However, the outsourced data such as emails, electronic health records, and company reports are sensitive and confidential. Therefore, It is primordial to protect the outsourced data against possible external attacks and the cloud server itself. That is why it is highly recommended to encrypt the sensitive data before being outsourced to a remote server. To perform searches over outsourced data, it is no longer possible to exploit traditional search engines given that these data are encrypted. Consequently, lots of searchable encryption (SE) schemes have been proposed in the literature. Three major research axes of searchable encryption area have been studied in the literature. The first axis consists in ensuring the security of the search approach. Indeed, the search process should be performed without decryption any data and without causing any sensitive information leakage. The second axis consists in studying the search performance. In fact, the encrypted indexes are less efficient than the plaintext indexes, which makes the searchable encryption schemes very slow in practice. More the approach is secure, less it is efficient, thus, the challenge consists in finding the best compromise between security and performance. Finally, the third research axis consists in the quality of the returned results in terms of relevance and recall. The problem is that the encryption of the index causes the degradation of the recall and the precision. Therefore, the goal is to propose a technique that is able to obtain almost the same result obtained in the traditional search.

arXiv:2002.08987

Taurus: A Data Plane Architecture for Per-Packet ML

Emerging applications -- cloud computing, the internet of things, and augmented/virtual reality -- demand responsive, secure, and scalable datacenter networks. These networks currently implement simple, per-packet, data-plane heuristics (e.g., ECMP and sketches) under a slow, millisecond-latency control plane that runs data-driven performance and security policies. However, to meet applications' service-level objectives (SLOs) in a modern data center, networks must bridge the gap between line-rate, per-packet execution and complex decision making. In this work, we present the design and implementation of Taurus, a data plane for line-rate inference. Taurus adds custom hardware based on a flexible, parallel-patterns (MapReduce) abstraction to programmable network devices, such as switches and NICs; this new hardware uses pipelined SIMD parallelism to enable per-packet MapReduce operations (e.g., inference). Our evaluation of a Taurus switch ASIC -- supporting several real-world models -- shows that Taurus operates orders of magnitude faster than a server-based control plane while increasing area by 3.8% and latency for line-rate ML models by up to 221 ns. Furthermore, our Taurus FPGA prototype achieves full model accuracy and detects two orders of magnitude more events than a state-of-the-art control-plane anomaly-detection system.

arXiv:2002.08303

Using AI for Mitigating the Impact of Network Delay in Cloud-based Intelligent Traffic Signal Control

The recent advancements in cloud services, Internet of Things (IoT) and Cellular networks have made cloud computing an attractive option for intelligent traffic signal control (ITSC). Such a method significantly reduces the cost of cables, installation, number of devices used, and maintenance. ITSC systems based on cloud computing lower the cost of the ITSC systems and make it possible to scale the system by utilizing the existing powerful cloud platforms. While such systems have significant potential, one of the critical problems that should be addressed is the network delay. It is well known that network delay in message propagation is hard to prevent, which could potentially degrade the performance of the system or even create safety issues for vehicles at intersections. In this paper, we introduce a new traffic signal control algorithm based on reinforcement learning, which performs well even under severe network delay. The framework introduced in this paper can be helpful for all agent-based systems using remote computing resources where network delay could be a critical concern. Extensive simulation results obtained for different scenarios show the viability of the designed algorithm to cope with network delay.

arXiv:2002.03129

GLSearch: Maximum Common Subgraph Detection via Learning to Search

Detecting the Maximum Common Subgraph (MCS) between two input graphs is fundamental for applications in drug synthesis, malware detection, cloud computing, etc. However, MCS computation is NP-hard, and state-of-the-art MCS solvers rely on heuristic search algorithms which in practice cannot find good solution for large graph pairs given a limited computation budget. We propose GLSearch, a Graph Neural Network (GNN) based learning to search model. Our model is built upon the branch and bound algorithm, which selects one pair of nodes from the two input graphs to expand at a time. Instead of using heuristics, we propose a novel GNN-based Deep Q-Network (DQN) to select the node pair, allowing the search process faster and more adaptive. To further enhance the training of DQN, we leverage the search process to provide supervision in a pre-training stage and guide our agent during an imitation learning stage. Experiments on synthetic and real-world large graph pairs demonstrate that our model learns a search strategy that is able to detect significantly larger common subgraphs given the same computation budget. Our GLSearch can be potentially extended to solve many other combinatorial problems with constraints on graphs.

arXiv:2002.01896

Topology optimization of 2D structures with nonlinearities using deep learning

The field of optimal design of linear elastic structures has seen many exciting successes that resulted in new architected materials and structural designs. With the availability of cloud computing, including high-performance computing, machine learning, and simulation, searching for optimal nonlinear structures is now within reach. In this study, we develop convolutional neural network models to predict optimized designs for a given set of boundary conditions, loads, and optimization constraints. We have considered the case of materials with a linear elastic response with and without stress constraint. Also, we have considered the case of materials with a hyperelastic response, where material and geometric nonlinearities are involved. For the nonlinear elastic case, the neo-Hookean model is utilized. For this purpose, we generate datasets composed of the optimized designs paired with the corresponding boundary conditions, loads, and constraints, using a topology optimization framework to train and validate the neural network models. The developed models are capable of accurately predicting the optimized designs without requiring an iterative scheme and with negligible inference computational time. The suggested pipeline can be generalized to other nonlinear mechanics scenarios and design domains.

arXiv:2001.09796

Knowledge Integration of Collaborative Product Design Using Cloud Computing Infrastructure

The pivotal key to the success of manufacturing enterprises is a sustainable and innovative product design and development. In collaborative design, stakeholders are heterogeneously distributed chain-like. Due to the growing volume of data and knowledge, effective management of the knowledge acquired in the product design and development is one of the key challenges facing most manufacturing enterprises. Opportunities for improving efficiency and performance of IT-based product design applications through centralization of resources such as knowledge and computation have increased in the last few years with the maturation of technologies such as SOA, virtualization, grid computing, and/or cloud computing. The main focus of this paper is the concept of ongoing research in providing the knowledge integration service for collaborative product design and development using cloud computing infrastructure. Potentials of the cloud computing to support the Knowledge integration functionalities as a Service by providing functionalities such as knowledge mapping, merging, searching, and transferring in product design procedure are described in this paper. Proposed knowledge integration services support users by giving real-time access to knowledge resources. The framework has the advantage of availability, efficiency, cost reduction, less time to result, and scalability.

arXiv:2001.09957

Reinforcement Learning-based Application Autoscaling in the Cloud: A Survey

Reinforcement Learning (RL) has demonstrated a great potential for automatically solving decision-making problems in complex uncertain environments. RL proposes a computational approach that allows learning through interaction in an environment with stochastic behavior, where agents take actions to maximize some cumulative short-term and long-term rewards. Some of the most impressive results have been shown in Game Theory where agents exhibited superhuman performance in games like Go or Starcraft 2, which led to its gradual adoption in many other domains, including Cloud Computing. Therefore, RL appears as a promising approach for Autoscaling in Cloud since it is possible to learn transparent (with no human intervention), dynamic (no static plans), and adaptable (constantly updated) resource management policies to execute applications. These are three important distinctive aspects to consider in comparison with other widely used autoscaling policies that are defined in an ad-hoc way or statically computed as in solutions based on meta-heuristics. Autoscaling exploits the Cloud elasticity to optimize the execution of applications according to given optimization criteria, which demands to decide when and how to scale-up/down computational resources, and how to assign them to the upcoming processing workload. Such actions have to be taken considering that the Cloud is a dynamic and uncertain environment. Motivated by this, many works apply RL to the autoscaling problem in the Cloud. In this work, we survey exhaustively those proposals from major venues, and uniformly compare them based on a set of proposed taxonomies. We also discuss open problems and prospective research in the area.

arXiv:2001.06585

Multi-factorial Optimization for Large-scale Virtual Machine Placement in Cloud Computing

The placement scheme of virtual machines (VMs) to physical servers (PSs) is crucial to lowering operational cost for cloud providers. Evolutionary algorithms (EAs) have been performed promising-solving on virtual machine placement (VMP) problems in the past. However, as growing demand for cloud services, the existing EAs fail to implement in large-scale virtual machine placement (LVMP) problem due to the high time complexity and poor scalability. Recently, the multi-factorial optimization (MFO) technology has surfaced as a new search paradigm in evolutionary computing. It offers the ability to evolve multiple optimization tasks simultaneously during the evolutionary process. This paper aims to apply the MFO technology to the LVMP problem in heterogeneous environment. Firstly, we formulate a deployment cost based VMP problem in the form of the MFO problem. Then, a multi-factorial evolutionary algorithm (MFEA) embedded with greedy-based allocation operator is developed to address the established MFO problem. After that, a re-migration and merge operator is designed to offer the integrated solution of the LVMP problem from the solutions of MFO problem. To assess the effectiveness of our proposed method, the simulation experiments are carried on large-scale and extra large-scale VMs test data sets. The results show that compared with various heuristic methods, our method could shorten optimization time significantly and offer a competitive placement solution for the LVMP problem in heterogeneous environment.