Real-time task scheduling and network device security for complex embedded systems based on deep learning networks

Zhou, Junyan

doi:10.1016/j.micpro.2020.103282

Cited by 46 publications

(16 citation statements)

References 57 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…With the emerge of deep neural networks (DNNs) [ [9] , [10] , [11] , [12] , [13] , [14] ], especially convolutional neural networks (CNNs), they leverage multi-level layer neural networks for representational learning and are widely used for image classification [ 15 , 16 ], object detection [ 17 , 18 ] and semantic segmentation [ 19 ]. Naturally, DNNs are very good at detecting COVID-19 [ [20] , [21] , [22] , [23] , [24] , [25] ].…”

Section: Introductionmentioning

confidence: 99%

COVID-19 diagnosis via chest X-ray image classification based on multiscale class residual attention

Liu

Cai

Tang

et al. 2022

Computers in Biology and Medicine

View full text Add to dashboard Cite

Section: Introductionmentioning

confidence: 99%

COVID-19 diagnosis via chest X-ray image classification based on multiscale class residual attention

Liu

Cai

Tang

et al. 2022

Computers in Biology and Medicine

View full text Add to dashboard Cite

“…In recent years with the rapid development of artificial intelligence technology, machine learning methods are gradually being applied to task scheduling problems. [6][7][8]20,21 Xie et al 6 employed MultiLogistic Regression theory (called MLRS for short) on task scheduling issue in HCE, the model of which is trained using the data collected from historical best scheduling plans. Besides research work using traditional machine learning methods, there are also some studies done using neural networks.…”

Section: Model-based Machine Learning Algorithmsmentioning

confidence: 99%

“…In the work of Gupta et al, 8 to achieve a high throughput heterogeneous system, an ANN‐based task scheduler was presented by predicting the possible application behavior of the next scheduling interval. Zhou 21 proposed a task scheduling algorithm using a dynamic integrity measurement model based on deep learning networks for real‐time task scheduling. For those machine learning‐based task scheduling algorithms, due to the strong correlation between model and data, these methods usually show good performance.…”

Section: Background and Related Workmentioning

confidence: 99%

DDDQN‐TS: A task scheduling and load balancing method based on optimized deep reinforcement learning in heterogeneous computing environment

Sun

Yang

Lei

2022

Int J of Intelligent Sys

View full text Add to dashboard Cite

Task scheduling and load balancing problem of heterogeneous computing environment (HCE) is getting more and more attention these days and has become a research hotspot in this field. The task scheduling and load balancing problem of heterogeneous environment, which refers to assigning a set of tasks to a specific set of machines with different hardware and different computing performance with the goal of minimizing task processing time and keeping load balance among machines, has been proved to be an NP-complete problem. The development of artificial intelligence provides new ideas to solve this problem. In this paper, we propose a novel task scheduling and load balancing method based on optimized deep reinforcement learning in HCE. First, we formulate task scheduling problem as a Markov decision process and then adopt a dueling double deep Q-learning network to search the optimal task allocation solution. Then we use two well-known large-scale cluster data sets Google Cloud Jobs data set and Alibaba Cluster Trace data set to validate our approach. The experimental results show that compared with other existing solutions, our proposed method can achieve much shorter task response time and better load balancing effect.

show abstract

“…During memory optimization, the meta-data could be stored in the persistent memory to run the model with the run time tensors. Zhou, et al [5] deployed a deep learning networks model for task allocation, and memory management in embedded systems. This paper mainly objects to ensure the security, and reduce the complexity of embedded systems by using a dynamic integrity measurement algorithm.…”

Section: ░2 Related Workmentioning

confidence: 99%

“…Typically, embedded systems [3,4] are considered as the kind of computers mainly designed for performing the specialized functions. Among the other domains, it plays a vital role in the digital vision technology [5], and its general architecture model is shown in Fig 1 . The modern embedded systems are developed based on the combination of software and hardware components, which performs certain functions according to the requirements. In embedded systems, memory management is one of the most crucial and essential task need to be addressed, because which are mainly used to ensure the better system performance.…”

Section: ░ 1 Introductionmentioning

confidence: 99%

A Classy Memory Management System (CyM2S) using an Isolated Dynamic Two-Level Memory Allocation (ID2LMA) Algorithm for the Real Time Embedded Systems

Sundari

Narmadha

Ramani³

2022

IJEER

View full text Add to dashboard Cite

Due to an increased scalability, flexibility, and reduced cost complexity, the dynamic memory allocation models are highly preferred for the real-time embedded systems. For this purpose, the different types of dynamic models have been developed in the conventional works, which are highly focused on allocating the memory blocks with increased searching capability. However, it faced some of the problems and issues related to the factors of complex operations, high time consumption, memory overhead, and reduced speed of processing. Thus, this research work objects to design an advanced and intelligent dynamic memory allocation mechanism for the real-time embedded systems. Here, a Classy Memory Management System (CyM2S) is developed by using an Isolated Dynamic Two-Level Memory Allocation (ID2LMA) algorithm for efficiently allocating the memory blocks with simple searching. The CyM2S helps to reduce the fragmentation rate and time consumption by optimally allocating the memory blocks. In this model, the small buffer has been maintained for surplus pointers, and the allocated blocks comprise the metadata and payload data. During evaluation, the performance of the proposed CyM2S- ID2LMA technique is validated and compared by using the measures of memory allocation time, release time, execution, and processing speed.

show abstract

Real-time task scheduling and network device security for complex embedded systems based on deep learning networks

Cited by 46 publications

References 57 publications

COVID-19 diagnosis via chest X-ray image classification based on multiscale class residual attention

COVID-19 diagnosis via chest X-ray image classification based on multiscale class residual attention

DDDQN‐TS: A task scheduling and load balancing method based on optimized deep reinforcement learning in heterogeneous computing environment

A Classy Memory Management System (CyM2S) using an Isolated Dynamic Two-Level Memory Allocation (ID2LMA) Algorithm for the Real Time Embedded Systems

Contact Info

Product

Resources

About