Research of breadth-first algorithm on the embedded device

2014 ◽  
Author(s):  
Yang Xu ◽  
Xiao-kang Li
Keyword(s):  
Embedded Device

scholarly journals RISC-V Virtual Platform-Based Convolutional Neural Network Accelerator Implemented in SystemC

Electronics ◽  
2021 ◽  
Vol 10 (13) ◽  
pp. 1514
Author(s):  
Seung-Ho Lim ◽  
WoonSik William Suh ◽  
Jin-Young Kim ◽  
Sang-Young Cho
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Network Model ◽  
Neural Network Model ◽  
Deep Neural Network ◽  
System Level ◽  
Neural Network Models ◽  
Data Set ◽  
Embedded Device ◽  
Virtual Platform

The optimization for hardware processor and system for performing deep learning operations such as Convolutional Neural Networks (CNN) in resource limited embedded devices are recent active research area. In order to perform an optimized deep neural network model using the limited computational unit and memory of an embedded device, it is necessary to quickly apply various configurations of hardware modules to various deep neural network models and find the optimal combination. The Electronic System Level (ESL) Simulator based on SystemC is very useful for rapid hardware modeling and verification. In this paper, we designed and implemented a Deep Learning Accelerator (DLA) that performs Deep Neural Network (DNN) operation based on the RISC-V Virtual Platform implemented in SystemC in order to enable rapid and diverse analysis of deep learning operations in an embedded device based on the RISC-V processor, which is a recently emerging embedded processor. The developed RISC-V based DLA prototype can analyze the hardware requirements according to the CNN data set through the configuration of the CNN DLA architecture, and it is possible to run RISC-V compiled software on the platform, can perform a real neural network model like Darknet. We performed the Darknet CNN model on the developed DLA prototype, and confirmed that computational overhead and inference errors can be analyzed with the DLA prototype developed by analyzing the DLA architecture for various data sets.

scholarly journals Unlimited and protected memory for flight data recorders

2016 ◽  
Vol 88 (6) ◽  
pp. 866-872 ◽  
Author(s):  
Yair Wiseman
Keyword(s):  
Design Methodology ◽  
Memory Device ◽  
Social Implications ◽  
Embedded Memory ◽  
Content Type ◽  
Flight Data ◽  
Embedded Device ◽  
Use Of Internet ◽  
Practical Implications

Purpose The purpose of this paper is to study extensive enlargement and safety of flight data recorder memory. Design/methodology/approach The study involves the moving the memory of flight data recorders from an internal embedded device to a cloud. Findings The implementation has made the embedded memory device of flight data recorder effectively unlimited, and, hence, much more information can be stored. Research limitations/implications The possibility of a flight data recorder to be damaged or lost in a crash is not so high, but the implementation can be very helpful in cases such as aerial disappearances. Practical implications The implication is larger and protected memory for flight data recorders. Social implications Finding reasons for crashes is faster, and immediate actions can be taken to find remedy to the failures. Originality/value The use of internet and cellphones in airplanes is nothing special at present. It is suggested to take this technology for flight data recorders as well.

Remote monitoring and diagnosing of fieldbus systems - an embedded device way

2009 ◽  
Author(s):  
Xiao' an Yao ◽  
Hongxin Li ◽  
Ronghua Ding ◽  
Jiayuan Yang ◽  
Haiwei Tang ◽  
...  
Keyword(s):  
Remote Monitoring ◽  
Embedded Device

Thermal management of embedded device package

2014 ◽  
Author(s):  
Yukari Imaizumi ◽  
Toru Suda ◽  
Shigenori Sawachi ◽  
Akio Katsumata ◽  
Yoichi Hiruta
Keyword(s):  
Thermal Management ◽  
Embedded Device

scholarly journals COVID-19 Authorized Entry with Face Mask Detection using Raspberry Pi

2021 ◽  
Vol 9 (VI) ◽  
pp. 1862-1867
Author(s):  
Anju Ajay
Keyword(s):  
Large Scale ◽  
Facial Recognition ◽  
Face Mask ◽  
Raspberry Pi ◽  
Wireless Internet ◽  
Great Demand ◽  
Embedded Device ◽  
Internet Connection ◽  
Battery Power ◽  
Python Programming

There are no effective face mask detection applications in the current COVID-19 scenario, which is in great demand for transportation, densely populated places, residential districts, large-scale manufacturers, and other organizations to ensure safety. In addition, the lack of big datasets of photographs with mask has made this task more difficult. With the use of Python programming, the Open CV library, Keras, and tensor flow, this project presents a way for recognizing persons without wearing a face mask using the facial recognition methodology. This is a self-contained embedded device that was created with the Raspberry Pi Electronic Development Board and runs on battery power. We make use of a wireless internet connection using USB modem. In comparison to other existing systems, our proposed method is more effective, reliable, and consumes significantly less data and electricity

Sign in / Sign up

Export Citation Format

Share Document