ED-255EK Embeded Education Platform Sebagai Modul Praktikum Embeded System Dengan Robot Arm Module Dan Voice Module

Abstract— Literally embedded systems are defined as equipment that computes a particular job. Embedded Linux System was also developed as a means of education, one of which is ED-255EK Embedded Education Platform, designed to be very practical and consume very low power. ED-255EK is also equipped with a PXA255 processor that is compatible with ARM version 5TE ISA, so it can be used to carry out various kinds of lab work or experiments on embedded systems. The working principle of this tool begins with the configuration of data communication between Fedora Linux and ED-255EK. When the communication goes well, it is downloaded by the ED-255EK system to a laptop or computer that has been installed with the Fedora 9.0 Linux operating system. To take advantage of the ED-255FPGA module, driver module installation is required first, after which the application program is installed. Laptops or computers that have installed the Fedora 9.0 Linux operating system will act as input and output programs making it easier to monitor each module that is being run. The module used is the ARM 1923 Robot Module and Voice Module ED4321.

Embedded Linux System for Digital Image Recognition using Internet of Things

The present paper describes the use of Digital Image Processing and Internet of Things for gestures recognition using depth sensors available on Kinect device. Using the open source libraries OpenCV and libfreenect, image data are translated and used for communicating Raspberry Pi embedded Linux system with PIC microcontroller board for peripheral devices controlling. A LED is triggered according to the hand gesture representing the corresponding number. Data are stored in a PHP Apache server running locally on Raspberry Pi. The proposed system can be used as a multifunctional tool in areas such as learning process, post-traumatic rehabilitation and visual and motor cognition time. Using image binarization and Naive-Bayes classifier, the achieved results show error lower than 5%.