Go to the main menu
Skip to content
Go to bottom
REFERENCE LINKING PLATFORM OF KOREA S&T JOURNALS
> Journal Vol & Issue
IEMEK Journal of Embedded Systems and Applications
Journal Basic Information
Journal DOI :
Institute of Embedded Engineering of Korea
Editor in Chief :
Volume & Issues
Volume 10, Issue 6 - Dec 2015
Volume 10, Issue 5 - Oct 2015
Volume 10, Issue 4 - Aug 2015
Volume 10, Issue 3 - Jun 2015
Volume 10, Issue 2 - Apr 2015
Volume 10, Issue 1 - Feb 2015
Selecting the target year
Spliced Image Detection Using Characteristic Function Moments of Co-occurrence Matrix
Park, Tae-Hee ; Moon, Yong-Ho ; Eom, Il-Kyu ;
IEMEK Journal of Embedded Systems and Applications, volume 10, issue 5, 2015, Pages 265~272
DOI : 10.14372/IEMEK.2015.10.5.265
This paper presents an improved feature extraction method to achieve a good performance in the detection of splicing forged images. Strong edges caused by the image splicing destroy the statistical dependencies between parent and child subbands in the wavelet domain. We analyze the co-occurrence probability matrix of parent and child subbands in the wavelet domain, and calculate the statistical moments from two-dimensional characteristic function of the co-occurrence matrix. The extracted features are used as the input of SVM classifier. Experimental results show that the proposed method obtains a good performance with a small number of features compared to the existing methods.
Resilience Evaluation of Vehicle Driving System Depending on System Architecture
Byun, Sungil ; Lee, Dongik ;
IEMEK Journal of Embedded Systems and Applications, volume 10, issue 5, 2015, Pages 273~279
DOI : 10.14372/IEMEK.2015.10.5.273
The vehicle has lots of embedded systems. Each of systems has its own role. In case of the vehicle, simple failure of system can be critical to driver. Therefore all of embedded system should be managed based on importance factors to be effective. In this paper, we consider the resilience as the importance factor for the driving system with ACC(Adaptive Cruise Control). We propose metrics to calculate the resilience of the embedded system. To get the resilience of system, we calculate the reliability and the resilience of nodes in the system using its failure rate. The resilience of whole system can be presented by the resilience of nodes and its weight. We calculate the resilience and compare the centralized structure and the distributed structure.
A Disaster Evacuation System Using Smart Devices for Indoor Crisis Management in BLE Environments
Jang, Minsoo ; Jeong, Wooyong ; Lim, Kyungshik ;
IEMEK Journal of Embedded Systems and Applications, volume 10, issue 5, 2015, Pages 281~296
DOI : 10.14372/IEMEK.2015.10.5.281
This paper describes a novel disaster evacuation system using embedded systems such as smart devices for crisis and emergency management. In indoor environments deployed with the Bluetooth Low Energy(BLE) beacons, smart devices detect their indoor positions from beacon messages and interact with Map Server(MS) and Route Server(RS) in the Internet over the LTE and/or Wi-Fi functions. The MS and RS generate an optimal path to the nearest emergency exit based on a novel graph generation method for less route computation, called the Disaster Evacuation Graph(DEG), for each smart device. The DEG also enables efficient processing of some constraints in the computation of route, such as load balancing in situation of different capacities of paths or exits. All data interfaces among three system components, the MS, RS, smart devices, have been defined for modular implementation of our disaster evacuation system. Our experimental system has been deployed and tested in our building thoroughly and gives a good evidence that the modular design of the system and a novel approach to compute emergency route based on the DEG is competitive and viable.
Safe Adaptive Headlight Controller with Symmetric Angle Sensor Compensator for Functional Safety Requirement
Youn, Jiae ; Yin, Meng Di ; An, Junghyun ; Cho, Jeonghun ; Park, Daejin ;
IEMEK Journal of Embedded Systems and Applications, volume 10, issue 5, 2015, Pages 297~305
DOI : 10.14372/IEMEK.2015.10.5.297
AFLS (Adaptive front lighting System) is being applied to improve safety in driving automotive at night. Safe embedded system for controlling head-lamp has to be tightly designed by considering safety requirement of hardware-dependent software, which is embedded in automotive ECU(Electronic Control Unit) hardware under severe environmental noise. In this paper, we propose an adaptive headlight controller with newly-designed symmetric angle sensor compensator, which is integrated with ECU-based adaptive front light system. The proposed system, on which additional backup hardware and emergency control algorithm are integrated, effectively detects abnormal situation and restore safe status of controlling the light-angle in AFLS operations by comparing result in symmetric angle sensor. The controlled angle value is traced into internal memory in runtime and will be continuously compared with the pre-defined lookup table (LUT) with symmetric angle value, which is used in normal operation. The watch-dog concept, which is based on using angle sensor and control-value tracer, enables quick response to restore safe light-controlling state by performing the backup sequence in emergency situation.
Arduino Based Smart Home System for the Elderly Living Alone
Lee, In-Gu ; Cho, Myeon-Gyun ;
IEMEK Journal of Embedded Systems and Applications, volume 10, issue 5, 2015, Pages 307~315
DOI : 10.14372/IEMEK.2015.10.5.307
Recently, Smart Home System(SHS) is applied in order to provide comfort, energy efficient and better security to the residence. Thus, by introducing the SHS in the house of elderly people, it is possible to provide a convenient and safe life for old people especially living alone. This paper presents the design and implementation of a low cost but yet flexible and secure smart-phone based SHS. The design is based on inter-working between Arduino board with Bluetooth and Arduino board with Ethernet shield, and the home monitor/appliances are connected to the input/output ports of this board via sensors/relays. In addition, when the old man is put on an emergency, the proposed system will automatically notify it the family. Therefore, we have implemented an inexpensive and efficient SHS for the elderly living alone by inter-working smart phones, internet server and Arduino micro-controller.
Location and Direction Tracking of Small UAVs on Occlusion Area in Moving Surveillance System
Moon, Yong-Ho ; Cheon, Seung-Hyeon ; Ha, Seok-Wun ;
IEMEK Journal of Embedded Systems and Applications, volume 10, issue 5, 2015, Pages 317~324
DOI : 10.14372/IEMEK.2015.10.5.317
In his paper, we propose the graphic-based direction tracking system that be able to detect the current location and direction of the flight object and virtually run the pointing to the flight direction when a small UAV is located in the occlusion area behind buildings or obstacles in the moving surveillance systems. Based on the experimental results about the simulation flight path extracted from the Mission Planner we found the proposed system operates the desired flight mission effectively in tracking.
Night-time Vehicle Detection Based On Multi-class SVM
Lim, Hyojin ; Lee, Heeyong ; Park, Ju H. ; Jung, Ho-Youl ;
IEMEK Journal of Embedded Systems and Applications, volume 10, issue 5, 2015, Pages 325~333
DOI : 10.14372/IEMEK.2015.10.5.325
Vision based night-time vehicle detection has been an emerging research field in various advanced driver assistance systems(ADAS) and automotive vehicle as well as automatic head-lamp control. In this paper, we propose night-time vehicle detection method based on multi-class support vector machine(SVM) that consists of thresholding, labeling, feature extraction, and multi-class SVM. Vehicle light candidate blobs are extracted by local mean based thresholding following by labeling process. Seven geometric and stochastic features are extracted from each candidate through the feature extraction step. Each candidate blob is classified into vehicle light or not by multi-class SVM. Four different multi-class SVM including one-against-all(OAA), one-against-one(OAO), top-down tree structured and bottom-up tree structured SVM classifiers are implemented and evaluated in terms of vehicle detection performances. Through the simulations tested on road video sequences, we prove that top-down tree structured and bottom-up tree structured SVM have relatively better performances than the others.