• IEMEK Journal of Embedded Systems and Applications
• /
• v.6 no.6
• /
• pp.361-367
• /
• 2011

In this paper, we propose an interactive embedded system framework for efficient training management in u-health environment. First, we analyzed various requirements of smart training systems for quality of life. We also analyzed the oversea trends and positive effects of the embedded system in terms of both technical and economical factors. Second, we proposed detailed design specification for embedded hardware implementation. Third, we developed effective OS(Operating System) specification for the embedded hardware. Finally, we developed a training scenario and embedded applications such as training control software and analysis software for the smart training systems.

• Journal of the Korean Society of Systems Engineering
• /
• v.4 no.2
• /
• pp.27-33
• /
• 2008

As a part of development of Korean K2 main battle tank, embedded training computer to be operated in the main equipment, which makes it possible to train without a special-purposed training simulator, was adopted for tank combat training. The category of embedded training of Korean K2 main battle tank includes driving training, gunnery training, single tank combat training, platoon level combat training, and command and platoon leaders combat training. For realization unit level tank embedded training system, the virtual reality was utilized for real time image rendering, and network based real time communication system of K2 tank was utilized for sharing status information between tanks. As a result, it is possible to train themselves on their own tank for enhancing the operational skills and harmonized task with members.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.21 no.5
• /
• pp.581-587
• /
• 2011

This paper presents a senior-level embedded software design course using a customized training kit. Embedded software design courses commonly entail a lot of practice hours and a semester-long project and thus requires a hardware platform on which the embedded software runs. A training kit has been designed such that both hardware system and operating system are not too complicated or heavy for undergraduate students to fully understand and to develop embedded software on their own. The course using the customized training kit gives the students hands-on experience of embedded software design and programming ranging from device drivers to user interface, thereby enabling them to have in-depth understanding of embedded software and to improve their programming skills more easily and faster than when using commercial training kits.

• Journal of Practical Engineering Education
• /
• v.11 no.2
• /
• pp.283-289
• /
• 2019

Recently, product mobility, data compatibility and communication connectivity have become very important to the control system, depending on the application of smart manufacturing. Accordingly, embedded systems are essential in all industries including home appliances, telecommunication, and national defense. Therefore, the demand for embedded system development personnel is increasing further, and education and training programs are needed to combine the practical skills of industrial sites, including programming skills and hardware. Currently, embedded system education offers a variety of education centered on Aduino, but this is mostly for beginners and is not sufficient for majors. In addition, while various prototype studies related to embedded systems are active, the training and training programs for working-level human resources needed at industrial sites are very scarce. Therefore, in order to foster the working personnel of the embedded system for the application of smart manufacturing, this paper selected the capability unit through in-depth interviews and survey analysis of 10 experts based on NCS, and developed education and training programs and contents.

• ETRI Journal
• /
• v.32 no.1
• /
• pp.160-162
• /
• 2010

For the acoustic models of embedded speech recognition systems, hidden Markov models (HMMs) are usually quantized and the original full space distributions are represented by combinations of a few quantized distribution prototypes. We propose a maximum likelihood objective function to train the quantized distribution prototypes. The experimental results show that the new training algorithm and the link structure adaptation scheme for the quantized HMMs reduce the word recognition error rate by 20.0%.

• The Journal of Korean Association of Computer Education
• /
• v.21 no.6
• /
• pp.27-37
• /
• 2018

In this paper, we propose a design and development method of an elevator simulator that can be used as an embedded application layer software learning tool and a teaching and learning method using it. The simulator provides students with an environment to implement the operating principle and control method of the elevator system in the application layer excluding the issues of hardware and embedded OS layer. This allows students to have a reactive and real-time embedded application development experience. In addition, we present a four-week embedded application software training course with hands-on exercises that add step-by-step functionality using a simulator. As a result of training for actual students, we obtained 83.3 points of learning achievement score and proved that the curriculum has a significant effect on embedded application learning.

• Proceedings of the IEEK Conference
• /
• 2002.07a
• /
• pp.690-693
• /
• 2002

According to the growth of communication biz, embedded market rapidly developing in domestic and overseas. Embedded system can be used in various way such as wire and wireless communication equipment or information products. There are lots of developing performance applying speech recognition to embedded system, for instance, PDA, PCS, CDMA-2000 or IMT-2000. This study implement minimum memory of speech recognition engine and DB for apply real time embedded system. The implement measure of speech recognition equipment to fit on embedded system is like following. At first, DC element is removed from Input voice and then a compensation of high frequency was achieved by pre-emphasis with coefficients value, 0.97 and constitute division data as same size as 256 sample by lapped shift method. Through by Levinson - Durbin Algorithm, these data can get linear predictive coefficient and again, using Cepstrum - Transformer attain feature vectors. During HMM training, We used Baum-Welch reestimation Algorithm for each words training and can get the recognition result from executed likelihood method on each words. The used speech data is using 40 speech command data and 10 digits extracted form each 15 of male and female speaker spoken menu control command of Embedded system. Since, in many times, ARM CPU is adopted in embedded system, it's peformed porting the speech recognition engine on ARM core evaluation board. And do the recognition test with select set 1 and set 3 parameter that has good recognition rate on commander and no digit after the several tests using by 5 proposal recognition parameter sets. The recognition engine of recognition rate shows 95%, speech commander recognizer shows 96% and digits recognizer shows 94%.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.17 no.3
• /
• pp.129-138
• /
• 2022

Collecting and labeling sufficient training data, which is essential to deep learning-based visual inspection, is difficult for manufacturers to perform because it is very expensive. This paper presents a steel plate surface defect detection system with industrial-grade detection performance by training a small amount of steel plate surface images consisting of labeled and non-labeled data. To overcome the problem of lack of training data, we propose two data augmentation techniques: program-based augmentation, which generates defect images in a geometric way, and generative model-based augmentation, which learns the distribution of labeled data. We also propose a 4-step semi-supervised learning using pseudo labels and consistency training with fixed-size augmentation in order to utilize unlabeled data for training. The proposed technique obtained about 99% defect detection performance for four defect types by using 100 real images including labeled and unlabeled data.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.10 no.6
• /
• pp.345-352
• /
• 2015

Recently, by developing many training systems in battle field, the demand for interconnecting and internetworking between Live, Virtual, Constructive training systems has been increased to support efficient data distribution and system control. But, there are lots of problems for them to interwork, because the existing researches only support L-L, V-V, C-C Interoperability. Therefore, we propose L-V-C gateway to provide interoperable simulation environment based on HLA and DDS between them. First, we illustrate FOM Management that parses RPR-FOM XML file to acquire Data information to be shared between them, and generates common data structure and source code used for L-V-C Gateway. L-V-C Gateway created from FOM Management supports Data Conversion and Quality of Service between HLA and DDS. HLA Federate and DDS Domainparticipant in L-V-C Gateway play a role of logical communication channel and relay data from HLA Federation to DDS Domain and vice versa.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.4
• /
• pp.207-218
• /
• 2019

The purpose of this study is to develop a model that can systematically study the whole learning process of machine learning. Since the existing model describes the learning process with minimum coding, it can learn the progress of machine learning sequentially through the new model, and can visualize each process using the tensor flow. The new model used all of the existing model algorithms and confirmed the importance of the variables that affect the target variable, survival. The used to classification training data into training and verification, and to evaluate the performance of the model with test data. As a result of the final analysis, the ensemble techniques is the all tutorial model showed high performance, and the maximum performance of the model was improved by maximum 5.2% when compared with the existing model using. In future research, it is necessary to construct an environment in which machine learning can be learned regardless of the data preprocessing method and OS that can learn a model that is better than the existing performance.