• The KIPS Transactions:PartB
• /
• v.9B no.3
• /
• pp.375-382
• /
• 2002

Handwritten character recognition is classified into on-line handwritten character recognition and off-line handwritten character recognition. On-line handwritten character recognition has made a remarkable outcome compared to off-line hacdwritten character recognition. This method can acquire the dynamic written information such as the writing order and the position of a stroke by means of pen-based electronic input device such as a tablet board. On the contrary, Any dynamic information can not be acquired in off-line handwritten character recognition since there are extreme overlapping between consonants and vowels, and heavily noisy images between strokes, which change the recognition performance with the result of the preprocessing. This paper proposes a method that effectively extracts the stroke including dynamic information of characters for off-line Korean handwritten character recognition. First of all, this method makes improvement and binarization of input handwritten character image as preprocessing procedure using watershed algorithm. The next procedure is extraction of skeleton by using the transformed Lu and Wang's thinning: algorithm, and segment pixel array is extracted by abstracting the feature point of the characters. Then, the vectorization is executed with a maximum permission error method. In the case that a few strokes are bound in a segment, a segment pixel array is divided with two or more segment vectors. In order to reconstruct the extracted segment vector with a complete stroke, the directional component of the vector is mortified by using right-hand writing coordinate system. With combination of segment vectors which are adjacent and can be combined, the reconstruction of complete stroke is made out which is suitable for character recognition. As experimentation, it is verified that the proposed method is suitable for handwritten Korean character recognition.

• Journal of Korea Multimedia Society
• /
• v.14 no.7
• /
• pp.895-904
• /
• 2011

In welding machine that executes existing spot welding, wrong operation of system has often occurs because of their mechanical motion that can be caused by a number of supply like the welding object. In exposed working environment for various situations such as worker or related equipment moving into any place that we are unable to exactly distinguish between good and not condition of nut. Also, in case of defective welding of nut, it needs various evaluation and analysis through image processing because the problem that worker should be inspected every single manually. Therefore in this paper, if the object was not stabilization state correctly, we have purpose to algorithm implementation that it is to reduce the analysis time and exact recognition as to improve system of image processing. As this like, as image analysis for assessment whether it is good or not condition of nut, in his paper, implemented algorithms were suggested and list by group and that it showed the effectiveness through more than one experiment. As the result, recognition rate of normality and error according to the estimation time have been shown as 40%~94.6% and 60%~5.4% from classification 1 of group 1 to classification 11 of group 5, and that estimation time of minimum, maximum, and average have been shown as 1.7sec.~0.08sec., 3.6sec.~1.2sec., and 2.5sec.~0.1sec.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.14 no.2
• /
• pp.828-834
• /
• 2013

In this paper, TMC (Tracker Motion Controller) as one of the many research methods for condensing efficiency improvements can be condensed into efficient solar system configuration to improve the power generation efficiency of the castle with Concentrated solar silicon and photovoltaic systems (CPV)experiments using PV systems. Microprocessor used on the solar system, tracing the development of solar altitude and latitude of each is calculated in real time. Also accept the value from the sensor, motor control and communication with the central control system by calculating the value of the current position of the sun, there is a growing burden on the applicability. Through the way the program is appropriate for solar power systems and sensors hybrid-type algorithm was implemented in the ARM core with built-in TMC, Concentrated CPV system compared to the existing PV systems, through the implementation of the TMC in the country's power generation efficiency compared and analyzed. Sensor method using existing experimental results Concentrated solar power systems to communicate the value of GPS location tracking method hybrid solar horizons in the coordinate system of the sun's azimuth and elevation angles calculated by the program in the calculations of astronomy through experimental resultslook clear day at high solar irradiation were shown to have a large difference. Stopped after a certain period of time, the sun appears in the blind spot of the sensor, the sensor error that can occur from climate change, however, do not have a cloudy and clear day solar radiation sensor does not keep track of the position of the sun, rather than the sensor of excellence could be found. It is expected that research is constantly needed for the system with ongoing research for development of solar cell efficiency increases to reduce the production cost of power generation, high efficiency condensing type according to the change of climate with the optimal development of the ability TMC.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.11
• /
• pp.693-700
• /
• 2020

This study compared the accuracy and reliability of definitive casts fabricated from a digital impression and conventional impression technique. A master model with the prepared upper full-arch tooth was used. Samples of ten plaster models and ten polyurethane models were duplicated using a selected standard master model. Six linear measurements were recorded between the landmarks, directly on each of the stone models and the polyurethane models on two occasions by a double examiner. The Wilcoxon signed-rank test, interclass correlation coefficient (ICC), measurement error (MSE), and limit of agreement (LoA) were used for statistical analysis. The ICC ranged from 0.76 to 0.99 when comparing the stone models and polyurethane models. The mean difference between the stone models and polyurethane models ranged from 0.09mm to 0.20mm, suggesting that stone models might be slightly larger than polyurethane models. Based on this study, the accuracy of the polyurethane models in evaluating the performance of an oral scanner and subtractive technology was acceptable. Further studies will be needed on patient subjects under clinical conditions that may involve missing or malpositioned teeth and fixed dental prostheses because this study was limited to use a standard master model and duplicated sample models in a laboratory setting.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.11
• /
• pp.851-860
• /
• 2020

With an increase in the aging population and a rising social interest in health and welfare, studies to improve healthcare in the elderly are being actively conducted. This study attempted to improve the current design and manufacture of elevating electric wheelchairs to enhance user safety and convenience. Seat design based on the user's body shape, convenience while boarding or alighting, caster turning radius and, safety and stability features that prevent shaking when the user gets up or sits down were improved. A driving experiment was conducted to evaluate the operation of the indoor electric wheelchair designed and manufactured with these additional functionalities. During the test, the performance parameters evaluated were continuous driving time, turning radius, maximum lifting and lowering load, maximum lifting height, noise level, minimum distance sensing by the driving auxiliary sensor, ability to interact with server and app programs, and the duty cycle maximum error rate. The test confirmed that this improved electric wheelchair successfully met target parameters. In a future study, we will evaluate this improved electric wheelchair from a user's perspective for its usability parameters, such as satisfaction, convenience and stability.

• Korean Journal of Cognitive Science
• /
• v.28 no.4
• /
• pp.245-265
• /
• 2017

Recently, studies on cognitive control revealed that the optimal level of control is determined on the basis of reward and cost. The value of reward can be subjective and therefore, the optimal control strength can vary accordingly. The inconsistent effect of aging on cognitive control can be the result of flexible adjustment of control signal strength made by the older subjects. In other words, the elderly people maintains the ability to set the optimal level of control, which is known as the function of the dorsal anterior cingulate cortex. On the other hand, the age-related decline in cognitive control is obvious in rule maintenance and inhibition, which has to do with the function of lateral prefrontal cortex. In this study, we had young and old adults perform go-no go task and compared the behavioral and neural results for different reward conditions. Both age groups showed the best performance and the largest ERN amplitude when the reward was most appealing to them. And there was no age effect in ERN amplitude even though older adults' d' and accuracy was inferior to younger participants. These findings suggest that the effect aging on different cognitive control processes can be asymmetric.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.4
• /
• pp.617-629
• /
• 2020

In order to overcome the limitations of the rule-based intrusion detection system due to changes in Internet computing environments, the emergence of new services, and creativity of attackers, network anomaly detection (NAD) using machine learning and deep learning technologies has received much attention. Most of these existing machine learning and deep learning technologies for NAD use supervised learning methods to learn a set of training data set labeled 'normal' and 'attack'. This paper presents the feasibility of the unsupervised learning AutoEncoder(AE) to NAD from data sets collecting of secured network traffic without labeled responses. To verify the performance of the proposed AE mode, we present the experimental results in terms of accuracy, precision, recall, f1-score, and ROC AUC value on the NSL-KDD training and test data sets. In particular, we model a reference AE through the deep analysis of diverse AEs varying hyper-parameters such as the number of layers as well as considering the regularization and denoising effects. The reference model shows the f1-scores 90.4% and 89% of binary classification on the KDDTest+ and KDDTest-21 test data sets based on the threshold of the 82-th percentile of the AE reconstruction error of the training data set.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.15 no.4
• /
• pp.833-838
• /
• 2011

RFID system in manufacturing industry is used to collect, categorize, and process the data of products. To install RFID system for a large factory, a large amount of wired data communication network is necessary for RS232 communication. If the installed location of RFID system in the factory is changed or extended, a reinstallment is required for the already installed wired data network. A large amount of time/financial reinvestment is necessary for such reinstallation. By using wireless data communication network, however, the initial installation and reinstallation are very simple. In this paper, we implemented a wireless communication system and RFID system. We used the CC1020 chip for wireless communication system and EM4095 chip for RFID system. CC1020 chip enables highly-reliable data communication, and by setting a simple status register, it can switch between transmitting/receiving status and it can choose the desired frequency of either 400 MHz or 900 MHz. Also, Communication range is 50 m, if external antenna is used. EM4095 is a chip for RFID reader system with the carrier frequency of 125 KHz. This chip can implement the reader system by connecting a small number of components. And EM4100 was used for RFID system. EM4100 is read-only type. Atmega128 is used to control a wireless communication system and RFID system. We confirm that the system can communicate without error up to 50 m from sender. In the paper, the circuit diagram and operation program for CC1020 and RFID system are presented. The system used in the experiment is shown in pictures, and the data movement pattern of CC1020 is shown in the diagram, and the performance of each transmission method is presented.

• Journal of the Korean Society of Radiology
• /
• v.12 no.3
• /
• pp.343-349
• /
• 2018

Dose rate regulated tracking is known to be an efficient method which adaptively delivers tracking treatments when patient breathing is irregular. The Motion Management Interface (MMI, Varian Medical System, CA), which provides beam on/off switching during treatment is available for clinic. Study is to test if delivering the adaptive tumor tracking is feasible for irregular breathing using beam switching with MMI. 55 free breathing RPM traces acquired from lung cancer patients are used. The first day RPM traces of the patients are utilized to design preprogrammed tracking MLC patterns, of which periods are intentionally reduced by 20% in order to catch up the variation of patient breathing irregularity in the treatment day. Eligibility criteria for this technique are the variation of amplitude and period less than 20%. An algorithm which determines beam on/off every 100 ms by considering the preprogrammed (MLC) positions and current breathing positions is developed. Tracking error and delivery efficacy are calculated by simulating the beam-switching adaptive tracking from the RPM traces. Breathing patterns of 38 patients (70%) met the eligibility criteria. Tracking errors of all of the cases who meet the criteria are less than 2 mm (average 1.4 mm) and the average delivery efficacy was 71%. Those of rest of the cases are 1.9 mm and 48%. Adaptive tracking with beam switching is feasible if patient selection is based on the eligibility criteria.

• Journal of Korea Society of Industrial Information Systems
• /
• v.19 no.1
• /
• pp.13-18
• /
• 2014

Sensor nodes are used for monitoring and collecting the environmental data via wireless sensor network. The wireless sensor network with various sensor nodes draws attention as a key technology in ubiquitous computing. Sensor nodes has very small memory capacity and limited power resource. Thus, it is essential to have energy efficient strategy for the sensor nodes. Since the sensor nodes are operating on the same frequency bands with ISM frequency bands, the interference by the devices operating on the ISM band degrades the quality of communication integrity. In this paper, the convolutional code is proposed instead of ARQ for the error control for the sensor network. The proposed convolutional code was implemented and the BER performance is measured. For the fixed transmitting powers of -19.2 dBm and -25dBm, the BER with various communication distances are measured. The packet loss rate and the retransmission rate are calculated from the measured BER. It is shown that the porposed method obtained about 9~12% and 12-19% reduction in retransmission rate for -19.2 dBm and -25 dBm respectively.