• The KIPS Transactions:PartA
• /
• v.16A no.3
• /
• pp.209-216
• /
• 2009

The ubiquitous smart home is the home of the future that takes advantage of context information from the human and the home environment and provides an automatic home service for the human. Human location and motion are the most important contexts in the ubiquitous smart home. We present a real-time human tracker that predicts human location and motion for the ubiquitous smart home. We used four network cameras for real-time human tracking. This paper explains the real-time human tracker's architecture, and presents an algorithm with the details of two functions (prediction of human location and motion) in the real-time human tracker. The human location uses three kinds of background images (IMAGE1: empty room image, IMAGE2: image with furniture and home appliances in the home, IMAGE3: image with IMAGE2 and the human). The real-time human tracker decides whether the human is included with which furniture (or home appliance) through an analysis of three images, and predicts human motion using a support vector machine. A performance experiment of the human's location, which uses three images, took an average of 0.037 seconds. The SVM's feature of human's motion recognition is decided from pixel number by array line of the moving object. We evaluated each motion 1000 times. The average accuracy of all the motions was found to be 86.5%.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.9
• /
• pp.419-428
• /
• 2017

In an embedded system, modules exchange data by interacting among themselves. Exchanging erroneous resource data among modules may lead to execution errors. The interacting resources produce dependencies between the two modules where any change of the resources by one module affects the functionality of another module. Several investigations of the embedded systems show that interaction faults between the modules are one of the major cause of critical software failure. Therefore, interaction testing is an essential phase for reducing the interaction faults and minimizing the risk. The direct and indirect interactions between the modules generate interaction faults. The direct interaction is the explicit call relation between the modules, and the indirect interaction is the remaining relation that is made underneath the interface that possesses data dependence relationship with resources. In this paper, we investigate the errors that are based on the indirect interaction between modules and introduce a new test criterion for identifying the errors that are undetectable by existing approaches at the integration level. We propose a novel approach for generating the interaction model using the indirect interaction pattern and design test criteria that are based on different interaction errors to generate test cases. Finally, we use the fault injection technique to evaluate the feasibility and effectiveness of our approach.

• KIPS Transactions on Computer and Communication Systems
• /
• v.6 no.4
• /
• pp.189-196
• /
• 2017

BIS(Bus Information System) provides the different information related to buses including predictions of arriving times at stations. BIS have been deployed almost all cities in our country and played active roles to improve the convenience of public transportation systems. Moving average filters, Kalman filter and regression models have been representative in forecasting the arriving times of buses in current BIS. The accuracy in prediction of arriving times depends largely on the forecasting algorithms and traffic conditions considered when forecasting in BIS. In present BIS, the simple prediction algorithms are used only considering the passage times and distances between stations. The forecasting of arrivals, however, have been influenced by the traffic conditions such as traffic signals, traffic accidents and pedestrians ets., and missing data. To improve the accuracy of bus arriving estimates, there are big troubles in building models including the above problems. Hidden Markov Models have been effective algorithms considering various restrictions above. So, we have built the HMM forecasting models for bus arriving times in the current BIS. When building models, the data collected from Sunchean City at 2015 have been utilized. There are about 2298 stations and 217 routes in Suncheon city. The models are developed differently week days and weekend. And then the models are conformed with the data from different districts and times. We find that our HMM models can provide more accurate forecasting than other existing methods like moving average filters, Kalmam filters, or regression models. In this paper, we propose Hidden Markov Model to obtain more precise and accurate model better than Moving Average Filter, Kalman Filter and regression model. With the help of Hidden Markov Model, two different sections were used to find the pattern and verified using Bootstrap process.

• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.12
• /
• pp.507-516
• /
• 2019

Costs invested in road maintenance and road development are on the rise. However, due to accidents such as portholes and ground subsidence, the risks to the drivers' safety and the material damage caused by accidents are also increasing. Following this trend, we have developed a system that determines road damage, according to the magnitude of vibration generated without directly intervening the driver when driving. In this paper, we implemented the system using a remote control car (RC car) simulator due to the limitation of the environment in which the actual vehicle is not available in the process of developing the system. In addition, we attached a vibration sensor and GPS sensor to the body of the RC car simulator to measure the vibration value and location information generated by the movement of the vehicle in real-time while driving, and transmitting the corresponding data to the server. In this way, we implemented a system that allows external users to check the damage of roads and the maintenance of the repaired roads based on data more easily than the existing systems. By using this system, we can perform early prediction of road breakage and pattern prediction based on the data. Further, for the RC car simulator, commercialization will be possible by combining it with business in other fields that require flatness.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.3
• /
• pp.12-26
• /
• 2000

In this paper, we propose a post-processing algorithm to remove false minutiae which decrease the overall performance of an automatic fingerprint identification system by increasing computational complexity, FAR(False Acceptance Rate), and FRR(False Rejection Rate) in matching process. The proposed algorithm extracts candidate minutiae from thinned fingerprint image. Considering characteristics of the thinned fingerprint image, the algorithm selects the minutiae that may be false and located in recoverable area. If the area where the selected minutiae reside is thinned incorrectly due to noise and loss of information, the algorithm recovers the area and the selected minutiae are removed from the candidate minutiae list. By examining the ridge pattern of the block where the candidate minutiae are found, true minutiae are recovered and in contrast, false minutiae are filtered out. In an experiment, Fingerprint images from NIST special database 14 are tested and the result shows that the proposed algorithm reduces the false minutiae extraction rate remarkably and increases the overall performance of an automatic fingerprint identification system.

• Journal of the Korean Academy of Child and Adolescent Psychiatry
• /
• v.8 no.2
• /
• pp.242-255
• /
• 1997

Characteristics of attention deficit of attention-deficit hyperactivity disorder(ADHD) were investigated by administering six computerized attention tests of Vienna Test System and four neuropsychological tests to children aged 6-12, with ADHD(n=21) and age-matched normal control children(n=22). The findings indicated that ADHD children show lower level of vigilance, more decline of performance in vigilance task on time, and impaired preparedness to response. They also have selective attention deficit on monitoring tasks, but did not have sustained attention deficit compared with normal control children. On the tasks wich overload their information processing capacity, ADHD children show more impulsive response pattern than normal control children. The performance of ADHD was worse than control on the neuropsychological tests sensitive to frontal lobe dysfunction. The presense 'These' attention deficits supports the theory that the defect of ADHD is due to the dysfunction of more than one brain region, including brain stem reticular formation and frontal lobe.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.9 no.2
• /
• pp.79-90
• /
• 2006

The partitioning level of a catchment becomes an issue if the calculated results from different levels show the same performance regardless of the levels. This study aims to identify the proper processing level of spatial resolution for the SWMM model application in an urban area. Using GIS overlaying technique, the division of subcatchments as a hydrologic similarity unit (HSU) is achieved with a comprehensive consideration of surface slope conditions, flow directions of storm sewers, and current land cover situation. Three surface-sewer alternatives are made on the basis of three different levels of surface divisions as well as the number of sewer connections and used as runoff simulation fields for the application of SWMM. As the result, it is found that the effect of a spatial resolution on the surface runoff results is not significant. On the other hand, the accumulated pollution load from an unit subcatchment, which is built by aggregation of several unit subcatchments consisting of various land cover conditions is reduced through the deterioration of surface spatial resolution. Although overall runoff pattern and accumulated runoff are little affected by spatial resolution, the simulated runoff from sewer outlet shows slight difference at the peak appearance time. The gap between surface pollution load accumulated and it discharged from the sewer outlet in a surface-sewer alternative during runoff period is monitored but the level of error is less than 5-10% except the lowest spatial resolution case.

• Journal of the Korean Dietetic Association
• /
• v.13 no.1
• /
• pp.61-72
• /
• 2007

In order to study milk preference and intake pattern of adolescents, the questionnaire survey was conducted with 929 middle and high school students residing in Chungnam cities through October and November 2004. Of the subjects, 56.3% liked milk or liked very much. They preferred chocolate and fruit-tasted milk to plain milk. Reasons for liking milk were for health and its taste, while the reasons of disliking were unpleasant smell and stomach upset. However those who disliked milk did like milk products such as ice-cream, yogurt or cheese. Of the students 35.1% drank milk 2 times or more a day, while 11.8% drank milk less than 2-3 times a month. As a whole they drank milk 8.6$\pm$6.7 times a week, of which 4.3$\pm$3.1 times for plain milk. Daily intake amount was estimated as 308$\pm$315mL. Middle-school students and boys drank more milk than high-school students and girls, respectively. Among the students 64.3% used to drink 1 cup of milk at a time, and 58.3% drank only milk without other foods. It was shown that 51.8% took milk school-serviced and their milk intake frequencies were higher than those of who were not given school milk service. Also milk intake frequencies was higher in students whose mother were housewives than in students whose mother had jobs. Milk preference, intake frequency, and one portion size showed significant and positive correlations each other. In conclusion, milk intake level of the subjects was insufficient and unpleasant smell and stomach upset were the main reasons which decreased milk preference and consumption. Students with low milk preference should be guided with how to drink milk deliciously, how to choose milk type and its products. It is also effective to go into school milk service and to provide milk at home anytime. As students like much fruit-tasted and chocolate milk, the milk processing industries should take their nutritional and health benefits into considerations importantly.

• KDI Journal of Economic Policy
• /
• v.12 no.1
• /
• pp.3-29
• /
• 1990

Korean input-output tables for 1975 and 1985 are first deflated into 1975 constant domestic prices(hypothetical terms), and the constant price I-O data are used to decompose the sources of industrial growth and structural change during the 1975-85 period. Using the same methodology, our results for the 1975-85 period are then linked to the results for the earlier period(1955-75) in order to analyze and evaluate the "demand-side" sources of industrialization over the past three decades. The results from the decomposition of the whole economy indicate that over three decades(1955-85) the relative contribution of domestic demand expansion (DDE) to growth and structural change has continuously declined while the contribution of export expansion(EE) has generally continued to rise. The contribution of import-substitution(IS) which had been significantly higher than that of EE during 1955-63 declined substantially, remaining at an insignificantly low level during the period following 1963. Although it is well known that the government's industrial policy in the 1970s emphasized import-substitution in heavy and chemical industries, no significant changes in the export-oriented growth pattern could be observed even for that period, except for a minor decline in the relative contribution of EE. This may be attributed to the substantially larger, backward-linkage effects of EE than that of IS. The sources-of-growth decompositions for major branches of the manufacturing sector generally support the major conclusions derived from the decomposition for the whole economy. The IS contribution which had been significantly high in almost all manufacturing branches during the 1955-63 period declined to low levels in all but two branches, heavy industry and machinery, during the following period. On the other hand, the relative contribution of EE showed a continuous rise in almost all manufacturing branches(except food processing). Finally, the sources of growth for 1975-85 which were decomposed by detailed sub branches, are analyzed by correlating them with changes in relative prices and industrial protection rates by sub-branches for the same period. A major result is that contrary to general expectations, the EE contributions by sub-branch are not negatively correlated with the nominal rates of protection and/or the effective rates of protection for the same sub-branches. It is also found that no statistically significant, positive correlation exists between IS contributions and nominal protection rates or effective protection rates. These unexpected results may be explained by the peculiar nature of the Korean system of industrial incentives for the past period.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.40 no.4
• /
• pp.193-205
• /
• 2003

There has been so many research activities about robot soccer system in the many research fields, for example, intelligent control, communication, computer technology, sensor technology, image processing, mechatronics. Especially researchers research strategy for attacking in the field of strategy, and develop intelligent strategy. Then, soccer robots cannot defense completely and efficiently by using simple defense strategy. Therefore, intention extraction of attacker is needed for efficient defense. In this thesis, intention extractor of soccer robots is designed and developed based on FMMNN(Fuzzy Min-Max Neural networks ). First, intention for soccer robot system is defined, and intention extraction for soccer robot system is explained.. Next, FMMNN based intention extractor for soccer robot system is determined. FMMNN is one of the pattern classification method and have several advantages: on-line adaptation, short training time, soft decision. Therefore, FMMNN is suitable for soccer robot system having dynamic environment. Observer extracts attack intention of opponents by using this intention exactor, and this intention extractor is also used for analyzing strategy of opponent team. The capability of developed intention extractor is verified by simulation of 3 vs. 3 robot succor simulator. It was confirmed that the rates of intention extraction each experiment increase.