• Journal of KIISE
• /
• v.44 no.11
• /
• pp.1149-1155
• /
• 2017

Recently, with the development of communication technology, it has become possible to collect various sensor data that indicate the environmental stimuli within a space. In this paper, we propose a group emotion prediction system using a modular Bayesian network that was designed considering the psychological impact of environmental stimuli. A Bayesian network can compensate for the uncertain and incomplete characteristics of the sensor data by the probabilistic consideration of the evidence for reasoning. Also, modularizing the Bayesian network has enabled flexible response and efficient reasoning of environmental stimulus fluctuations within the space. To verify the performance of the system, we predict public emotion based on the brightness, volume, temperature, humidity, color temperature, sound, smell, and group emotion data collected in a kindergarten. Experimental results show that the accuracy of the proposed method is 85% greater than that of other classification methods. Using quantitative and qualitative analyses, we explore the possibilities and limitations of probabilistic methodology for predicting group emotion.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.3
• /
• pp.155-160
• /
• 2017

Recently, Deep learning has been used successfully to solve many recognition problems. It has many advantages over existing machine learning methods that extract feature points through hand-crafting. Deep neural networks for human activity recognition split video data into frame images, and then classify activities by analysing the connectivity of frame images according to the time. But it is difficult to apply to actual problems which has small-scale activity classes. Because this situations has a problem of overfitting and insufficient training data. In this paper, we defined 5 type of small-scale human activities, and classified them. We construct video database using 700 video clips, and obtained a classifying accuracy of 74.00%.

• Journal of Korean Society for Geospatial Information Science
• /
• v.13 no.1 s.31
• /
• pp.63-69
• /
• 2005

Interferometric Synthetic Aperture Radar(InSAR) is a rapidly evolving technique. Spectacular results obtained in various fields such as the monitoring of earthquakes, volcanoes, land subsidence and glacier dynamics, as well as in the construction of Digital Elevation Models(DEMs) of the Earth's surface and the classification of different land types have demonstrated its strength. As InSAR is a remote sensing technique, it has various sources of errors due to the satellite positions and attitude, atmosphere, and others. Therefore, it is important to validate its accuracy, especially for the DEM derived from Satellite SAR images. In this study, Real Time Kinematic(RTK) GPS and Kinematic GPS positioning were chosen as tools for the validation of InSAR derived DEM. The results showed that Kinematic GPS positioning had greater coverage of test area in terms of the number of measurements than RTK GPS. But tracking the satellites near and/or under trees md transmitting data between reference and rover receivers are still pending tasks in GPS techniques.

• The Journal of the Korea Contents Association
• /
• v.10 no.4
• /
• pp.84-90
• /
• 2010

DBMS is used for a range of applications from data warehousing through on-line transaction processing. As a result of this demand, DBMS has continued to grow in terms of its size. This growth invokes the most important issue of manually tuning the performance of DBMS. The DBMS tuning should be adaptive to the type of the workload put upon it. But, identifying workloads in mixed database applications might be quite difficult. Therefore, a method is necessary for identifying workloads in the mixed database environment. In this paper, we propose a SVM workload classifier to automatically identify a DBMS workload. Database workloads are collected in TPC-C and TPC-W benchmark while changing the resource parameters. Parameters for SVM workload classifier, C and kernel parameter, were chosen experimentally. The experiments revealed that the accuracy of the proposed SVM workload classifier is about 9% higher than that of Decision tree, Naive Bayes, Multilayer perceptron and K-NN classifier.

• Journal of Biosystems Engineering
• /
• v.36 no.1
• /
• pp.40-47
• /
• 2011

Image analysis algorithm for the quality evaluation of ginseng seedling was investigated. The images of ginseng seedling were acquired with a color CCD camera and processed with the image analysis methods, such as binary conversion, labeling, and thinning. The processed images were used to calculate the length and weight of ginseng seedlings. The length and weight of the samples could be predicted with standard errors of 0.343 mm, and 0.0214 g respectively, $R^2$ values of 0.8738 and 0.9835 respectively. For the evaluation of the three quality grades of Gab, Eul, and abnormal ginseng seedlings, features from the processed images were extracted. The features combined with the ratio of the lengths and areas of the ginseng seedlings efficiently differentiate the abnormal shapes from the normal ones of the samples. The grade levels were evaluated with an efficient pattern recognition method of support vector machine analysis. The quality grade of ginseng seedling could be evaluated with an accuracy of 95% and 97% for training and validation, respectively. The result indicates that color image analysis with support vector machine algorithm has good potential to be used for the development of an automatic sorting system for ginseng seedling.

• Journal of Korean Society of Rural Planning
• /
• v.15 no.4
• /
• pp.213-220
• /
• 2009

Farmland spatial data are needed as a basic information in conducting rational use of farmlands in regional scale. This study develops a method that can be used to make up such farmland spatial data in a simple way and to develop a technique to manage them in a unitary way, and examines the effectiveness of the technique by applying it to the case area. A method that Web-Service Raster Image and Digital Cadastal Map can be utilized as a base map was devised. It was designed applying the vector system, in which one lot of farmland is area unit. Raster image and field survey data were combined to increase the accuracy of data. The lot boundaries of the existing boundary map were adjusted to the shapes of actual farmlands using GIS edition function. A proper farmland use classification system to the area characteristics was established and data obtained from the field survey were coded. Usually it is very difficult to identify the size of one lot of actual farmland in the existing space data, based on the results of the case study, the result map showed actual topography very realistically. Also the frequently occurring lot divisions and the serious topographical modifications by natural disasters frequently have made it impossible to survey farmlands on the catastral map in the field. But the final map had a great usefulness in that it may solve such problems by expressing the filed survey results graphically.

• Ecology and Resilient Infrastructure
• /
• v.5 no.2
• /
• pp.59-71
• /
• 2018

Lake Enriquillo, the largest lake in the Dominican Republic, recently has undergone unusual water area changes since 2001 thus it has been affected seriously by local community's livelihood. Earthquakes and seismic activities of Hispaniola plate tectonic coupled with human activities and climate change are addressed as factors causing the increasing. Thus, a thorough study on relationship between lake area changing, and those factors is needed urgently. To do so, this study applied MESMA on MODIS data to extract water area of Lake Enriquillo during 2001 and 2012 bimonthly, with six issues 12-year. MODIS provides high temporal resolution, and its coarse spatial resolution is compensated by MESMA fraction map. The increase in water area was $142.2km^2$, and the maximum lake area was $338.0km^2$ (in 2012). Water areas extracted by two Landsat scenes at two different times with three image classification approaches (ISODATA, MNDWI, and TCW) were used to assess accuracy of MODIS and MESMA results; it indicated that MESMA water areas are same as ISODATA's, less than 0.4%, while the highest difference is between MESMA and TCW, 2.4%. A number of previously formulated hypotheses of lake area change were investigated based on the outcomes of the present study, though none of them could fully explain the changes.

• Progress in Superconductivity
• /
• v.8 no.1
• /
• pp.46-53
• /
• 2006

Magnetocardiography(MCG) has been proposed as a novel and non-invasive diagnostic tool for the detection of cardiac electrical abnormality associated with myocardial ischemia. In our previous study, we have proposed a new classification method of MCG parameters, based on the different populations of the parameters between coronary artery disease(CAD) patients, symptomatic patients and healthy volunteers. We used four parameters, representing the directional changes of the electrical activity in the period of an R-ST-T interval. In patients with chest pain and without ST-segment elevation, who were selected consecutively from all patients admitted to the hospital in 2004, the patients with CAD could be classified with a higher sensitivity than conventional methods, showing that the proposed method can be useful for the diagnosis of CAD with MCG. In this study, we examined the validity of the algorithm with the prior probability distribution in diagnosis of new patients admitted to the hospital in 2005. In the results, presence of CAD could be found with sensitivity and specificity of 81.3% and 71.4%, respectively, in patients with chest pain and non-diagnostic ECG findings.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2011.04a
• /
• pp.618-626
• /
• 2011

Recent development of related technologies and efficient utilization of the entire country for the purpose of railway construction, and plans are being accelerated. the railway noise has been improved by increasing the high speed railway station, and accelerating the existing trains. Nord2000 which is an overseas noise prediction equation could not be applied directly to the domestic railway vehicles. So the specific vehicles in the Nordic countries which is a similar specification to domestic trains should be selected. Nord2000's accuracy was compared to Schall03, CRN's. Prediction of Ground impedance and Roughness class were carried out at different. In this paper, the result of selected vehicles for Nord2000 was as follows. S-1aX2 was for express trains, N-$^*2c$-3b was for Mugunghwa, S-Pass/wood was for Saemaul, N-4a was for freight trains, N-3a was for subway, the calculation time for Nord2000 took longer than others, in addition, Ground absorption was indispensable to calculate a noise map for Nord2000. As a result, CRN's prediction noise levels at Wonju-si was closest to the measurements. However, the predicted noise levels of Nord2000 was the most accurate.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.45 no.4
• /
• pp.78-88
• /
• 2003

The land use changes from non-urban areas to urban areas lead to the increased impervious areas, consequently increased direct runoff and higher peak runoff. Urban areas have also been recognized as significant sources of Nonpoint Source (NPS) pollution, while agricultural activities have been known as the primary sources of NPS pollution. Many features of the L-THIA/NPS GIS, L-THIA/NPS WWW system have been enhanced to provide easy-to-use system. The L-THIA model was applied to the Little Eagle Creek (LEC) watershed in Indiana to evaluate the accuracy of the model. The L-THIA/NPS GIS estimated yearly direct runoff values match the direct runoff separated from U.S. Geological Survey stream flow data reasonably. The $R^2$ and Nash-Sutcliffe values are 0.67 and 0.60, respectively. The L-THIA estimated runoff volume and total nitrogen loading for each land use classification in the LEC watershed were computed. The estimated runoff volume and total nitrogen loading in the LEC watershed increased by 180% and 270% for the 20 years. Urbanized areas -"Commercial", "High Density Residential", and "Low Density Residential"- of the LEC watershed made up around 68% of the 1991 total land areas, however contributed more than 92% of average annual runoff and 86% of total nitrogen loading. Therefore, it is essential to consider the impacts of land use change on hydrology and water quality in land use planning of urbanizing watershed.nning of urbanizing watershed.