• The Journal of Engineering Geology
• /
• v.16 no.3 s.49
• /
• pp.227-233
• /
• 2006

Bedrock is inhomogeneous for its genetically diverse origins and geological conditions when it forms, and especially, conglomerates and core-stones are one of these typical composite geo-materials composed of weak matrixes and strong pebbles. Mechanical properties of these composite bedrocks, like a conglomerate, generally vary depending on the mechanical properties and distributions of pebbles and the matrix. Therefore, regarding the consequence of understanding mechanical property of bedrocks in the designing slopes, tunnels, and other engineering facilities, empirical rock classification methods generally applied in the mechanical property modeling may not be suitable and rather, we may need some other classification methods, or tests more specific for these inhomogeneous composite bedrocks. This study includes a series of analyses to see elastic behaviors and modulus of composite geo-materials using homogenization theory. Forty nine case models were made for the elastic analysis with considering 5 factors such as gravel content, gravel size, strength of matrix, sorting and dip angle. The results analyzed are applicable to calculate elastic modulus of composite geo-materials as conglomerates and core-stones.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.18 no.6
• /
• pp.1275-1282
• /
• 2014

Too much information exists in ubiquitous environment, and therefore it is not easy to obtain the appropriately classified information from the available data set. Decision tree algorithm is useful in the field of data mining or machine learning system, as it is fast and deduces good result on the problem of classification. Sometimes, however, a decision tree may have leaf nodes which consist of only a few or noise data. The decisions made by those weak leaves will not be effective and therefore should be excluded in the decision process. This paper proposes a method using a classifier, UChoo, for solving a classification problem, and suggests an effective method of decision process involving only the important leaves and thereby excluding the noisy leaves. The experiment shows that this method is effective and reduces the erroneous decisions and can be applied when only important decisions should be made.

• Journal of Korean Tunnelling and Underground Space Association
• /
• v.20 no.4
• /
• pp.701-715
• /
• 2018

A reliability based design approach of the tunnel reinforcement with umbrella arch method was considered to better represent the uncertainties of the weak rock properties around the tunnel. For this, a machine learning approach called an Adaptive Support Vector Machine (ASVM) together with the limit equilibrium method were introduced to minimize the iteration numbers during the classification training of the tunnel stability. The proposed method was compared with the results of typical Monte Carlo simulations. It was concluded that the ASVM was very efficient and accurate to calculate the probability of failure having auxiliary umbrella arches and uncertain material properties of the tunnel. Future work will be concentrated on the refinement of the fast adaptation of the SVM classification so that the minimum number of numerical analyses can be used where the limit solution is not available.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.13 no.6
• /
• pp.1333-1342
• /
• 2018

Until now, Electroencephalography(: EEG) has been the most important and convenient method for the diagnosis and treatment of epilepsy. However, it is difficult to identify the wave characteristics of an epileptic EEG signals because it is very weak, non-stationary and has strong background noise. In this paper, we analyse the effect of dimensionality reduction methods on Epileptic EEG feature selection and classification. Three dimensionality reduction methods: Pincipal Component Analysis(: PCA), Kernel Principal Component Analysis(: KPCA) and Linear Discriminant Analysis(: LDA） were investigated. The performance of each method was evaluated by using Support Vector Machine SVM, Logistic Regression(: LR), K-Nearestneighbor(: K-NN), Decision Tree(: DR) and Random Forest(: RF). From the experimental result, PCA recorded 75% of highest accuracy in SVM, LR and K-NN. KPCA recorded 85% of best performance in SVM and K-KNN while LDA achieved 100% accuracy in K-NN. Thus, LDA dimensionality reduction is found to provide the best classification result for epileptic EEG signal.

• Journal of the Korean Association of Oral and Maxillofacial Surgeons
• /
• v.47 no.2
• /
• pp.99-111
• /
• 2021

Objectives: It is unclear whether the extent of intraoral mucosa defects in patients with medication-related osteonecrosis of the jaw indicates disease severity. Therefore, this study investigated whether mucosal lesions correlate with the true extent of osseous defects in stage I patients. Materials and Methods: Retrospectively, all patients with stage I medication-related osteonecrosis of the jaw who underwent surgical treatment between April 2018 and April 2019 were enrolled. Preoperatively, the extent of their mucosal lesions was measured in clinical evaluations, and patients were assigned to either the visible or the probeable bone group. Intraoperatively, the extent of necrosis was measured manually and with fluorescence. Results: Fifty-five patients (36 female, 19 male) with 86 lesions (46 visible bone, 40 probeable bone) were enrolled. Intraoperatively, the necrotic lesions were significantly larger (P<0.001) than the preoperative mucosal lesions in both groups. A significant (P<0.05) but very weak (R2<0.2) relationship was noted between the extent of the mucosal lesions and the necrotic bone area. Conclusion: Preoperative mucosal defects (visible or probeable) in patients with medication-related osteonecrosis of the jaw do not indicate the extent of bone necrosis or disease severity.

• Atmosphere
• /
• v.32 no.2
• /
• pp.119-133
• /
• 2022

From 2015 to 2021, high-concentration fine dust episodes with a daily average PM_2.5 concentration of 50 ㎍ m^-3 or higher were selected and classified into 3 types [long range transport (LRT), mixed (MIX) and Local emission and stagnant (LES)] using synoptic chart and backward trajectory analysis. And relationships between the fine particle data (PM_2.5 and PM₁₀ concentration and PM_2.5/PM₁₀ ratio) and meteorological data (PBLH, Ta, WS, U-wind, and Rainfall) were analyzed using hourly observation for the classification episodes on the Korean Peninsula and the Seoul metropolitan area (SMA). In LRT, relatively large particles such as dust are usually included, and in LES, fine particle is abundant. In the Korean peninsula, the rainfall was relatively increased centered on the middle and western coasts in MIX and LES. In the SMA, wind speed was rather strong in LRT and weak in LES. In LRT, rainfall was centered in Seoul, and in MIX and LES, rainfall appeared around Seoul. However, when the dust cases were excluded, the difference between the LRT and other types of air quality was decreased, but the meteorological variables (Ta, RH, Pa, PBLH, etc.) were further strengthened. In the case of the Korean Peninsula, it is difficult to find a clear relationship because regional influences (topographical elevation, cities and coasts, etc.) are complexly included in a rather wide area. In the SMA, it is analyzed that the effects of urbanization such as the urban heat island centered on Seoul coincide with the sea and land winds, resulting in a combination of high concentrations and meteorological phenomena.

• The Korean Journal of Community Living Science
• /
• v.22 no.3
• /
• pp.351-364
• /
• 2011

Hot and spicy flavor grading in hot pepper powder for gochujang in various cultivars was studied using sensory and physicochemical characteristics. Chungyang, which had the highest capsaicin content had very low redness a value of 17.49 representing stronger red color does not relate to the stronger hot and spicy flavor. Sensory results showed that chungyang had significantly the highest value of hot and spicy aroma and flavor of 5.73 and 7.87, respectively(p<0.05). Although wurigun had the second highest capsaicin contents, it had relatively low hot and spicy aroma value as 3.87, some sweet flavor, and relatively low stingingness in the mouth value of 4.67, thus, comparatively weak hot and spicy flavor of 4.87 suggesting the difficulties in grading the hot and spicy flavor only by the capsaicin contents. Capsaicin content was highly positively correlated with the hot and spicy flavor, aftertaste and stinging flavor, and negatively correlated with the sweet flavor. In the principal component analysis, samples of chunyang, balita, and gumbit groups with greater hot and spicy aroma and flavor, were loaded in the first principal component. Classifying hot and spicy flavor of hot pepper powder for gochujang in various cultivars are suggested as 'very weak', 'weak', 'intermediate', 'strong', and 'very strong' with capsaicin contents under 40.00 mg/dL, 40~100 mg/dL, 100~150 mg/dL, 150~500 mg/dL, and those higher than 500 mg/dL, respectively. Since too many sample groups were located in the specific stages in the five stage grading, the nine staged classification is also suggested.

• Journal of Environmental Science International
• /
• v.17 no.6
• /
• pp.679-687
• /
• 2008

In this study, we implemented landslide distribution of Jeju Island using ANN and GIS, respectively. To do this, we first get the counter line from 1:2,5000 digital map and use this counter line to make the DEM. for the evaluate the land slide susceptibility. Next, we abstracted slop map and aspect map from the DEM and get the land use map using ISODATA classification method from Landsat 7 images. In the computation processes of landslide analysis, we make the class to the soil map, tree diameter map, Isohyet map, geological map and so on. Finally, we applied the ANN method to the landslide one and calculated its weighted values. GIS results can be calculated by using Acrview program and produced Jeju landslide susceptibility map by usign Weighted Overlay method. Based on our results, we found the relatively weak points of landslide ware concentrated to the top of Halla mountains.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.4
• /
• pp.1760-1778
• /
• 2018

For image segmentation with intensity inhomogeneity, many region-based level set methods have been proposed. Some of them however can't get the relatively ideal segmentation results under the severe intensity inhomogeneity and weak edges, and without use of the image gradient information. To improve that, we propose a new level set method combined with local direction gradient in this paper. Firstly, based on two assumptions on intensity inhomogeneity to images, the relationships between segmentation objects and image gradients to local minimum and maximum around a pixel are presented, from which a new pixel classification method based on weight of Euclidian distance is introduced. Secondly, to implement the model, variational level set method combined with image spatial neighborhood information is used, which enhances the anti-noise capacity of the proposed gradient information based model. Thirdly, a new diffusion process with an edge indicator function is incorporated into the level set function to classify the pixels in homogeneous regions of the same segmentation object, and also to make the proposed method more insensitive to initial contours and stable numerical implementation. To verify our proposed method, different testing images including synthetic images, magnetic resonance imaging (MRI) and real-world images are introduced. The image segmentation results demonstrate that our method can deal with the relatively severe intensity inhomogeneity and obtain the comparatively ideal segmentation results efficiently.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.6
• /
• pp.602-608
• /
• 2020

PRAIRIE(Propeller Air Induced Emission) system is a kind of underwater radiated noise suppression systems to reduce the probability of the identification or classification of our warship's acoustic signature by an enemy ship. It is effective in case of strong cavitation events. This is because air bubbles emitted from the PRAIRIE system mitigate drastic collapses of the cavity bubbles that can generate an intense shock wave. However, when the PRAIRIE system is operated in a non or weak cavitation condition, it might increase the total level of underwater radiated noise and induce the acoustic signatures. Therefore, this paper presents the trial results on ventilation control of PRAIRIE to find a more efficient operation depend on the cavitation condition. Then, we show a variation of the amplitude modulation characteristics according to ventilation control.