• Journal of Korea Multimedia Society
• /
• v.8 no.10
• /
• pp.1337-1346
• /
• 2005

In this paper, we describe an algorithm which can automatically recognize human gesture for Human-Robot interaction. In early works, many systems for recognizing human gestures work under many restricted conditions. To eliminate these restrictions, we have proposed the method that can represent 3D and 2D gesture information simultaneously, APM. This method is less sensitive to noise or appearance characteristic. First, the feature vectors are extracted using APM. The next step is constructing a gesture space by analyzing the statistical information of training images with PCA. And then, input images are compared to the model and individually symbolized to one portion of the model space. In the last step, the symbolized images are recognized with HMM as one of model gestures. The experimental results indicate that the proposed algorithm is efficient on gesture recognition, and it is very convenient to apply to humanoid robot or intelligent interface systems.

• Journal of Sensor Science and Technology
• /
• v.25 no.6
• /
• pp.423-430
• /
• 2016

This study used a single metal oxide semiconductor (MOS) sensor to classify the major odorous gases hydrogen sulfide ($H_2S$), ammonia ($NH_3$) and toluene ($C_6H_5CH_3$). In order to classify these odorous substances, the voltage on the MOS sensor heater was gradually reduced in 0.5 V steps 5.0 V to examine the changes to the response by the cooling effect on the sensor as the voltage decreased. The hydrogen sulfide gas showed the highest sensitivity compared to odorless air under approximately 2.5 V and the ammonia and toluene gases showed the highest sensitivity under approximately 5.0 V. In other words, the hydrogen sulfide gas reacted better in the low temperature range of the MOS sensor, and the ammonia and toluene gases reacted better in the high-temperature range. In order to analyze the response characteristics of the MOS sensor by temperature in a pattern, a two-dimensional (2D) x-y pattern analysis was introduced to clearly classify the hydrogen sulfide, ammonia, and toluene gases. The hydrogen sulfide gas was identified by a straight line with a slope of 1.73, whereas the ammonia gas had a slope of 0.05 and the toluene gas had a slope of 0.52. Therefore, the 2D x-y pattern analysis is suggested as a new way to classify these odorous substances.

• Journal of Preventive Medicine and Public Health
• /
• v.12 no.1
• /
• pp.43-48
• /
• 1979

For the purpose of further health control, D-penicillamine was orally administered to 8 persons who were employed in lead industry and suspected lead intoxication routine industrial health examination. The does of D-penicillamine was 600 mg per day and was administered orally in every other 5 days, For the laboratory analysis 24 hours urine and 10 gm of whole blood were collected every day. The results were as follows; 1. It was found that mean urinary lead excretion per day was 446.5 g/l and 394.98 g/l, respectively during the first 5-day and the second 5-day administration with D-penicillamine. 2. Mean lead excretion per day was $130.56{\pm}66.42g/l$ after first 5-day administration and $159.28{\pm}104.44g/l$ after second 5-day administration with D-penicillamine. 3. The level of urinary lead excretion after administration increased 3 to 4 times than that before administration with D-peniciilamine. 4. Blood and urinary lead level investigated after 6 months were $44.4{\pm}10.2g/100g\;and\;72.7{\pm}29.7\;g/l$ for the eight persons.

• Journal of Soil and Groundwater Environment
• /
• v.12 no.2
• /
• pp.20-26
• /
• 2007

The microbial community properties of groundwater samples contaminated with landfill leachates were examined using Ecoplate including 31 sole carbon sources. The samples were KSG1-12 (leachate), KSG1-16 (treated leachate), KSG1-07 (contaminated groundwater), KSG1-08 (contaminated groundwater), and KSG1-13 (uncontaminated groundwater). Among the carbon sources used as substrates, 2-hydroxy benzoic acid, D,L-$\alpha$-glycerol phosphate, and D-malic acid were not utilized in any sample, while D-xylose, D-galacturonic acid, L-aspargine, tween 80, and L-serine were utilized in all 5 samples. The rest of substrates showed very different patterns among the samples. Average well color development (AWCD) analysis demonstrated that the potential activity on 31 substrates was in the order of KSG1-16 > KSG1-12 > KSG1-07 > KSG-08 > KSG1-13, which generally agrees with the degree of pollution, except KSG1-16. Principal component analysis (PCA) on similarity between samples showed two groups (KSG1-12, -07 and -08 vs KSG1-16 and -13), coinciding with contaminated and uncontaminated groups. Shannon index showed that the microbial diversities were similar among the samples.

• Journal of Dairy Science and Biotechnology
• /
• v.21 no.2
• /
• pp.97-104
• /
• 2003

It is extremely important to destroy the antigenicity of milk proteins for dietetic treatment of infants with milk allergy. Enzymatic digestion of milk protein is not only effective for destroying antigenicity, but it also is less liable to alter the nutritive value. Bovine casein was hydrolyzed with eight different commercial proteases derived from bacterias or fungi, either individually or in combination to eliminate protein allergenicity. The average molecular weight of casein hyrdolysates determined by size exclusion chromatography is about 550${\sim}$2,300 dalton range. Antigenicity of the casein hyrdolysates was not detected by heterologous passive cutaneous anaphylaxis in guinea pig-rabbit antiserum system. The inhibition test on the enzyme-linked immunosorbent assay(ELISA) showed that the antigenicity of casein hydrolysates is lowed up to 1/8,000 than that of intact bovine casein. As the enzyme reaction was carried out by the combination of bacterial and fungal protease, casein hydrolysates showed much lower bitterness and antigenicity. It suggests that these hydrolysates will be applied to many kinds of foods including the development of hypo-allergenic infant formula.

• Smart Structures and Systems
• /
• v.20 no.4
• /
• pp.427-440
• /
• 2017

One of the suitable structural damage detection methods using vibrational characteristics are damage-index-based methods. In this study, a damage index for identifying damages in plate structures using frequency response function (FRF) data has been provided. One of the significant challenges of identifying the damages in plate structures is high number of degrees of freedom resulting in decreased damage identifying accuracy. On the other hand, FRF data are of high volume and this dramatically decreases the computing speed and increases the memory necessary to store the data, which makes the use of this method difficult. In this study, FRF data are compressed using two-dimensional principal component analysis (2D-PCA), and then converted into damage index vectors. The damage indices, each of which represents a specific condition of intact or damaged structures are stored in a database. After computing damage index of structure with unknown damage and using algorithm of lookup tables, the structural damage including the severity and location of the damage will be identified. In this study, damage detection accuracy using the proposed damage index in square-shaped structural plates with dimensions of 3, 7 and 10 meters and with boundary conditions of four simply supported edges (4S), three clamped edges (3C), and four clamped edges (4C) under various single and multiple-element damage scenarios have been studied. Furthermore, in order to model uncertainties of measurement, insensitivity of this method to noises in the data measured by applying values of 5, 10, 15 and 20 percent of normal Gaussian noise to FRF values is discussed.

• Journal of Korea Multimedia Society
• /
• v.12 no.11
• /
• pp.1692-1700
• /
• 2009

This paper proposes the direction distribution of surface normal vectors as a feature descriptor of three-dimensional models. Proposed the feature descriptor handles rotation invariance using a principal component analysis(PCA) method, and performs mesh simplification to make it robust and nonsensitive against noise addition. Our method picks samples for the distribution of normal vectors to be proportional to the area of each polygon, applies weight to the normal vectors, and applies interpolation to enhance discrimination so that the information on the surface with less area may be less reflected on composing a feature descriptor. This research measures similarity between models with a L1-norm in the probability density histogram where the distances of feature descriptors are normalized. Experimental results have shown that the proposed method has improved the retrieval performance described in an average normalized modified retrieval rank(ANMRR) by about 17.2% and the retrieval performance described in a quantitative discrimination scale by 9.6%~17.5% as compared to the existing method.

• The KIPS Transactions:PartD
• /
• v.10D no.2
• /
• pp.277-282
• /
• 2003

The knowledge discovery from web has been studied in many researches. There are some difficulties using web log for training data on efficient information predictive models. In this paper, we studied on the method to eliminate sparseness from web log data and to perform web user clustering. Using missing value imputation by Bayesian inference of MCMC, the sparseness of web data is removed. And web user clustering is performed using self organizing maps based on 3-D plot by principal component. Finally, using KDD Cup data, our experimental results were shown the problem solving process and the performance evaluation.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.21 no.2
• /
• pp.137-143
• /
• 2022

Composite materials, being light-weight and of high mechanical strength, are increasingly used in various industries such as the aerospace, automobile, sporting-goods manufacturing, and ship-building industries. Recently, manufacturing of composite materials using 3D printers has increased. 3D-printed composite materials are made in free-form and adapted for end-use by adjusting the fiber content and orientation. However, research on the machining of 3D printed composite materials is limited. The aim of this study is to develop a machine learning method to select machining conditions for machining of 3D-printed composite materials. The composite material was composed of Onyx and carbon fibers and stacked sequentially. The experiments were performed using the following machining conditions: spindle speed, feed rate, depth of cut, and machining direction. Cutting forces of the different machining conditions were measured by milling the composite materials. PCA, a method of machine learning, was developed to select the machining conditions and will be used in subsequent experiments under various machining conditions.

• The Korean Journal of Applied Statistics
• /
• v.13 no.2
• /
• pp.383-392
• /
• 2000

Since late 1970, methods of influence or sensitivity analysis for detecting influential observations have been studied not only in regression and related methods but also in various multivariate methods. If results of multivariate analyses sometimes depend heavily on a small number of observations, we should be very careful to draw a conclusion. Similar phenomena may also occur in the case of incomplete data. In this research we try to study such influential observations in multivariate statistical analysis of incomplete data. Case of principal component analysis is studied with a numerical example.