• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.4
• /
• pp.42-53
• /
• 2012

In pattern recognition and machine learning society, classification has been a classical problem and the most widely researched area. Adaptive boosting also known as Adaboost has been successfully applied to binary classification problems. It is a kind of boosting algorithm capable of constructing a strong classifier through a weighted combination of weak classifiers. On the other hand, the PCA and LDA algorithms are the most popular linear feature extraction methods used mainly for dimensionality reduction. In this paper, the combination of Adaboost and feature extraction methods is proposed for efficient classification of two class data. Conventionally, in classification problems, the roles of feature extraction and classification have been distinct, i.e., a feature extraction method and a classifier are applied sequentially to classify input variable into several categories. In this paper, these two steps are combined into one resulting in a good classification performance. More specifically, each projection vector is treated as a weak classifier in Adaboost algorithm to constitute a strong classifier for binary classification problems. The proposed algorithm is applied to UCI dataset and FRGC dataset and showed better recognition rates than sequential application of feature extraction and classification methods.

• Journal of Soil and Groundwater Environment
• /
• v.18 no.1
• /
• pp.6-15
• /
• 2013

The influence of processing fluids and electrode spacing on the electrokinetic process was evaluated to remediate As-, Cu-, Pb-contaminated soil. Single and mixture of sodium citrate, EDTA and NaOH was used to investigate the metal extraction. EDTA for washing reagent showed the highest removal efficiency. Based on the extraction result, the electrode spacing (20, 40, 60 cm) on the electrokinetic process was investigated to remove the multi-metals from soil. The highest removal was observed at the experiment with 60 cm of electrode spacing, however, the correlation between electrode spacing and removal of metals was not clear. The electrode spacing influenced the amount of accumulated electro-osmotic flow. BCR sequential extraction showed that electrokinetic process removed the fractionation of metals bound to Fe-Mn oxyhydroxide.

• Analytical Science and Technology
• /
• v.10 no.5
• /
• pp.307-314
• /
• 1997

Inductively coupled plasma atomic emission spectrometry(ICP/AES) was used for the determination of uranium and thorium in geological materials. Samples were predecomposed by mixed acid digestion technique. The separation of the uranium and thorium was achieved by systematic solvent extraction with TTA(thenoyltrifluoroacetone) and TOA (tri-n-octylamine) and back extraction into HCl. The results for standard rock sample, NIST SRM 278, showed a good agreement with those certified from NIST as well as found values by other non-destructive techniques. Additional purification for extracted portions was carried out by anion exchange chromatography for measurement of several natural radioisotopes of uranium and thorium by alpha spectrometry.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.37 no.6
• /
• pp.38-47
• /
• 2000

In pattern classification, the Bhattacharyya distance has been used as a class separability measure. Furthemore, it is recently reported that the Bhattacharyya distance can be used to estimate error of Gaussian ML classifier within 1-2% margin. In this paper, we propose a feature extraction method utilizing the Bhattacharyya distance. In the proposed method, we first predict the classification error with the error estimation equation based on the Bhauacharyya distance. Then we find the feature vector that minimizes the classification error using two search algorithms: sequential search and global search. Experimental reslts show that the proposed method compares favorably with conventional feature extraction methods. In addition, it is possible to determine how man, feature vectors arc needed for achieving the same classification accuracy as in the original space.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.17 no.7
• /
• pp.913-918
• /
• 2007

Human motion analysis is an important research subject in human-robot interaction (HRI). However, before analyzing the human motion, silhouette of human body should be extracted from sequential images obtained by CCD camera. The intelligent robot system requires more robust silhouette extraction method because it has internal vibration and low resolution. In this paper, we discuss the hybrid silhouette extraction method for detecting and tracking the human motion. The proposed method is to combine and optimize the temporal and spatial gradient information. Also, we propose some compensation methods so as not to miss silhouette information due to poor images. Finally, we have shown the effectiveness and feasibility of the proposed method through some experiments.

• Journal of Environmental Science International
• /
• v.27 no.12
• /
• pp.1205-1214
• /
• 2018

During the past few decades, significant increase in the consumption of coffee has led to rapid increase in the production of coffee waste in South Korea. Spent coffee waste is often treated as a general waste and is directly disposed without the necessary treatment. Spent Coffee Grounds (SCGs) can release several organic contaminants, including caffeine. In this study, leaching tests were conducted for SCGs and oxidative degradation of caffeine were also conducted. The tested SCGs contained approximately 4.4 mg caffeine per gram of coffee waste. Results from the leaching tests show that approximately 90% of the caffeine can be extracted at each step during sequential extraction. Advanced oxidation methods for the degradation of caffeine, such as $UV/H_2O_2$, photo-Fenton reaction, and $UV/O_3$, were tested. UV radiation has a limited effect on the degradation of caffeine. In particular, UV-A and UV-B radiations present in sunlight cause marginal degradation, thereby indicating that natural degradation of caffeine is minimal. However, $O_3$ can cause rapid degradation of caffeine, and the values of pseudo-first order rate constants were found to be ranging from $0.817min^{-1}$ to $1.506min^{-1}$ when the ozone generation rate was $37.1g/m^3$. Additionally, the degradation rate of caffeine is dependent on the wavelength of irradiation.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.27 no.4B
• /
• pp.353-364
• /
• 2002

In this paper, a new onto-digital stereo object-tracking system using hierarchical digital algorithms and optical BPEJTC is proposed. This proposed system can adaptively track a moving target by controlling the convergence of stereo camera. firstly, the target is detected through the background matching of the sequential input images by using optical BPEJTC and then the target area is segmented by using the target projection mask which is composed by hierarchical digital processing of image subtraction, logical operation and morphological filtering. Secondly, the location's coordinate of the moving target object for each of the sequential input frames can be extracted through carrying out optical BPEJTC between the reference image of the target region mask and the stereo input image. Finally, the convergence and pan/tilt of stereo camera can be sequentially controlled by using these target coordinate values and the target can be kept in tracking. Also, a possibility of real-time implementation of the adaptive stereo object tracking system is suggested through optically implementing the proposed target extraction and convergence control algorithms.

• Journal of Soil and Groundwater Environment
• /
• v.8 no.3
• /
• pp.45-55
• /
• 2003

This study investigates the fractional composition and the leaching characteristics of heavy metals in polluted soils due to mining activities. The fractionated composition of heavy metals is classified into five fractions; adsorbed, carbonate, reducible, organic and residual fraction. The status of humic substances in mine wastes of most sites are polyhumic except tailing from Sangdong mine. According to the sequential extraction procedures (SEPs), leaching probabilities of Cd in coal wastes and tailing are relatively low due to high percentage of residual fraction. 46.4% of Ni in tailings from Sangdong mine is probably leached under oxidized environment, and 39.4% of Cu in these tailings is readily extracted under strongly oxidized environment by organic fraction. According to leaching condition of pH 3.0 and pH 5.6, the amount of heavy metals leached out of coal wastes and tailing increases to 1/2 hours. At pH 3.0 and pH 5.6, concentration of Ni in tailing increases up three times of the initial value. Heavy metals released from coal wastes and tailing were not influenced significantly by leaching time.

• Journal of Environmental Science International
• /
• v.17 no.2
• /
• pp.185-193
• /
• 2008

This study has been carried out to examine the feasibility of soil washing process for reducing arsenic contamination level of soil around $Dalch\hat{e}n$ Mine. The results of physicochemical tests of the target soil showed that pH was weak alkalic ($pH{\simeq}7.8$), soil texture was coarse sand, and organic contents (5.7%) and CEC (Cation exchange capacity; 21.5 meq/100 g) were similar with those of soils generally found in Korea. Contamination levels of arsenic were found to over 201 mg/kg which exceed the Korea standard levels of countermeasure and concern. To investigate chemical partitioning of heavy metals, sequential extraction procedures were adopted and it was found that arsenic was predominantly associated with the residual fraction among five fractional forms as much as over 85%, which is demonstrating that only less than 15% of all might be vulnerable to a selected washing agents. Among 6 kinds of washing agents applied on the screening for arsenic-contaminated soil, HCl and $H_3PO_4$ solution were selected as promising washing agents. In comparison with HCl and $H_3PO_4$ solutions for arsenic washing by kinetic experiment in the change of pH, soil-solution ratio, temperature, and washing solution concentration, $H_3PO_4$ solution was determined to best one of agents tested, which showed faster washing rate than HCl to accomplish regulatory goal.

• Journal of Soil and Groundwater Environment
• /
• v.19 no.5
• /
• pp.1-8
• /
• 2014

The metals contamination of farmland soil nearby abandoned metal mine was serious problem in Korea. Stabilization of contaminated soil was reported using various stabilizers. Application of limestone and steel refining slag was reported as effective stabilizers in the stabilization of metals. The batch studies confirmed that the mixture of limestone and steel refining slag was suitable for stabilization of metals in contaminated soil. The limestone and steel refining slag mixture (2 : 1 and 3 : 2) were used in column studies and it was confirmed that the stabilizers effectively stabilized heavy metals in contaminated soil. The pH of the soil was increased with the addition of stabilizers. Total leached concentration of metals from the column study was reduced 44, 17, and 93% in comparison to the control at arsenic, cadmium and copper, respectively. The sequential extraction studies showed that the exchangeable fraction was changed into carbonate bound fraction (Cd and Cu) and Fe-Mn oxide bound fraction (As). Based on the results we confirmed that 2:1 ratio of limestone and steel refining slag effectively stabilizes the heavy metals. The mixed treatment of lime stone with steel refining slag would be an effective and feasible method for controlling metals leaching in contaminated soil.