• Journal of KIISE:Software and Applications
• /
• v.30 no.3_4
• /
• pp.251-258
• /
• 2003

A support vector machine (SVM) is supposed to provide a good generalization performance, but the actual performance of a actually implemented SVM is often far from the theoretically expected level. This is largely because the implementation is based on an approximated algorithm, due to the high complexity of time and space. To improve this limitation, we propose ensemble of SVMs by using Bagging (bootstrap aggregating) and Boosting. By a Bagging stage each individual SVM is trained independently using randomly chosen training samples via a bootstrap technique. By a Boosting stage an individual SVM is trained by choosing training samples according to their probability distribution. The probability distribution is updated by the error of independent classifiers, and the process is iterated. After the training stage, they are aggregated to make a collective decision in several ways, such ai majority voting, the LSE(least squares estimation) -based weighting, and double layer hierarchical combining. The simulation results for IRIS data classification, the hand-written digit recognition and Face detection show that the proposed SVM ensembles greatly outperforms a single SVM in terms of classification accuracy.

• Journal of Korean Society of Occupational and Environmental Hygiene
• /
• v.33 no.1
• /
• pp.34-39
• /
• 2023

Objectives: In this study, the safety of alcohol-based hand sanitizers (ABHSs) for quasi-drugs and cosmetics was investigated by analyzing the ethanol content, which is an active ingredient with a sterilizing effect, and methanol, which is toxic. Methods: Forty-one ABHSs were purchased at large supermarkets and online stores. Ethanol quantification was performed by gas chromatography-flame ionization detector, and methanol quantification was performed by headspace-gas chromatography-mass spectrometry. Results: The ethanol content of ABHS in quasi-drugs was 49.6-67.8%, which was suitable for standard manufacturing procedures for external disinfectants, and the ethanol content of ABHS in cosmetics was 9.1-61.3%. The methanol content of ABHS in quasi-drugs ranged from not detected(N.D.)-131.8 ppm, which was suitable for the methanol detection standard of ethanol raw materials in the Korean Pharmacopoeia. The methanol content of ABHS in cosmetics was 23.4-859.7 ppm, which was suitable for the detection limit of methanol in cosmetics. Conclusions: The ethanol and methanol content of ABHS was judged to be safe. When selecting an ABHS to be used for sterilization, it seems necessary to check the content of ethanol, an active ingredient, and use it according to its intended purpose.

• Plant Biotechnology Reports
• /
• v.1 no.1
• /
• pp.19-25
• /
• 2007

To develop an efficient screening method for detection of the transgene in Chinese cabbage (Brassica rapa spp. pekinensis) utilizing Basta spray, optimal conditions for Basta application were examined in this study. Two transgenic Chinese cabbage lines were obtained through Agrobacterium-mediated transformation and used as transgenic positive controls in the Basta screening experiment. Differential concentrations of glufosinate-ammonium were sprayed into three different growth stages of 12 commercial Chinese cabbage cultivars. The results showed that no plants could survive higher than 0.05% glufosinate-ammonium, and plants at the 2-3 leaf stage were most vulnerable to glufosinate-ammonium. On the other hand, no damage was observed in the transgenic control plants. Reliability of the Basta spray method was proven by showing perfect co-segregation of the tolerance to glufosinate-ammonium and the presence of the bar gene in T₁ segregating populations of the transgenic lines, as revealed by both PCR and Southern blot analyses. Using the developed Basta screening method, we tried to investigate the transgene flow through pollen dispersal, but failed to detect any transgene-containing non-transgenic Chinese cabbages whose parents had been planted adjacent to transgenic Chinese cabbages in field conditions. However, the transgene was successfully detected using Basta spray from the non-transgenic plants bearing the transgene introduced by hand-pollination. Since the Basta spray method developed in this study is easy to apply and economical, it will be a valuable tool for understanding the mechanism of gene flow through pollen transfer and for establishing a biosafety test protocol for genetically modified (GM) Chinese cabbage cultivars.

• Journal of Internet Computing and Services
• /
• v.12 no.3
• /
• pp.119-129
• /
• 2011

Vision-based Human computer interaction is an emerging field of science and industry to provide natural way to communicate with human and computer. Especially, recent increasing demands for mobile augmented reality require the development of efficient interactive technologies between the augmented virtual object and users. This paper presents a novel approach to construct marker-less mobile augmented reality object and control the object. Replacing a traditional market, the human hand interface is used for marker-less mobile augmented reality system. In order to implement the marker-less mobile augmented system in the limited resources of mobile device compared with the desktop environments, we proposed a method to extract an optimal hand region which plays a role of the marker and augment object in a realtime fashion by using the camera attached on mobile device. The optimal hand region detection can be composed of detecting hand region with YCbCr skin color model and extracting the optimal rectangle region with Rotating Calipers Algorithm. The extracted optimal rectangle region takes a role of traditional marker. The proposed method resolved the problem of missing the track of fingertips when the hand is rotated or occluded in the hand marker system. From the experiment, we can prove that the proposed framework can effectively construct and control the augmented virtual object in the mobile environments.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1627-1627
• /
• 2001

In this study, a newly constructed optical measurement system, whose main components were a parametric tunable laser and a near infrared photoelectric multiplier, was applied to detection of the information for the inside of Satsuma mandarin using time-of-flight near infrared spectroscopy (TOF-NIRS). The combined effects on the time resolved profile of sample diameter, sugar content, the wavelength of the laser beam, and the detection position of transmitted light were investigated in detail. The samples used were Satsuma mandarin (Citrus unshu $M^{ARC}$.) (location: Wakayama, Japan) having the diameters of 50-84 mm. The sugar content measured by a refractometer varied from 9.9 to 16.3 Brix%. Equator of sample was irradiated vertically with the pulsed laser, and transmitted output power was measured on the restricted position of the equator using the optical fiber cable. The sampling time and the number of averaging the output power were 100 ns and 100 times, respectively. The variation of the attenuance of peak maxima At, the time delay of peak maxima t and the variation of full width at half maximum w were strongly dependent on the detection position and the wavelength of the laser beam. At, t and w increased gradually as the sample diameter increased to be much absorbed and vigorously scattered. On the other hand, each optical parameter had a tendency to increase as the sugar content increased. Such behavior was remarkable when the transmitted light was detected at the side face of a sample. When we apply TOF-NIRS to detection of the information for the inside of fruit with high moisture content like Satsuma mandarin, it is very important to give attention to the difference in the scattered light within tissues and the semi-straightly propagated light. Furthermore, we tried to express the resulting phenomena by using a model samples composed of water, sucrose, and milk. The variation of the time resolved profile is strongly governed by the combination of the light absorption component, scattering medium, and refractive index.

• Proceedings of the Korean Society of Near Infrared Spectroscopy Conference
• /
• 2001.06a
• /
• pp.1626-1626
• /
• 2001

In this study, a newly constructed optical measurement system, whose main components were a parametric tunable laser and a near infrared photoelectric multiplier, was applied to detection of the information for the inside of Satsuma mandarin using time-of-flight near infrared spectroscopy (TOF-NIRS). The combined effects on the time resolved profile of sample diameter, sugar content, the wavelength of the laser beam, and the detection position of transmitted light were investigated in detail. The samples used were Satsuma mandarin (Citrus unshu $M_{ARC}$.) (location: Wakayama, Japan) having the diameters of 50-84 mm. The sugar content measured by a refractometer varied from 9.9 to 16.3 Brix%. Equator of sample was irradiated vertically with the pulsed laser, and transmitted output power was measured on the restricted position of the equator using the optical fiber cable. The sampling time and the number of averaging the output power were 100 ns and 100 times, respectively. The variation of the attenuance of peak maxima At, the time delay of peak maxima $\Delta$t and the variation of full width at half maximum Δw were strongly dependent on the detection position and the wavelength of the laser beam. At, $\Delta$t and $\Delta$w increased gradually as the sample diameter increased to be much absorbed and vigorously scattered. On the other hand, each optical parameter had a tendency to increase as the sugar content increased. Such behavior was remarkable when the transmitted light was detected at the side face of a sample. When we apply TOF-NIRS to detection of the information for the inside of fruit with high moisture content like Satsuma mandarin, it is very important to give attention to the difference in the scattered light within tissues and the semi-straightly propagated light. Furthermore, we tried to express the resulting phenomena by using a model samples composed of water, sucrose, and milk. The variation of the time resolved profile is strongly governed by the combination of the light absorption component, scattering medium, and refractive index.

• Journal of KIISE:Information Networking
• /
• v.36 no.2
• /
• pp.69-79
• /
• 2009

Today's Internet is one of the necessaries of our life. Anomalies of the Internet provoke social problems. For that reason, Internet Measurement which studies characteristics on Internet traffic attracts pubic attention. Recently, Traffic Dispersion Graph (TDG), a novel traffic analysis method, was proposed. The TDG is not a statistical analysis method but a graphical visualization method on interactions among network components. In this paper, we propose a new anomaly detection paradigm and its technique using TDG. The existing studies have focused on detecting anomalous packets of flows. On the other hand, we focus on detecting the sources of anomalous traffic. To realize our paradigm, we designed the TDG Clustering method. Through this method, we could classify anomalous hosts infected by various worm viruses. We obtained normal traffic through dropping traffic of the anomalous hosts. Especially, we expect that the TDG clustering method can be applied to real-time anomaly detection because calculations of the method are fast.

• The Korean Journal of Pesticide Science
• /
• v.20 no.2
• /
• pp.128-132
• /
• 2016

Volatile organic solvents are used to extract the bioactive materials from raw materials for environmentally-friendly farming materials (EFFM), but the solvent should not remain in EFFM for the safety reasons. Thus qualitative and quantitative analysis method for the solvents using Headspace-GC were evaluated. Water content depleted the detection ratio of hydrophilic solvents and disturbing the hydrophilic interaction with solvents by DMSO might be helped to increase the detection ratio (up to 715%). Surfactant concentration affected to the detection ratio (68.5-179.1%) while surfactant type was not deeply involved the solvent detection. On the other hand, matrix-matched calibration method was accepted the minimum requirements for the quantitative analysis of the solvents in EFFM.

• Proceedings of the KSRS Conference
• /
• 2008.10a
• /
• pp.320-323
• /
• 2008

This study attempts to establish a system extracting and monitoring cultural grounds of seaweeds (lavers, brown seaweeds and seaweed fulvescens) and abalone on the basis of both KOMPSAT-2 and Terrasar-X data. The study areas are located in the northwest and southwest coast of South Korea, famous for coastal cultural grounds. The northwest site is in a high tidal range area (on the average, 6.1 min Asan Bay) and has laver cultural grounds for the most. An semi-automatic detection system of laver facilities is described and assessed for spacebome optic images. On the other hand, the southwest cost is most famous for seaweeds. Aquaculture facilities, which cover extensive portions of this area, can be subdivided into three major groups: brown seaweeds, capsosiphon fulvescens and abalone farms. The study is based on interpretation of optic and SAR satellite data and a detailed image analysis procedure is described here. On May 25 and June 2, 2008 the TerraSAR-X radar satellite took some images of the area. SAR data are unique for mapping those farms. In case of abalone farms, the backscatters from surrounding dykes allows for recognition and separation of abalone ponds from all other water-covered surfaces. But identification of seaweeds such as laver, brown seaweeds and seaweed fulvescens depends on the dampening effect due to the presence of the facilities and is a complex task because objects that resemble seaweeds frequently occur, particularly in low wind or tidal conditions. Lastly, fusion of SAR and optic spatial images is tested to enhance the detection of aquaculture facilities by using the panchromatic image with spatial resolution 1 meter and the corresponding multi-spectral, with spatial resolution 4 meters and 4 spectrum bands, from KOMPSAT-2. The mapping accuracy achieved for farms will be estimated and discussed after field verification of preliminary results.

• Journal of the Korea Society of Computer and Information
• /
• v.17 no.12
• /
• pp.219-228
• /
• 2012

In this paper, we propose a paper keyboard piano implementation using the finger movement detection with the 3D image data from a kinect. Keyboard pattern and keyboard depth information are extracted from the color image and depth image to detect the touch event on the paper keyboard and to identify the touched key. Hand region detection error is unavoidable when using the simple comparison method between input depth image and background depth image, and this error is critical in key touch detection. Skin color is used to minimize the error. And finger tips are detected using contour detection with area limit and convex hull. Finally decision of key touch is carried out with the keyboard pattern information at the finger tip position. The experimental results showed that the proposed method can detect key touch with high accuracy. Paper keyboard piano can be utilized for the easy and convenient interface for the beginner to learn playing piano with the PC-based learning software.