• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.7
• /
• pp.1064-1073
• /
• 2015

In this study, we introduce the pedestrian detection system by using the feature of HOG-PCA and RBFNNs pattern classifier. HOG(Histogram of Oriented Gradient) feature is extracted from input image to identify and recognize a object. And a dimension is reduced for improving performance as well as processing speed by using PCA which is a typical dimensional reduction algorithm. So, the feature of HOG-PCA through the dimensional reduction by using PCA leads to the improvement of the detection rate. FCM clustering algorithm is used instead of gaussian function to apply the characteristic of input data as well and connection weight is used by polynomial expression such as constant, linear, quadratic and modified quadratic. Finally, INRIA person database known as one of the benchmark dataset used for pedestrian detection is applied for the performance evaluation of the proposed classifier. The experimental result of the proposed classifier are compared with those studied by Dalal.

• The Korean Journal of Applied Statistics
• /
• v.26 no.5
• /
• pp.785-796
• /
• 2013

News Impact Curves(NIC) developed by Engle and Ng (1993) have been useful for graphically representing the volatilities arising from financial time series. Adding an improvement and refinement to the original NIC, this article proposes so called two dimensional NIC and principal component NIC. We illustrate the methodology via Kosdaq data.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.20 no.3
• /
• pp.247-253
• /
• 2007

Determination of crack depth in filed using the self-calibrating surface wane transmission measurement and the cutting frequency in the transmission function (TRF) is very difficult due to variations of the measurement conditions. In this study, it is proposed to use the measured full TRF as a feature for crack depth assessment. A Principal component analysis (PCA) is employed to generate a basis of the measured TRFs for various crack cases. The measured TRFs are represented by their projections onto the most significant principal components. Then artificial neural networks (NNs) using the PCA-compressed TRFs is applied to assess the crack in concrete. Experimental study is carried out for five different crack cases to investigate the effectiveness of the proposed method. Results reveal that the proposed method can be effectively used for the crack depth assessment of concrete structures.

• Korean Journal of Agricultural Science
• /
• v.49 no.1
• /
• pp.129-136
• /
• 2022

In this study, we aimed to develop a maturity classification model for tomatoes using hyperspectral imaging in the range of 400 - 1,000 nm. Fifty-seven tomatoes harvested in August and November of 2021 were used as the sample set, and hyperspectral data was extracted from the surfaces of these tomatoes. A combined method of SNV (standard normal variate) and SG (Savitzky-Golay) methods was used for the pre-processing of the hyperspectral data. In addition, the hyperspectral data were analyzed for all maturity stages and considering bandwidths with different FWHM (full width at half maximum) values of 2, 25, and 50 nm. The PCA (principal component analysis) method was used to analyze the principal components related to maturity stages for the tomatoes. As a result, 500 - 550 nm and 650 - 700 nm bands were found to be related to the maturity stages of tomatoes. In addition, PC1 and PC2 explained approximately 97% of the variance at all FWHM conditions and thus were used as input data for classification model training based on the SVM (support vector machine). The SVM models were able to classify tomato maturity into five stages (Green, Turning, Pink, Light red, and Red) with over 95% accuracy regardless of the FWHM condition. Therefore, it was considered that hyperspectral data with 50 nm FWHM and SVM is feasible for use in the classification of tomato maturity into five stages.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.831-832
• /
• 2008

This paper proposes the experimental results and analysis of face recognition on an conventional UMPC(Ultra Mobile Personal Computer). With face images acquired by the embedded camera of UMPC, we detected the facial region by using Adaboost face detector. The detected image was normalized into a $32{\times}32$ pixel sized image for face recognition. We performed face recognition based on PCA (Principal Component Analysis). As experimental results, the TER (Total Error Rate) of face recognition was 19.77%.

• Korean Journal of Pharmacognosy
• /
• v.44 no.4
• /
• pp.332-335
• /
• 2013

Geographical classification of A. gigas was performed in the present study using UHPLC-DAD combined with multivariate data analysis techniques. Six active constituents were isolated from A. gigas; nodakenin, marmesin, decursinol, demethylsuberosin, decursin and decursinol angelate. One hundred sixty eight A. gigas samples were simultaneously determined using UHPLC-DAD. A principal component analysis (PCA) and partial least square discriminant analysis (PLS-DA) was used to classify the samples according to geographical origins (Korea and China). The origins of A. gigas from Korea and China were correctly classified by 81.6% and 93.8% using PLS-DA Y prediction. This result demonstrates the potential use of UHPLC-DAD combined with multivariate analysis techniques as an accurate and rapid method to classify A. gigas according to their geographical origin.

• Journal of Environmental Health Sciences
• /
• v.41 no.2
• /
• pp.90-101
• /
• 2015

Objective: This study was conducted to develop a chemical oxygen demand (COD) regression model using water quality monitoring data (January, 2014) obtained from the Han River auto-monitoring stations. Methods: Surface water quality data at 198 sampling stations along the six major areas were assembled and analyzed to determine the spatial distribution and clustering of monitoring stations based on 18 WQPs and regression modeling using selected parameters. Statistical techniques, including combined genetic algorithm-multiple linear regression (GA-MLR), cluster analysis (CA) and principal component analysis (PCA) were used to build a COD model using water quality data. Results: A best GA-MLR model facilitated computing the WQPs for a 5-descriptor COD model with satisfactory statistical results ($r^2=92.64$,$Q{^2}_{LOO}=91.45$,$Q{^2}_{Ext}=88.17$). This approach includes variable selection of the WQPs in order to find the most important factors affecting water quality. Additionally, ordination techniques like PCA and CA were used to classify monitoring stations. The biplot based on the first two principal components (PCs) of the PCA model identified three distinct groups of stations, but also differs with respect to the correlation with WQPs, which enables better interpretation of the water quality characteristics at particular stations as of January 2014. Conclusion: This data analysis procedure appears to provide an efficient means of modelling water quality by interpreting and defining its most essential variables, such as TOC and BOD. The water parameters selected in a COD model as most important in contributing to environmental health and water pollution can be utilized for the application of water quality management strategies. At present, the river is under threat of anthropogenic disturbances during festival periods, especially at upstream areas.

• Smart Structures and Systems
• /
• v.15 no.5
• /
• pp.1329-1344
• /
• 2015

The stiffness of a structure is one of several structural signals that are useful indicators of the amount of damage that has been done to the structure. To accurately estimate the stiffness, an equation of motion containing a stiffness parameter must first be established by expansion as a linear series model, a Taylor series model, or a power series model. The model is then used in multivariate autoregressive modeling to estimate the structural stiffness and compare it to the theoretical value. Stiffness assessment for modeling purposes typically involves the use of one of three statistical model refinement approaches, one of which is the efficient Akaike information criterion (AIC) proposed in this paper. If a newly added component of the model results in a decrease in the AIC value, compared to the value obtained with the previously added component(s), it is statistically justifiable to retain this new component; otherwise, it should be removed. This model refinement process is repeated until all of the components of the model are shown to be statistically justifiable. In this study, this model refinement approach was compared with the two other commonly used refinement approaches: principal component analysis (PCA) and principal component regression (PCR) combined with the AIC. The results indicate that the proposed AIC approach produces more accurate structural stiffness estimates than the other two approaches.

• Korean Journal of Construction Engineering and Management
• /
• v.13 no.5
• /
• pp.94-102
• /
• 2012

Recently, the global financial crisis and the increasing number of unsold houses in Korea are construction companies to assess their efficiency. The most important factor in analyzing the efficiency of a company is the input-output variable. However, systematic stud the core input-output variables, which have a great influence on the efficiency analysis. Thus, to the core input-output variables for efficiency analysis of construction companies, this study propose a model that includes all combinations of input-output variables and to find the core input-output variables using the Data Envelopment Analysis(DEA) model and Principal Component Analysis(PCA). Existing research and theories were studied variables and 21 models were established to measure efficiency. were obtained that the core input and output variable in 2006 the number of employees and sales. For 2008, the core input variable was capital stock and the core output variable was quarterly net profit. For 2010, the core input variable was fixed asset and the core output variable was sales. Through obtaining the variables that greatly affect the efficiency of construction companies, it is considered that individual construction companies will be able to prepare a priority strategy to enhance efficiency.

• Korean Journal of Optics and Photonics
• /
• v.31 no.3
• /
• pp.125-133
• /
• 2020

An innovative method for separating overlapping latent fingerprints, using laser-induced plasma spectroscopy (LIPS) combined with multivariate analysis, is reported in the current study. LIPS provides the capabilities of real-time analysis and high-speed scanning, as well as data regarding the chemical components of overlapping fingerprints. These spectra provide valuable chemical information for the forensic classification and reconstruction of overlapping latent fingerprints, by applying appropriate multivariate analysis. This study utilizes principal-component analysis (PCA) and partial-least-squares (PLS) techniques for the basis classification of four types of fingerprints from the LIPS spectra. The proposed method is successfully demonstrated through a classification example of four distinct latent fingerprints, using discrimination such as soft independent modeling of class analogy (SIMCA) and partial-least-squares discriminant analysis (PLS-DA). This demonstration develops an accuracy of more than 85% and is proven to be sufficiently robust. In addition, by laser-scanning analysis at a spatial interval of 125 ㎛, the overlapping fingerprints were separated as two-dimensional forms.