• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2667-2682
• /
• 2015

Due to the wide application of face recognition (FR) in information security, surveillance, access control and others, it has received significantly increased attention from both the academic and industrial communities during the past several decades. However, partial face occlusion is one of the most challenging problems in face recognition issue. In this paper, a novel method based on linear regression-based classification (LRC) algorithm is proposed to address this problem. After all images are downsampled and divided into several blocks, we exploit the evaluator of each block to determine the clear blocks of the test face image by using linear regression technique. Then, the remained uncontaminated blocks are utilized to partial occluded face recognition issue. Furthermore, an improved Distance-based Evidence Fusion approach is proposed to decide in favor of the class with average value of corresponding minimum distance. Since this occlusion removing process uses a simple linear regression approach, the completely computational cost approximately equals to LRC and much lower than sparse representation-based classification (SRC) and extended-SRC (eSRC). Based on the experimental results on both AR face database and extended Yale B face database, it demonstrates the effectiveness of the proposed method on issue of partial occluded face recognition and the performance is satisfactory. Through the comparison with the conventional methods (eigenface+NN, fisherfaces+NN) and the state-of-the-art methods (LRC, SRC and eSRC), the proposed method shows better performance and robustness.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.18 no.10
• /
• pp.960-964
• /
• 2005

In this paper, we dealt with a partial discharge(PD) measurement method that has been accepted as an effective and non-destructive technique to estimate insulation performance of low-voltage electric and electronic devices. The PD measurement system Is composed of a coupling network, a low noise amplifier, and associated electronics. h shielded box Is adopted to make a better measurement environment against around noise. A low cut-off frequency of the coupling network estimated by a sinusoidal wave input was 125 kHz (-3 dB). Calibration tests on laboratory set-up have shown that the PD measurement system has a stable sensitivity of 10 mV/pC. In an application test oil a low-voltage three phase Induction motor (5 HP), we could detect 0.53 pC level of partial discharge at the applied voltage of AC 650 $V_{peak}$.

• Journal of Electrical Engineering and Technology
• /
• v.11 no.3
• /
• pp.699-706
• /
• 2016

Partial discharges (PD) lead to the degradation of high voltage cables and accessories. PD activities occur due to the existence of impurities, voids, contaminants, defects and protrusions during the manufacture and installation of power cables. Commonly, insulation failures occur at cable joints and terminations, caused by inhomogeneous electric field distributions. In this work, a blend of natural rubber (NR) and linear low density polyethylene (LLDPE) was investigated, and the optimal formulation of the blend that could resist PD was discussed. The experiments were conducted under a constant high voltage stress test of 6.5 kV AC and the magnitude of partial discharge activities was recorded using the CIGRE method II. Pattern analysis of PD signals was performed along with the interpretation of morphological changes. The results showed that the addition of 10 wt% of NR and 5 wt% of Alumina Trihydrate (ATH) provided promising results in resisting PD activities. However, as the NR content increased, more micropores existed, thus resulting in increased PD activities within the samples.

• Journal of the Korean Data and Information Science Society
• /
• v.24 no.1
• /
• pp.33-39
• /
• 2013

In the transformation of response variable in partial linear models outliers can cause a bad effect on estimating the transformation parameter, just as in the linear models. To solve this problem the processes of estimating transformation parameter and detecting outliers are needed, but have difficulties to be performed due to the arbitrariness of the nonparametric function included in the partial linear model. In this study, through the estimation of nonparametric function and outlier detection methods such as a sequential test and a maximum trimmed likelihood estimation, processes for transforming response variable robust to outliers in partial linear models are suggested. The proposed methods are verified and compared their effectiveness by simulation study and examples.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2008.06a
• /
• pp.265-266
• /
• 2008

The objective of this paper is to effectively detect partial discharges in XLPE power cables. In this field, we have been usually applied several sensors for such partial discharges. This study used a type of beyond compare antenna based on the influence of background noises. Also, we designed a new structure that is able to easily apply in the adhesion of planar patch types for XLPE power cables in measurement sensitiveness elevation. A high frequency simulation tool (CST-MWS) was applied to the antenna used in this study, and it was used to evaluate certain characteristics. We fabricated an antenna using the simulation data obtained from a specific test. After checking the sensitivity of this Planar Patch Sensor in the Lab, it was tested in an actual site. This paper analyzed the data as a part of time and frequency domain using an oscilloscope and spectrum analyzer, respectively.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.57 no.12
• /
• pp.2313-2321
• /
• 2008

In order to develop reliable on-site partial discharge(PD) pattern recognition algorithm, the fuzzy neural network based on fuzzy set(FNN) and the polynomial network pattern classifier based on fuzzy Inference(PNC) were investigated and designed. Using PD data measured from laboratory defect models, these algorithms were learned and tested. Considering on-site situation where it is not easy to obtain voltage phases in PRPDA(Phase Resolved Partial Discharge Analysis), the measured PD data were artificially changed with shifted voltage phases for the test of the proposed algorithms. As input vectors of the algorithms, PRPD data themselves were adopted instead of using statistical parameters such as skewness and kurtotis, to improve uncertainty of statistical parameters, even though the number of input vectors were considerably increased. Also, results of the proposed neuro-fuzzy algorithms were compared with that of conventional BP-NN(Back Propagation Neural Networks) algorithm using the same data. The FNN and PNC algorithms proposed in this study were appeared to have better performance than BP-NN algorithm.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.10
• /
• pp.1461-1466
• /
• 2014

GIS(Gas Insulated Switchgear) is important power apparatus which have strong dielectric strength, supply electric power and is a part of the power system. Most substation type is configured as GIS. Recently, because of continuous increasement of GIS demand resulted from high quality & big capacity of electric power, the necessity of the preventive & diagnosis system is being expanded gradually. GIS partial discharge occurred on the UHF band is detected effectively by the method to IEC 60270 that recommend to be able to detect the apparent minimum discharge, 5 pC. Additionally, the UHF sensor should be installed to detect PD signal if Partial discharge signal, 5 pC occur in every part of GIS. Currently PD diagnosis system applying UHF sensor for GIS with various voltage level like 154 kV, 345 kV, 765 kV have been operated. And it is necessary to measure and analyze insulation breakdown phenomenon of inside GIS exactly. In this paper, we proposed Fat-dipole patch UHF sensor that is developed and more sensitive, excellent wide-range characteristic than the exising UHF sensor. And we performed KERI (Korea Electrotechnology Research Institute) reference test, which showed the excellent result for the all tests.

• Proceedings of the Korean Institute of Electrical and Electronic Material Engineers Conference
• /
• 2007.11a
• /
• pp.210-211
• /
• 2007

The objective of this paper is to effectively detect partial discharges in underground power cables. In this field, we have been usually applied several sensors for such partial discharges. This study used a type of beyond compare antenna based on the influence of background noises. Also, we designed a new structure that is able to easily apply in the adhesion of planar loop types for underground power cables in measurement sensitiveness elevation. A high frequency simulation tool (CST-MWS) was applied to the antenna used in this study, and it was used to evaluate certain characteristics. We fabricated an antenna using the simulation data obtained from a specific test. After checking the sensitivity of this Planar Loop Sensor in the Lab, it was tested in an actual site. This paper analyzed the data as a part of time and frequency domain using an oscilloscope and spectrum analyzer, respectively.

• Biomolecules & Therapeutics
• /
• v.4 no.2
• /
• pp.196-201
• /
• 1996

The N-methyl-D-aspartate (NMDA) receptor-ion channel complex is activated by the simultaneous presence of L-glutamate and glycine, allowing the binding of MK-801 to the phencyclidine (PCP) site of the receptor. The $[^3H]$MK-801 binding assay system was established for determination of pharmacological functions of test compounds acting at the glycine site of the receptor. The binding in the presence of 0.1 $\mu$M L-glutamate was increased by an agonist (glycine) in a dose-dependent fashion, while decreased by either partial agonist (R-(+)-HA-966) or antagonist (5,7-dichlorokynurenic acid: 5,7-DCKA). To distinguish partial agonism from antagonism, various concentrations of 7-chlorokynurenic acid (7-CKA) were added in the assay to eliminate the interference of the endogenous glycine present in the membrane preparations. The bindings in the presence of L-glutamate (0.1$\muM$) and 7-CKA (1, 5, or 10$\muM$) were increased by R-(+)-HA-966. Being a weak partial agonist, the extent of potentiation was much less than that by the agonist. These binding profiles were clearly distinguishable from those by the antagonist, 5,7-DCKA, which exhibited no intrinsic activity. The binding assays established in the present study are a useful system to classify ligands acting at the glycine site of the NMDA receptor by their pharmacological functions.

• The Korean Journal of Applied Statistics
• /
• v.34 no.6
• /
• pp.937-944
• /
• 2021

The problem of selecting variables is addressed in partial linear regression. Model selection for partial linear models is not easy since it involves nonparametric estimation such as smoothing parameter selection and estimation for linear explanatory variables. In this work, several approaches for variable selection are proposed using a fast forward selection algorithm, least angle regression (LARS). The proposed procedures use t-test, all possible regressions comparisons or stepwise selection process with variables selected by LARS. An example based on real data and a simulation study on the performance of the suggested procedures are presented.