• Journal of Korea Water Resources Association
• /
• v.49 no.6
• /
• pp.565-577
• /
• 2016

The objective of this study is to propose a method for computing the Natural Drought Index (NDI) that does not consider man-made drought facilities. Principal Component Analysis (PCA) was used to estimate the NDI. Three monthly moving cumulative runoff, soil moisture and precipitation were selected as input data of the NDI during 1977~2012. Observed precipitation data was collected from KMA ASOS (Korea Meteorological Association Automatic Synoptic Observation System), while model-driven runoff and soil moisture from Variable Infiltration Capacity Model (VIC Model) were used. Time series analysis, drought characteristic analysis and spatial analysis were used to assess the utilization of NDI and compare with existing SPI, SRI and SSI. The NDI precisely reflected onset and termination of past drought events with mean absolute error of 0.85 in time series analysis. It explained well duration and inter-arrival time with 1.3 and 1.0 respectively in drought characteristic analysis. Also, the NDI reflected regional drought condition well in spatial analysis. The accuracy rank of drought onset, termination, duration and inter-arrival time was calculated by using NDI, SPI, SRI and SSI. The result showed that NDI is more precise than the others. The NDI overcomes the limitation of univariate drought indices and can be useful for drought analysis as representative measure of different types of drought such as meteorological, hydrological and agricultural droughts.

• Korean Journal of Agricultural Science
• /
• v.39 no.1
• /
• pp.111-116
• /
• 2012

Nondestructive evaluation of seed viability is one of the highly demanding technologies for seed production industry. Conventional seed sorting technologies, such as tetrazolium and standard germination test are destructive, time consuming, and labor intensive methods. Near infrared spectroscopy technique has shown good potential for nondestructive quality measurements for food and agricultural products. In this study, FT-NIR spectroscopy was used to classify normal and artificially aged lettuce seeds. The spectra with the range of 1100~2500 nm were scanned for lettuce seeds and analyzed using the principal component analysis(PCA) method. To classify viable seeds from nonviable seeds, a calibration modeling set was developed with a partial least square(PLS) method. The calibration model developed from PLS resulted in 98% classification accuracy with the Savitzky-Golay $1^{st}$ derivative preprocessing method. The prediction accuracy for the test data set was 93% with the MSC(Multiplicative Scatter Correction) preprocessing method. The results show that FT-NIR has good potential for discriminating non-viable lettuce seeds from viable ones.

• IEIE Transactions on Smart Processing and Computing
• /
• v.6 no.3
• /
• pp.183-192
• /
• 2017

k-nearest neighbor (K-NN) is a well-known classification algorithm, being feature space-based on nearest-neighbor training examples in machine learning. However, K-NN, as we know, is a lazy learning method. Therefore, if a K-NN-based system very much depends on a huge amount of history data to achieve an accurate prediction result for a particular task, it gradually faces a processing-time performance-degradation problem. We have noticed that many researchers usually contemplate only classification accuracy. But estimation speed also plays an essential role in real-time prediction systems. To compensate for this weakness, this paper proposes correlation coefficient-based clustering (CCC) aimed at upgrading the performance of K-NN by leveraging processing-time speed and plurality rule-based density (PRD) to improve estimation accuracy. For experiments, we used real datasets (on breast cancer, breast tissue, heart, and the iris) from the University of California, Irvine (UCI) machine learning repository. Moreover, real traffic data collected from Ojana Junction, Route 58, Okinawa, Japan, was also utilized to lay bare the efficiency of this method. By using these datasets, we proved better processing-time performance with the new approach by comparing it with classical K-NN. Besides, via experiments on real-world datasets, we compared the prediction accuracy of our approach with density peaks clustering based on K-NN and principal component analysis (DPC-KNN-PCA).

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.25 no.5
• /
• pp.1001-1009
• /
• 2015

In Smart Grid, smart meter sends our electric signal data to the main server of power supply in real-time. However, the more efficient the management of power loads become, the more likely the user's pattern of usage leaks. This paper points out the threat of privacy and the need of security measures in smart device environment by showing that it's possible to identify the appliances and the specific usage patterns of users from the smart meter's data. Learning algorithm PCA is used to reduce the dimension of the feature space and k-NN Classifier to infer appliances and states of them. Accuracy is validated with 10-fold Cross Validation.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.65 no.9
• /
• pp.1531-1540
• /
• 2016

In this paper, we propose vehicle license plate recognition system based on Radial Basis Function Neural Networks (RBFNNs) with the use of local binarization functions and canny edge algorithm. In order to detect the area of license plate and also recognize license plate numbers, binary images are generated by using local binarization methods, which consider local brightness, and canny edge detection. The generated binary images provide information related to the size and the position of license plate. Additionally, image warping is used to compensate the distortion of images obtained from the side. After extracting license plate numbers, the dimensionality of number images is reduced through Principal Component Analysis (PCA) and is used as input variables to RBFNNs. Particle Swarm Optimization (PSO) algorithm is used to optimize a number of essential parameters needed to improve the accuracy of RBFNNs. Those optimized parameters include the number of clusters and the fuzzification coefficient used in the FCM algorithm, and the orders of polynomial of networks. Image data sets are obtained by changing the distance between stationary vehicle and camera and then used to evaluate the performance of the proposed system.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2006.05a
• /
• pp.203-207
• /
• 2006

This paper deals with a problem of detecting BCC using confocal raman spectrum. Specially, we propose Fisher measure based filtering for rejection of frequency components being noisy or non-discriminative. we use PCA (principal component analysis) for reduction of feature space dimension. Also, we apply MAP detector for classification of BCC raman spectrum. The experimental results shows that our proposed method can reduce the feature dimension and also raise the detection ratio.

• Proceedings of the IEEK Conference
• /
• 2002.07b
• /
• pp.1236-1239
• /
• 2002

When we see an object, we usually can say what it is easily even for the case where the object isn't shown in the frontal view. However, it is difficult to believe that all views of every object we have ever seen are fully memorized in our brain. Possibly, when an object is shown, we have some typical views of the object in our brain through our past experience and reconstruct the view to recognize what the presented object is. Non-negative Matrix Factorization (NMF) is one of the methods to extract the basis images from sample data set. The prominent feature of this method is that the reconstructed image is obtained by only additions of the basis images with suitable positive weights. So NMF can be seen more biologically plausible method than any other feature extraction methods such as Vector Quantization (VQ) and principal Component Analysis (PCA). In this paper, we adopt NMF to extract the aspect features from the set of images, which consists of various views of a given object. Some experiments are shown how much well NMF can extract the aspect features than any other methods such as VQ and PCA.

• Journal of Information Processing Systems
• /
• v.12 no.3
• /
• pp.468-488
• /
• 2016

The paper proposes a novel framework for 3D face verification using dimensionality reduction based on highly distinctive local features in the presence of illumination and expression variations. The histograms of efficient local descriptors are used to represent distinctively the facial images. For this purpose, different local descriptors are evaluated, Local Binary Patterns (LBP), Three-Patch Local Binary Patterns (TPLBP), Four-Patch Local Binary Patterns (FPLBP), Binarized Statistical Image Features (BSIF) and Local Phase Quantization (LPQ). Furthermore, experiments on the combinations of the four local descriptors at feature level using simply histograms concatenation are provided. The performance of the proposed approach is evaluated with different dimensionality reduction algorithms: Principal Component Analysis (PCA), Orthogonal Locality Preserving Projection (OLPP) and the combined PCA+EFM (Enhanced Fisher linear discriminate Model). Finally, multi-class Support Vector Machine (SVM) is used as a classifier to carry out the verification between imposters and customers. The proposed method has been tested on CASIA-3D face database and the experimental results show that our method achieves a high verification performance.

• Journal of the Institute of Convergence Signal Processing
• /
• v.5 no.1
• /
• pp.25-31
• /
• 2004

This paper is research about the improvement of recognition rate of the biometrics user identification system using the data previously stored in the non contact Ic smart card. The proposed system identifies the user by analyzing the iris pattern his or her us. First, after extracting the area of the iris from the image of the iris of an eye which is taken by CCD camera, and then we save PCA Coefficient using GHA(Generalized Hebbian Algorithm) into the Smart Card. When we confirmed the users, we compared the imformation of the biometrics of users with that of smart card. In case two kinds of information was the same, we classified the data by using SVM(Support Vector Machine). The Experimental result showed that this system outperformed the previous developed system.

• Journal of Environmental Science International
• /
• v.14 no.7
• /
• pp.629-637
• /
• 2005

Polychlorinated dibenzo-p-dioxins (PCDDs) and polychlorinated dibenzofurans (PCDFs) were investigated in soil and pine needle samples taken from 16 sites of industrial and residential areas in Changwon, Korea to assess their distribution levels and to suggest the influence of industrial activities, PCDDs/DFs levels in the soil samples ranged from 0.57 to 20.79 pg I-TEQ/g dry weight with a mean value of 4.20 pg I-TEQ/g dry weight. PCDDs/DFs levels in the pine needle samples ranged from 0.39 to 8.75 pg I-TEQ/g dry weight with a mean value of 4.09 pg I-TEQ/g dry weight. In both soil and pine needle samples, the PCDDs/DFs concentrations in the industrial area sites were higher than those in the residential area sites. Homologue profiles in pine needle samples showed different patterns compared with soil samples. Based on the results of principal component analysis (PCA), it was confirmed that pine needles reflected a direct influence from local potential sources of PCDDs/DFs, showing a much higher degree of reflection than in soils. Pine needles are very useful as an indicator for monitoring or estimating the contamination of PCDDs/DFs in other areas which have been impacted by point pollution sources.