• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.35 no.4
• /
• pp.235-243
• /
• 2012

The Voronoi diagram of spheres and power diagram have been known as powerful tools to analyze spatial characteristics of weighted points, and these structures have variety range of applications including molecular spatial structure analysis, location based optimization, architectural design, etc. Due to the fact that both diagrams are based on different distance metrics, one has better usability than another depending on application problems. In this paper, we compare these diagrams in various situations from the user's viewpoint, and show the Voronoi diagram of spheres is more effective in the problems based on the Euclidean distance metric such as nearest neighbor search, path bottleneck locating, and internal void finding.

• Proceedings of the IEEK Conference
• /
• summer
• /
• pp.435-437
• /
• 2004

This paper presents a personal identification method using teeth images. The method uses images for teeth expressions of anterior and posterior occlusion state and LDA-based technique. Teeth images give merits for recognition because teeth, rigid objects, cannot be deformed at the moment of image acquisition. In the experiments, personal identification for 12 people was successful. It was shown that our method can contribute to multi-modal authentication systems.

• Proceedings of the IEEK Conference
• /
• 2006.06a
• /
• pp.395-396
• /
• 2006

본 논문에서는 얼굴 인식의 성능을 효율적으로 향상시키기 위하여 Discrete Cosine Transform (DCT)와 Principal Component Analysis(PCA)에 기반한 새로운 특징 추출 방법을 제안한다. 얼굴 영상의 공간 영역은 DCT를 이용하여 주파수 영역으로 변환되며, DCT 도메인에서 얼굴 영상이 갖는 고유한 주파수 특성을 최적화 하는 주파수 밴드 영역을 추출한다. 차원이 축소된 데이터는 PCA 를 이용하여 데이터의 변별력에 가장 적합한 얼굴의 특징을 추출하고 Nearest Neighbor Classification 을 통해 본인여부를 확인 한다. 실험 결과 제안된 방법은 데이터의 차원을 효과적으로 축소하면서 기존의 얼굴 인식 방법에 비해 높은 인식률 향상을 보였다.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.4 no.3
• /
• pp.85-90
• /
• 2008

Recently, with the sensor technology, research about the electronic nose system which imitated the olfactory organ are being pushed actively. But, in case of general electronic nose system, an aroma is measured at the laboratory space where blocked external environment and is analyzed a part of measured data. In this paper, we propose the system which can measure and recognize an aroma in natural environment. We propose the Entropy algorithm which can detect the sensor reaction section among the continuous detection processing about an aroma. And we implement the aroma recognition system using the PCA(Principal Components Analysis) and K-NN(K-Nearest Neighbor) about the detected aroma. In order to evaluate the performance, we measured the aroma pattern, about 9 aroma oil, 50 times respectively. And we experimented the aroma detection and recognition using this. There was an error of 0.2s in the aroma detection and we get 84.3% recognition rate of the aroma recognition.

• Annual Conference of KIPS
• /
• 2022.11a
• /
• pp.40-42
• /
• 2022

People's focus steadily shifted toward fashion as a popular aesthetic expression as their quality of life improved. Humans are inevitably drawn to things that are more aesthetically appealing. This human proclivity has resulted in the evolution of the fashion industry over time. However, too many clothing alternatives on e-commerce platforms have created additional obstacles for clients in recognizing their suitable outfit. Thus, in this paper, we proposed a personalized Fashion Recommender system that generates recommendations for the user based on their previous purchases and history. Our model aims to generate recommendations using an image of a product given as input by the user because many times people find something that they are interested in and tend to look for products that are like that. In the system, we first reduce data dimensionality by component analysis to avoid the curse of dimensionality, and then the final suggestion is generated by neural network. To create the final suggestions, we have employed neural networks to evaluate photos from the H&M dataset and a nearest neighbor backed recommender.

• Journal of Internet Computing and Services
• /
• v.15 no.6
• /
• pp.117-124
• /
• 2014

Cluttered background is a major obstacle in developing salient object detection and tracking system for mobile device captured natural scene video frames. In this paper we propose a context aware feature vector selection model to provide an efficient noise filtering by machine learning based classifiers. Since the context awareness for feature selection is achieved by searching nearest neighborhoods, known as NP hard problem, we apply a fast approximation method with complexity analysis in details. Separability enhancement in feature vector space by adding the context aware feature subsets is studied rigorously using principal component analysis (PCA). Overall performance enhancement is quantified by the statistical measures in terms of the various machine learning models including MLP, SVM, Naïve Bayesian, CART. Summary of computational costs and performance enhancement is also presented.

• Journal of rehabilitation welfare engineering & assistive technology
• /
• v.11 no.3
• /
• pp.261-270
• /
• 2017

Bad sitting postures are known to cause for a variety of diseases or physical deformation. However, it is not easy to fit right sitting posture for long periods of time. Therefore, methods of distinguishing and inducing good sitting posture have been constantly proposed. Proposed methods were image processing, using pressure sensor attached to the chair, and using the IMU (Internal Measurement Unit). The method of using IMU has advantages of simple hardware configuration and free of various constraints in measurement. In this paper, we researched on distinguishing sitting postures with a small amount of data using just one IMU. Feature extraction method was used to find data which contribution is the least for classification. Machine learning algorithms were used to find the best position to classify and we found best machine learning algorithm. Used feature extraction method was PCA(Principal Component Analysis). Used Machine learning models were five : SVM(Support Vector Machine), KNN(K Nearest Neighbor), K-means (K-means Algorithm) GMM (Gaussian Mixture Model), and HMM (Hidden Marcov Model). As a result of research, back neck is suitable position for classification because classification rate of it was highest in every model. It was confirmed that Yaw data which is one of the IMU data has the smallest contribution to classification rate using PCA and there was no changes in classification rate after removal it. SVM, KNN are suitable for classification because their classification rate are higher than the others.

• Composites Research
• /
• v.33 no.3
• /
• pp.108-114
• /
• 2020

Piecewise Integrated Composite (PIC) beam is composed of different stacking against loading type depending upon location. The aim of current study is to assign robust stacking sequences against external loading to every corresponding part of the PIC beam based on the value of stress triaxiality at generated reference points using the k-NN (k-Nearest Neighbor) classification, which is one of representative machine learning techniques, in order to excellent superior bending characteristics. The stress triaxiality at reference points is obtained by three-point bending analysis of the Al beam with training data categorizing the type of external loading, i.e., tension, compression or shear. Loading types of each plane of the beam were classified by independent plane scheme as well as total beam scheme. Also, loading fidelities were calibrated for each case with the variation of hyper-parameters. Most effective stacking sequences were mapped into the PIC beam based on the k-NN classification model with the highest loading fidelity. FE analysis result shows the PIC beam has superior external loading resistance and energy absorption compared to conventional beam.

• Korean Journal of Remote Sensing
• /
• v.38 no.6_1
• /
• pp.1385-1394
• /
• 2022

This study was to analyze the change in albedo by level-2 land cover map for 20 years(2002-2021) using MODerate resolution Imaging Spectroradiometer (MODIS) data. Also, the difference from the MODIS data was analyzed using the 10-year (2012-2021) data of Visible Infrared Imaging Radiometer Suite (VIIRS). For the albedo data of MODIS and VIIRS, daily albedo data, MCD43A3 and VNP43IA, of 500 m spatial resolution of sinusoidal tile grid produced by Bidirectional Reflectance Distribution Function (BRDF) model were prepared for the South Korea range. Reprojection was performed using the code written based on Python 3.9, and the nearest neighbor was applied as the resampling method. White sky albedo and black sky albedo of shortwave were used for analysis. As a result of 20-year albedo analysis using MODIS data, the albedo tends to rise in all land use. Compared to the 2000s (2002-2011), the average albedo of the 2010s (2012-2021) showed the most significant increase of 0.0027 in the forest area, followed by the grass increase of 0.0024. As a result of comparing the albedo of VIIRS and MODIS, it was found that the albedo of VIIRS was larger from 0.001 to 0.1, which was considered to be due to differences in the surface reflectivity according to the time of image capture and sensor characteristics.

• Korean Journal of Remote Sensing
• /
• v.31 no.5
• /
• pp.385-394
• /
• 2015

Pine wilt disease has greatly damaged pine forests not only in East Asia including South Korea and China, but also in European region. The damage caused by pine wood nematode (Bursaphelenchus xylophilus) is expressed in bundles within stands and rapidly spreading, however, present field survey methods have limitations to detecting damaged trees at regional level. This study extracted the damaged trees by pine wilt disease using time series hyperspectral aerial photographs, and analyzed their distribution characteristics. Hyperspectral aerial photographs of 1 meter spatial resolution were obtained in June, September, and October. Damaged trees by pine wilt disease were extracted using Normalized Difference Vegetation Index (NDVI) and Vegetation Index green (VIgreen) of the September photograph. Among extracted damaged trees, dead trees with leaves and without leaves were classified, and the spectral reflectance values from the photographs obtained in June, September, and October were compared to extract new outbreaks in September and October. Based on the time series dispersion of extracted damaged trees, nearest neighbor analysis was conducted to analyze distribution characteristics of the damaged trees within the region where hyperspectral aerial photographs were acquired. As a result, 2,262 damaged trees were extracted in the study area, and 604 dead trees (dead trees in last year) with leaves in relation to the damaged time and 300 and 101 newly damaged trees in September and October were classified. The result of nearest neighbor analysis using the data shows that aggregated distribution was the dominant pattern both previous and current year in the study area. Also, 80% of the damaged trees in current year were found within 60 m of dead trees in previous year.