• Korean Journal of Remote Sensing
• /
• v.31 no.2
• /
• pp.51-64
• /
• 2015

We improved the MODerate resolution Imaging Spectroradiometer (MODIS) land cover map over the Asia-Oceania region through the reclassification of the misclassified pixels. The misclassified pixels are defined where the number of land cover types are greater than 3 from the 12 years of MODIS land cover map. The ratio of misclassified pixels in this region amounts to 17.53%. The MODIS Normalized Difference Vegetation Index (NDVI) time series over the correctly classified pixels showed that continuous variation with time without noises. However, there are so many unreasonable fluctuations in the NDVI time series for the misclassified pixels. To improve the quality of input data for the reclassification, we corrected the MODIS NDVI using Correction based on Spatial and Temporal Continuity (CSaTC) developed by Cho and Suh (2013). Iterative Self-Organizing Data Analysis (ISODATA) was used for the clustering of NDVI data over the misclassified pixels and land cover types was determined based on the seasonal variation pattern of NDVI. The final land cover map was generated through the merging of correctly classified MODIS land cover map and reclassified land cover map. The validation results using the 138 ground truth data showed that the overall accuracy of classification is improved from 68% of original MODIS land cover map to 74% of reclassified land cover map.

• 한국약용작물학회:학술대회논문집
• /
• 2007.05a
• /
• pp.49-50
• /
• 2007

• Proceedings of the Microbiological Society of Korea Conference
• /
• 2005.05a
• /
• pp.195.3-195
• /
• 2005

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 2005.05a
• /
• pp.260-267
• /
• 2005

자기조직화지도(Self Organizing Map, SOM)는 비지도 신경망으로서 고차원의 입력공간을 위상적관계를 유지시키면서 저차원으로 사영 시킬 수 있는 특징을 갖고 있다. SOM은 패턴인 식과 자료압축/재생 등 여러 분야에서 유용하게 활용될 수 있으며 특히 고차원 자료의 시각화 방법으로 많은 관심을 받고 있다. 본 연구에서는 SOM의 quantization error를 줄이기 위한 목적으로 인공데이터를 생성시켜 학습에 이용하는 방법을 제시한다. 이는 특히 데이터가 부족한 상황에서 SOM을 학습시켜야 할 때 유용하게 적용될 수 있을 것으로 기대된다.

• Proceedings of the Korean Statistical Society Conference
• /
• 2004.11a
• /
• pp.219-225
• /
• 2004

코호넨(T. Kohonen)의 자기조직화지도(Self-Organizing Map; SOM)은 저차원 그리드 공간에 고차원 다변량 자료를 축약하여 시각적으로 나타내는 비지도 학습법의 일종으로 최근 들어 통계 분석자들이 많은 관심을 가지고 있는 분야이다. 그러나 SOM은 개체공간의 연속형으로 표현되는 개체를 저차원 그리드공간에 승자노드에 비연속적으로 표현한다는 단점을 지니고 있다. 본 논문에서는 SOM을 통계적 목적으로 사용하기 위해 요구되는 그리드공간에 개체를 연속적으로 표현하는 방법들을 제안하고 활용 예를 제시하고자 한다

• Journal of the Korean Institute of Telematics and Electronics
• /
• v.26 no.11
• /
• pp.1857-1866
• /
• 1989

In this paper, an algorithm to update a codebook using a neural network in consecutive images, is proposed. With the Kohonen's self-organizing feature map, we adopt the iterative technique to update a centroid of each cluster instead of the unsupervised learning technique. Because the performance of this neural model is comparable to that of the LBG algorithm, it is possible to update the codebooks of consecutive frames sequentially in TV and to realize the hardwadre on the real-time implementation basis.

• Proceedings of the KIEE Conference
• /
• 2001.07c
• /
• pp.1484-1486
• /
• 2001

In this study, The underwater object recognition using ultrasonic sensor fabricated with porous PZT-Polymer 3-3 type composites and invariant moment vector and SOFM(Self Organizing Feature Map) neural networks are presented. The recognition rates for the training data and the testing data were 98% and 94%, respectively.

• Proceedings of the Korean Society for Quality Management Conference
• /
• 2004.04a
• /
• pp.573-575
• /
• 2004

This study presents a new customer segmentation method based on features that can predict the customer's buying behavior. In this method, we consider all variables that can affect the customer's buying behavior including demographics, psychographics, technographics, transaction pattern-related variables, etc. We define several features which are the combination of variables with the interaction effect by using C5.0, use SOM (Self-Organizing Map) neural networks in odor to extract the feature's patterns and classify, and then make features' rules using C5.0 far the prediction of customer buying behavior

• Proceedings of the Korean Society for Quality Management Conference
• /
• 2004.04a
• /
• pp.148-151
• /
• 2004

This study presents a new intelligent yield management methodology which can forecast the yield level of a production unit based on features' behaviors. In this proposed methodology, we identify the existing features using C5.0 that are combination of nodes (i.e., variables) in the decision tree generated by C5.0, use SOM(Self-Organizing Map) neural networks in oder to extract the feature's patterns and classify, and then make features' control rules using C5.0.

• Proceedings of The Korean Society of Agricultural and Forest Meteorology Conference
• /
• 2005.09a
• /
• pp.74-77
• /
• 2005