• Korean Journal of Remote Sensing
• /
• v.26 no.5
• /
• pp.477-487
• /
• 2010

In North Korea, forests were intensively degraded by forest land reclamation for food production and firewood collection since the mid-1970s. These degraded forests have to be certainly recovered for economic support, environmental protection and disaster prevention. In order to provide detailed land cover information of forest recovery project (A/R CDM), this study was focused to develop an improved classification method for degraded forest using 2.5m SPOT-5 pan-sharpened image. The degraded forest of North Korea shows various different types of texture. This study used GLCM texture bands of segmented image with spectral bands during forest cover classification. When scale factor 40/shape factor 0.3 was used as a parameter set to generate segment image, segment image was generated on suitable segment scale that could classify types of degraded forest. Forest land cover types were classified with an optimum band combination of Band1, Band2, band3, GLCM dissimilarity (band2), GLCM homogeneity (band2) and GLCM standard deviation (band3). Segment-based classification method using spectral bands and texture bands reached an 80.4% overall accuracy, but the method using only spectral bands yielded an 70.3% overall accuracy. As using spectral and texture bands, a classification accuracy of stocked forest and unstocked forest showed an increase of 23~25%. In this research, SPOT-5 pan-sharpened high-resolution satellite image could provide a very useful information for classifying the forest cover of North Korea in which field data collection was not available for ground truth data and verification directly. And segment-based classification method using texture information improved classification accuracy of degraded forest.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.3
• /
• pp.265-276
• /
• 2019

In our previous study, the LeNet3 model successfully classified images from the transverse surfaces of five Korean softwood species (cedar, cypress, Korean pine, Korean red pine, and larch). However, a practical limitation exists in our system stemming from the nature of the training images obtained from the transverse plane of the wood species. In real-world applications, it is necessary to utilize images from the longitudinal surfaces of lumber. Thus, we improved our model by training it with images from the longitudinal and transverse surfaces of lumber. Because the longitudinal surface has complex but less distinguishable features than the transverse surface, the classification performance of the LeNet3 model decreases when we include images from the longitudinal surfaces of the five Korean softwood species. To remedy this situation, we adopt ensemble methods that can enhance the classification performance. Herein, we investigated the use of ensemble models from the LeNet and MiniVGGNet models to automatically classify the transverse and longitudinal surfaces of the five Korean softwoods. Experimentally, the best classification performance was achieved via an ensemble model comprising the LeNet2, LeNet3, and MiniVGGNet4 models trained using input images of $128{\times}128{\times}3pixels$ via the averaging method. The ensemble model showed an F1 score greater than 0.98. The classification performance for the longitudinal surfaces of Korean pine and Korean red pine was significantly improved by the ensemble model compared to individual convolutional neural network models such as LeNet3.

• The Korean Journal of Ecology
• /
• v.17 no.4
• /
• pp.471-484
• /
• 1994

The forest vegetation types and their structural characteristics in Mt. $Mud\v{u}ng$ were investigated by classification method and ordination method. The forest was classified into 7 communities by ristic composition table: Quercus monogolica community, Q. serrata community, Q.acutissima community, Q.variabilis community, Q.dentata community, Pinus densiflora community and Frainus mandshurica community. Considering the moisture gradient, two kinds of distributuin pattern were shown as follows; F. mandshurica, Q. acturissima, Platycarya strobilacea and Staphylea bumalda were distribute at moist habitats, while Q. monogolica, P. densiflora and Q.variabilis at dry habitats. In continuum analysis, each population occupied different distribution area but it was continuously overlapped. On the successional trends of tree species, it is postulated that Q. mongolica species might dominate the altitudinal zone over 700m.

• Industrial Engineering and Management Systems
• /
• v.13 no.4
• /
• pp.421-431
• /
• 2014

The market basket data in the form of a binary user-item matrix or a binary item-user matrix can be modelled as a binary classification problem. The binary logistic regression approach tackles the binary classification problem, where principal components are predictor variables. If users or items are sparse in the training data, the binary classification problem can be considered as a cold-start problem. The binary logistic regression approach may not function appropriately if the principal components are inefficient for the cold-start problem. Assuming that the market basket data can also be considered as a special regression problem whose response is either 0 or 1, we propose three supervised learning approaches: random forest regression, random forest classification, and elastic net to tackle the cold-start problem, comparing the performance in a variety of experimental settings. The experimental results show that the proposed supervised learning approaches outperform the conventional approaches.

• Journal of Korean Society of Rural Planning
• /
• v.26 no.1
• /
• pp.101-112
• /
• 2020

Recently, public awareness regarding mountain villages' landscapes is increasing. Thus, this study aimed to provide standards for conservation, management and creation of mountain village landscape by characterizing and classifying those exist. 286 mountain villages' data were collected and 19 variables - extracted from GIS spatial information and statistic data of mountain villages, chosen as right sources according to former studies - were utilized to conduct factor and cluster analysis. As a result of the factor analysis, 7 characteristics of the mountain villages' landscapes were defined - 'Location', 'Cultivation', 'Ecology·Nature', 'Tourism', 'Residence', 'Recreation'. The K-means cluster analysis categorized the mountain villages' landscapes into four types - 'Residential', 'Touristic', 'General', 'Environmentally protected'. The classification was examined to be appropriate by field assessment, and basic guidelines of mountain village landscape management were set. The results of this study are expected to be utilized planning and implementing regarding mountain village landscape in the future.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.2
• /
• pp.229-238
• /
• 2019

Various wood defects occur during tree growing or wood processing. Thus, to use wood practically, it is necessary to objectively assess their quality based on the usage requirement by accurately classifying their defects. However, manual visual grading and species classification may result in differences due to subjective decisions; therefore, computer-vision-based image analysis is required for the objective evaluation of wood quality and the speeding up of wood production. In this study, the SIFT+k-NN and CNN models were used to implement a model that automatically classifies knots and analyze its accuracy. Toward this end, a total of 1,172 knot images in various shapes from five domestic conifers were used for learning and validation. For the SIFT+k-NN model, SIFT technology was used to extract properties from the knot images and k-NN was used for the classification, resulting in the classification with an accuracy of up to 60.53% when k-index was 17. The CNN model comprised 8 convolution layers and 3 hidden layers, and its maximum accuracy was 88.09% after 1205 epoch, which was higher than that of the SIFT+k-NN model. Moreover, if there is a large difference in the number of images by knot types, the SIFT+k-NN tended to show a learning biased toward the knot type with a higher number of images, whereas the CNN model did not show a drastic bias regardless of the difference in the number of images. Therefore, the CNN model showed better performance in knot classification. It is determined that the wood knot classification by the CNN model will show a sufficient accuracy in its practical applicability.

• Journal of the Korean Wood Science and Technology
• /
• v.47 no.4
• /
• pp.509-518
• /
• 2019

This study analyzed the effect of organic solvent extractives on the classification of wood species via near-infrared spectroscopy (NIR). In our previous research, five species of Korean softwood were classified into three groups (i.e., Cryptomeria japonica (cedar)/Chamaecyparis obtuse (cypress), Pinus densiflora (red pine)/Pinus koraiensis (Korean pine), and Larix kaempferi (Larch)) using an NIR-based principal component analysis method. Similar tendencies of extractive distribution were observed among the three groups in that study. Therefore, in this study, we qualitatively analyzed extractives extracted by an organic solvent and analyzed the NIR spectra in terms of the extractives' chemical structure and band assignment to determine their effect in more detail. Cedar/cypress showed a similar NIR spectra patterns by removing the extractives at 1695, 1724, and 2291 nm. D-pinitol, which was detected in cedar, contributed to that wavelength. Red pine/Korean pine showed spectra changes at 1616, 1695, 1681, 1705, 1724, 1731, 1765, 1780, and 2300 nm. Diterpenoids and fatty acid, which have a carboxylic group and an aliphatic double bond, contributed to that wavelength. Larch showed a catechin peak in gas chromatography and mass spectroscopy analysis, but it exhibited very small NIR spectra changes. The aromatic bond in larch seemed to have low sensitivity because of the 1st overtone of the O-H bond of the sawdust cellulose. The three groups sorted via NIR spectroscopy in the previous research showed quite different compositions of extractives, in accordance with the NIR band assignment. Thus, organic solvent extractives are expected to affect the classification of wood species using NIR spectroscopy.

• Journal of the Korean Society for information Management
• /
• v.36 no.2
• /
• pp.57-77
• /
• 2019

Random Forest (RF), a representative ensemble technique, was applied to automatic classification of journal articles in the field of library and information science. Especially, I performed various experiments on the main factors such as tree number, feature selection, and learning set size in terms of classification performance that automatically assigns class labels to domestic journals. Through this, I explored ways to optimize the performance of random forests (RF) for imbalanced datasets in real environments. Consequently, for the automatic classification of domestic journal articles, Random Forest (RF) can be expected to have the best classification performance when using tree number interval 100~1000(C), small feature set (10%) based on chi-square statistic (CHI), and most learning sets (9-10 years).

• Journal of Forest and Environmental Science
• /
• v.36 no.3
• /
• pp.199-206
• /
• 2020

Satchari National Park is one of the most biodiverse forest in Bangladesh and home of many endangered flora and fauna. 206 tons of CO₂ per hectare is sequestrated in this national park every year which helps to mitigate climate issues. As people living near the area are dependent on this forest, degradation has become a regular phenomenon destroying the forest biodiversity by altering its forest cover. So, it is important to map land cover quickly and accurately for the sustainable management of Satchari National Park. The main objective of this study was to obtain information on land cover change using remote sensing data. Combination of unsupervised NDVI classification and supervised classification using maximum likelihood is followed in this study to find out land cover map. The analysis showed that the land cover is gradually converting from one land use type to another. Dense forest becoming degraded forest or bare land. Although it was slowed down by the establishment of 'National Park' on the study site, forecasting shows that it is not enough to mitigate forest degradation. Legal steps and proper management strategies should be taken to mitigate causes of degradation such as illegal felling.

• Journal of Information Processing Systems
• /
• v.14 no.5
• /
• pp.1167-1175
• /
• 2018

Microarray data plays an essential role in diagnosing and detecting cancer. Microarray analysis allows the examination of levels of gene expression in specific cell samples, where thousands of genes can be analyzed simultaneously. However, microarray data have very little sample data and high data dimensionality. Therefore, to classify microarray data, a dimensional reduction process is required. Dimensional reduction can eliminate redundancy of data; thus, features used in classification are features that only have a high correlation with their class. There are two types of dimensional reduction, namely feature selection and feature extraction. In this paper, we used k-means algorithm as the clustering approach for feature selection. The proposed approach can be used to categorize features that have the same characteristics in one cluster, so that redundancy in microarray data is removed. The result of clustering is ranked using the Relief algorithm such that the best scoring element for each cluster is obtained. All best elements of each cluster are selected and used as features in the classification process. Next, the Random Forest algorithm is used. Based on the simulation, the accuracy of the proposed approach for each dataset, namely Colon, Lung Cancer, and Prostate Tumor, achieved 85.87%, 98.9%, and 89% accuracy, respectively. The accuracy of the proposed approach is therefore higher than the approach using Random Forest without clustering.