• Korean Journal of Remote Sensing
• /
• v.27 no.4
• /
• pp.457-466
• /
• 2011

The objectives of this study are to produce level 3 type LULC map and analysis of phenological features of North Korea, ISODATA clustering of the 88scenes of MVC of MODIS NDVI in 2008 and 8scenes in 2009 was carried out. Analysis of phenological phases based mapping method was conducted, In level 2 type map, the confusion matrix was summarized and Kappa coefficient was calculated. Total of 27 typical habitat types that represent the dominant species or vegetation density that cover land surface of North Korea in 2008 were made. The total of 27 classes includes the 17 forest biotopes, 7 different croplands, 2 built up types and one water body. Dormancy phase of winter (${\sigma}^2$ = 0.348) and green up phase in spring (${\sigma}^2$ = 0.347) displays phenological dynamics when much vegetation growth changes take place. Overall accuracy is (851/955) 85.85% and Kappa coefficient is 0.84. Phenological phase based mapping method was possible to minimize classification error when analyzing the inaccessible land of North Korea.

• Journal of the Korean Society of Radiology
• /
• v.12 no.2
• /
• pp.139-148
• /
• 2018

Assessment of NPP(Nuclear Power Plant) decommissioning cost is very important for safe decommissioning of nuclear power plants. In the United States, which has the most NPP decommissioning experience, the cost evaluation study has been conducted since the 1970s in order to decommissioning nuclear facilities. The US NRC has conducted studies on decommissioning technology, safety and cost for a variety of reactor type and nuclear installations. In the total decommissioning costs, the end of operation licenses accounted for the largest portion, followed by spent fuel management and site restoration. In case of immediate decommissioning, spent fuel management cost increased compared to delayed decommissioning, and delayed deocmmissioning increased the cost of terminating the operation license. However, in general, delayed decommissioning does not show any significant benefit as compared with immediate decommissioning. It is necessary to consider the evaluation according to the site conditions when evaluating the cost of decommissioning domestic nuclear power plants. Also, in Korea, IAEA recommendations were applied to reorganize the radioactive waste classification system. Therefore, it is necessary to develop a method to appropriately use the decommissioning data of the preceding US Nuclear Power Plant in the new classification system when estimating the amount of radioactive waste generated during decommissioning. In particular, the establishment of the evaluation methodology for the waste to be disposed of will be an important factor in securing the accuracy of the decommissioning cost. In addition, it is necessary to construct information data that can be applied to facility characteristics and work characteristics in order to evaluate the cost of demolition of domestic nuclear power plants.

• 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.

• Journal of Internet Computing and Services
• /
• v.18 no.6
• /
• pp.35-46
• /
• 2017

Recently, attackers using malicious code in cyber security have been increased by attaching malicious code to a mail and inducing the user to execute it. Especially, it is dangerous because it is easy to execute by attaching a document type file. The author analysis is a research area that is being studied in NLP (Neutral Language Process) and text mining, and it studies methods of analyzing authors by analyzing text sentences, texts, and documents in a specific language. In case of attack mail, it is created by the attacker. Therefore, by analyzing the contents of the mail and the attached document file and identifying the corresponding author, it is possible to discover more distinctive features from the normal mail and improve the detection accuracy. In this pager, we proposed IADA2(Intelligent Attack mail Detection based on Authorship Analysis) model for attack mail detection. The feature vector that can classify and detect attack mail from the features used in the existing machine learning based spam detection model and the features used in the author analysis of the document and the IADA2 detection model. We have improved the detection models of attack mails by simply detecting term features and extracted features that reflect the sequence characteristics of words by applying n-grams. Result of experiment show that the proposed method improves performance according to feature combinations, feature selection techniques, and appropriate models.

• Journal of the Korean Society of Surveying, Geodesy, Photogrammetry and Cartography
• /
• v.8 no.2
• /
• pp.45-51
• /
• 1990

DEM must have a high accuracy against the actual topographic model. A model which can compute heights responding to random plane position by using of the topographic data and interpolation must be constructed. Interpolation affected by the accuraccy of the observations included noise, which affected by the slop and curvature weight. Data smoothing is a method to reduce the noise. Average declination and area ratio are variable which result similarity in according to slope. But in local area, area ratio well shows a local change. This study try to classify the terrain by the declination to analysis the effects of the declination and curvature weights, and then to represent the most probable model. The result are following : In terrain classification by the slop, p16 and p24 were fitted in the plane surface fit p16 and S in the varying surface, and S and p24 in the irregular surface in classification by curvature, p24 and S were fitted in the plane or varying surface, and p16 in the irregular surface In case of hybrid, p16, p24 and S are fitted in the plane, varying and irregular surface respectively. Smoothing is the most effective in case of slope of 50 persentage and of curvature weight of 0.0015.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.22 no.2
• /
• pp.135-140
• /
• 2012

The mirror neuron system in the cerebrum, which are handled by visual information-based imitative learning. When we observe the observer's range of mirror neuron system, we can assume intention of performance through progress of neural activation as specific range, in include of partially hidden range. It is goal of our paper that imitative learning is applied to 3D vision-based intelligent system. We have experiment as stereo camera-based restoration about acquired 3D image our previous research Using Optical flow, unscented Kalman filter. At this point, 3D input image is sequential continuous image as including of partially hidden range. We used Hidden Markov Model to perform the intention recognition about performance as result of restoration-based hidden range. The dynamic inference function about sequential input data have compatible properties such as hand gesture recognition include of hidden range. In this paper, for proposed intention recognition, we already had a simulation about object outline and feature extraction in the previous research, we generated temporal continuous feature vector about feature extraction and when we apply to Hidden Markov Model, make a result of simulation about hand gesture classification according to intention pattern. We got the result of hand gesture classification as value of posterior probability, and proved the accuracy outstandingness through the result.

• The KIPS Transactions:PartB
• /
• v.13B no.7 s.110
• /
• pp.643-652
• /
• 2006

Decision trees are mainly used for the classification and prediction in data mining. The distribution of spatial data and relationships with their neighborhoods are very important when conducting classification for spatial data mining in the real world. Spatial decision trees in previous works have been designed for reflecting spatial data characteristic by rating Euclidean distance. But it only explains the distance of objects in spatial dimension so that it is hard to represent the distribution of spatial data and their relationships. This paper proposes a decision tree based on spatial entropy that represents the distribution of spatial data with the dispersion and dissimilarity. The dispersion presents the distribution of spatial objects within the belonged class. And dissimilarity indicates the distribution and its relationship with other classes. The rate of dispersion by dissimilarity presents that how related spatial distribution and classified data with non-spatial attributes we. Our experiment evaluates accuracy and building time of a decision tree as compared to previous methods. We achieve an improvement in performance by about 18%, 11%, respectively.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.20 no.2
• /
• pp.165-172
• /
• 2010

In clinical data minig, choosing the optimal subset of features is such important, not only to reduce the computational complexity but also to improve the usefulness of the model constructed from the given data. Moreover the threshold values (i.e., cut-off points) of selected features are used in a clinical decision criteria of experts for differential diagnosis of diseases. In this paper, we propose a fuzzy discretization approach, which is evaluated by measuring the degree of separation of redundant attribute values in overlapping region, based on spatial distribution of data with continuous attributes. The weighted average of the redundant attribute values is then used to determine the threshold value for each feature and rough set theory is utilized to select a subset of relevant features from the overall features. To verify the validity of the proposed method, we compared experimental results, which applied to classification problem using 668 patients with a chief complaint of dyspnea, based on three discretization methods (i.e., equal-width, equal-frequency, and entropy-based) and proposed discretization method. From the experimental results, we confirm that the discretization methods with fuzzy partition give better results in two evaluation measures, average classification accuracy and G-mean, than those with hard partition.

• The Korean Journal of Applied Statistics
• /
• v.30 no.1
• /
• pp.25-39
• /
• 2017

Over 5 million people participate in cycle racing betting and its revenue is more than 2 trillion won. This study predicts the ranking of cycle racing using various statistical analyses and identifies important variables which have influence on ranking. We propose competitive ranking prediction models using various classification and regression methods. Our model can predict rankings with low misclassification rates most of the time. We found that the ranking increases as the grade of a racer decreases and as overall scores increase. Inversely, we can observe that the ranking decreases when the grade of a racer increases, race number four is given, and the ranking of the last race of a racer decreases. We also found that prediction accuracy can be improved when we use centered data per race instead of raw data. However, the real profit from the future data was not high when we applied our prediction model because our model can predict only low-return events well.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.22 no.5
• /
• pp.7-14
• /
• 2021

Tomato crops are highly affected by tomato diseases, and if not prevented, a disease can cause severe losses for the agricultural economy. Therefore, there is a need for a system that quickly and accurately diagnoses various tomato diseases. In this paper, we propose a system that classifies nine diseases as well as healthy tomato plants by applying various pretrained deep learning-based CNN models trained on an ImageNet dataset. The tomato leaf image dataset obtained from PlantVillage is provided as input to ResNet, Xception, and DenseNet, which have deep learning-based CNN architectures. The proposed models were constructed by adding a top-level classifier to the basic CNN model, and they were trained by applying a 5-fold cross-validation strategy. All three of the proposed models were trained in two stages: transfer learning (which freezes the layers of the basic CNN model and then trains only the top-level classifiers), and fine-tuned learning (which sets the learning rate to a very small number and trains after unfreezing basic CNN layers). SGD, RMSprop, and Adam were applied as optimization algorithms. The experimental results show that the DenseNet CNN model to which the RMSprop algorithm was applied output the best results, with 98.63% accuracy.