• Journal of Environmental Science International
• /
• v.15 no.4
• /
• pp.373-378
• /
• 2006

The western coast of South Korea is famous for its large and broad tidal lands. Nevertheless, land reclamation, which has been conducted on a large scale, such as Sihwa embankment construction project has accelerated coastal environmental changes in the embankment inland. For monitoring of environmental change, vegetation change detecting of the embankment inland were carried out and field survey data compared with Landsat TM, ETM+, IKONOS, and EOC satellite remotely sensed data. In order to utilize multi-temporal remotely sensed images effectively, all data set with pixel size were analyzed by same geometric correction method. To detect the tidal land vegetation change, the spectral characteristics and spatial resolution of Landsat TM and ETM+ images were analyzed by SMA(spectral mixture analysis). We obtained the 78.96% classification accuracy and Kappa index 0.2376 using March 2000 Landsat data. The SMA(spectral mixture analysis) results were considered with comparing of vegetation seasonal change detection method.

• Journal of Korean Society for Quality Management
• /
• v.23 no.3
• /
• pp.69-83
• /
• 1995

In a large number of literature on of inspection tasks, one of the most consistent findings is the existence of large and consistent differences among inspectors. It is possible that the individual difference is described by the difference of cognitive skills, because cognitive skills are required more than manual skills in inspection tasks. Therefore, a set of cognitive factors in human information processing may underly human performance in inspection tasks. In this study, a cognitive skill was described as the relative importance of the cognitive factors involved. A hierarchical task analysis and a fuzzy hierarchical analysis were used to represent how the importance of cognitive factors contribute to inspection performance. An experiment was conducted using the computer simulations of PCB inspection tasks. The results revealed that the subject group with better performance showed the importance weights of cognitive factors in the following rank; (attention, perception, judgement, classification, recognition)<(detection)$\ll$(memory). The results of the experiment can serve as a selection criterion for efficient inspection performance and the information of skilled learning for an inspection training program. The usefullness of a hierarchical task analysis and a fuzzy hierarchical task analysis for the analysis of cognitive tasks are also confirmed.

• Journal of KIISE:Software and Applications
• /
• v.36 no.8
• /
• pp.633-641
• /
• 2009

In this paper, we proposed a new pattern classifier which can be incrementally learned, be added new class in learning time, and handle with analog data. Proposed pattern classifier has hierarchical structure and the classification rate is improved by using different metric for each levels. Proposed model is based on the Gaussian ARTMAP which is an artificial neural network model for the pattern classification. We hierarchically constructed the Gaussian ARTMAP and proposed the Principal Component Emphasis(P.C.E) method to be learned different features in each levels. And we defined new metric based on the P.C.E. P.C.E is a method that discards dimensions whose variation are small, that represents common attributes in the class. And remains dimensions whose variation are large. In the learning process, if input pattern is misclassified, P.C.E are performed and the modified pattern is learned in sub network. Experimental results indicate that Hierarchical Gaussian ARTMAP yield better classification result than the other pattern recognition algorithms on variable data set including real applicable problem.

• Journal of the Korean Society for information Management
• /
• v.36 no.4
• /
• pp.83-105
• /
• 2019

This study aims to suggest an effective method for the automatic classification of keywords with similar patterns by calculating pattern similarity of temporal data. For this, large scale news on the Web were collected and time series data composed of 120 time segments were built. To make training data set for the performance test of the proposed model, 440 representative keywords were manually classified according to 8 types of trend. This study introduces a Dynamic Time Warping(DTW) method which have been commonly used in the field of time series analytics, and proposes an application model, MA-DTW based on a Moving Average(MA) method which gives a good explanation on a tendency of trend curve. As a result of the automatic classification by a k-Nearest Neighbor(kNN) algorithm, Euclidean Distance(ED) and DTW showed 48.2% and 66.6% of maximum micro-averaged F1 score respectively, whereas the proposed model represented 74.3% of the best micro-averaged F1 score. In all respect of the comprehensive experiments, the suggested model outperformed the methods of ED and DTW.

• Journal of the Ergonomics Society of Korea
• /
• v.28 no.1
• /
• pp.21-27
• /
• 2009

The purpose of this research is to understand the physiological characteristics of muscular men between the ages of 20 and 34 years who are distinct from the general population due to their muscular development, and to categorize them according to upper body somatotypes. This research was conducted in order to provide basic data necessary for developing clothing products for muscular men. The research method and results were as follows: 1. The study carried out factor analysis with the body measuring value of 168 muscular men according to the body classification method of Sheldon and Heath-Carter. The study materialized muscular men's lower body types statistically by carrying out cluster analysis, regarding scores of each factor extracted from the factor analysis as an independent variable. The study also carried out discriminant analysis with the results of cluster analysis classified so that morphological characters of each type were remarkably distinguished. 2. As the results of factor analysis, the study set up number of factors as three. Factor 1 occupied 38.149% of the total variables as a size factor of the lower body. Factor 2 occupied 20.417% of the total variables as a height and length factor of the lower body. Factor 3 occupied 8.466% of the total variables as a length factor of the hip. 3. The study classified the lower body type into three types and the characteristics by each type were as follows. Type 1 was a group with the best developed muscle in the lower of the body, considering that a size of their lower bodies was the largest. Type 2 was well-balanced muscular males though a size of the lower body was smaller than other types. This type didn't have fatness of the abdomen and large hips. Type 3 was a body type that the length from the waist to the hip was long. 4. As the results of carrying out discriminant analysis to distinguish muscular men's lower body types, the discriminant accuracy was 86.3% over all in the lower bodies.

• Korean Journal of Remote Sensing
• /
• v.22 no.6
• /
• pp.613-619
• /
• 2006

This study proposed an unsupervised image classification through the dendrogram of agglomerative clustering as a higher stage of image segmentation in image processing. The proposed algorithm is a hierarchical clustering which includes searching a set of MCSNP (Mutual Closest Spectral Neighbor Pairs) based on the data structures of RAG(Regional Adjacency Graph) defined on spectral space and Min-Heap. It also employes a multi-window system in spectral space to define the spectral adjacency. RAG is updated for the change due to merging using RNV (Regional Neighbor Vector). The proposed algorithm provides a dendrogram which is a graphical representation of data. The hierarchical relationship in clustering can be easily interpreted in the dendrogram. In this study, the proposed algorithm has been extensively evaluated using simulated images and applied to very large QuickBird imagery acquired over an area of Korean Peninsula. The results have shown it potentiality for the application of remotely-sensed imagery.

• Neurospine
• /
• v.15 no.4
• /
• pp.329-337
• /
• 2018

Objective: Machine learning algorithms excel at leveraging big data to identify complex patterns that can be used to aid in clinical decision-making. The objective of this study is to demonstrate the performance of machine learning models in predicting postoperative complications following anterior cervical discectomy and fusion (ACDF). Methods: Artificial neural network (ANN), logistic regression (LR), support vector machine (SVM), and random forest decision tree (RF) models were trained on a multicenter data set of patients undergoing ACDF to predict surgical complications based on readily available patient data. Following training, these models were compared to the predictive capability of American Society of Anesthesiologists (ASA) physical status classification. Results: A total of 20,879 patients were identified as having undergone ACDF. Following exclusion criteria, patients were divided into 14,615 patients for training and 6,264 for testing data sets. ANN and LR consistently outperformed ASA physical status classification in predicting every complication (p < 0.05). The ANN outperformed LR in predicting venous thromboembolism, wound complication, and mortality (p < 0.05). The SVM and RF models were no better than random chance at predicting any of the postoperative complications (p < 0.05). Conclusion: ANN and LR algorithms outperform ASA physical status classification for predicting individual postoperative complications. Additionally, neural networks have greater sensitivity than LR when predicting mortality and wound complications. With the growing size of medical data, the training of machine learning on these large datasets promises to improve risk prognostication, with the ability of continuously learning making them excellent tools in complex clinical scenarios.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.23 no.5
• /
• pp.533-539
• /
• 2019

This study proposes a malware classification model that can handle arbitrary length input data using the Microsoft Malware Classification Challenge dataset. We are based on imaging existing data from malware. The proposed model generates a lot of images when malware data is large, and generates a small image of small data. The generated image is learned as time series data by Dynamic RNN. The output value of the RNN is classified into malware by using only the highest weighted output by applying the Attention technique, and learning the RNN output value by Residual CNN again. Experiments on the proposed model showed a Micro-average F1 score of 92% in the validation data set. Experimental results show that the performance of a model capable of learning and classifying arbitrary length data can be verified without special feature extraction and dimension reduction.

• Journal of the Korean Geotechnical Society
• /
• v.26 no.7
• /
• pp.25-36
• /
• 2010

Tertiary unconsolidated mudstones spread throughout the eastern coast area. The demand for high quality filling materials in these areas is increasing due to harbors and large-scale residential land development. Rock produced in-situ or near site has been used as road subbase construction or reclamation materials for economical reason, but it is hard to decide appropriateness of quality specification because of its characteristics. The test results showed that unconsolidated rocks are diversely considered according to a different method of the applied geotechnical investigation. Therefore, the site of tertiary unconsolidated mudstones, the classification of rock and evaluation of rock properties that must be evaluated by objective criteria and apply a different set of criteria are needed. In addition, the environmental impact must be considered due to acid mine drainage.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.1
• /
• pp.1-8
• /
• 2019

Among the methods for extracting the most appropriate information from a large amount of log data, there is a method using inductive inference. In this paper, we use SVM (Support Vector Machine), which is an excellent classification method for inductive inference, in order to determine the ranking of intrusion logs in digital forensic analysis. For this purpose, the logs of the training log set are classified into intrusion logs and normal logs. The associated words are extracted from each classified set to generate a related word dictionary, and each log is expressed as a vector based on the generated dictionary. Next, the logs are learned using the SVM. We classify test logs into normal logs and intrusion logs by using the log set extracted through learning. Finally, the recommendation orders of intrusion logs are determined to recommend intrusion logs to the forensic analyst.