• Journal of the Speleological Society of Korea
• /
• no.93
• /
• pp.13-25
• /
• 2009

This study, which includes case studies that provide information of cave tour resources, considered a variety of selected variables of the internal and external parts of caves with the expanded factors of the academic classification in caves. It uses the cluster analysis, one of the multivariate analysis techniques, and applied the results for review. As a result, public caves can present multiple classification criteria according to the factors of the surrounding area's human environment. The result, classified by the region in public caves, is derived from this study.

• The Journal of the Acoustical Society of Korea
• /
• v.13 no.4
• /
• pp.5-11
• /
• 1994

In this paper, the ciassification of Korean character type using multi neural network and fuzzy inference based on block partition is studied. For the effective classification of a consonant and a vowel, block partition method which devide the region of a consonant and a vowel for each type in the character is proposed. And the partitioned block can be changed according to the each type adaptively. For the improvement of classification rate, the multi neural network with a whole and a part neural network is consisted, and the character type by using fuzzy inference is decided. To verify the validity of the proposed method, computer simulation is accomplished, and from the classification rate $92.6\%$, the effectivity of the method is confirmed.

• Journal of Computing Science and Engineering
• /
• v.10 no.4
• /
• pp.111-117
• /
• 2016

An accurate approach for diagnosis of attention deficit hyperactivity disorder (ADHD) is presented in this paper. The presented technique efficiently classifies three subtypes of ADHD (ADHD-C, ADHD-H, ADHD-I) and typically developing control (TDC) by using only structural magnetic resonance imaging (MRI). The research examines structural MRI of the hippocampus from the ADHD-200 database. Each available MRI has been processed by a region-of-interest (ROI) to build a set of features for further analysis. The presented ADHD diagnostic approach unifies feature selection and classification techniques. The feature selection technique based on the proposed binary-coded genetic algorithm searches for an optimal subset of features extracted from the hippocampus. The classification technique uses a chosen optimal subset of features for accurate classification of three subtypes of ADHD and TDC. In this study, the famous Extreme Learning Machine is used as a classification technique. Experimental results clearly indicate that the presented BCGA-ELM (binary-coded genetic algorithm coupled with Extreme Learning Machine) efficiently classifies TDC and three subtypes of ADHD and outperforms existing techniques.

• Proceedings of the Korea Institute of Fire Science and Engineering Conference
• /
• 1997.11a
• /
• pp.311-318
• /
• 1997

On April 27,1993, a forest fire occurred in Morito-area, Manba-city, Gunma-prefecture Japan. Under the prevailing strong winds, the fire spread and extended to the largest scale ever in Gunma-prefecture. The author chartered a helicopter on May 5, one week after the fire was extinguished, and took aerial photos of tile damaged area, and investigated the condition. of the fire through field survey and data collection. The burnt area extended. over about 100 hectares, and the damage amounted to about 190 million yen (about two million dollar). The fire occurred at a steep mountainous area and under strong winds, therefore, md and topography strongly facilitated the spreading, It is the purpose of this paper to report a damage investigation of the fire and to develop the forecasting method of forest fires based on the topographical analysis and spreading speed of fire. In the first place, I analyze the topographical structure of the regions which became the bject of this study with some topographical factors, and construct a land form classification ap. Secondly, I decide the dangerous condition of each region in the land form classification map according to the direction of the wind and spreading speed of f'kre. In the present paper, I try to forecast forest fires in Morito area, and the basic results for the forecasting method of forest fires were obtained with the topographical classification system and spreading speed of fire.

• Korean Journal of Remote Sensing
• /
• v.22 no.3
• /
• pp.199-209
• /
• 2006

The Global Land Cover 2000 (GLC 200) project, as a most recent issue, is to provide for the year 2000 a harmonized land cover database over the whole globe. The classifications were performed according to continental or regional scales by corresponding organization using the data of VEGETATION sensor onboard the SPOT4 Satellite. Even if the global land cover classification for Asia provided by Chiba University showed a good accuracy in whole Asian area, some problems were detected in Korean region. Therefore, the construction of new land cover database over Korea is strongly required using more recent data set. The present study focuses on the development of a new upgraded land cover map at 1 km resolution over Korea considering the widely used K-means clustering, which is one of unsupervised classification technique using distance function for land surface pattern classification, and the principal components transformation. It is based on data sets from the Earth observing system SPOT4/VEGETATION. Newly classified land cover was compared with GLC 2000 for Korean peninsula to access how well classification performed using confusion matrix.

• Korean Journal of Remote Sensing
• /
• v.17 no.1
• /
• pp.57-69
• /
• 2001

This study propose a image processing system of unsupervised analysis. This system integrates low-level segmentation and high-level classification. The segmentation and classification are conducted respectively with and without spatial constraints on merging by a hierarchical clustering procedure. The clustering utilizes the local mutually closest neighbors and multi-window operation of a pyramid-like structure. The proposed system has been evaluated using simulated images and applied for the LANDSATETM+ image collected from Youngin-Nungpyung area on the Korean Peninsula.

• The Journal of Asian Finance, Economics and Business
• /
• v.8 no.8
• /
• pp.443-451
• /
• 2021

The classification standards for hotels in Vietnam are different from many other hotel classification standards in the world. This study aims to analyze customer reviews on the TripAdvisor website to develop a new algorithm for hotel rating that is independent of Vietnam's hotel classification standards. This method can be applied to individual hotels, or hotels of a region or the whole country, while online booking sites only rate individual hotels. Data was crawled from TripAdvisor with 22,287 reviews of 5 cities in Vietnam. This study used a statistical model to analyze the review dataset and build an algorithm to rate hotels according to aspects or hotel overall. The results have less rating deviation when compared to the TripAdvisor system. This study also supports hotel managers to regularly update the status of their hotels using data from customer reviews, from which, managers can strategize long-term solutions to improve the quality of the hotel in all aspects and attract more travelers to Vietnam. Moreover, this method can be developed into an automatic system to rate hotels and update the status of service quality more quickly, thus, saving time and costs.

• Journal of KIISE:Information Networking
• /
• v.32 no.3
• /
• pp.318-326
• /
• 2005

This paper presents the image feature extraction method and the image classification technique to select the harmful image flowed from the Internet by grade of image contents such as harmlessness, sex-appealing, harmfulness (nude), serious harmfulness (adult) by the characteristic of the image. In this paper, we suggest skin area detection technique to recognize whether an input image is harmful or not. We also propose the ROI detection algorithm that establishes region of interest to reduce some noise and extracts harmful degree effectively and defines the characteristics in the ROI area inside. And this paper suggests the multiple-SVM training method that creates the image classification model to select as 4 types of class defined above. This paper presents the multiple-SVM classification algorithm that categorizes harmful grade of input data with suggested classification model. We suggest the skin likelihood image made of the shape information of the skin area image and the color information of the skin ratio image specially. And we propose the image feature vector to use in the characteristic category at a course of traininB resizing the skin likelihood image. Finally, this paper presents the performance evaluation of experiment result, and proves the suitability of grading image using image feature classification algorithm.

• Journal of KIISE:Software and Applications
• /
• v.31 no.12
• /
• pp.1684-1690
• /
• 2004

This paper presents a method for classifier selection that uses distribution information of the training samples in a small region surrounding a sample. The conventional DCS-LA(Dynamic Classifier Selection - Local Accuracy) selects a classifier dynamically by comparing the local accuracy of each classifier at the test time, which inevitably requires long classification time. On the other hand, in the proposed approach, the best classifier in a local region is stored in the FSA(Feature Space Attribute) table during the training time, and the test is done by just referring to the table. Therefore, this approach enables fast classification because classification is not needed during test. Two feature space attributes are used entropy and density of k training samples around each sample. Each sample in the feature space is mapped into a point in the attribute space made by two attributes. The attribute space is divided into regular rectangular cells in which the local accuracy of each classifier is appended. The cells with associated local accuracy comprise the FSA table. During test, when a test sample is applied, the cell to which the test sample belongs is determined first by calculating the two attributes, and then, the most accurate classifier is chosen from the FSA table. To show the effectiveness of the proposed algorithm, it is compared with the conventional DCS -LA using the Elena database. The experiments show that the accuracy of the proposed algorithm is almost same as DCS-LA, but the classification time is about four times faster than that.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.392-399
• /
• 2023

This paper proposes a deep learning model to determine the region and depth of cabbage cores for robotic automation of the cabbage core removal process during the kimchi manufacturing process. In addition, rather than predicting the depth of the measured cabbage, a model was presented that simultaneously detects and classifies the area by converting it into a discrete class. For deep learning model learning and verification, RGB images of the harvested cabbage 522 were obtained. The core region and depth labeling and data augmentation techniques from the acquired images was processed. MAP, IoU, acuity, sensitivity, specificity, and F1-score were selected to evaluate the performance of the proposed YOLO-v4 deep learning model-based cabbage core area detection and classification model. As a result, the mAP and IoU values were 0.97 and 0.91, respectively, and the acuity and F1-score values were 96.2% and 95.5% for depth classification, respectively. Through the results of this study, it was confirmed that the depth information of cabbage can be classified, and that it can be used in the development of a robot-automation system for the cabbage core removal process in the future.