• 한국환경복원기술학회지
• /
• 제12권5호
• /
• pp.101-109
• /
• 2009

There are increasing needs about creation and sustainable management of urban forest for environmental conservation and recreational service for citizen. However, it is difficult for local governments to create or manage urban forest in recreational or conservational way. The purpose of this study is to classify the urban forest types by considering its geographical feature, biological and sociological characteristics in order to suggest a guide to local governments about effective creation or management of urban forest. In this study, we extracted common characteristics of the selected five indicators. Factors about urban forest are divided into two groups. Factors were named according to the variables as 'Urban Forest Naturalness', and 'High Accessibility and Disturbed by Human.' In addition, we classified urban forests into four types in this study. The type I of urban forest is a large forest and has high naturalness such as Mt. Bukhan and Mt. Gwanak. The type II is fragmented to large forests by developmental projects. The type III is flat and has high accessibility such as forest behind Seonjeongneung. The type IV is located near residential area such as Mt. Ansan, Mt. Inwang and Mt. Bonghwa. It is possible to set up recreational area for citizens and ecological networks for species by the research of the urban forest type. The results of the study, classification of urban forest types and its application, contribute to provide a guide for local governments to create or manage urban forests effectively.

• 한국측량학회지
• /
• 제36권5호
• /
• pp.423-432
• /
• 2018

Surface water mapping has been widely used in various remote sensing applications. Water indices have been commonly used to distinguish water bodies from land; however, determining the optimal threshold and discriminating water bodies from similar objects such as shadows and snow is difficult. Deep learning algorithms have greatly advanced image segmentation and classification. In particular, FCN (Fully Convolutional Network) is state-of-the-art in per-pixel image segmentation and are used in most benchmarks such as PASCAL VOC2012 and Microsoft COCO (Common Objects in Context). However, these data sets are designed for daily scenarios and a few studies have conducted on applications of FCN using large scale remotely sensed data set. This paper aims to fine-tune the pre-trained FCN network using the CRMS (Coastwide Reference Monitoring System) data set for surface water mapping. The CRMS provides color infrared aerial photos and ground truth maps for the monitoring and restoration of wetlands in Louisiana, USA. To effectively learn the characteristics of surface water, we used pre-trained the DeepWaterMap network, which classifies water, land, snow, ice, clouds, and shadows using Landsat satellite images. Furthermore, the DeepWaterMap network was fine-tuned for the CRMS data set using two classes: water and land. The fine-tuned network finally classifies surface water without any additional learning process. The experimental results show that the proposed method enables high-quality surface mapping from CRMS data set and show the suitability of pre-trained FCN networks using remote sensing data for surface water mapping.

• 대한의용생체공학회:의공학회지
• /
• 제32권2호
• /
• pp.134-143
• /
• 2011

The selection of meaningful clinical tests and its reference values from a high-dimensional clinical data with imbalanced class distribution, one class is represented by a large number of examples while the other is represented by only a few, is an important issue for differential diagnosis between similar diseases, but difficult. For this purpose, this study introduces methods based on the concepts of both discernibility matrix and function in rough set theory (RST) with two discretization approaches, equal width and frequency discretization. Here these discretization approaches are used to define the reference values for clinical tests, and the discernibility matrix and function are used to extract a subset of significant clinical tests from the translated nominal attribute values. To show its applicability in the differential diagnosis problem, we have applied it to extract the significant clinical tests and its reference values between normal (N = 351) and abnormal group (N = 101) with either cholecystitis or cholelithiasis disease. In addition, we investigated not only the selected significant clinical tests and the variations of its reference values, but also the average predictive accuracies on four evaluation criteria, i.e., accuracy, sensitivity, specificity, and geometric mean, during l0-fold cross validation. From the experimental results, we confirmed that two discretization approaches based rough set approximation methods with relative frequency give better results than those with absolute frequency, in the evaluation criteria (i.e., average geometric mean). Thus it shows that the prediction model using relative frequency can be used effectively in classification and prediction problems of the clinical data with imbalanced class distribution.

• IEIE Transactions on Smart Processing and Computing
• /
• 제4권1호
• /
• pp.35-43
• /
• 2015

Over the past couple of years, tremendous progress has been made in applying deep learning (DL) techniques to computer vision. Especially, deep convolutional neural networks (DCNNs) have achieved state-of-the-art performance on standard recognition datasets and tasks such as ImageNet Large-Scale Visual Recognition Challenge (ILSVRC). Among them, GoogLeNet network which is a radically redesigned DCNN based on the Hebbian principle and scale invariance set the new state of the art for classification and detection in the ILSVRC 2014. Since there exist various deep learning techniques, this review paper is focusing on techniques directly related to DCNNs, especially those needed to understand the architecture and techniques employed in GoogLeNet network.

• 대한원격탐사학회:학술대회논문집
• /
• 대한원격탐사학회 2005년도 Proceedings of ISRS 2005
• /
• pp.65-68
• /
• 2005

In order for effective disaster prevention, it is necessary to have some idea of when, where, why and what kind of weather disasters may occur, and how large they may be. But the regional characteristics of Shizuoka Prefecture from the viewpoint of weather disasters have not been studied before. In this study, the authors gathered the data which represent how many times weather disasters occurred in Shizuoka Prefecture in the last fourteen years, and then divided it into some regions using a multivariate analysis. The authors adopted principal component analysis on this data, and then adopted cluster analysis with principal component scores which must be significant in the previous analysis. Finally the authors set the regional division based on these clusters and described the regional characteristics. This study could contribute to the weather disaster prevention in Shizuoka Prefecture.

• 대한전자공학회:학술대회논문집
• /
• 대한전자공학회 2002년도 ITC-CSCC -2
• /
• pp.814-817
• /
• 2002

High-dimensional data with two or more attributes are considered. A typical example of such data is face images of various individuals and expressions. In these cases, collecting a complete data set is often difficult since the number of combinations can be large. In the present study, we propose a method to interpolate data of missing combinations from other data. If this becomes possible, robust recognition of multiple attributes is expectable. The key of this subject is appropriate extraction of the similarity that the face images of same individual or same expression have. Bilinear model ［1］has been proposed as a solution of this subjcet. However, experiments on application of bilinear model to classification of face images resulted in low performance ［2］. In order to overcome the limit of bilinear model, in this research, a nonlinear model on a neural network is adopted and usefulness of this model is experimentally confirmed.

• Journal of Information Processing Systems
• /
• 제14권5호
• /
• pp.1075-1086
• /
• 2018

In this paper a cross-validation algorithm for training probabilistic neural networks (PNNs) is presented in order to be applied to automatic face identification. Actually, standard PNNs perform pretty well for small and medium sized databases but they suffer from serious problems when it comes to using them with large databases like those encountered in biometrics applications. To address this issue, we proposed in this work a new training algorithm for PNNs to reduce the hidden layer's size and avoid over-fitting at the same time. The proposed training algorithm generates networks with a smaller hidden layer which contains only representative examples in the training data set. Moreover, adding new classes or samples after training does not require retraining, which is one of the main characteristics of this solution. Results presented in this work show a great improvement both in the processing speed and generalization of the proposed classifier. This improvement is mainly caused by reducing significantly the size of the hidden layer.

• ETRI Journal
• /
• 제33권2호
• /
• pp.259-266
• /
• 2011

We present a new method for an automated markerless system to describe, analyze, and classify human gait motion. The automated system consists of three stages: I) detection and extraction of the moving human body and its contour from image sequences, ii) extraction of gait figures by the joint angles and body points, and iii) analysis of motion parameters and feature extraction for classifying human gait. A sequential set of 2D stick figures is used to represent the human gait motion, and the features based on motion parameters are determined from the sequence of extracted gait figures. Then, a k-nearest neighbor classifier is used to classify the gait patterns. In experiments, this provides an alternative estimate of biomechanical parameters on a large population of subjects, suggesting that the estimate of variance by marker-based techniques appeared generous. This is a very effective and well-defined representation method for analyzing the gait motion. As such, the markerless approach confirms uniqueness of the gait as earlier studies and encourages further development along these lines.

• 대한전기학회:학술대회논문집
• /
• 대한전기학회 1996년도 하계학술대회 논문집 B
• /
• pp.778-780
• /
• 1996

The predictive maximum demand controllers often bring about large number of control actions during the every integrating period and/or undesirable load-disconnecting operations during the begining stage if the integrating period. To solve these problems, a fuzzy predictive maximum demand control algorithm is proposed, which determines the sensitivity if control action by urgency if the load interrupting action along with the predicted demand reading to the target or the time arriving at the end stage if the integrating period. A prototype controller employing the proposed algorithm also is developed and its performances are tested by PROCOM SYSTEMS Corperation of Korea.

• BMB Reports
• /
• 제57권3호
• /
• pp.125-134
• /
• 2024

Whole-genome doubling (WGD), characterized by the duplication of an entire set of chromosomes, is commonly observed in various tumors, occurring in approximately 30-40% of patients with different cancer types. The effect of WGD on tumorigenesis varies depending on the context, either promoting or suppressing tumor progression. Recent advances in genomic technologies and large-scale clinical investigations have led to the identification of the complex patterns of genomic alterations underlying WGD and their functional consequences on tumorigenesis progression and prognosis. Our comprehensive review aims to summarize the causes and effects of WGD on tumorigenesis, highlighting its dualistic influence on cancer cells. We then introduce recent findings on WGD-associated molecular signatures and genetic aberrations and a novel subtype related to WGD. Finally, we discuss the clinical implications of WGD in cancer subtype classification and future therapeutic interventions. Overall, a comprehensive understanding of WGD in cancer biology is crucial to unraveling its complex role in tumorigenesis and identifying novel therapeutic strategies.