• Korean Journal of Remote Sensing
• /
• v.35 no.6_3
• /
• pp.1285-1298
• /
• 2019

Drought is one of the factors that can cause wildfires. Drought is related to not only the occurrence of wildfires but also their frequency, extent and severity. In South Korea, most wildfires occur in dry seasons (i.e. spring and autumn), which are highly correlated to drought events. In this study, we examined the relationship between wildfire occurrence and drought factors, and developed satellite-based new drought indices for assessing wildfire risk over South Korea. Drought factors used in this study were high-resolution downscaled soil moisture, Normalized Different Water Index (NDWI), Normalized Multi-band Drought Index (NMDI), Normalized Different Drought Index (NDDI), Temperature Condition Index (TCI), Precipitation Condition Index (PCI) and Vegetation Condition Index (VCI). Drought indices were then proposed through weighted linear combination and one-class support vector machine (One-class SVM) using the drought factors. We found that most drought factors, in particular, soil moisture, NDWI, and PCI were linked well to wildfire occurrence. The validation results using wildfire cases in 2018 showed that all five linear combinations produced consistently good performance (> 88% in occurrence match). In particular, the combination of soil moisture and NDWI, and the combination of soil moisture, NDWI, and precipitation were found to be appropriate for representing wildfire risk.

• The KIPS Transactions:PartB
• /
• v.17B no.3
• /
• pp.233-238
• /
• 2010

In this paper, we propose a multiple classifier combination method based on image degradation modeling to improve recognition performance on low-quality images. Using an image degradation model, it generates a set of classifiers each of which is specialized for a specific image quality. In recognition, it combines the results of the recognizers by weighted averaging to decide the final result. At this time, the weight of each recognizer is dynamically decided from the estimated quality of the input image. It assigns large weight to the recognizer specialized to the estimated quality of the input image, but small weight to other recognizers. As the result, it can effectively adapt to image quality variation. Moreover, being a multiple-classifier system, it shows more reliable performance then the single-classifier system on low-quality images. In the experiment, the proposed multiple-classifier combination method achieved higher recognition rate than multiple-classifier combination systems not considering the image quality or single classifier systems considering the image quality.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.4
• /
• pp.534-540
• /
• 2014

In this paper, we propose a fuzzy combined Polynomial Neural Network(PNN) for pattern classification. The fuzzy combined PNN comes from the generic TSK fuzzy model with several linear polynomial as the consequent part and is the expanded version of the fuzzy model. The proposed pattern classifier has the polynomial neural networks as the consequent part, instead of the general linear polynomial. PNNs are implemented by stacking the simple polynomials dynamically. To implement one layer of PNNs, the various types of simple polynomials are used so that PNNs have flexibility and versatility. Although the structural complexity of the implemented PNNs is high, the PNNs become a high order-multi input polynomial finally. To estimate the coefficients of a polynomial neuron, The weighted linear discriminant analysis. The output of fuzzy rule system with PNNs as the consequent part is the linear combination of the output of several PNNs. To evaluate the classification ability of the proposed pattern classifier, we make some experiments with several machine learning data sets.

• Journal of Korea Multimedia Society
• /
• v.23 no.5
• /
• pp.625-632
• /
• 2020

In the diagnosis of lung cancer, the tumor size is measured by the longest diameter of the tumor in the entire slice of the CT. In order to accurately estimate the size of the tumor, it is better to measure the volume, but there are some limitations in calculating the volume in the clinic. In this study, we propose an algorithm to segment lung cancer by applying a custom loss function that combines focal loss and dice loss to a U-Net model that shows high performance in segmentation problems in chest CT images. The combination of values of the various parameters in custom loss function was compared to the results of the model learned. The purposed loss function showed F1 score of 88.77%, precision of 87.31%, recall of 90.30% and average precision of 0.827 at α=0.25, γ=4, β=0.7. The performance of the proposed custom loss function showed good performance in lung cancer segmentation.

• Smart Structures and Systems
• /
• v.3 no.2
• /
• pp.147-172
• /
• 2007

The present paper is concerned with the design of distributed sensors and actuators. Strain type sensors and actuators are considered with their intensity continuously distributed throughout a continuous structure. The sensors measure a weighted average of the strain tensor. As a starting point for their design we introduce the concept of collocated sensors and actuators as well as the so-called natural output. Then we utilize the principle of virtual work for an auxiliary quasi-static problem to assign a mechanical interpretation to the natural output of the sensors to be designed. Therefore, we take the virtual displacements in the principle of virtual work as that part of the displacement in the original problem, which characterizes the deviation from a desired one. We introduce different kinds of distributed sensors, each of them with a mechanical interpretation other than a weighted average of the strain tensor. Additionally, we assign a mechanical interpretation to the collocated actuators as well; for that purpose we use an extended body force analogy. The sensors and actuators are applied to solve the displacement tracking problem for continuous structures; i.e., the problem of enforcing a desired displacement field. We discuss feed forward and feed back control. In the case of feed back control we show that a PD controller can stabilize the continuous system. Finally, a numerical example is presented. A desired deflection of a clamped-clamped beam is tracked by means of feed forward control, feed back control and a combination of the two.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.66 no.4
• /
• pp.692-700
• /
• 2017

In this paper, we propose the structural design of Interval Type-2 FCM based RBFNN. Proposed model consists of three modules such as condition, conclusion and inference parts. In the condition part, Interval Type-2 FCM clustering which is extended from FCM clustering is used. In the conclusion part, the parameter coefficients of the consequence part are estimated through LSE(Least Square Estimation) and WLSE(Weighted Least Square Estimation). In the inference part, final model outputs are acquired by fuzzy inference method from linear combination of both polynomial and activation level obtained through Interval Type-2 FCM and acquired activation level through Interval Type-2 FCM. Additionally, The several parameters for the proposed model are identified by using differential evolution. Final model outputs obtained through benchmark data are shown and also compared with other already studied models' performance. The proposed algorithm is performed by using Iris and Vehicle data for pattern classification. For the validation of regression problem modeling performance, modeling experiments are carried out by using MPG and Boston Housing data.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.6
• /
• pp.51-56
• /
• 2001

Recent researches have been focusing on jointly using lip motions and speech for reliable speech recognitions in noisy environments. To this end, this paper proposes the method of combining the visual speech recognizer and the conventional speech recognizer with each output properly weighted. In particular, we propose the method of autonomously determining the weights, depending on the amounts of noise in the speech. The correlations between adjacent speech samples and the residual errors of the LPC analysis are used for this determination. Simulation results show that the speech recognizer combined in this way provides the recognition performance of 83 ％ even in severely noisy environments.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2003.11a
• /
• pp.177-182
• /
• 2003

This study is directed toward determining the number and characteristics of psychologically meaningful perceptual dimensions required for assessing the sound Ouaiity with respect to vehicle interior and/or exterior noises. and toward identifying the acoustical or psychoacoustical bases underlying the perception. By nonmetric MDS and clustring analysis of sound quality data sets on our own, of critical importance are two perceptual dimensions for which subjective verdicts can be interpreted as loudness and sharpness. The perceptual dimensions based upon similarity judgments could be accounted for 48% and 24% of the variance. each of which might be a match for the acoustic parameter "A-weighted maximum pressure level"(r= .85) and for the psychoacoustic parameter "sharpness" (r= .65), respectively. On the other hand, the perceptual dimensions based upon preference ratings could explain 66% and 10% of the variance. where the acoustic parameter "A-weighted maximum pressure leve"(r= .92) might be taken to be a best predictor, but sharpness appeared to be less suitable for the description of Preference behavior. Linked to the results, the problems of quantitative modelling of subjective sound quality evaluation and also of implementing corresponding cognitive combination rule for technical and industrial applications, say having "winner-sound qualify" according to preference criteria will be shortly in discussion.

• Magazine of the Korean Society of Agricultural Engineers
• /
• v.43 no.5
• /
• pp.70-82
• /
• 2001

This study was conducted to derive the regional design rainfall by the regional frequency analysis based on the regionalization of the precipitation suggested by the first report of this project. Using the L-moment ratios and Kolmogorov-Smirnov test, the underlying regional probability distribution was identified to be the Generalized extreme value distribution among applied distributions. Regional and at-site parameters of the generalized extreme value distribution were estimated by the linear combination of the probability weighted moments, L-moment. The regional and at-site analysis for the design rainfall were tested by Monte Carlo simulation. Relative root-mean-square error(RRMSE), relative bias(RBIAS) and relative reduction(RR) in RRMSE were computed and compared with those resulting from at-site Monte Carlo simulation. All show that the regional analysis procedure can substantially reduce the RRMSE, RBIAS and RR in RRMSE in the prediction of design rainfall. Consequently, optimal design rainfalls following the legions and consecutive durations were derived by the regional frequency analysis.

• Industrial Engineering and Management Systems
• /
• v.9 no.3
• /
• pp.262-274
• /
• 2010

This article investigates how to adaptively predict the time-varying metrology delay that could realistically occur in the semiconductor manufacturing practice. Metrology delays pose a great challenge for the existing run-to-run (R2R) controllers, driving the process output significantly away from target if not adequately predicted. First, the expected asymptotic double exponentially weighted moving average (DEWMA) control output, by using the EWMA and recursive least squares (RLS) prediction methods, is derived. It has been found that the relationships between the expected control output and target in both estimation methods are parallel, and six cases are addressed. Within the context of time-varying metrology delay, this paper presents a modified recursive least squares-linear trend (RLS-LT) controller, in combination with runs test. Simulated single input-single output (SISO) R2R processes subject to various time-varying metrology delay scenarios are used as a testbed to evaluate the proposed algorithms. The simulation results indicate that the modified RLS-LT controller can yield the process output more accurately on target with smaller mean squared error (MSE) than the original RLSLT controller that only deals with constant metrology delays.