• Journal of the Korean Data Analysis Society
• /
• v.20 no.6
• /
• pp.2747-2757
• /
• 2018

We consider the MLE (maximum likelihood estimate) and Bayesian estimates of three-parameter bathtub-shaped lifetime distribution based on the progressive type II censoring with binomial removal. Jung, Chung (2018) proposed the three-parameter bathtub-shaped distribution which is the extension of the two-parameter bathtub-shaped distribution given by Zhang (2004). Jung, Chung (2018) investigated its properties and estimations. The maximum likelihood estimates are computed using Newton-Raphson algorithm. Also, Bayesian estimates are obtained under the balanced loss function using MCMC (Markov chain Monte Carlo) method. In particular, BSEL (balanced squared error loss) function is considered as a special form of balanced loss function given by Zellner (1994). For comparing theirs MLEs with the corresponding Bayes estimates, some simulations are performed. It shows that Bayes estimates is better than MLEs in terms of risks. Finally, concluding remarks are mentioned.

• The Korean Society of Law and Medicine
• /
• v.13 no.2
• /
• pp.179-214
• /
• 2012

There are two opinions on the legal characteristics of damages for non-pecuniary loss, a private sanctions theory and complementary function of damages for non-pecuniary loss, briefly. There is a close connection between the legal characteristics and the function of damages for non-pecuniary loss. The functions of damages for non-pecuniary loss are consist of satisfaction, prevention( sanctions) and complementation. Several cases of medical injury relief reported to Korea Comsumer Agency are categorized as follows, 1) cases of death after having an operation, 2) diagnosed with disability after a medical accident, 3) extended damages happening related to delayed diagnosis, 4) et cetera(a plastic surgery, a treatment with oriental medicine), and the damages for non-pecuniary loss in respect to each cases are examined. In the case of occurring death or disability, Korea Comsumer Agency has set up guidelines for assessment of damages for non-pecuniary loss by classifying into major and collateral violation for a duty of care. Furthermore, the damages for non-pecuniary loss in the case of all sorts of cancers, are assessed in accordance with the degree of responsibility subsequent to dividing cancer into good and poor prognosis. When it comes to a complementary function of damages for non-pecuniary loss in the actual work, it is hard to assess the damages as it is difficult to objectify non-pecuniary loss, such as emotional distress. Though compensation for damages is major legal characteristics of consolation money, preventing a damage(private sanctions) through consolation for a victim or sanctions against an assailant also has great significance. Therefore, it is necessary to approach flexibly for mutual agreement by considering specialty( concrete facts) of individual issue thoroughly. If considering this aging society that limits the possible age for work to 60 years old, it is needed to have a complementary function of consolation money in mind not to make it less meaningful for victims due to small sum of consolation money.

• Communications for Statistical Applications and Methods
• /
• v.17 no.2
• /
• pp.183-191
• /
• 2010

Support vector quantile regression(SVQR) is capable of providing more complete description of the linear and nonlinear relationships among random variables. In this paper we propose an iterative reweighted least squares(IRWLS) procedure to solve the problem of SVQR with a weighted quadratic loss function. Furthermore, we introduce the generalized approximate cross validation function to select the hyperparameters which affect the performance of SVQR. Experimental results are then presented which illustrate the performance of the IRWLS procedure for SVQR.

• Smart Structures and Systems
• /
• v.29 no.1
• /
• pp.153-166
• /
• 2022

Identifying fine cracks in steel bridge facilities is a challenging task of structural health monitoring (SHM). This study proposed an end-to-end crack image segmentation framework based on a one-step Convolutional Neural Network (CNN) for pixel-level object recognition with high accuracy. To particularly address the challenges arising from small object detection in complex background, efforts were made in loss function selection aiming at sample imbalance and module modification in order to improve the generalization ability on complicated images. Specifically, loss functions were compared among alternatives including the Binary Cross Entropy (BCE), Focal, Tversky and Dice loss, with the last three specialized for biased sample distribution. Structural modifications with dilated convolution, Spatial Pyramid Pooling (SPP) and Feature Pyramid Network (FPN) were also performed to form a new backbone termed CrackDet. Models of various loss functions and feature extraction modules were trained on crack images and tested on full-scale images collected on steel box girders. The CNN model incorporated the classic U-Net as its backbone, and Dice loss as its loss function achieved the highest mean Intersection-over-Union (mIoU) of 0.7571 on full-scale pictures. In contrast, the best performance on cropped crack images was achieved by integrating CrackDet with Dice loss at a mIoU of 0.7670.

• Journal of Korean Society for Quality Management
• /
• v.21 no.2
• /
• pp.61-70
• /
• 1993

The concept of producer's tolerance, in contrast to the consumer's tolerance, is a natural consequence of continuous loss functions. It is based on the premise that any unit product whose quality characteristic deviated from its traget value inflicts a loss, and that this less is a continuous monotonically increasing function of the magnitude of deviation. This concept of the emphasis on loss function to improve quality of products on the side of customer is introduced by Taguchi. This paper considers the problem of determining the optimum producer's tolerance by continous loss fuction of Taguchi and proposes a probablistic model for the problem. The difference between the proposed probablistic approach and the approach taken in Taguchi is also pointed out.

• Journal of the Korean Wood Science and Technology
• /
• v.46 no.4
• /
• pp.338-345
• /
• 2018

The sound insulation capacity of a barrier is indicated by its transmission loss. In this study, the sound transmission loss of a sound barrier filled with rice-straw particles was measured by the transfer function method and a laboratory measurement method. The results of the two measurements were compared. The transmission losses measured by the two methods were similar above a frequency of 500 Hz. The loss increased greatly upon the introduction of a plywood to the sound barrier. The results of this study are expected to be used to design sound barriers for roads.

• Communications for Statistical Applications and Methods
• /
• v.14 no.1
• /
• pp.71-80
• /
• 2007

The present paper investigates estimation of a scale parameter of a gamma distribution using a loss function that reflects both goodness of fit and precision of estimation. The Bayes and empirical Bayes estimators rotative to balanced loss functions (BLFs) are derived and optimality of some estimators are studied.

• Journal of Korean Society for Quality Management
• /
• v.41 no.3
• /
• pp.443-456
• /
• 2013

Purpose: Recently, many quality issues are aroused in military forces, such as failures in K-series weapons, combat boots defects and 40mm ammunition explosion accident. To address these problems, this paper suggests to use so called, Defense Quality Score, which is based on Taguchi loss function and developed in this research. Methods: Current defense specification states only the minimum requirement to produce the military supplies. Therefore, it is not easy to indue the continuous quality improvement of the supplies. This research suggests to use the defense quality score which measures the current status of defense supplies'quality characteristics. Results: We applied the defense quality score concept into the hot pepper sauce and long time stockpiled ammunition. We first categorize the quality characteristics into three categories, then assign the certain amount of score based on the importance of the characteristics. Lastly, we applied the modified Taguchi loss function to calculate the achieved score of the characteristics. The perfect score is 100 and the closer to the score, the better product it indicates. Conclusions: In this research, we developed the modified Taguchi loss function to apply into the korean defense supplies. The loss function is utilized to calculate the achieved level of satisfaction of the supplies based on the defense specifications. The application of defense quality score may help to stimulate the continuous quality improvement and encourage the good will quality competition among the military providers.

• Journal of the Earthquake Engineering Society of Korea
• /
• v.28 no.3
• /
• pp.149-158
• /
• 2024

Piloti-type structures with vertical irregularity are vulnerable to earthquakes due to the soft structure of the first story. Structural characteristics of buildings can significantly affect the seismic loss function, calculated based on seismic fragility, and therefore need to be considered. This study investigated the effects of the number of stories and core locations on the seismic loss function of piloti-type buildings in Korea. Twelve analytical models were developed considering two variations: three stories (4-story, 5-story, and 6-story) and four core locations (center core, x-eccentric core, y-eccentric core, and xy-eccentric core). The interstory drift ratio and peak floor acceleration were assessed through incremental dynamic analysis using 44 earthquake records, and seismic fragility was derived. Seismic loss functions were calculated and compared using the derived seismic fragility and repair cost ratio of each component. The results indicate that the seismic loss function increases with more stories and when the core is eccentrically located in the piloti-type structure model. Therefore, the uncertainty due to the number of stories and core location should be considered when deriving the seismic loss function of piloti-type structures.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.109-114
• /
• 2021

GAN(Generative Adversarial Network) is an image generation model, which is composed of a generator network and a discriminator network, and generates an image similar to a real image. Since the image generated by the GAN should be similar to the actual image, a loss function is used to minimize the loss error of the generated image. However, there is a problem that the loss function of GAN degrades the quality of the image by making the learning to generate the image unstable. To solve this problem, this paper analyzes GAN-related studies and proposes an edge GAN(eGAN) using edge detection. As a result of the experiment, the eGAN model has improved performance over the existing GAN model.