• Proceedings of the Safety Management and Science Conference
• /
• 2005.11a
• /
• pp.324-327
• /
• 2005

급속도로 발전하는 산업의 고도화와 이에 따른 업종의 다양화, 이에 동반되는 예상치 못한 산업재해는 불특정 다수에게 인적, 물적 피해를 야기 시키고 있다. 산업재해 예방을 위해 다양한 선행 연구들이 진행되었으나 이들 연구는 기존의 산업재해 데이터를 토대로 빈도분석, 비교분석을 통한 관리적, 교육적 등치 대책만을 제시하고 있다. 본 연구에서는 산업재해 예방을 위해 객관적이고 정량화된 데이터를 통한 예측 분석이 가능한 데이터마이닝을 적용하여 대표적인 기법인 의사결정나무의 CHAID, CART, C4.5, QUEST 4가지 알고리즘 비교분석하여 산업재해 예방 및 전문가 시스템 구축을 위해 적용할 수 있는 최적의 알고리즘을 제시하도록 한다.

• Proceedings of the KIEE Conference
• /
• 2006.07d
• /
• pp.1775-1776
• /
• 2006

This paper deals with the problem of friction measurement of an inverted pendulum system using the regression analysis and proposes a solution. The approach taken in this study is getting the friction from a regression relational expression between the motor voltage and the cart velocity of an inverted pendulum system. The result to compensate LQR (linear Quadratic Regulator) controller with the friction which is measured in system, improved the performance of the system. Above all, the study has found that the proposed compensation of the friction reduces the oscillation of the cart position. In conclusion, the proposed method is useful when parameters in the given system model are not known.

• Proceedings of the Korean Statistical Society Conference
• /
• 2003.10a
• /
• pp.263-268
• /
• 2003

Breiman, Friedman, Olshen and Stone(1984)의 전체탐색법에 의한 회귀나무는 상대적으로 많은 분리가 가능한 변수로 분리기준이 정해지는 편의 현상을 갖고 있다. 본 연구에서는 이런 문제점을 해결할 수 있는 알고리즘을 제안하여 변수선택편의가 없는 회귀나무를 만들고자 한다. 제안하는 알고리즘은 노드의 분리변수를 선택하는 단계와 그 선택된 변수에 의해 이진분리를 위한 분리점을 찾는 단계로 구성되어 있다. 예측변수 중에서 목표변수와 가장 밀접하게 연관된 예측변수는 예측변수의 자료의 종류에 따라 스피어만의 순위상관계수에 의한 검정 혹은 크루스칼-왈리스의 통계량에 의한 검정을 수행하여 가장 통계적으로 유의한 변수로 선택하였고, 선택된 변수에만 Breiman et al.(1984)의 전체선택법을 적용하여 분리점을 결정하였다. 모의실험을 통해 변수선택편의, 변수선택력 , 그리고 평균제곱오차 측면에서 Breiman et al. (1984)의 CART(Classification and Regression Trees)와 제안한 알고리즘을 서로 비교하였다. 또한, 두 알고리즘을 실제 자료에 적용하여 효율을 서로 비교하였다.

• Speech Sciences
• /
• v.10 no.2
• /
• pp.7-25
• /
• 2003

Predicting the right prosodic elements is a key factor in improving the quality of synthesized speech. Prosodic elements include break, pitch, duration and loudness. Pitch, which is realized by Fundamental Frequency (F0), is the most important element relating to the quality of the synthesized speech. However, the previous method for predicting the F0 appears to reveal some problems. If voiced and unvoiced sounds are not correctly classified, it results in wrong prediction of pitch, wrong unit of triphone in synthesizing the voiced and unvoiced sounds, and the sound of click or vibration. This kind of feature is usual in the case of the transformation from the voiced sound to the unvoiced sound or from the unvoiced sound to the voiced sound. Such problem is not resolved by the method of grammar, and it much influences the synthesized sound. Therefore, to steadily acquire the correct value of pitch, in this paper we propose a new model for predicting and classifying the voiced and unvoiced sounds using the CART tool.

• International Journal of Precision Engineering and Manufacturing
• /
• v.3 no.3
• /
• pp.21-27
• /
• 2002

In this paper, a simple test rig of high-speed crash for the front members of vehicles was developed for the improvement of crashworthiness of vehicle's side rail. The cart hanging the specimen is accelerated up to 35 mph by the traction wire and by the force of freely dropping weight and 1:3 accelerating pulleys. The cart with shock absorbers travels on the rail roads, so it does not transfer any additional vibration to the specimen. In order to measure the energy absorbed by the specimen when it collapse to the wall and during it deform, the two strain gage type load cells are used at the wall place. The test rig rated good to test the specimen like a side rail of vehicle as developing the vehicle's structures in the early design stage.

• Proceedings of the Safety Management and Science Conference
• /
• 2007.11a
• /
• pp.269-274
• /
• 2007

Ultimate goal of this research is to develop a web-based forecasting system of industrial accidents. As an initial step for the purpose of this study, this paper provides a comparative analysis of 4 kinds of algorithms including CHAID, CART, C4.5, and QUEST. In addition, this paper presents the logical process for development of a forecasting system. Decision tree algorithm is utilized to predict results using objective and quantified data as a typical technique of data mining. The sample for this work was chosen from 10,536 data related to manufacturing industries during three years(2002$^{\sim}$2004) in korea.

• Proceedings of the KIEE Conference
• /
• 1997.11a
• /
• pp.83-85
• /
• 1997

In this paper, a self-tunning fuzzy inference technique for stabilization of the inverted pendulum system is proposed. The facility of this self-tunning fuzzy controller which has swing-up control mode and a stabilization one, moves a pendulum in an initial natural stable equilibrium point and a cart in arbitrary position, to an unstable equilibrium point and a center of rail. Specially, the virtual equilibrium point(${\phi}_{VEq}$) which describes functionally considers the interactive dynamics between a position of cart and a angle of inverted pendulum is introduced. And comparing with the convention optimal controller, the proposed self-tunning fuzzy inference structure made substantially the inverted pendulum system robust and stable.

• Asian-Australasian Journal of Animal Sciences
• /
• v.14 no.8
• /
• pp.1062-1066
• /
• 2001

Studies were carried out on forty young bulls of the Hariana breed (around 18 months of age) selected on the basis of their dam's milk yield at the animal farm of CCS HAU, Hisar during the period 1993-1999. Since animals showed variation in capacity to work over prolonged periods, they were subjected to regimes of carting without load and with 8 qtls. of load for three hours. The study revealed that maximum change took place in the pulse rate, followed by respiration rate and rectal temperature. The mean fatigue score for pulling an empty cart ranged between 1.66 to 2.20 after two hours work, and 2.36 to 2.73 after three hours work. For a cart loaded with 8 qtls., the corresponding ranges were 2.90 to 3.36 and 3.40 to 4.10, respectively. These results indicated that the animals under experiment had the capacity to pull moderate load (8 qtls.) for about two hours without showing any serious effect on the ability to recover and soon to work again.

• Annual Conference of KIPS
• /
• 2005.05a
• /
• pp.1513-1516
• /
• 2005

백화점이나 대형할인점과 같은 기존 매장에서의 쇼핑은 고객이 구매할 물건을 카트에 담아 이동하며 쇼핑을 마친 후 값을 지불하는 방식으로 구성되어 있다. 카트를 이용하는 쇼핑 방식은 여러가지 장점을 가지고 있으나 공간의 부족으로 카트가 다른 고객들의 진로에 방해가 되기도 하고 또한 무거운 카트를 끌고 다녀야 하는 등의 불편한 문제점들도 가지고 있다. 본 논문에서는 카트를 제공하는 기존 매장의 문제점을 살펴보고 그 문제점을 해결하기 위한 방법으로 카트가 없는 매장 아이디어를 제안한다. 본 논문에서 제시하는 Cart-free Mart 는 Bluetooth, RFID, 휴대전화 등을 이용하여 카트 없이 고객이 원하는 상품을 구매할 수 있도록 도와주는 시스템이며, 미래의 유비쿼터스형 매장 시스템에 적용되면 고객들은 물론 매장의 운영 효율 측면에 있어서도 유익할 것으로 기대된다.

• Journal of the Korean Society for Precision Engineering
• /
• v.16 no.6
• /
• pp.176-182
• /
• 1999

In this paper, we consider a decoupling control and a servo control for the JINAMCHA of which the cart and the pointer is coupled very strongly. The right eigenstructure assignment(i.e. simultaneous assignment of eigenvalues and right eigenvectors) is used for decoupling the motions of the cart and the pointer. The CGT(Command Generator Tracker) is used for a servo control of the JINAMCHA. The performance of the proposed control scheme, that is the combination of the right eigenstructure assignment and the CGT, is evaluated by simulations. The results show that the proposed controller has better performance than the LQR with limiting properties and the conventional LQ servo.