• Soft Computing and Machine Intelligence
• /
• 제1권1호
• /
• pp.11-23
• /
• 2021

House price prediction is a significant financial decision for individuals working in the housing market as well as for potential buyers. From investment to buying a house for residence, a person investing in the housing market is interested in the potential gain. This paper presents machine learning algorithms to develop intelligent regressions models for House price prediction. The proposed research methodology consists of four stages, namely Data Collection, Pre Processing the data collected and transforming it to the best format, developing intelligent models using machine learning algorithms, training, testing, and validating the model on house prices of the housing market in the Capital, Islamabad. The data used for model validation and testing is the asking price from online property stores, which provide a reasonable estimate of the city housing market. The prediction model can significantly assist in the prediction of future housing prices in Pakistan. The regression results are encouraging and give promising directions for future prediction work on the collected dataset.

• 소성∙가공
• /
• 제29권5호
• /
• pp.257-264
• /
• 2020

This paper is concerned with the influence of the plastic property of the rivet on the numerical prediction of the Self-Piercing Rivet (SPR) Joining. In order to predict the plastic property of the rivet, a ring compression specimen was directly fabricated from the rivet used for the mechanical joining of dissimilar materials, and the FE analysis together with the ring compression test was iteratively carried out by changing the plastic property of the rivet. For reliable FE analysis, a friction coefficient was estimated based on a friction calibration curve, measuring the reductions in inner diameter and height of the ring specimen after the compression test. From each simulation result, the force-displacement curves were then compared from each other so as to obtain the rivet plastic property that shows good agreement with the experimental result. The SPR joining between GA590 1.0t and Al5052 2.0t was conducted, and the numerical prediction was performed with the use of the plastic property evaluated based on the inverse analysis and the one referred from Mori et al. [11]. Comparison of the experiment and the numerical predictions in terms of the interlock and bottom thickness revealed that the reliable evaluation of the plastic property of the rivet is necessary for the trustworthy numerical prediction of the SPR joining.

• Journal of Mechanical Science and Technology
• /
• 제19권6호
• /
• pp.1229-1242
• /
• 2005

When natural rubber is used for a long period of time, it becomes aged; it usually becomes hardened and loses its damping capability. This aging process affects not only the material property but also the (fatigue) life of natural rubber. In this paper the aging effects on the material property and the fatigue life were experimentally investigated. In addition, several fatigue life prediction equations for natural rubber were proposed. In order to investigate the aging effects on the material property, the load-stretch ratio curves were plotted from the results of the tensile test, the compression test and the simple shear test for virgin and heat-aged rubber specimens. Rubber specimens were heat-aged in an oven at a temperature ranging from $50^{\circ}C$ to $90^{\circ}C$ for a period ranging from 2 days to 16 days. In order to investigate the aging effects on the fatigue life, fatigue tests were conducted for differently heat-aged hourglass-shaped and simple shear specimens. Moreover, finite element simulations were conducted for the specimens to calculate physical quantities occurring in the specimens such as the maximum value of the effective stress, the strain energy density, the first invariant of the Cauchy-Green deformation tensor and the maximum principal nominal strain. Then, four fatigue life prediction equations based on one of the physical quantities could be obtained by fitting the equations to the test data. Finally, the fatigue life of a rubber bush used in an automobile was predicted by using the prediction equations, and it was compared with the test data of the bush to evaluate the reliability of those equations.

• 한국추진공학회지
• /
• 제22권4호
• /
• pp.55-60
• /
• 2018

열적 특성은 에너지 물질 분야에서 중요한 특성 중 하나로, 분해열을 방출하기 때문에, 열적 특성 분석에 DSC(Differential Scanning Calorimetry)가 자주 사용된다. 그러나 DSC 측정의 경우, 용융과 같은 열역학적 변화가 kinetics 분석에 방해를 끼친다. 이번 연구에서는 이 문제점을 해결하는 방안으로, 등온 조건으로 한 DSC 기초 데이터와 g 단위로 측정하는 ARC(Accelerating Rate Calorimetry)의 데이터를 이용하여 AKTS(Advanced Kinetics and Technology Solutions) thermokinetic 프로그램을 이용하여 열적 노화 특성을 예측, 비교한다.

• 한국정밀공학회:학술대회논문집
• /
• 한국정밀공학회 2013년도 춘계학술대회 논문집
• /
• pp.1155-1156
• /
• 2013

• Journal of the Korean Statistical Society
• /
• 제24권1호
• /
• pp.243-248
• /
• 1995

In this article we show that a class of random coefficient autoregressive processes including the NEAR (New exponential autoregressive) process has the strong mixing property in the sense of Rosenblatt with mixing order decaying to zero. The result can be used to construct model free prediction interval for the future observation in the NEAR processes.

• 한국연초학회지
• /
• 제29권2호
• /
• pp.80-84
• /
• 2007

This study was conducted to evaluate the prediction of sensory property of smoke from the leaf chemical property and characterize leaf chemical components for the best tobacco taste's leaves in burley tobacco. For analytical and sensory evaluations, sixteen grades were used. The major leaf chemical components to predict the sensory property of smoke were ether extract for tobacco-like, chloride for impact and total nitrogen/nicotine for irritation. Within ${\pm}20\;%$ range of difference, the predictable probabilities of sensory property of smoke from the leaf chemical properties were 100 % for tobacco-like, impact and irritation. As a result of K-means cluster analysis on the basis of tobacco taste, the desirable leaf chemical component contents were $6.5{\sim}6.8\;%$ in ether extract, $0.25{\sim}0.30\;%$ in chloride and $1.26{\sim}1.54$ in total nitrogen/nicotine ratio. This study suggest that the some regression equations may be useful to predict the sensory components of tobacco smoke from a few selected leaf chemical properties in burley tobacco and to select the burley tobacco leaves for enhance the tobacco taste of cigarette.

• Korean Chemical Engineering Research
• /
• 제58권2호
• /
• pp.230-234
• /
• 2020

딥러닝 기법을 활용하여 분자 구조로부터 물성을 예측하는 시스템은 화학, 생물학, 재료 연구에 적용하기 위해 개발되었다. 분자 구조와 물성 정보가 축적된 데이터베이스를 기반으로, 구조와 물성간의 관계식을 찾는 딥러닝 모형을 구축한 후 최종적으로는 새로운 분자 구조에 대한 물성 예측값을 제공할 수 있다. 또한 선정된 분자 구조의 실제 물성값에 대한 실험을 병행하여 지속적인 검증 및 모형 업데이트를 수행하게 된다. 이를 통해 다량의 분자구조로부터 물성이 우수한 분자 구조를 빠른 시간 안에 스크리닝할 수 있으며, 연구의 효율성 및 성공률을 높일 수 있다. 본 논문에서는 딥러닝을 활용한 물성 예측 시스템의 전반적인 구성과 LG화학에서 실제 신규 구조 발굴에 적용된 사례를 중심으로 소개하고자 한다.

• Bulletin of the Korean Chemical Society
• /
• 제28권9호
• /
• pp.1472-1476
• /
• 2007

Artificial neural networks (ANNs) are successfully developed for the modeling and prediction of normalized polarity parameter (ETN) of 216 various solvents with diverse chemical structures using a quantitative-structure property relationship. ANN with architecture 5-9-1 is generated using five molecular descriptors appearing in the multi-parameter linear regression (MLR) model. The most positive charge of a hydrogen atom (q+), total charge in molecule (qt), molecular volume of solvent (Vm), dipole moment (μ) and polarizability term (πI) are input descriptors and its output is ETN. It is found that properly selected and trained neural network with 192 solvents could fairly represent the dependence of normalized polarity parameter on molecular descriptors. For evaluation of the predictive power of the generated ANN, an optimized network is applied for prediction of the ETN values of 24 solvents in the prediction set, which are not used in the optimization procedure. Correlation coefficient (R) and root mean square error (RMSE) of 0.903 and 0.0887 for prediction set by MLR model should be compared with the values of 0.985 and 0.0375 by ANN model. These improvements are due to the fact that the ETN of solvents shows non-linear correlations with the molecular descriptors.

• Communications for Statistical Applications and Methods
• /
• 제18권1호
• /
• pp.23-34
• /
• 2011

부동산 경매는 최근 새로운 부동산 투자방법 가운데 하나로 자리잡고있다. 이는 부동산 시장의 성장과 더불어 부동산 경매 시장 또한 증가하고 있는 추세에 기인한다 할 수 있다. 본 연구는 부동산 경매에 참여하는 사람 및 기관들에게 가장 중요한 지표라 할 수 있는 낙찰률의 변화를 설명하고 예측하는 모형을 구축하고자 하였다. 월별 평균 낙찰률을 예측하기 위하여 단순한 지역별, 기간별 평균값을 보완하고 의사결정나무 분석을 이용하여 예측오차를 보정하는 방법을 제안하였고 선형회귀모형을 이용하여 개별 경매 물건별 낙찰률을 예측하기 위한 모형을 구축하였다. 구축된 모형은 전국 아파트 경매 물건에 적용하여 예측 모형을 구현하였으며 그 응용방법으로 예측결과에 대한 등급화를 함께 수행하였다.