• 한국컴퓨터정보학회논문지
• /
• 제23권11호
• /
• pp.25-30
• /
• 2018

Pattern classification system is often an important component of intelligent systems. In this paper, we present a pattern classification system consisted of the feature selection module, knowledge base construction module and decision module. We introduce a feature impact evaluation selection method based on fuzzy cluster analysis considering computational approach and generalization capability of given data characteristics. A fuzzy neural network, OFUN-NET based on unsupervised learning data mining technique produces knowledge base for representative clusters. 240 blemish pattern images are prepared and applied to the proposed system. Experimental results show the feasibility of the proposed classification system as an automating defect inspection tool.

• ETRI Journal
• /
• 제32권3호
• /
• pp.482-485
• /
• 2010

Feature selection is very important for feature-based relation classification tasks. While most of the existing works on feature selection rely on linguistic information acquired using parsers, this letter proposes new features, including probabilistic and semantic relatedness features, to manifest the relatedness between patterns and certain relation types in an explicit way. The impact of each feature set is evaluated using both a chi-square estimator and a performance evaluation. The experiments show that the impact of relatedness features is superior to existing well-known linguistic features, and the contribution of relatedness features cannot be substituted using other normally used linguistic feature sets.

• Journal of information and communication convergence engineering
• /
• 제15권3호
• /
• pp.165-169
• /
• 2017

Altmetrics is an emergent research area whereby social media is applied as a source of metrics to evaluate scientific impact. Recently, the interest in altmetrics has been growing. Traditional scientific impact evaluation indictors are based on the number of publications, citation counts and peer reviews of a researcher. As research publications were increasingly placed online, usage metrics as well as webometrics appeared. This paper explores the potential benefits of altmetrics and the deep relationship between each metrics. Firstly, we found a weak-to-medium correlation among the 11 altmetrics and visualized such correlation. Secondly, we conducted principal component analysis and exploratory factor analysis on altmetrics of social media, divided the 11 altmetrics into four feature sets, confirming the dispersion and relative concentration of altmetrics groups and developed the altmetrics evaluation model. We can use this model to evaluate the scientific impact of articles on social media.

• 환경영향평가
• /
• 제4권2호
• /
• pp.71-91
• /
• 1995

In order to develop an appropriate set of criteria applicable for environmental impact assessment (EIA) of natural forest 8 items are proposed. The criteria are vegetation distribution area (DA), distribution pattern (DP), size (S), diameter of breast height of tree (DBH), humus (H), sustainment (ST), successional stage (SS) and impact of adjacent ecosystem (IAE), Each criterion has an interval which minimum 1 score to maximum 5 score Forest Evaluation Index (FEI) was obtained as the sum of 8 criteria value. Above 70% is considered to be absolutely conservative and from 50% to 70% range of total score is to be considered conservative. In the case of the Sancho˘ng Pumping-up Power Plant of Mt. Chiri, 8 criteria were applied base on actual vegetation map. Pinus densiflora community got 73%(29 scores) and Quercus variabilis - Q. serrata community got 60%(24 scores). This may be said that this local vegetation has high ecological potentiality. These criteria cannot always be absolutely evaluation tool. So it is expected to take the more time to be developed further, and holistically added by the other field such as fauna, geological feature etc.

• International Journal of Fluid Machinery and Systems
• /
• 제9권1호
• /
• pp.39-46
• /
• 2016

A high frequency hydraulic rock drill drifter with sleeve valve is developed to use on arm of excavator. In order to ensure optimal working parameters of impact system for the new hydraulic rock drill drifter controlled by sleeve valve, the performance test system is built using the arm and the hydraulic source of excavator. The evaluation indexes are gained through measurement of working pressure, supply oil flow and stress wave. The relations of working parameters to impact system performance are analyzed. The result demonstrates that the maximum impact energy of the drill drifter is 98.34J with impact frequency of 71HZ. Optimal pressure of YZ45 rock drill is 12.8 MPa-13.6MPa, in which the energy efficiency reaches above 58.6%, and feature moment of energy distribution is more than 0.650.

• 대한기계학회:학술대회논문집
• /
• 대한기계학회 2003년도 춘계학술대회
• /
• pp.101-106
• /
• 2003

In order to investigate the mechanical behavior of newly developed materials, the evaluation of mechanical properties using small-size specimen is essential. For those purposes, an instrumented impact testing apparatus, which provides the load-displacement curve under impact loading without oscillations, was devised. To develop the test procedure with the setup, the impact behaviors of various kinds of structural materials such as S45C, SCM4, Ti alloys (Ti-6V-4Al) and Zr-based bulk amorphous metal, were investigated through the instrumented Charpy V-notch impact tests. The calibrations of the dynamic load and displacement that was calculated based on the Newton' second law were carried out through the quasi-static load test and the comparison of a directly measured value using a laser displacement meter. Satisfactory results could be obtained. The crack initiation and propagation processes during impact fracture could be well divided on the curve, depending on the intrinsic characteristic of specimen tested; ductile or brittle. The absorbed impact energy in Zr-basd BAM was largely used for crack initiation not for crack propagation process. The fracture surfaces under impact loading showed different feature when compared with the static cases.

• International Journal of Computer Science & Network Security
• /
• 제22권1호
• /
• pp.167-174
• /
• 2022

In metaheuristic algorithms such as Genetic Algorithm (GA), initial population has a significant impact as it affects the time such algorithm takes to obtain an optimal solution to the given problem. In addition, it may influence the quality of the solution obtained. In the machine learning field, feature selection is an important process to attaining a good performance model; Genetic algorithm has been utilized for this purpose by scientists. However, the characteristics of Genetic algorithm, namely random initial population generation from a vector of feature elements, may influence solution and execution time. In this paper, the use of a statistical algorithm has been introduced (Chi2) for feature relevant checks where p-values of conditional independence were considered. Features with low p-values were discarded and subject relevant subset of features to Genetic Algorithm. This is to gain a level of certainty of the fitness of features randomly selected. An ensembled-based learning model for Hepatitis has been developed for Hepatitis C stage classification. 1385 samples were used using Egyptian-dataset obtained from UCI repository. The comparative evaluation confirms decreased in execution time and an increase in model performance accuracy from 56% to 63%.

• Advances in Energy Research
• /
• 제6권2호
• /
• pp.91-101
• /
• 2019

This paper proposes an efficient data-driven approach to build models for predicting energy consumption in buildings. Data used in this research is collected by installing humidity and temperature sensors at different locations in a building. In addition to this, weather data from nearby weather station is also included in the dataset to study the impact of weather conditions on energy consumption. One of the main emphasize of this research is to make feature selection independent of domain knowledge. Therefore, to extract useful features from data, two different approaches are tested: one is feature selection through principal component analysis and second is relative importance-based feature selection in original domain. The regression model used in this research is gradient boosting regression and its optimal parameters are chosen through a two staged coarse-fine search approach. In order to evaluate the performance of model, different performance evaluation metrics like r2-score and root mean squared error are used. Results have shown that best performance is achieved, when relative importance-based feature selection is used with gradient boosting regressor. Results of proposed technique has also outperformed the results of support vector machines and neural network-based approaches tested on the same dataset.

• Computers and Concrete
• /
• 제33권4호
• /
• pp.409-423
• /
• 2024

Using an extensive database, a sensitivity analysis across fifteen machine learning (ML) classifiers was conducted to evaluate the impact of various data manipulation techniques, evaluation metrics, and explainability tools. The results of this sensitivity analysis reveal that the examined models can achieve an accuracy ranging from 72-93% in predicting the fire-induced spalling of concrete and denote the light gradient boosting machine, extreme gradient boosting, and random forest algorithms as the best-performing models. Among such models, the six key factors influencing spalling were maximum exposure temperature, heating rate, compressive strength of concrete, moisture content, silica fume content, and the quantity of polypropylene fiber. Our analysis also documents some conflicting results observed with the deep learning model. As such, this study highlights the necessity of selecting suitable models and carefully evaluating the presence of possible outcome biases.

• 한국전자거래학회지
• /
• 제12권3호
• /
• pp.33-47
• /
• 2007

소프트웨어 개발 초기에 모든 요구사항을 정의하는 것은 불가능하기 때문에 요구사항은 소프트웨어 개발이 진행되는 동안에 지속적으로 변경된다. 이러한 요구사항 변경은 개발자가 소프트웨어 구조나 행위를 완벽하게 이해하지 못하거나 변경에 따라 영향을 받는 모든 부분을 식별할 수 없을 경우 많은 오류를 야기 시킨다. 그러므로, 조직의 비즈니스에 공헌하면서 비용 효과적으로 적절히 처리되기 위하여 요구사항은 관리되고 평가되어야한다. 본 논문은 가치분석을 통하여 생성된 휘처 기반의 요구사항추적 링크를 근간으로 하는 요구사항변경 관리 기법을 제안한다. 이는 사용자 요구사항과 산출물간의 연결을 분석하기 위하여 휘처를 중간 매개체로 활용한 추적 링크를 이용한다. 그리고, 요구사항 변경 요청을 휘처 단위로 상세화하기 위한 변경 트리 모델을 정의하고 변경 관리가 수행되는 전체적인 프로세스를 제시한다. 또한, 요구사항 변경 관리 기법을 자산관리포탈시스템에 적용한 사례의 결과를 기술한다.