• Ocean and Polar Research
• /
• 제26권3호
• /
• pp.465-473
• /
• 2004

Five parameters such as the entrance size of the front wall, conduit size, wave period, wave height and the width of water pool were selected to estimate the inflow rate, which is basic and essential input data to design seawater exchange breakwater with a submerged mound by conducting hydraulic model experiments. In the results of multiple regression analysis, log-log equation showed a good agreement rather than linear equation and the estimation of inflow rate was well done with only two parameters except entrance size of the front wall, wave period and the width of water pool. Finally, non-dimensional flow rate equation is derived.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권12호
• /
• pp.5765-5781
• /
• 2018

Extreme learning machine (ELM) is emerging as a powerful machine learning method in a variety of application scenarios due to its promising advantages of high accuracy, fast learning speed and easy of implementation. However, how to select the optimal hidden layer of ELM is still an open question in the ELM community. Basically, the number of hidden layer nodes is a sensitive hyperparameter that significantly affects the performance of ELM. To address this challenging problem, we propose to adopt multiple kernel learning (MKL) to design a multi-hidden-layer-kernel ELM (MHLK-ELM). Specifically, we first integrate kernel functions with random feature mapping of ELM to design a hidden-layer-kernel ELM (HLK-ELM), which serves as the base of MHLK-ELM. Then, we utilize the MKL method to propose two versions of MHLK-ELMs, called sparse and non-sparse MHLK-ELMs. Both two types of MHLK-ELMs can effectively find out the optimal linear combination of multiple HLK-ELMs for different classification and regression problems. Experimental results on seven data sets, among which three data sets are relevant to classification and four ones are relevant to regression, demonstrate that the proposed MHLK-ELM achieves superior performance compared with conventional ELM and basic HLK-ELM.

• 한국산업정보학회논문지
• /
• 제27권4호
• /
• pp.1-10
• /
• 2022

컴퓨터 비전을 활용하여 인간의 시각을 해석하려는 시도가 다양한 분야에서 발전되어 왔다. 본 논문에서는 도로영상으로부터 영상의 의미론적 분할 결과를 통해 보행 환경을 평가하는 방법을 제안한다. 먼저 도로영상을 수집하기 위해 카카오 지도 API를 활용하였으며 전주시지역의 약 5만 점에서 4방향 영상을 수집한다. 수집된 영상의 20%는 크라우드 소싱기반 쌍체 비교를 통해 데이터 셋을 구축하고, 쌍체 비교 데이터를 이용하여 다양한 회귀 모델을 훈련한다. 영상 데이터의 보행성 점수를 도출하기 위해 순위 알고리즘인 Trueskill 알고리즘을 활용하여 랭킹 점수를 계산하고, 구축된 데이터를 활용하여 다양한 회귀모델을 사용한 보행성 평가 및 분석 작업을 수행한다. 본 연구를 통해 사람의 시각이 아닌 픽셀 분포 분류 정보 간의 상관관계를 통해 컴퓨터 시스템만으로 전주시의 보행 환경을 평가하고 점수를 도출해 낼 수 있다는 것을 보여준다.

• 한국학교ㆍ지역보건교육학회지
• /
• 제19권1호
• /
• pp.99-109
• /
• 2018

Objectives: The study was conducted to understand job stress and fatigue conditions by dividing nurses in a polyclinic-level public medical institution, Seoul with more than 600 beds into ward nurses and non-ward nurses and to comprehend sub-areas of job stress that affect fatigue. Methods: A survey was conducted from August 18 2014 to September 12 2014, so 216 cases were analyzed by using PASW statistics 18.0. Results: Job stress of ward nurses is significantly high in the psychological burden of nursing service area and medical limit. Fatigue of ward nurses is also higher. As a result of multiple Linear regression, nursing service area affects fatigue of ward nurses and there is no significant influence factors in non-ward nurses. Conclusion: Therefore, mental health education and interest of hospital in nursing service area are more needed for ward nurses with high job stress and fatigue among nurses.

• 아태비즈니스연구
• /
• 제12권1호
• /
• pp.87-100
• /
• 2021

Purpose - This study aims to examine the antecedents of willingness to pay in the domain of duty free shop. Design/methodology/approach - This study chooses willingness to pay as explained variable. The candidates of explanatory variables are price fairness, brand awareness, employee service, product diversity, and crowding. This study uses survey to explore the linear relation between variables. This research collected data using online panel data collection service. The number of valid observation is 265. The research targe is Lotte duty free store. Statistical analysis was for statistical inference. To attain the information of survey respondents, frequency analysis is employed. Next, this study implemented exploratory factor analysis and reliability to ensure both validity and reliability of measurement items. This study executed multiple regression analysis to test research hypotheses Findings - Regrading results, brand awareness, employee service, and product diversity are positively associated with willingness to pay of duty free shop product. Moreover, the results of regression analysis suggest the inverted-U shape association between crowding and willingness to pay. However, price fairness appeared as non-significant variable to account for willingness to pay in the multiple regression analysis. Originality - This study contributes to the literature by examining duty free shop customers more.

• 한국산학기술학회논문지
• /
• 제21권11호
• /
• pp.543-553
• /
• 2020

본 연구는 2018년 제7기 국민건강영양조사 결과를 이용한 2차 자료 분석이었다. 본 연구의 목적은 65세 이상 여성노인의 신체활동, 체질량지수, 우울이 건강관련 삶의 질에 미치는 영향을 파악하고 비교하기 위함이다. 구체적으로 연구대상자는 고혈압 진단을 받은 여성노인 550명, 고혈압 진단을 받지 않은 여성노인 375명으로 구성되었다. SPSS/WIN 22.0 프로그램을 이용하여 기술통계, chi-square test, t-test, multiple linear regression으로 분석하였다. 다중 선형 회귀 분석결과, 고혈압군에서 나이, 교육, 신체활동, 체질량 지수, 우울이 건강관련 삶의 질에 유의한 예측인자로 확인되었고 설명력은 26.9%였다(F=14.30, p<.001). 즉 신체활동량이 많을수록(t=3.02, p=.003), 체질량 지수가 낮을수록(t=-3.12, p=.002), 우울이 낮을수록(t=-7.69, p<.001) 건강관련 삶의 질이 높았다. 반면, 비고혈압군에서 교육과 우울이 건강관련 삶의 질에 유의한 영향인자로 확인되었고 설명력은 31.7%였다(F=5.37, p<.001). 즉, 우울이 낮을수록 (t=-5.53, p<.001) 건강관련 삶의 질이 높았다. 이러한 결과를 바탕으로 향후 고혈압 질환을 갖고 있는 여성노인을 대상으로 다른 구체적 신체활동의 특성을 비교하는 연구와 여성노인의 우울 및 비만 감소를 위한 신체활동 중재 프로그램의 개발이 필요하다.

• Journal of Electrical Engineering and Technology
• /
• 제11권6호
• /
• pp.1628-1633
• /
• 2016

This paper derives an effective shape of the ferromagnetic pole pieces (low-speed rotor) for the reduction of transmission torque ripple in a magnetic-geared machine based on a Box-Behnken design (BBD). In particular, using a non-linear finite element method (FEM) based on 2-D numerical analysis, we conduct a numerical investigation and analysis between independent variables (selected by the BBD) and reaction variables. In addition, we derive a regression equation for reaction variables according to the independent variables by using multiple regression analysis and analysis of variance (ANOVA). We assess the validity of the optimized design by comparing characteristics of the optimized model derived from a response surface analysis and an initial model.

• Advances in concrete construction
• /
• 제10권6호
• /
• pp.463-478
• /
• 2020

Multiple mathematical modeling for prediction of slump, compressive strength and depth of water penetration at 28 days were performed using statistical analysis for the concrete containing waste limestone powder as partial replacement of sand obtained from experimental program reported in this research. To extract experimental data, 180 concrete cubic samples with 20 different mix designs were investigated. The twenty non-linear regression models were used to predict each of the concrete properties including slump, compressive strength and water depth penetration of concrete with waste limestone powder. Evaluation of the models using numerical methods showed that the majority of models give acceptable prediction with a high accuracy and trivial error rates. The 15-term regression models for predicting the slump, compressive strength and water depth were found to have the best agreement with the tested concrete specimens.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2021년도 춘계학술대회
• /
• pp.271-273
• /
• 2021

본 논문은 이동노드의 클러스터링내에서 보다 효율적인클러스터링을 제공하고 유지하기위한 딥러닝의 선형회귀적 적응적 보정가중치에 따른 군집적 알고리즘을 제안한다. 대부분의 클러스터링 군집데이터를 처리함에 있어 상호관계에 따른 분류체계가 제공된다. 이러한 경우 이웃한 이동노드중 목적노드와는 연결가능성이 가장높은 이동노드를 클러스터내에서 중계노드로 선택해야 한다. 본 연구에서는 이러한 상황정보를 이해하고 동적이동노드간 속도와 방향속성정보간의 상관관계의 친밀도를 고려한 자율학습기반의 회귀적 모델에서 적응적 가중치에 따른 분류를 제시한다. 본 논문에서는 이러한 상황정보를 이해하고 클러스터링을 유지할 수 있는 자율학습기반의 적응적 가중치에 따른 딥러닝 모델을 제시 한다.

• Advances in concrete construction
• /
• 제10권6호
• /
• pp.479-488
• /
• 2020

The experimental and numerical works were carried out on high performance fiber reinforced concrete (HPFRC) with w/cm ratios ranging from 0.25 to 0.40, fiber volume fraction (Vf)=0-1.5% and 10% silica fume replacement. Improvements in compressive and flexural strengths obtained for HPFRC are moderate and significant, respectively, Empirical equations developed for the compressive strength and flexural strength of HPFRC as a function of fiber volume fraction. A relation between flexural strength and compressive strength of HPFRC with R=0.78 was developed. Due to the complex mix proportions and non-linear relationship between the mix proportions and properties, models with reliable predictive capabilities are not developed and also research on HPFRC was empirical. In this paper due to the inadequacy of present method, a back propagation-neural network (BP-NN) was employed to estimate the 28-day compressive strength of HPFRC mixes. BP-NN model was built to implement the highly non-linear relationship between the mix proportions and their properties. This paper describes the data sets collected, training of ANNs and comparison of the experimental results obtained for various mixtures. On statistical analyses of collected data, a multiple linear regression (MLR) model with R2=0.78 was developed for the prediction of compressive strength of HPFRC mixes, and average absolute error (AAE) obtained is 6.5%. On validation of the data sets by NNs, the error range was within 2% of the actual values. ANN model has given the significant degree of accuracy and reliability compared to the MLR model. ANN approach can be effectively used to estimate the 28-day compressive strength of fibrous concrete mixes and is practical.