• Journal of the Korea Institute of Building Construction
• /
• v.13 no.2
• /
• pp.159-168
• /
• 2013

Construction projects have become increasingly complex in recent years, resulting in substantial safety hazards and frequent fall accidents. In an attempt to prevent fall accidents, various safety management systems have been developed. These systems have mainly been evaluated qualitatively and subjectively by practitioners or supervisors, and there are few tools that can be used to quantitatively evaluate the performance of safety management systems. We propose an expertise-based safety performance evaluation model (EXSPEM), which integrates a fuzzy approach-based analytic hierarchy process and a regression approach. The proposed model uses S-shaped curves to represent the degree of contribution by subjective expertise and is verified by a genetic algorithm. To illustrate its practical application, EXSPEM was applied to evaluate the safety performance of a newly developed real-time mobile detector monitoring system. It is expected that this model will be a helpful tool for systematically evaluating the application of a robust safety control and management system in a complex construction environment.

• Journal of the Korean Society of Safety
• /
• v.18 no.2
• /
• pp.73-78
• /
• 2003

In order to improve the safety performance oi construction projects, effective and corporative safety management program between head office and job site must be implemented. And its performance must be measured and analyzed for the identification of the problems in the safety management area. This study proposes a previous evaluation model of safety performance for the large construction firm in order to enhance their safety level. The fundamental data for proposed model is based on the past research(Son 2002), which is structured of evaluation criteria. weighted factor. statistical evaluation formula. The model would help the firm management in identifying the weak areas of safety performance in terms of the degree performing certain safety tasks. It is expected that the model could contribute to achieving the "zero accident" level.ot; level.

• Journal of the Semiconductor & Display Technology
• /
• v.21 no.3
• /
• pp.63-68
• /
• 2022

In this study, we produced defect detection models using parallel convolution neural networks. If convolution neural networks are constructed parallel type, the model's detection accuracy will increase and detection time will decrease. We produced parallel-type defect detection models using 4 types of convolutional algorithms. The performance of models was evaluated using evaluation indicators. The model's performance is detection accuracy and detection time. We compared the performance of each parallel model. The detection accuracy of the model using AlexNet is 97 % and the detection time is 0.3 seconds. We confirmed that when AlexNet algorithm is constructed parallel type, the model has the highest performance.

• Journal of Korean Society of Water and Wastewater
• /
• v.36 no.4
• /
• pp.239-248
• /
• 2022

The prediction of algal bloom is an important field of study in algal bloom management, and chlorophyll-a concentration(Chl-a) is commonly used to represent the status of algal bloom. In, recent years advanced machine learning algorithms are increasingly used for the prediction of algal bloom. In this study, XGBoost(XGB), an ensemble machine learning algorithm, was used to develop a model to predict Chl-a in a reservoir. The daily observation of water quality data and climate data was used for the training and testing of the model. In the first step of the study, the input variables were clustered into two groups(low and high value groups) based on the observed value of water temperature(TEMP), total organic carbon concentration(TOC), total nitrogen concentration(TN) and total phosphorus concentration(TP). For each of the four water quality items, two XGB models were developed using only the data in each clustered group(Model 1). The results were compared to the prediction of an XGB model developed by using the entire data before clustering(Model 2). The model performance was evaluated using three indices including root mean squared error-observation standard deviation ratio(RSR). The model performance was improved using Model 1 for TEMP, TN, TP as the RSR of each model was 0.503, 0.477 and 0.493, respectively, while the RSR of Model 2 was 0.521. On the other hand, Model 2 shows better performance than Model 1 for TOC, where the RSR was 0.532. Explainable artificial intelligence(XAI) is an ongoing field of research in machine learning study. Shapley value analysis, a novel XAI algorithm, was also used for the quantitative interpretation of the XGB model performance developed in this study.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.14 no.4
• /
• pp.207-218
• /
• 2019

The purpose of this study is to develop a model that can systematically study the whole learning process of machine learning. Since the existing model describes the learning process with minimum coding, it can learn the progress of machine learning sequentially through the new model, and can visualize each process using the tensor flow. The new model used all of the existing model algorithms and confirmed the importance of the variables that affect the target variable, survival. The used to classification training data into training and verification, and to evaluate the performance of the model with test data. As a result of the final analysis, the ensemble techniques is the all tutorial model showed high performance, and the maximum performance of the model was improved by maximum 5.2% when compared with the existing model using. In future research, it is necessary to construct an environment in which machine learning can be learned regardless of the data preprocessing method and OS that can learn a model that is better than the existing performance.

• Journal of Intelligence and Information Systems
• /
• v.21 no.1
• /
• pp.119-142
• /
• 2015

With the explosive growth in the volume of information, Internet users are experiencing considerable difficulties in obtaining necessary information online. Against this backdrop, ever-greater importance is being placed on a recommender system that provides information catered to user preferences and tastes in an attempt to address issues associated with information overload. To this end, a number of techniques have been proposed, including content-based filtering (CBF), demographic filtering (DF) and collaborative filtering (CF). Among them, CBF and DF require external information and thus cannot be applied to a variety of domains. CF, on the other hand, is widely used since it is relatively free from the domain constraint. The CF technique is broadly classified into memory-based CF, model-based CF and hybrid CF. Model-based CF addresses the drawbacks of CF by considering the Bayesian model, clustering model or dependency network model. This filtering technique not only improves the sparsity and scalability issues but also boosts predictive performance. However, it involves expensive model-building and results in a tradeoff between performance and scalability. Such tradeoff is attributed to reduced coverage, which is a type of sparsity issues. In addition, expensive model-building may lead to performance instability since changes in the domain environment cannot be immediately incorporated into the model due to high costs involved. Cumulative changes in the domain environment that have failed to be reflected eventually undermine system performance. This study incorporates the Markov model of transition probabilities and the concept of fuzzy clustering with CBCF to propose predictive clustering-based CF (PCCF) that solves the issues of reduced coverage and of unstable performance. The method improves performance instability by tracking the changes in user preferences and bridging the gap between the static model and dynamic users. Furthermore, the issue of reduced coverage also improves by expanding the coverage based on transition probabilities and clustering probabilities. The proposed method consists of four processes. First, user preferences are normalized in preference clustering. Second, changes in user preferences are detected from review score entries during preference transition detection. Third, user propensities are normalized using patterns of changes (propensities) in user preferences in propensity clustering. Lastly, the preference prediction model is developed to predict user preferences for items during preference prediction. The proposed method has been validated by testing the robustness of performance instability and scalability-performance tradeoff. The initial test compared and analyzed the performance of individual recommender systems each enabled by IBCF, CBCF, ICFEC and PCCF under an environment where data sparsity had been minimized. The following test adjusted the optimal number of clusters in CBCF, ICFEC and PCCF for a comparative analysis of subsequent changes in the system performance. The test results revealed that the suggested method produced insignificant improvement in performance in comparison with the existing techniques. In addition, it failed to achieve significant improvement in the standard deviation that indicates the degree of data fluctuation. Notwithstanding, it resulted in marked improvement over the existing techniques in terms of range that indicates the level of performance fluctuation. The level of performance fluctuation before and after the model generation improved by 51.31% in the initial test. Then in the following test, there has been 36.05% improvement in the level of performance fluctuation driven by the changes in the number of clusters. This signifies that the proposed method, despite the slight performance improvement, clearly offers better performance stability compared to the existing techniques. Further research on this study will be directed toward enhancing the recommendation performance that failed to demonstrate significant improvement over the existing techniques. The future research will consider the introduction of a high-dimensional parameter-free clustering algorithm or deep learning-based model in order to improve performance in recommendations.

• Asian Pacific Journal of Cancer Prevention
• /
• v.16 no.8
• /
• pp.3429-3434
• /
• 2015

Background: This study analyzed predictors of regular mammography performance in Korea. In addition, we determined factors affecting regular mammography performance in life-transition aged women by applying an attitude, social influence, and self-efficacy (ASE) model. Materials and Methods: Data were collected from women aged over 40 years residing in province J in Korea. The 178 enrolled subjects provided informed voluntary consent prior to completing a structural questionnaire. Results: The overall regular mammography performance rate of the subjects was 41.6%. Older age, city residency, high income and part-time job were associated with a high regular mammography performance. Among women who had undergone more breast self-examinations (BSE) or more doctors' physical examinations (PE), there were higher regular mammography performance rates. All three ASE model factors were significantly associated with regular mammography performance. Women with a high level of positive ASE values had a significantly high regular mammography performance rate. Within the ASE model, self-efficacy and social influence were particularly important. Logistic regression analysis explained 34.7% of regular mammography performance and PE experience (${\beta}=4.645$, p=.003), part-time job (${\beta}=4.010$, p=.050), self-efficacy (${\beta}=1.820$, p=.026) and social influence (${\beta}=1.509$, p=.038) were significant factors. Conclusions: Promotional strategies that could improve self-efficacy, reinforce social influence and reduce geographical, time and financial barriers are needed to increase the regular mammography performance rate in life-transition aged.

• Proceedings of the Korean Society of Propulsion Engineers Conference
• /
• 2004.03a
• /
• pp.513-520
• /
• 2004

A steady-state/transient performance simulation model was newly developed for the propulsion system of the CRW (Canard Rotor Wing) type UAV (Unmanned Aerial Vehicle) during flight mode transition. The CRW type UAV has a new concept RPV (Remotely Piloted Vehicle) which can fly at two flight modes such as the take-off/landing and low speed forward flight mode using the rotary wing driven by engine bypass exhaust gas and the high speed forward flight mode using the stopped wing and main engine thrust. The propulsion system of the CRW type UAV consists of the main engine system and the duct system. The flight vehicle may generally select a proper type and specific engine with acceptable thrust level to meet the flight mission in the propulsion system design phase. In this study, a turbojet engine with one spool was selected by decision of the vehicle system designer, and the duct system is composed of main duct, rotor duct, master valve, rotor tip-jet nozzles, and variable area main nozzle. In order to establish the safe flight mode transition region of the propulsion system, steady-state and transient performance simulation should be needed. Using this simulation model, the optimal fuel flow schedules were obtained to keep the proper surge margin and the turbine inlet temperature limitation through steady-state and transient performance estimation. Furthermore, these analysis results will be used to the control optimization of the propulsion system, later. In the transient performance model, ICV (Inter-Component Volume) model was used. The performance analysis using the developed models was performed at various flight conditions and fuel flow schedules, and these results could set the safe flight mode transition region to satisfy the turbine inlet temperature overshoot limitation as well as the compressor surge margin. Because the engine performance simulation results without the duct system were well agreed with the engine manufacturer's data and the analysis results using a commercial program, it was confirmed that the validity of the proposed performance model was verified. However, the propulsion system performance model including the duct system will be compared with experimental measuring data, later.

• Journal of the Korean Solar Energy Society
• /
• v.27 no.3
• /
• pp.135-142
• /
• 2007

The model to predict flow duration characteristics and performance for small scale hydro power(SSHP) plants is studied to analyze the effects of rainfall condition. One existing SSHP plant was selected and performance characteristics was analyzed by using the developed model. The predicted results from the model developed show that the data were in good agreement with operational results of existing SSHP plant. The results show that both the scale parameter and the shape parameter have large effects on the performance of SSHP sites. And also it was found that the model developed in this study can be a useful tool to predict the performance of SSHP sites.

• Journal of Korean Society for Quality Management
• /
• v.33 no.4
• /
• pp.42-54
• /
• 2005

This paper has the purpose to find out the causal model between QCC activities and performance. This study consists of four hypotheses. First, QCC teamwork has positive influence on QCC performance. Second, QCC atmosphere has positive influence on QCC performance. Third, QCC autonomy has positive influence on QCC performance. Fourth, this causal model is appropriate for representing the relationship between QCC activities and performance. The results of hypothesis testing are as follows. The first and the fourth hypotheses are adopted. The second and the third hypotheses are rejected. Therefore, QCC teamwork will accelerate QCC activities more than atmosphere and autonomy of QCC.