• Journal of the Korean Institute of Navigation
• /
• v.17 no.3
• /
• pp.57-68
• /
• 1993

The economy of Korea has grown up significantly in its scale. It has, therefore, become imperative to develop countermeasures to prevent work related injuries and occupational illnesses resultining from haza-rdous working conditions and handling harmful substances. A lot of cargo handling accident in port have occurred due to the characteristics of poor working environment, diversity of working place and method, fluctuation of the amount of cargo and handling of heavy, long, harmful and dangerous cargo, etc. According to '91 industrial accident analysis carried out by the ministry of labour, the number of the stevedores injured by cargo handling accident in port were 1, 432 persons (the death accident : 22 per-sons), the amount of industrial accident compensation in port was 6.7 billion won (the amount of economic loss : 33.6 billion won), and the injury occurance rate of the stevedoring industry was higher than that of the whole industry. This paper, therefore, aims to the actual status of the stevedoring industry and to extract the main cau-ses of the accidents related to cargo handling in port through factor analysis using the data of the accide-nts in the whole habour from 1990 to 1992, and to suggest the countermeasures to prevent such accident. The main causes of the accident and countermeasures are found to be as follows through the factor analy-sis : Factor1, factor2, and factor3 related to a defect of human being and management, a defect of state and environment, and an insufficiency of education and law are extracted. The short-term countermeasures to prevent these accidents are 1) to consolidate the safety and health organization in the working spot, 2) to secure a safe condition in working spot before dock work, 3) to strengthen a dock worker's safety educa-tion. The long-term countermeasures are 1) to promote a decasualisation of dock workers, 2) to modernize the cargo working methods through constructing exclusive pier and introducing exclusive cargo handling equipment, 3) to establish a exclusive dock accident prevention organization and the dock workers law. Factor 4, factor5, factor6, and factor7 related to an unfitness, a deficiency of technical knowledge, a nonfu-lfilment of safety measures, and a bad arrangement are extracted. The countermeasures to prevent these accidents are 1) to perform a complete safety inspection of cargo handling equipments and tools and to carry out the dock work according to a working plan, 2) to publish and supply technical safety books, safety instruction book, safety check list, etc., 3) to strengthen the safety patrol at the working spot in habour and to activate a safety fund, 4) to maintain always a clean workshop with the safety consciousness in which the good arragement of the working spot is considered to be the beginning of safety.

• Proceedings of the Korean Operations and Management Science Society Conference
• /
• 1997.10a
• /
• pp.177-180
• /
• 1997

Outliers, unexpected extraordinary observations that look discordant from most observation in a data set are commonplace in various kinds of data analysis. Since the effect of outliers on model identification could be serious, the aim of this paper is to present some ways of handling outliers in given data set and to specify a model in the presence of outliers. A procedure based on neural network which identifies outliers, removes their effects, and specifies a model for the underlying process is proposed. In contrast with traditional parametric methods requiring to estimate the model's structure and parameters before detecting outliers, the proposed procedure is a nonparametric method without the estimation of model's structure and parameters before handling outliers and could be applied for real problems in the presence of outliers. The proposed methodology is performed as followings. Firstly, outliers are detected and the detected outliers replace the prediction values using outliers detection neural network. The data set removing the effect of outliers is retraining using neural network. Therefore the effects of outliers are removed and the modeling precision can be improved. Experimental results show that the proposed method is suitable for predicting data set in the presence of outliers.

• The Journal of the Korea Contents Association
• /
• v.19 no.11
• /
• pp.567-577
• /
• 2019

Recently, more and more attempts have been made to solve the problems faced by academia and industry through machine learning. Accordingly, various attempts are being made to solve non-general situations through machine learning, such as deviance, fraud detection and disability detection. A variety of attempts have been made to resolve the non-normal situation in which data is distributed disproportionately, generally resulting in errors. In this paper, we propose handling method of imbalance data for machine learning. The proposed method to such problem of an imbalance in data by verifying that the population distribution of major class is well extracted. Performance Evaluations have proven the proposed method to be better than the existing methods.

• Geomechanics and Engineering
• /
• v.33 no.3
• /
• pp.231-242
• /
• 2023

This paper represents a comparative study in which Gene Expression Programming (GEP), Group Method of Data Handling (GMDH), and multiple linear regressions (MLR) were utilized to derive new equations for the prediction of time-dependent bearing capacity of pile foundations driven in cohesive soil, technically called pile set-up. This term means that many piles which are installed in cohesive soil experience a noticeable increase in bearing capacity after a specific time. Results of researches indicate that side resistance encounters more increase than toe resistance. The main reason leading to pile setup in saturated soil has been found to be the dissipation of excess pore water pressure generated in the process of pile installation, while in unsaturated conditions aging is the major justification. In this study, a comprehensive dataset containing information about 169 test piles was obtained from literature reviews used to develop the models. to prepare the data for further developments using intelligent algorithms, Data mining techniques were performed as a fundamental stage of the study. To verify the models, the data were randomly divided into training and testing datasets. The most striking difference between this study and the previous researches is that the dataset used in this study includes different piles driven in soil with varied geotechnical characterization; therefore, the proposed equations are more generalizable. According to the evaluation criteria, GEP was found to be the most effective method to predict set-up among the other approaches developed earlier for the pertinent research.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 1998.06a
• /
• pp.139-142
• /
• 1998

Missing values in data for fuzzy c-menas clustering is discussed. Two basic methods of fuzzy c-means, i.e., the standard fuzzy c-means and the entropy method are considered and three options of handling missing values are proposed, among which one is to define a new distance between data with missing values, second is to alter a weight in the new distance, and the third is to fill the missing values by an appropriate numbers. Experimental Results are shown.

• Journal of the Korean Society of Safety
• /
• v.25 no.4
• /
• pp.30-35
• /
• 2010

For the safe handling of acetone, the flash point, the explosion limit at $25^{\circ}C$ and the temperature dependence of the explosion limits were investigated. And the AIT for acetone were experimented. By using the literatures data, the lower and upper explosion limits of acetone recommended 2.5 vol% and 13.0 vol%, respectively. In this study, the lower flash points of acetone recommended $-20^{\circ}C$. This study was determined relationship between the AITs and the ignition delay times by using ASTM E659-78 apparatus for acetone, and the experimental AIT of acetone was $565^{\circ}C$. The new equations for predicting the temperature dependence of the explosion limits of acetone is proposed. The values calculated by the proposed equations were a good agreement with the literature data.

• Journal of the Korean Society of Safety
• /
• v.24 no.5
• /
• pp.28-33
• /
• 2009

The thermochemical parameters for safe handling, storage, transport, operation and process design of flammable substances are explosion limit, flash point, autoignition temperatures(AITs), minimum oxygen concentration(MOC), heat of combustion etc.. Also it is necessary to know explosion limit at high temperature and pressure. For the safe handling of benzene, lower explosion limit(LEL) at $25^{\circ}C$, the temperature dependence of the explosion limits and flash point were investigated. And the AITs for benzene were experimented. By using the literatures data, the lower and upper explosion limits of benzene recommended 1.3 vol% and 8.0 vol%, respectively. This study measured relationship between the AITs and the ignition delay times by using ASTM E659-78 apparatus for benzene, and the experimental AIT of benzene was $583^{\circ}C$. The new equations for predicting the temperature dependence of the explosion limits of benzene is proposed. The values calculated by the proposed equations were a good agreement with the literature data.

• Journal of the Ergonomics Society of Korea
• /
• v.13 no.2
• /
• pp.49-55
• /
• 1994

It is not difficult to find risky manual material handling which requires various arm exertion for moving and assembling irregular stuffs in industries. Many of workers have been hurt on their muscular and skeletal system due to the manual material handling. This study is to provide data for isokinetic muscular strength elbow flexors and extensors of Korean male and female adults. Provided standard data for isokinetic muscular strength of elbow flexous and extensors can be used for scientific and systematic analysis of arm exertionl.

• Journal of the Korean Society of Safety
• /
• v.26 no.2
• /
• pp.36-41
• /
• 2011

For the safe handling of n-hexane, the explosion limit at $25^{\circ}C$, the temperature dependence of the explosion limits and the lower flash point were investigated. And AITs(auto-ignition temperatures) by ignition delay time for n-hexane were experimented. By using the literatures data, the lower and upper explosion limits of n-hexane recommended 1.0 Vol% and 8.0 Vol%, respectively. In this study, the lower flash points of n-hexane recommended $-23^{\circ}C$. This study measured relationship between the AITs and the ignition delay times by using ASTM E659-78 apparatus for n-hexane, and the experimental AIT of n-hexane was $240^{\circ}C$. The new equations for predicting the temperature dependence of the explosion limits of n-hexane is proposed. The values calculated by the proposed equations were a good agreement with the literature data.

• KSBB Journal
• /
• v.9 no.2
• /
• pp.98-103
• /
• 1994

A bed configuration wherein sheets of modified fibrous polyethylene are potted within a Millipore Filter Cartridge matrix has been developed. Polyethylene fibers form sturdy beds but the native hydrophobicity and inertness of polyethylene have precluded their use in protein chromatography The polyethylene fibers used in this system were modified by plasma oxidation and further derivatization. The resulting fibers are hydrophilic, bind protein reversibly and serve as an anion-exchange stationary phase. Separation of Bovine Serum Albumin on this bed, as well as results of basic studies on capacity and reversibility of binding within a fibrous bed and experimental data handling system are shown.