• Journal of the Korean Institute of Gas
• /
• v.4 no.2 s.10
• /
• pp.52-57
• /
• 2000

This paper suggests the evaluation sheet to ensure the objective and detailed information based on a classification table of PIF (Performance Influencing Factor). And this paper shows the results of HEP(Human Error Probability), using a quantitative method with the evaluated data as a result of estimating the likelihood of . human errors in the gas industry facility together with the evaluation sheet. Finally, these results are programmed to be operated in personal computer so that field workers an apply it in easy and convenient manner. The results of this study offer two key benefits; sharing reliable information on human errors with the Data Base and establishing a strategy to reduce human errors as well as to improve working proficiency.

• Journal of the Korean Institute of Gas
• /
• v.18 no.4
• /
• pp.68-75
• /
• 2014

It is necessary to control and evaluate human factors to reduce economic loss by major accident in toxic gas facilities. Conventional works to evaluate hazards have been focused on mechanical and systematic failure, while only a little works have been studied on managing human errors. In this work, a classification system of performance shaping factor (PSF) was suggested to consist human error in managing accident in the toxic gas facilities. Four types of PSFs (human, system, task characteristics, and task environment) were collected, reviewed, and analyzed to be categorized selected according their characteristics of situational, task, and environmental parameters. The PSFs were further modified to set up PSF systems adequate to evaluate human error, and the proposed system to consist PSFs to evaluate human error was further studied through accident analysis in toxic gas facilities.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.25 no.4
• /
• pp.161-169
• /
• 2017

The Human Factors Analysis and Classification System (HFACS) is a general human error framework originally developed and tested within the U.S. military as a tool for investigating and analyzing the human causes of aviation accidents. Based upon Reason's (1990) model of latent and active failures, HFACS addresses human error at all levels of the system, including the condition of aircrew and organizational factors. As a result, this study aims to examine the influence between the latent conditions based on HFACS. This study seeks to verify the factors of "Organizational Influence" effecting the "Precondition for Unsafe Acts" of HFACS. The results of empirical analysis demonstrated that the organizational influence had a positive influence on precondition for unsafe act, especially the "Organizational Climate" of organizational influence had even greater influence on precondition for unsafe acts.

• Proceedings of the KOSOMBE Conference
• /
• v.1997 no.11
• /
• pp.133-136
• /
• 1997

The human chromosome analysis is widely used to diagnose genetic disease and various congenital anomalies. Many researches on automated chromosome karyotype analysis has been carried out, some of which produced commercial systems. However, there still remains much room or improving the accuracy of chromosome classification. In this paper, We propose an optimal pattern classifier by neural network to improve the accuracy of chromosome classification. The proposed pattern classifier was built up of multi-step multi-layer neural network(MMANN). We reconstructed chromosome image to improve the chromosome classification accuracy and extracted three morphological features parameters such as centromeric index(C.I.), relative length ratio(R.L.), and relative area ratio(R.A.). This Parameters employed as input in neural network by preprocessing twenty human chromosome images. The experiment results show that the chromosome classification error is reduced much more than that of the other classification methods.

• Journal of the Korean Society for Railway
• /
• v.11 no.4
• /
• pp.404-409
• /
• 2008

This paper consists largely of two parts: the first part introduces the revised railway human reliability analysis (R-HRA) method which is to be used under the railway risk assessment framework, and the second part presents the features of a computer software which was developed for aiding the R-HRA process. The revised R-HRA method supplements the original R-HRA method by providing a specific task analysis guideline and a classification of performance shaping factors (PSFs) to support a consistent analysis between analysts. The R-HRA software aids the analysts in gathering information for HRA, qualitative error prediction including identification of external error modes and internal error modes, quantification of human error probability, and reporting the overall analysis results. The revised R-HRA method and software are expected to support the analysts in an effective and efficient way in analysing human error potential in railway event or accident scenarios.

• Proceedings of the Korean Nuclear Society Conference
• /
• 1995.10a
• /
• pp.293-299
• /
• 1995

A methodology is applied to identify tile learning trend related to the safety and availability of U.S. commercial nuclear power plants. The application is intended to aid in reducing likelihood of human errors. To assure that tile methodology ran be easily adapted to various types of classification schemes of operation data, a data bank classified by the Transient Analysis Classification and Evaluation(TRACE) scheme is selected for the methodology. The significance criteria for human-initiated events affecting tile systems and for events caused by human deficiencies were used. Clustering analysis was used to identify the learning trend in multi-dimensional histograms. A computer rode is developed based on tile K-Means algorithm and applied to find the learning period in which error rates are monotonously decreasing with plant age.

• Proceedings of the KSR Conference
• /
• 2010.06a
• /
• pp.2021-2028
• /
• 2010

Rail human factors research has grown rapidly in both quantity and quality of output over the past few years. Human factors, also, still plays a significant part in many railway accidents. In this paper we review categorized performance shaping factors of human errors associated with railway accidents within and out of the country. This paper deals with the selection of the important performance shaping factors under accident management situations in railway for use in the assessment of human errors. The purpose of this study is to classify which human error would be selected for accident analysis. Therefore, the classification of human errors suggested in this study may be useful to enhance the Korean railway system safety.

• Proceedings of the KIEE Conference
• /
• 2004.05a
• /
• pp.92-94
• /
• 2004

We become an industry information society which is advanced to the altitude with the today. The information to be loading various goods each other together at a circumstance environment is increasing extremely. The restriction recognizes the data of many Quantity and it follows because the human deals the task to classify. The development of a mathematical formulation for solving a problem like this is often very difficult. But Artificial intelligent systems such as neural networks have been successfully applied to solving complex problems in the area of pattern recognition and classification. So, in this paper a neural network approach is used to recognize and classification problem was broken into two steps. The first step consist of using a neural network to recognize the existence of purpose pattern. The second step consist of a neural network to classify the kind of the first step pattern. The neural network leaning algorithm is to use error back-propagation algorithm and to find the weight and the bias of optimum. Finally two step simulation are presented showing the efficacy of using neural networks for purpose recognition and classification.

• Journal of Navigation and Port Research
• /
• v.41 no.5
• /
• pp.303-318
• /
• 2017

In the shipping industry, it is well known that around 80 % or more of all marine accidents are caused fully or at least in part by human error. In this regard, the International Maritime Organization (IMO) stated that the study of human factors would be important for improving maritime safety. Consequently, the IMO adopted the Casualty Investigation Code, including guidelines to assist investigators in the implementation of the Code, to prevent similar accidents occurring again in the future. In this paper, a process of the human factors investigation is proposed to provide investigators with a guide for determining the occurrence sequence of marine accidents, to identify and classify human error-inducing underlying factors, and to develop safety actions that can manage the risk of marine accidents. Also, an application of these investigation procedures to a collision accident is provided as a case study This is done to verify the applicability of the proposed human factors investigation procedures. The proposed human factors investigation process provides a systematic approach and consists of 3 steps: 'Step 1: collect data & determine occurrence sequence' using the SHEL model and the cognitive process model; 'Step 2: identify and classify underlying human factors' using the Maritime-Human Factor Analysis and Classification System (M-HFACS) model; and 'Step 3: develop safety actions,' using the causal chains. The case study shows that the proposed human factors investigation process is capable of identifying the underlying factors and indeveloping safety actions to prevent similar accidents from occurring.

• International Journal of Computer Science & Network Security
• /
• v.22 no.4
• /
• pp.101-110
• /
• 2022

Histopathological analysis of biopsy specimens is still used for diagnosis and classifying the brain tumors today. The available procedures are intrusive, time consuming, and inclined to human error. To overcome these disadvantages, need of implementing a fully automated deep learning-based model to classify brain tumor into multiple classes. The proposed CNN model with an accuracy of 92.98 % for categorizing tumors into five classes such as normal tumor, glioma tumor, meningioma tumor, pituitary tumor, and metastatic tumor. Using the grid search optimization approach, all of the critical hyper parameters of suggested CNN framework were instantly assigned. Alex Net, Inception v3, Res Net -50, VGG -16, and Google - Net are all examples of cutting-edge CNN models that are compared to the suggested CNN model. Using huge, publicly available clinical datasets, satisfactory classification results were produced. Physicians and radiologists can use the suggested CNN model to confirm their first screening for brain tumor Multi-classification.