• Journal of the Korean Society of Marine Environment & Safety
• /
• v.9 no.1
• /
• pp.51-56
• /
• 2003

The prevention of marine accidents has been a major topic in marine society for long time and various safety policies and Countermeasures have been developed and applied to prevent those accidents. In spite of these efforts, however significant marine accidents have taken place intermittently. Ship is being operated under a highly dynamic environments and many factors are related with ship's collision and those factors are interacting. So, the analysis on ship's collision rouses are very important to prepare countermeasures which will ensure the safe navigation. This study analysed the ship's collision data over the past 10 years(1991-2000), which is compiled by Korea Marine Accidents Inquiry Agency. The analysis confirmed that ‘ship's collision’ is occurred most frequently and the cause is closely related with human factor. The main purpose if this study is to propose risk control countermeasures of ship's collision. For this, the structure of human factor is analysed by the questionnaire methodology. Marine experts were surveyed based on major elements that were extracted from the human factor affecting to ship's collision FSM has been widely adopted in modeling a dynamic system which is composed of human factors. Then, the structure analysis on the rouses of ship's collision using FSM are performed. This structure model could be used in understanding and verifying the procedure of real ship's collision. Furthermore it could be used as the model to prevent ship's collision and to reduce marine accidents.

• Journal of Digital Convergence
• /
• v.18 no.1
• /
• pp.301-307
• /
• 2020

In recent years, a recommendation system is introduced in many different fields with the beginning of the 5G era and making a considerably prominent appearance mainly in books, movies, and music. In such a recommendation system, however, the preference degrees of users are subjective and uncertain, which means that it is difficult to provide accurate recommendation service. There should be huge amounts of learning data and more accurate estimation technologies in order to improve the performance of a recommendation system. Trying to solve this problem, this study proposed a movie recommendation system based on Fuzzy-AHP and Word2vec. The proposed system used Fuzzy-AHP to make objective predictions about user preference and Word2vec to classify scraped data. The performance of the system was assessed by measuring the accuracy of Word2vec outcomes based on grid search and comparing movie ratings predicted by the system with those by the audience. The results show that the optimal accuracy of cross validation was 91.4%, which means excellent performance. The differences in move ratings between the system and the audience were compared with the Fuzzy-AHP system, and it was superior at approximately 10%.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.25 no.2
• /
• pp.174-179
• /
• 2015

Failure Mode and Effects Analysis (FMEA) has been used by Dynamic Positioning (DP) system for risk and reliability analysis. However, there are limitations associated with its implementation in offshore project. 1) since the failure data measured from the SCADA system is missing or unreliable, assessments of Severity, Occurrence, Detection are based on expert's knowledge; 2) it is not easy for experts to precisely evaluate the three risk factors. The risk factors are often expressed in a linguistic way. 3) the relative importance among three risk factors are rarely even considered. To solve these problems and improve the effectiveness of the traditional FMEA, we suggest a Fuzzy-FMEA method for risk and failure mode analysis in Dynamic Positioning System of offshore. The information gathered from DP FMEA report and DP FMEA Proving Trials is expressed using fuzzy linguistic terms. The proposed method is applied to an offshore Dynamic Positioning system, and the results are compared with traditional FMEA.

• Journal of the Korea Convergence Society
• /
• v.12 no.1
• /
• pp.99-104
• /
• 2021

In this paper, we propose health risk management using feature extraction and cluster analysis considering time flow. The proposed method proceeds in three steps. The first is the pre-processing and feature extraction step. It collects user's lifelog using a wearable device, removes incomplete data, errors, noise, and contradictory data, and processes missing values. Then, for feature extraction, important variables are selected through principal component analysis, and data similar to the relationship between the data are classified through correlation coefficient and covariance. In order to analyze the features extracted from the lifelog, dynamic clustering is performed through the K-means algorithm in consideration of the passage of time. The new data is clustered through the similarity distance measurement method based on the increment of the sum of squared errors. Next is to extract information about the cluster by considering the passage of time. Therefore, using the health decision-making system through feature clusters, risks able to managed through factors such as physical characteristics, lifestyle habits, disease status, health care event occurrence risk, and predictability. The performance evaluation compares the proposed method using Precision, Recall, and F-measure with the fuzzy and kernel-based clustering. As a result of the evaluation, the proposed method is excellently evaluated. Therefore, through the proposed method, it is possible to accurately predict and appropriately manage the user's potential health risk by using the similarity with the patient.

• Journal of the Computational Structural Engineering Institute of Korea
• /
• v.37 no.3
• /
• pp.173-178
• /
• 2024

This study presents a technique for assessing the dimensional quality of assembly parts in Prefabricated Steel Structures (PSS) using a stereo vision sensor. The stereo vision system captures images and point cloud data of the assembly area, followed by applying image processing algorithms such as fuzzy-based edge detection and Hough transform-based circular bolt hole detection to identify bolt hole locations. The 3D center positions of each bolt hole are determined by correlating 3D real-world position information from depth images with the extracted bolt hole positions. Principal Component Analysis (PCA) is then employed to calculate coordinate axes for precise measurement of distances between bolt holes, even when the sensor and structure orientations differ. Bolt holes are sorted based on their 2D positions, and the distances between sorted bolt holes are calculated to assess the assembly part's dimensional quality. Comparison with actual drawing data confirms measurement accuracy with an absolute error of 1mm and a relative error within 4% based on median criteria.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.13 no.9
• /
• pp.1905-1912
• /
• 2009

Clustering results based on the FCM algorithm sometimes produces undesirable clustering result through data distribution in the clustered space because data is classified by comparison with membership degree which is calculated by the Euclidean distance between input vectors and clusters. Symmetrical measurement of clusters and fuzzy theory are applied to the classification to tackle this problem. The enhanced FCM algorithm has a low impact with the variation of changing distance about each cluster, middle of cluster and cluster formation. Improved hybrid network of applying FCM algorithm is proposed to classify patterns effectively. The proposed enhanced FCM algorithm is applied to the learning structure between input and middle layers, and normalized delta learning rule is applied in learning stage between middle and output layers in the hybrid network. The proposed algorithms compared with FCM-based RBF network using Max_Min neural network, FMC-based RBF network and HCM-based RBF network to evaluate learning and recognition performances in the two-dimensional coordinated data.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.28 no.6
• /
• pp.390-395
• /
• 2015

Molded insulation materials are widely used from large electric power transformer apparatus to small electrical machinery and apparatus. In this study, by adding MgO with the average particle of several tens nm and the excellent thermal conductivity into molding material, we improved the problem of insulation breakdown strength decrease according to rising temperature in overload or in bad environmental condition. We confirmed the life evaluation by using the insulation breakdown and inverse involution to investigate the electrical characteristics of nano-composites materials. By using a scanning electron microscope, it is confirmed that MgO power with the average particle size of several tens nm is distributed and the filler particles is uniformly distributed in the cross section of specimens. And it is confirmed that the insulation breakdown strength of Virgin specimens is rapidly decreased at the high temperature area. But it is confirmed that the insulation breakdown strength of specimens added MgO slow decreased by thermal properties in the high temperature area improved by the contribution of the heat radiation of MgO and the suppression of tree. The results of life prediction using inverse involution, it is confirmed that the life of nano-composites is improved by contribution of MgO according to the predicted insulation breakdown strength after 10 years of specimens added 5.0 wt% of MgO is increased about 2.9 times at RT, and 4.9 times at $100^{\circ}C$ than Virgin specimen, respectively.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.49 no.9
• /
• pp.314-321
• /
• 2012

Harmful gases which are generated from various rout at growth environment of livestock ban have a direct and indirect bad influence to the livestock and farmers, and also step-up breeding density and long-term exposure to the sealed environment of winter can be fatal. In this paper, we propose a gas measurement system for monitoring gases of ammonia, hydrogen sulfide, volatile organic compounds, etc. which arise from the muck. The measurement system consist of both wireless gas sensor node and gas recognition software using a Fuzzy Min-Max neural network. To evaluate the performance of suggested system, gas measurement experiments are performed in laboratory environment by using the designed wireless gas sensor node. And we show the performance through classification test for the target gases by the designed gas recognition software.

• Ecology and Resilient Infrastructure
• /
• v.4 no.1
• /
• pp.63-70
• /
• 2017

Tetracycline (TC) groups, widely used veterinary antibiotics, can enter into environment through animal manure application. TC forms a ligand complex with multivalent metal cations via chelation that can affect sorption and mobility of TC in soil. So far, however, it has been confirmed through the reaction of the soil outside in the aqueous solution and the evaluation of the performance in the soil cultivation process is insufficient. The purpose of this study was to examine effects of copper on TC toxicity to lettuce growth. In this research, $750mg\;kg^{-1}$ of TC and 2.5, 7.5, $17.5mg\;kg^{-1}$ of Cu are treated in soil and lettuce was cultivated in the treated soil. Growth difference of lettuce by treatment was observed. As a result, $750mg\;kg^{-1}$ of TC treated soil showed toxic effect to lettuce and the effect is alleviated by copper treatment.

• Archives of design research
• /
• v.20 no.3 s.71
• /
• pp.203-214
• /
• 2007

This study proposes an information retrieval method reflecting the user's preferences based on the fuzzy set theory to develop information contents which support pedestrian's navigation. Firstly, the research evaluated subjects' preferences on commercial spaces set to a hypothetical destination. Also it surveyed the causal relationship between the visual characteristics and the emotional characteristics to propose methods of Navigation Knowledge Base (NKB). The NKB was composed of three elements; 1. the correlation model between emotional characteristics, 2. the causal relationship between visual characteristics and emotional characteristics, 3. the transformation model between visual characteristics and the physical characteristics. Secondly, this study classified the pedestrian's destination search into 4 types with his or her preferences and the time conditions limited during navigation. For each type it presented the Destination Search Algorithm (DSA). Finally, the research simulated the destination search in 4 navigation types using NKB and DSA and verified the availability of the information retrieval method reflecting pedestrian's preferences. In conclusion, the proposed information search method will be applied to reflect the user's preferences to develop information appliances.