• Journal of the Korean Society of Safety
• /
• v.38 no.5
• /
• pp.51-57
• /
• 2023

Numerous studies have been conducted to analyze the causal relationships of maritime accidents using natural language processing techniques. However, when multiple causes and effects are associated with a single accident, the effectiveness of extracting these causal relations diminishes. To address this challenge, we compiled a dataset using verdicts from maritime accident cases in this study, analyzed their causal relations, and applied labeling considering the association information of various causes and effects. In addition, to validate the efficacy of our proposed methodology, we fine-tuned the KoELECTRA Korean language model. The results of our validation process demonstrated the ability of our approach to successfully extract multiple causal relationships from maritime accident cases.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.3
• /
• pp.291-296
• /
• 2006

In context-aware computing environment, some context is characterized by a single event, but many other contexts are determined by a sequence of events which happen with some timing constraints. Therefore context inference could be conducted by monitoring the sequence of event occurrence along with checking their conformance with timing constraints. Some context could be described with fuzzy concepts instead of concrete concepts. Multiple entities may interact with a service system in the context-aware environments, and thus the context inference mechanism should be equipped to handle multiple entities in the same situation. This paper proposes a context inference model which is based on the so-called fuzzy colored timed Petri net. The model represents and handles the sequential occurrence of some events along with involving timing constraints, deals with the multiple entities using the colored Petri net model, and employs the concept of fuzzy tokens to manage the fuzzy concepts.

• Journal of the Korea Society of Computer and Information
• /
• v.16 no.4
• /
• pp.73-81
• /
• 2011

In this paper, an improved block-based background modeling technique using adaptive parameter estimation that judiciously adjusts the number of model histograms at each frame sequence is proposed. The conventional block-based background modeling method has a fixed number of background model histograms, resulting to false negatives when the image sequence has either rapid illumination changes or swiftly moving objects, and to false positives with motionless objects. In addition, the number of optimal model histogram that changes each type of input image must have found manually. We demonstrate the proposed method is promising through representative performance evaluations including the background modeling in an elevator environment that may have situations with rapid illumination changes, moving objects, and motionless objects.

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.32 no.8
• /
• pp.642-653
• /
• 2008

In this paper, we propose a 3-D finite element (FE) analysis model with combined physical behavior and kinematical impact factors for evaluation of residual stress in multi-impact shot peening. The FE model considers both physical behavior of material and characteristics of kinematical impact. The physical parameters include elastic-plastic FE modeling of shot ball, material damping coefficient, dynamic friction coefficient. The kinematical parameters include impact velocity and diameter of shot ball. Multi-impact FE model consists of 3-D symmetry-cell. We can describe a certain repeated area of peened specimen under equibiaxial residual stress by the cell. With the cell model, we investigate the FE peening coverage, dependency on the impact sequence, effect of repeated cycle. The proposed FE model provides converged and unique solution of surface stress, maximum compressive residual stress and deformation depth at four impact positions. Further, in contrast to the rigid and elastic shots, plastically deformable shot produces residual stresses closer to experimental solutions by X-ray diffraction. Consequently, it is confirmed that the FE model with peening factors and plastic shot is valid for multi-shot peening analyses.

• Korean Journal of Computational Design and Engineering
• /
• v.20 no.4
• /
• pp.367-374
• /
• 2015

Sandwich panels consisting of various materials have widely been applied for mitigating dynamic impacts such as ballistic and blast impacts. Especially, the selection of materials for different core set-ups can directly influence its performance. In this study, we design the sandwich panels for alleviating ballistic and blast impacts by controlling the stacking sequence of core materials and their thicknesses. FEM studies are performed to simulate the dynamic behavior of sandwich panels subjected to ballistic and blast impacts. Delamination between the core layers is also considered in the FEM studies for feasible design. Based on the FEM data, kriging models are generated for approximating design space and quickly predicting the FEM outputs. Finally, design optimizations are implemented to find the optimum stacking sequence of core materials and thicknesses with given impact situations.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2022.11a
• /
• pp.93-94
• /
• 2022

Although various studies about indoor positioning systems, such as beacon and Wifi, have been conducting for indoor positioning of workers at construction sites, these systems have limitations in terms of accuracy or economics. To overcome these limitations, geomagnetic field sequence-based indoor positioning technology can be a good alternative. However, it is necessary to correct the geomagnetic field near the construction material stocking area since the geomagnetic field can be distorted near construction materials such as rebars. Therefore, this study conducted an experiment for identifying correction range of geomagnetic field near the construction material stocking area. It was analyzed that the geomagnetic field should be corrected up to 60cm in the horizontal direction from the stocking point if the height of stocking area for rebars is 40cm or more. This study can be used for important reference for development of geomagnetic field sequence-based indoor positioning technology suitable for construction sites.

• Journal of Biomedical Engineering Research
• /
• v.12 no.3
• /
• pp.171-176
• /
• 1991

A solution for the course of the general deterministic epidemic model is obtained by elementary series expansion. This is valid over all times, and appears to hold accurate]y over a very wide range of population and threshould parameter values. This algorithm can be more efficient than either numerical or recursive procedures in terms of the number of operations required to evaluate a sequence of points along the course of the epidemic.

• Journal of the Korean School Mathematics Society
• /
• v.8 no.3
• /
• pp.357-366
• /
• 2005

This Study suggests some ideas how we develop a network of content structure based on informal context and method how we decide a sequence of mathematical syllabus from those Structures. 10th grade students in the process conceptual development was observed and interviewed in 2 hour teaching and learning experiment. Three related characteristics of student's thought in structuring math. Content and sequencing it were investigated as follows : (a) the reasoning that they do reflective abstraction well(or do not well) in acquisition of conceptual knowledge. (b) the method that teacher can use resuits in (a) to organize the content structure. (c) the ways that teacher find the process knowledge in informal content structure. That is, this study investigated the way we, curriculum designer, can create well defined content structure and instructional sequence strongly based on the learners' understanding.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.11
• /
• pp.310-318
• /
• 2018

Recently, the importance of big data analysis is increasing as a large amount of data is generated by various devices connected to the Internet with the advent of Internet of Things (IoT). Especially, it is necessary to analyze various large-scale IoT streaming sensor data generated in real time and provide various services through new meaningful prediction. This paper proposes a real-time indoor PM10 concentration prediction LSTM model based on streaming data generated from IoT sensor using AWS. We also construct a real-time indoor PM10 concentration prediction service based on the proposed model. Data used in the paper is streaming data collected from the PM10 IoT sensor for 24 hours. This time series data is converted into sequence data consisting of 30 consecutive values from time series data for use as input data of LSTM. The LSTM model is learned through a sliding window process of moving to the immediately adjacent dataset. In order to improve the performance of the model, incremental learning method is applied to the streaming data collected every 24 hours. The linear regression and recurrent neural networks (RNN) models are compared to evaluate the performance of LSTM model. Experimental results show that the proposed LSTM prediction model has 700% improvement over linear regression and 140% improvement over RNN model for its performance level.

• Journal of KIISE:Software and Applications
• /
• v.30 no.5_6
• /
• pp.487-496
• /
• 2003

The promoter that plays a very important role in gene expression as a signal part has various binding sites for transcription factors. These binding sites are located on various parts in promoter region and have highly conserved consensus sequence patterns. This paper presents a new method for the consensus pattern search in promoter regions using genetic algorithm, which adopts the assumption of N-occurrence-per-dataset model of MEME algorithm and employs the advantage of Wataru method in determining the pattern length. Our method will be employed by genome researchers who try to predict the promoter region on anonymous DNA sequence and to find out the binding site for a specific transcription factor.