• Geomechanics and Engineering
• /
• v.37 no.6
• /
• pp.539-554
• /
• 2024

This study explores development of prediction model for seismic site classification through the integration of machine learning techniques with horizontal-to-vertical spectral ratio (HVSR) methodologies. To improve model accuracy, the research employs outlier detection methods and, synthetic minority over-sampling technique (SMOTE) for data balance, and evaluates using seven machine learning models using seismic data from KiK-net. Notably, light gradient boosting method (LGBM), gradient boosting, and decision tree models exhibit improved performance when coupled with SMOTE, while Multiple linear regression (MLR) and Support vector machine (SVM) models show reduced efficacy. Outlier detection techniques significantly enhance accuracy, particularly for LGBM, gradient boosting, and voting boosting. The ensemble of LGBM with the isolation forest and SMOTE achieves the highest accuracy of 0.91, with LGBM and local outlier factor yielding the highest F1-score of 0.79. Consistently outperforming other models, LGBM proves most efficient for seismic site classification when supported by appropriate preprocessing procedures. These findings show the significance of outlier detection and data balancing for precise seismic soil classification prediction, offering insights and highlighting the potential of machine learning in optimizing site classification accuracy.

• Interdisciplinary Bio Central
• /
• v.4 no.4
• /
• pp.14.1-14.6
• /
• 2012

Splice site prediction in DNA sequence is a basic search problem for finding exon/intron and intron/exon boundaries. Removing introns and then joining the exons together forms the mRNA sequence. These sequences are the input of the translation process. It is a necessary step in the central dogma of molecular biology. The main task of splice site prediction is to find out the exact GT and AG ended sequences. Then it identifies the true and false GT and AG ended sequences among those candidate sequences. In this paper, we survey research works on splice site prediction based on support vector machine (SVM). The basic difference between these research works is nucleotide encoding technique and SVM kernel selection. Some methods encode the DNA sequence in a sparse way whereas others encode in a probabilistic manner. The encoded sequences serve as input of SVM. The task of SVM is to classify them using its learning model. The accuracy of classification largely depends on the proper kernel selection for sequence data as well as a selection of kernel parameter. We observe each encoding technique and classify them according to their similarity. Then we discuss about kernel and their parameter selection. Our survey paper provides a basic understanding of encoding approaches and proper kernel selection of SVM for splice site prediction.

• Journal of Korean Society for Atmospheric Environment
• /
• v.9 no.3
• /
• pp.207-215
• /
• 1993

In order to statistically predict $O_3$ levels in Seoul, the study used the TMS (telemeted air monitoring system) data from the Department of Environment, which have monitored at 20 sites in 1989 and 1990. Each data in each site was characterized by 6 major criteria pollutants ($SO_2, TSP, CO, NO_2, THC, and O_3$) and 2 meteorological parameters, such as wind speed and wind direction. To select proper variables and to determine each pollutant's behavior, univariate statistical analyses were extensively studied in the beginning, and then various applied statistical techniques like cluster analysis, regression analysis, and expert system have been intensively examined. For the initial study of high level $O_3$ prediction, the raw data set in each site was separated into 2 group based on 60 ppb $O_3$ level. A hierarchical cluster analysis was applied to classify the group based on 60 ppb $O_3$ into small calsses. Each class in each site has its own pattern. Next, multiple regression for each class was repeatedly applied to determine an $O_3$ prediction submodel and to determine outliers in each class based on a certain level of standardized redisual. Thus, a prediction submodel for each homogeneous class could be obtained. The study was extended to model $O_3$ prediction for both on-time basis and 1-hr after basis. Finally, an expect system was used to build a unified classification rule based on examples of the homogenous classes for all of sites. Thus, a concept of high level $O_3$ prediction model was developed for one of $O_3$ alert systems.

• Journal of Korean Critical Care Nursing
• /
• v.15 no.3
• /
• pp.75-87
• /
• 2022

Purpose : This retrospective investigation study aimed to determine the predictive validity of superficial surgical site infection assessment tools by measuring the risk score at the surgical site. Methods : This study included patients hospitalized to the general surgery department of a Hospital from January 2021 to December 31, 2021. The inclusion criteria were age ≥19 years, general abdominal surgery under general anesthesia, and hospital stay longer than 2 days. Patients who had undergone transplantation were excluded. Results : Tool validity results showed that tools including surgical time and operative procedure were more accurate than previously developed tools, with a sensitivity of 71.1%, specificity of 71.4%, positive prediction of 12.3%, negative prediction of 97.8%, and area under the curve of 0.743 (95% confidence interval, 0.678~0.745). The tool's cut-off score was 15, and the risks of infection was increased by 6.14 times at or above this cut-off point. Preoperative hair removal period, surgical wound classification, surgery time, body temperature on the second day after surgery, drainage tube type, and suture type affected the risk of infection at the surgical site. Conclusion : The incidence of healthcare-associated infections has been declining in the past decade; however, surgical site infections still account for a considerable proportion. Therefore, early identification of high-risk groups for surgical site infection is crucial for reducing the incidence of surgical site infection using appropriate management.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2008.03a
• /
• pp.563-574
• /
• 2008

Most of earthquake-induced geotechnical hazards have been caused by the site effects relating to the amplification of ground motion, which are strongly influenced by the local geologic conditions such as soil thickness or bedrock depth and soil stiffness. In this study, an integrated GIS-based information system for geotechnical data, called geotechnical information system (GTIS), was constructed to establish a regional counterplan against earthquake-induced hazards at an urban area, Daejeon, which is represented as a hub of research and development in Korea. To build the GTIS for the area of interesting, pre-existing geotechnical data collections were performed across the extended area including the study area and a walk-over site survey was additionally carried out to acquire surface geo-knowledge data. For practical application of the GTIS used to estimate the site effects at the area of interesting, seismic microzoning map of the characteristic site period was created and presented as regional synthetic strategy for earthquake-induced hazards prediction. In addition, seismic zonation for site classification according to the spatial distribution of the site period was also performed to determine the site amplification coefficients for seismic design and seismic performance evaluation at any site in the study area. Based on the case study on seismic zonations at Daejeon, it was verified that the GIS-based GTIS was very useful for the regional prediction of seismic hazards and also the decision support for seismic hazard mitigation.

• The Journal of Engineering Geology
• /
• v.17 no.3
• /
• pp.411-418
• /
• 2007

It is a very difficult thing to estimate an occurrence possibility location and hazard expectation area by landslide. The prediction difficulty of landslide occurrence has relativity in factor of various geological physical factors and contributions. However, estimation of landslide occurrence possibility and classification of hazard area became available correlation mechanism through analysis of landslide occurrence through landslide data analysis and statistical analysis. This study analyzed a damage possibility of a cultual heritage area due to landslide occurrence by a heavy rainfall. We make a landslide prediction map and tried to analysis of landslide occurrence possibility for the cultural heritage site. The study area chooses a temple of Silsang-Sa Baekjang-Am site and made a landslide prediction map. In landslide prediction map, landslide hazard possibility area expressed by occurrence probability and divided by each of probability degrees. This degree used to evaluate occurrence possibility for existence and nonexistence of landslide in the study site. For the prediction and evaluation of landslide hazard for the cultural heritage site, investigation and analysis technique which is introduced in this study may contribute an efficient management and investigation in the cultural heritage site, Korea.

• Journal of Environmental Impact Assessment
• /
• v.5 no.1
• /
• pp.95-105
• /
• 1996

Meteorological Joint Frequency Function required indispensably in long-term air quality prediction models were discussed for practical application in Korea. The algorithm, proposed by Turner(l964), is processed with daily solar insolation and cloudiness and height basically using Pasquill's atmospheric stability classification method. In spite of its necessity and applicability, the computer program, called STAR(STability ARray), had some significant difficulties caused from the difference in meteorological data format between that of original U.S. version and Korean's. To cope with the problems, revised STAR program for Korean users were composed of followings; applicability in any site of Korea with regard to local solar angle modification; feasibility with both of data which observed by two classes of weather service centers; and examination on output format associated with prediction models which should be used.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2009.09a
• /
• pp.233-242
• /
• 2009

Based on the data obtained from field investigation and soil testing to slope hazards occurrence section and non-occurrence section in crystalline rocks like gneiss, granite, and so on, a prediction model was developed by the use of a decision tree model. The classification standard of the selected prediction model is composed of the slope angle, the coefficient of permeability and the void ratio in the order. The computer program, SHAPP ver. 1.0 for prediction of slope hazards around an important national facilities using GIS technique and the developed model. To prove the developed prediction model and the computer program, the field data surveyed from Jumunjin, Gangneung city were compared with the prediction result in the same site. As the result of comparison, the real occurrence location of slope hazards was similar to the predicted section. Through the continuous study, the accuracy about prediction result of slope hazards will be upgraded and the computer program will be commonly used in practical.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.42 no.6
• /
• pp.843-852
• /
• 2022

Despite continuous safety management, the death rate of construction workers is not decreasing every year. Accordingly, various studies are in progress to prevent construction site accidents. In this paper, we developed an AI-based priority inspection target selection model that preferentially selects sites are expected to cause construction accidents among construction sites with construction costs of less than 5 billion won (KRW). In particular, Random Forest (90.48 % of accident prediction AUC-ROC) showed the best performance among applied AI algorithms (Classification analysis). The main factors causing construction accidents were construction costs, total number of construction days and the number of construction performance evaluations. In this study an ROI (return of investment) of about 917.7 % can be predicted over 8 years as a result of better efficiency of manual inspections human resource and a preemptive response to construction accidents.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.230-237
• /
• 2022

It is difficult to predict industrial accidents in the construction industry because many accident factors, such as human-related factors and environment-related factors, affect the accidents. Many studies have analyzed the severity of injuries and types of accidents; however, there were few studies on the prediction of injured body parts. This study aims to develop a classification model to predict the part of the injured body based on accident-related factors. Construction accident cases from June 2018 to July 2021 provided by the Korea Construction Safety Management Integrated Information were collected through web crawling and then preprocessed. A naïve Bayes classifier, one of the supervised learning algorithms, was employed to construct a classification model of the injured body part, which has four categories: 1) torso, 2) upper extremity, 3) head, and 4) lower extremity. The predictor variables are accident type, type of work, facility type, injury source, and activity type. As a result, the average accuracy for each injured body part was 50.4%. The accuracy of the upper extremity and lower extremity was relatively higher than the cases of the torso and head. Unlike the other classifications, such as spam mail filtering, a naïve Bayes classifier does not provide a good classification performance in construction accidents. The reasons are discussed in the study. Based on the results of this study, more detailed guidelines for construction safety management can be provided, which help establish safety measures at the construction site.