• Journal of Navigation and Port Research
• /
• v.46 no.6
• /
• pp.562-569
• /
• 2022

The alarm monitoring technology applied to existing operating ships manages data items such as temperature and pressure with AMS (Alarm Monitoring System) and provides an alarm to the crew should these sensing data exceed the normal level range. In addition, the maintenance of existing ships follows the Planned Maintenance System (PMS). whereby the sensing data measured from the equipment is monitored and if it surpasses the set range, maintenance is performed through an alarm, or the corresponding part is replaced in advance after being used for a certain period of time regardless of whether the target device has a malfunction or not. To secure the reliability and operational safety of ship engine operation, it is necessary to enable advanced diagnosis and prediction based on real-time condition monitoring data. To do so, comprehensive measurement of actual ship data, creation of a database, and implementation of a condition diagnosis monitoring system for condition-based predictive maintenance of auxiliary equipment and piping must take place. Furthermore, the system should enable management of auxiliary equipment and piping status information based on a responsive web, and be optimized for screen and resolution so that it can be accessed and used by various mobile devices such as smartphones as well as for viewing on a PC on board. This update cost is low, and the management method is easy. In this paper, we propose CBM (Condition Based Management) technology, for autonomous ships. This core technology is used to identify abnormal phenomena through state diagnosis and monitoring of pumps and purifiers among ship auxiliary equipment, and seawater and steam pipes among pipes. It is intended to provide performance diagnosis and failure prediction of ship auxiliary equipment and piping for convergence analysis, and to support preventive maintenance decision-making.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.999-1008
• /
• 2023

Early prediction of chronic diseases such as diabetes is an important issue, and improving the accuracy of diabetes prediction is especially important. Various machine learning and deep learning-based methodologies are being introduced for diabetes prediction, but these technologies require large amounts of data for better performance than other methodologies, and the learning cost is high due to complex data models. In this study, we aim to verify the claim that DNN using the pima dataset and k-fold cross-validation reduces the efficiency of diabetes diagnosis models. Machine learning classification methods such as decision trees, SVM, random forests, logistic regression, KNN, and various ensemble techniques were used to determine which algorithm produces the best prediction results. After training and testing all classification models, the proposed system provided the best results on XGBoost classifier with ADASYN method, with accuracy of 81%, F1 coefficient of 0.81, and AUC of 0.84. Additionally, a domain adaptation method was implemented to demonstrate the versatility of the proposed system. An explainable AI approach using the LIME and SHAP frameworks was implemented to understand how the model predicts the final outcome.

• The Journal of Bigdata
• /
• v.8 no.1
• /
• pp.111-129
• /
• 2023

With the diffusion of digital innovation, the adoption of innovative medical technologies based on artificial intelligence is increasing in the medical field. This is driving the launch and adoption of AI-based SaMD(Software as a Medical Device), but there is a lack of research on the factors that influence the adoption of SaMD by medical institutions. The purpose of this study is to identify key factors that influence medical institutions' decisions to adopt AI-based SaMDs, and to analyze the weights and priorities of these factors. For this purpose, we conducted Delphi surveys based on the results of literature studies on technology acceptance models in healthcare industry, medical AI and SaMD, and developed a research model by combining HOTE(Human, Organization, Technology and Environment) framework and HABIO(Holistic Approach {Business, Information, Organizational}) framework. Based on the research model with 5 main criteria and 22 sub-criteria, we conducted an AHP(Analytical Hierarchy Process) analysis among the experts from domestic medical institutions and SaMD providers to empirically analyze SaMD adoption factors. The results of this study showed that the priority of the main criteria for determining the adoption of AI-based SaMD was in the order of technical factors, economic factors, human factors, organizational factors, and environmental factors. The priority of sub-criteria was in the order of reliability, cost reduction, medical staff's acceptance, safety, top management's support, security, and licensing & regulatory levels. Specifically, technical factors such as reliability, safety, and security were found to be the most important factors for SaMD adoption. In addition, the comparisons and analyses of the weights and priorities of each group showed that the weights and priorities of SaMD adoption factors varied by type of institution, type of medical institution, and type of job in the medical institution.

• The Journal of Bigdata
• /
• v.8 no.2
• /
• pp.97-107
• /
• 2023

Small business owners are relatively likely to be alienated from various benefits caused by the change to a big data/AI-based society. To support them, we would like to detect a hot place based on the floating population to support small business owners' decision-making in the start-up area. Through various studies, it is known that the population size of the region has an important effect on the sales of small business owners. In this study, inland regions were extracted from the Incheon floating population data from January 2019 to June 2022. the Data is consisted of a grid of 50m intervals, central coordinates and the population for each grid are presented, made image structure through imputation to maintain spatial information. Spatial outliers were removed and imputated using LOF and GAM, and temporal outliers were removed and imputated through LOESS. We used ConvLSTM which can take both temporal and spatial characteristics into account as a predictive model, and used AutoEncoder structure, which performs outliers detection based on reconstruction error to define an area with high MAPE as a hot place.

• The KIPS Transactions:PartD
• /
• v.11D no.4
• /
• pp.967-974
• /
• 2004

An OLAP system is the decision support tool with which a user can analyze the information interactively in the various aspects. However, the traditional existing construction of an OLAP system has the inefficiency problem of increasing the time and cost caused by the frequent changes of the users requirements. In this paper, we analyse existing construction procedure of OLAP systems and propose a prototyping OLAP View based on the star schema which can help and guide the designer In supporting efficiently of users requirements. Through an implementation of S shopping mall using the OLAP View, we show that our proposal is able to support OLAP construction strategy and provide accurate understanding of data resources. With an OLAP View, we can reduce the required time and cost of implementing OLAP system.

• The Korean Journal of Applied Statistics
• /
• v.34 no.5
• /
• pp.773-794
• /
• 2021

Prediction of vehicle traffic volume is very important in planning municipal administration. It may help promote social and economic interests and also prevent traffic congestion costs. Traffic volume as a time-varying trajectory is considered as functional data. In this paper we study three functional regression models that can be used to predict an unseen trajectory of traffic volume based on already observed trajectories. We apply the methods to highway tollgate traffic volume data collected at some tollgates in Seoul, Chuncheon and Gangneung. We compare the prediction errors of the three models to find the best one for each of the three tollgate traffic volumes.

• Journal of the Korea Convergence Society
• /
• v.12 no.7
• /
• pp.45-51
• /
• 2021

In accordance with the rapid non-face-to-face environment and mobile first strategy, the explosive increase and creation of many structured/unstructured data every year demands new decision making and services using big data in all fields. However, there have been few reference cases of using the Hadoop Ecosystem, which uses the rapidly increasing big data every year to collect and load big data into a standard platform that can be applied in a practical environment, and then store and process well-established big data in a relational database. Therefore, in this study, after collecting unstructured data searched by keywords from social network services based on Hadoop 2.0 through three virtual machine servers in the Spring Framework environment, the collected unstructured data is loaded into Hadoop Distributed File System and HBase based on the loaded unstructured data, it was designed and implemented to store standardized big data in a relational database using a morpheme analyzer. In the future, research on clustering and classification and analysis using machine learning using Hive or Mahout for deep data analysis should be continued.

• Smart Media Journal
• /
• v.9 no.1
• /
• pp.75-83
• /
• 2020

Compensation services that are indispensable during large-scale public utilities projects have been gradually increasing with the recent increase in construction, but there are no systematic compensation services due to the complicated procedures and manual work. For this reason, various problems such as construction period delays due to various complaints, corruption in compensation work, and impossible to trace the history of compensation data in the past are emerging. In this paper, in order to solve this problem, in-depth interviews and questionnaires were conducted to find out the problems of each compensation status. Based on this, 3 core technologies and 10 technical needs based on ICT were selected to improve the compensation work by deriving STEEP analysis and Issue Tree. The three core technologies are big data-based decision-making and prediction technology, advanced measurement technology, and open cloud-based compensation platform technology. In order to introduce the derived technologies to the institutions in charge of compensation, the possibility of technology diffusion by project operators was suggested based on the results of the current status of informatization by institution. Based on the core technology derived from this paper, it is necessary to make a prototype that can be advanced in compensation work and apply it to each institution and analyze the effect.

• Korean Journal of Construction Engineering and Management
• /
• v.19 no.3
• /
• pp.43-51
• /
• 2018

Facility Management (FM) phase in building lifecycle management is the most crucial phase concerning building value and life cycle cost management. Nevertheless, systematic and rational FM process is not yet constructed, leading to failure of facility value and cost management from accurate and proactive FM. This is because there has been minimal approach regarding construction of optimal FM process based on rational FM data analysis. The purpose of this study is to provide optimal FM process with quantitative FM data analysis method using spatial data. This study investigated existing FM data structure and derive the limitation of it from both expert interview and practical FM material analysis. As a solution for this limitation, this study provided optimal FM process with MTBF (Mean Time Between Failure), which is quantitative FM data analysis method. The effect of the provided process was validated with a case study. It is expected that this process allows rational and objective FM data analysis, resulting in accurate and proactive FM. And it is expected that it can be used as a useful basic data for developing an effective system for the FM process.

• Korean Journal of Construction Engineering and Management
• /
• v.12 no.6
• /
• pp.110-119
• /
• 2011

Global warming caused by excessive greenhouse gas emission is causing climate change all over the world. In Korea, greenhouse gas emission from residential buildings accounts for about 10% of gross domestic emission. Also, the number of deteriorated multi-family housing complexes is increasing. Therefore, the goal of this research is to establish the bases to manage energy consumption continuously and methodically during MR&R period of multi-family housings. The research process and methodologies are as follows. First, research team collected the data on project characteristics and energy consumption of multi-family housing complexes in Seoul. Second, an ontology-based breakdown structure was established with some primary characteristics affecting the energy consumption, which were selected by statistical analysis. Finally, a predictive model of energy consumption was developed based on the ontology-based breakdown structure, with application of CBR, ANN, MRA and GA. In this research, PASW (Predictive Analytics SoftWare) Statistics 18, Microsoft EXCEL, Protege 4.1 were utilized for data analysis and prediction. In future research, the model will be more continuous and methodical by developing the web-base system. And it has facility manager of government or local government, or multi-family housing complex make a decision with definite references regarding moderate energy consumption.