• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.20 no.6
• /
• pp.1-13
• /
• 2021

In this study, a time series analysis technique was applied to calibrate and predict traffic data for various purposes, such as planning, design, maintenance, and research. Existing algorithms have limitations in application to data such as traffic data because they show strong periodicity and seasonality or irregular data. To overcome and supplement these limitations, we applied the SARIMA model, an analytical technique that combines the autocorrelation model, the Seasonal Auto Regressive(SAR), and the seasonal Moving Average(SMA). According to the analysis, traffic volume prediction using the SARIMA(4,1,3)(4,0,3) 12 model, which is the optimal parameter combination, showed excellent performance of 85% on average. In addition to traffic data, this study is considered to be of great value in that it can contribute significantly to traffic correction and forecast improvement in the event of missing traffic data, and is also applicable to a variety of time series data recently collected.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.1
• /
• pp.8-19
• /
• 2021

The air pollution problem caused by industrialization in recent years is attracting great attention to both the country and the people. Domestic wide-area air pollution information is provided to the public through public data nationally, but regional air pollution information with different environmental variables is very insufficient. Therefore, in this study, we design and implement an air pollution analysis and prediction system based on regional environmental variables that can more accurately analyze and predict regional air pollution phenomena. In particular, the proposed system accurately analyzes and provides regional atmospheric information based on environmental data measured locally and public big data, and predicts and presents future regional atmospheric information using artificial intelligence algorithms. Furthermore, through the proposed system, it is expected that local air pollution can be prevented by accurately identifying the cause of regional air pollution.

• Journal of the Institute of Electronics Engineers of Korea SD
• /
• v.49 no.7
• /
• pp.30-38
• /
• 2012

This paper presents packet detection, frequency offset estimation architecture and performance analysis for OFDM-based wireless personal area network (WPAN) systems. Packet detection structure is used to find the start point of a packet exactly in WPAN system as the correlation value passes the constant threshold value. The applied autocorrelation structure of the algorithm can be implemented simply compared to conventional packet detection algorithms. The proposed frequency offset estimation architecture is designed for phase rotation process structure, internal bit reduction to reduce hardware size and the frequency offset adjustment block to reduce look-up table size unlike the conventional structure. If the received signal can be compensated by estimated frequency offset through the correction block, it can reduce the impact on the frequency offset. Through the performance result, the proposed structure has lower hardware complexity and gate count compared to the conventional structure. Thus, the proposed structure for OFDM-based WPAN systems can be applied to the initial synchronization process and high-speed low-power WPAN chips.

• The Journal of Korean Association of Computer Education
• /
• v.17 no.5
• /
• pp.89-98
• /
• 2014

Programming is excellent tool on realizing ideas. However students often complain of difficulties due to requiring the strict programming grammar and the highly thinking. Although various researches have been conducted to teach the programming easily for students, it should precede the analysis of what and why programming concept is difficult for learners. In this study, we analyzed what and why the programming concept is difficult for novice learners in basic programming education. Based on the results, we suggested: improving problem-solving skills based on accurate understanding and internalization on the programming concept, on reducing error between thought and execution results through the creation of sophisticated algorithms and on offering a variety of troubleshooting experience, establishing strategies to think freely for problem-solving process, and promoting the effectiveness of the learning through the learning procedure design.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.15 no.6
• /
• pp.311-319
• /
• 2015

In this paper, in order to increase the production efficiency of the industrial plant, and predicts the resources of the manufacturing process, we have proposed a decision-making system for resource implementing the risk management effectively forecasting and risk management. A variety of information that occurs at each step efficiently difficult the creation of detailed process steps in the scenario you want to manage, is a frequent condition change of manufacturing facilities for the production of various products even within the same process. The data that is not contiguous products production cycle also not constant occurs, there is a problem that needs to check the variation in the small amount of data. In order to solve these problems, data centralized manufacturing processes, process resource prediction, risk prediction, through a process current status monitoring, must allow action immediately when a problem occurs. In this paper, the range of change in the design drawing, resource prediction, a process completion date using a regression algorithm to derive the formula, classification tree technique was proposed decision system in three stages through the boundary value analysis.

• Structural Engineering and Mechanics
• /
• v.27 no.2
• /
• pp.117-134
• /
• 2007

The force (load) reduction factor, R, which is one of the most important parameters in earthquake load calculation, is independent of the dimensions of the structure but is defined on the basis of the load bearing system of the structure as defined in earthquake codes. Significant damages and failures were experienced on prefabricated reinforced concrete structures during the last three major earthquakes in Turkey (Adana 1998, Kocaeli 1999, Duzce 1999) and the experts are still discussing the main reasons of those failures. Most of them agreed that they resulted mainly from the earthquake force reduction factor, R that is incorrectly selected during design processes, in addition to all other detailing errors. Thus this wide spread damages caused by the earthquake to prefabricated structures aroused suspicion about the correctness of the R coefficient recommended in the current Turkish Earthquake Codes (TEC - 98). In this study, an attempt was made for an approximate determination of R coefficient for widely utilized prefabricated structure types (single-floor single-span) with variable dimensions. According to the selecting variable dimensions, 140 sample frames were computed using pushover analysis. The force reduction factor R was calculated by load-displacement curves obtained pushover analysis for each frame. Then, formulated artificial neural network method was trained by using 107 of the 140 sample frames. For the training various algorithms were used. The method was applied and used for the prediction of the R rest 33 frames with about 92% accuracy. The paper also aims at proposing the authorities to change the R coefficient values predicted in TEC - 98 for prefabricated concrete structures.

• Spatial Information Research
• /
• v.9 no.2
• /
• pp.239-261
• /
• 2001

A large suite of official statistical data sets has been compiled for geographical units under the national directives, and it is the quantitative regional analysis procedures that could add values to them. This paper reports our attempts at prototyping a statistical GIS which is capable of serving over the Web a variety of regional analysis routines as well as value-added statistics and maps. A pilot database of some major statistical data was ingested for the city of Seoul. The baseline subset of regional analysis methods of practical usage was selected and accommodated into the business logic of the target system, which ranges from descriptive statistics, regional structure/inequality measures, spatial ANOVA, spatial (auto) correlation to regression and residual analysis. The leading-edge information technologies including the application server were adopted in the system design and implementation so that the database, analysis modules and analytic mapping components may cooperate seamlessly behind the Web front-end. The prototyped system supports tables, maps, and files of downloadable format for input and output of the analyses. One of the most salient features of out proposed system is that both the database and analysis modules are extensible via the bi-directional interface for end users; The system provides users with operators and parsers for algebraic formulae such that the stored statistical variables may be transformed and combined into the newly-derived set of variables. This functionality eventually leads to on-the-fly fabrication of user-defined regional analysis algorithms. The stored dataset may also be temporarily augmented by user-uploaded dataset; The extension of this form, in essence, results in a virtual database which awaits for users commands as usual. An initial evaluation of the proposed system confirms that the issues involving the usage and dissemination of information can be addressed with success.

• Journal of Intelligence and Information Systems
• /
• v.28 no.3
• /
• pp.259-278
• /
• 2022

With the spread of Artificial Intelligence (AI), various AI-based services are expanding in the financial sector such as service recommendation, automated customer response, fraud detection system(FDS), credit scoring services, etc. At the same time, problems related to reliability and unexpected social controversy are also occurring due to the nature of data-based machine learning. The need Based on this background, this study aimed to contribute to improving trust in AI-based financial services by proposing a checklist to secure fairness in AI-based credit scoring services which directly affects consumers' financial life. Among the key elements of trustworthy AI like transparency, safety, accountability, and fairness, fairness was selected as the subject of the study so that everyone could enjoy the benefits of automated algorithms from the perspective of inclusive finance without social discrimination. We divided the entire fairness related operation process into three areas like data, algorithms, and user areas through literature research. For each area, we constructed four detailed considerations for evaluation resulting in 12 checklists. The relative importance and priority of the categories were evaluated through the analytic hierarchy process (AHP). We use three different groups: financial field workers, artificial intelligence field workers, and general users which represent entire financial stakeholders. According to the importance of each stakeholder, three groups were classified and analyzed, and from a practical perspective, specific checks such as feasibility verification for using learning data and non-financial information and monitoring new inflow data were identified. Moreover, financial consumers in general were found to be highly considerate of the accuracy of result analysis and bias checks. We expect this result could contribute to the design and operation of fair AI-based financial services.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.111-124
• /
• 2018

This study aims to develop a classification model for predicting the occurrence of hyperlipidemia, one of the chronic diseases. Prior studies applying data mining techniques for predicting disease can be classified into a model design study for predicting cardiovascular disease and a study comparing disease prediction research results. In the case of foreign literatures, studies predicting cardiovascular disease were predominant in predicting disease using data mining techniques. Although domestic studies were not much different from those of foreign countries, studies focusing on hypertension and diabetes were mainly conducted. Since hypertension and diabetes as well as chronic diseases, hyperlipidemia, are also of high importance, this study selected hyperlipidemia as the disease to be analyzed. We also developed a model for predicting hyperlipidemia using SVM and meta learning algorithms, which are already known to have excellent predictive power. In order to achieve the purpose of this study, we used data set from Korea Health Panel 2012. The Korean Health Panel produces basic data on the level of health expenditure, health level and health behavior, and has conducted an annual survey since 2008. In this study, 1,088 patients with hyperlipidemia were randomly selected from the hospitalized, outpatient, emergency, and chronic disease data of the Korean Health Panel in 2012, and 1,088 nonpatients were also randomly extracted. A total of 2,176 people were selected for the study. Three methods were used to select input variables for predicting hyperlipidemia. First, stepwise method was performed using logistic regression. Among the 17 variables, the categorical variables(except for length of smoking) are expressed as dummy variables, which are assumed to be separate variables on the basis of the reference group, and these variables were analyzed. Six variables (age, BMI, education level, marital status, smoking status, gender) excluding income level and smoking period were selected based on significance level 0.1. Second, C4.5 as a decision tree algorithm is used. The significant input variables were age, smoking status, and education level. Finally, C4.5 as a decision tree algorithm is used. In SVM, the input variables selected by genetic algorithms consisted of 6 variables such as age, marital status, education level, economic activity, smoking period, and physical activity status, and the input variables selected by genetic algorithms in artificial neural network consist of 3 variables such as age, marital status, and education level. Based on the selected parameters, we compared SVM, meta learning algorithm and other prediction models for hyperlipidemia patients, and compared the classification performances using TP rate and precision. The main results of the analysis are as follows. First, the accuracy of the SVM was 88.4% and the accuracy of the artificial neural network was 86.7%. Second, the accuracy of classification models using the selected input variables through stepwise method was slightly higher than that of classification models using the whole variables. Third, the precision of artificial neural network was higher than that of SVM when only three variables as input variables were selected by decision trees. As a result of classification models based on the input variables selected through the genetic algorithm, classification accuracy of SVM was 88.5% and that of artificial neural network was 87.9%. Finally, this study indicated that stacking as the meta learning algorithm proposed in this study, has the best performance when it uses the predicted outputs of SVM and MLP as input variables of SVM, which is a meta classifier. The purpose of this study was to predict hyperlipidemia, one of the representative chronic diseases. To do this, we used SVM and meta-learning algorithms, which is known to have high accuracy. As a result, the accuracy of classification of hyperlipidemia in the stacking as a meta learner was higher than other meta-learning algorithms. However, the predictive performance of the meta-learning algorithm proposed in this study is the same as that of SVM with the best performance (88.6%) among the single models. The limitations of this study are as follows. First, various variable selection methods were tried, but most variables used in the study were categorical dummy variables. In the case with a large number of categorical variables, the results may be different if continuous variables are used because the model can be better suited to categorical variables such as decision trees than general models such as neural networks. Despite these limitations, this study has significance in predicting hyperlipidemia with hybrid models such as met learning algorithms which have not been studied previously. It can be said that the result of improving the model accuracy by applying various variable selection techniques is meaningful. In addition, it is expected that our proposed model will be effective for the prevention and management of hyperlipidemia.

• Korean Journal of Environment and Ecology
• /
• v.32 no.6
• /
• pp.686-697
• /
• 2018

Due to the advance in remote sensing technology, it has become easier to more frequently obtain high resolution imagery to detect delicate changes in an extensive area, particularly including forest which is not readily sub-classified. Time-series analysis on high resolution images requires to collect extensive amount of ground truth data. In this study, the potential of land coverage mapas ground truth data was tested in classifying high-resolution imagery. The study site was Wonju-si at Gangwon-do, South Korea, having a mix of urban and natural areas. KOMPSAT-3A imagery taken on March 2015 and land coverage map published in 2017 were used as source data. Two pixel-based classification algorithms, Support Vector Machine (SVM) and Random Forest (RF), were selected for the analysis. Forest only classification was compared with that of the whole study area except wetland. Confusion matrixes from the classification presented that overall accuracies for both the targets were higher in RF algorithm than in SVM. While the overall accuracy in the forest only analysis by RF algorithm was higher by 18.3% than SVM, in the case of the whole region analysis, the difference was relatively smaller by 5.5%. For the SVM algorithm, adding the Majority analysis process indicated a marginal improvement of about 1% than the normal SVM analysis. It was found that the RF algorithm was more effective to identify the broad-leaved forest within the forest, but for the other classes the SVM algorithm was more effective. As the two pixel-based classification algorithms were tested here, it is expected that future classification will improve the overall accuracy and the reliability by introducing a time-series analysis and an object-based algorithm. It is considered that this approach will contribute to improving a large-scale land planning by providing an effective land classification method on higher spatial and temporal scales.