• Journal of the Korea Society of Computer and Information
• /
• v.28 no.11
• /
• pp.29-42
• /
• 2023

In this paper, we propose a method to enhance the prediction accuracy of solar irradiance for three major South Korean cities: Seoul, Busan, and Incheon. Our method entails the development of five generative models-vanilla GAN, CTGAN, Copula GAN, WGANGP, and TVAE-to generate independent variables that mimic the patterns of existing training data. To mitigate the bias in model training, we derive values for the dependent variables using random forests and deep neural networks, enriching the training datasets. These datasets are integrated with existing data to form comprehensive solar irradiance prediction models. The experimentation revealed that the augmented datasets led to significantly improved model performance compared to those trained solely on the original data. Specifically, CTGAN showed outstanding results due to its sophisticated mechanism for handling the intricacies of multivariate data relationships, ensuring that the generated data are diverse and closely aligned with the real-world variability of solar irradiance. The proposed method is expected to address the issue of data scarcity by augmenting the training data with high-quality synthetic data, thereby contributing to the operation of solar power systems for sustainable development.

• Korean Journal of Remote Sensing
• /
• v.39 no.5_4
• /
• pp.1085-1095
• /
• 2023

Time-series data generated from satellite data are crucial resources for change detection and monitoring across various fields. Existing research in time-series data generation primarily relies on single-image analysis to maintain data uniformity, with ongoing efforts to enhance spatial and temporal resolutions by utilizing diverse image sources. Despite the emphasized significance of time-series data, there is a notable absence of automated data collection and preprocessing for research purposes. In this paper, to address this limitation, we propose a system that automates the collection of satellite information in user-specified areas to generate time-series data. This research aims to collect data from various satellite sources in a specific region and convert them into time-series data, developing an automatic satellite image collection system for this purpose. By utilizing this system, users can collect and extract data for their specific regions of interest, making the data immediately usable. Experimental results have shown the feasibility of automatically acquiring freely available Landsat and Sentinel images from the web and incorporating manually inputted high-resolution satellite images. Comparisons between automatically collected and edited images based on high-resolution satellite data demonstrated minimal discrepancies, with no significant errors in the generated output.

• Spatial Information Research
• /
• v.19 no.4
• /
• pp.21-31
• /
• 2011

As large scaled natural or man-made disasters being increased, the demand for rapid responses for such emergent situations also has been ever-increasing. These responses need to acquire spatial information of each individual site rapidly for more effective management of the situations. Therefore, we are developing a close-range real-time aerial monitoring system based on a low altitude unmanned helicopter. This system can acquire airborne sensory data in real-time and generate rapidly geospatial information. The system consists of two main parts: aerial and ground parts. The aerial part includes an aerial platform equipped with multi-sensor(cameras, a laser scanner, a GPS receiver, an IMU) and sensor supporting modules. The ground part includes a ground vehicle, a receiving system to receive sensory data in real-time and a processing system to generate the geospatial information rapidly. Development and testing of the individual modules and subsystems have been almost completed. Integration of the modules and subsystems is now in progress. In this paper, we w ill introduce our system, explain intermediate results, and discuss expected outcome.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.26 no.3
• /
• pp.208-217
• /
• 2016

This paper describes a simulation method to generate sensor measurements for location estimation of an underwater robot. Field trial of a navigation method of an underwater robot takes much time and expenses and it is difficult to change the environment of the field trial as desired to test the method in various situations. Therefore, test and verification of a navigation method through simulation is inevitable for underwater environment. This paper proposes a method to generate sensor measurements of range, depth, velocity, and attitude taking the uncertainties of measurements into account through simulation. The uncertainties are Gaussian noise, outlier, and correlation between the measurement noise. Also, the method implements uncertainty in sampling time of measurements. The method is tested and verified by comparing the uncertainty parameters calculated statistically from the generated measurements with the designed uncertainty parameters. The practical feasibility of the measurement data is shown by applying the measurement data for location estimation of an underwater robot.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.36 no.3
• /
• pp.521-528
• /
• 2016

The tollbooths of a main motorway toll plaza are usually operated proactively responding to the variations of traffic demands of two-type vehicles, i.e. cars and the other (heavy) vehicles, respectively. In this vein, it is one of key elements to forecast accurate traffic volumes for the two vehicle types in advanced tollgate operation. Unfortunately, it is not easy for existing univariate short-term prediction techniques to simultaneously generate the two-vehicle-type traffic demands in literature. These practical and academic backgrounds make it one of attractive research topics in Intelligent Transportation System (ITS) forecasting area to forecast the future traffic volumes of the two-type vehicles at an acceptable level of accuracy. In order to address the shortcomings of univariate short-term prediction techniques, a Multiple In-and-Out (MIO) forecasting model to simultaneously generate the two-type traffic volumes is introduced in this article. The MIO model based on a non-parametric approach is devised under the on-line access conditions of large-scale historical data. In a feasible test with actual data, the proposed model outperformed Kalman filtering, one of a widely-used univariate models, in terms of prediction accuracy in spite of multivariate prediction scheme.

• Journal of Practical Engineering Education
• /
• v.12 no.1
• /
• pp.213-230
• /
• 2020

Until now, various educational budgets, facilities, and programs have been put into school education, but the results have not been clearly evaluated. This study presents a model to analyze the effectiveness of educational support for students in high schools across the country. In this model, we first use EM cluster analysis to make clusters with similar inputs for school operation, and then calculate the relative efficiency in each cluster by using Network DEA analysis. The Network DEA analysis has a two-stage structure where the first stage uses six inputs in terms of school infrastructure to generate outputs such as the number of academic persistence. In the Network DEA analysis, the second stage uses 10 inputs in terms of school programs to generate outputs such as the number of enrollees to higher learning and the number of employees and per capita usage of library as the connection variable. Based on the efficiency analysis results, Tier analysis is performed by applying the Euclidean distance to select targets for benchmarking. In this study, we applied the model to analyze the efficiency of educational support by collecting data regarding student education support in general and vocational high school nationwide. The stepwise benchmarking method proposed that the target be selected for efficiency improvement step by step, taking into account inefficient school elements to complement the problem of the choice of benchmarking targets. Based on this study, it is expected that schools with low efficiency of educational support for students will be used as basic data for stepwise benchmarking for efficient operation of educational support for students.

• Journal of KIISE:Computer Systems and Theory
• /
• v.33 no.12
• /
• pp.894-906
• /
• 2006

There are many difficulties to develop a mobile contents due to many constraints on mobile environments. It is difficult to make a good mobile contents with only visual reduction of existing contents on wire Internet. Therefore, it is essential to devise the data representation and to develop the authoring tool to meet the needs of the mobile contents market. We suggest the compact mobile contents to learn Chinese characters and developed its authoring tool. The animation which our system produces is realistic as if someone writes letters with pen or brush. Moreover, our authoring tool makes a user generate a Chinese character animation easily and rapidly although she or he has not many knowledge in computer graphics, mobile programming or Chinese characters. The method to generate the stroke animation is following: We take basic character shape information represented with several contours from TTF(TrueType Font) and get the information for the stroke segmentation and stroke ordering from simple user input. And then, we decompose whole character shape into some strokes by using polygonal approximation technique. Next, the stroke animation for each stroke is automatically generated by the scan line algorithm ordered by the stroke direction. Finally, the ordered scan lines are compressed into some integers by reducing coordinate redundancy As a result, the stroke animation of our system is even smaller than GIF animation. Our method can be extended to rendering and animation of Hangul or general 2D shape based on vector graphics. We have the plan to find the method to automate the stroke segmentation and ordering without user input.

• The Journal of Engineering Geology
• /
• v.24 no.4
• /
• pp.501-510
• /
• 2014

Volcanic eruptions alone may lead to serious natural disasters, but the associated release of water from a caldera lake may be equally damaging. There is both historical and geological evidence of the past eruptions of Mt. Baekdusan, and the volcano, which has not erupted for over 100 years, has recently shown signs of reawakening. Action is required if we are to limit the social, political, cultural, and economic damage of any future eruption. This study aims to identify the area that would be inundated following a volcanic flood from the Cheon-Ji caldera lake that lies within Mt. Baekdusan. A scenario-based numerical analysis was performed to generate a flood hydrograph, and the parameters required were selected following a consideration of historical records from other volcanoes. The amount of water at the outer rim as a function of time was used as an upper boundary condition for the downstream routing process for a period of 10 days. Data from the USGS were used to generate a DEM with a resolution of 100 m, and remotely sensed satellite data from the moderate-resolution imaging spectroradiometer (MODIS) were used to show land cover and use. The simulation was generated using the software FLO-2D and was superposed on the remotely sensed map. The results show that the inundation area would cover about 80% of the urban area near Erdaobaihezhen assuming a 10 m/hr collapse rate, and 98% of the area would be flooded assuming a 100 m/hr collapse rate.

• Journal of Energy Engineering
• /
• v.8 no.4
• /
• pp.567-575
• /
• 1999

This study found potential ability to generate electric power using difference in water temperature between sea surface water and deep water in the East Sea which includes the East Sea Proper Water with the temperature less than 1$^{\circ}C$ throughout a year without seasonal variation. To quantify the difference in water temperature between sea surface water and deep water in the East Sea. We computed the annual mean ($^{\circ}C$), the annual amplitude ($^{\circ}C$), the annual phase (degree) and the duration time which showed more than 15$^{\circ}C$ temperature difference from the water temperature data using Harmonic analysis during 1961~1997. The best place for generating electric power in the East Sea seems to be the eastward ocean areas (36$^{\circ}$ 05'N, 129$^{\circ}$ 48'E~36$^{\circ}$ 05'N, 130$^{\circ}$ 00E'E) from Pohang city. The annual mean of the difference in water temperature between sea surface water and 500 m depth was 24$^{\circ}$C at the place to generate electric power in August according to the data of 1961~1997. the maximum duration periods with more than 15$^{\circ}C$ temperature difference were 215 days (5/5-12/10) a year in the place mentioned electricity with a stable plan. In the East Sea coastal areas of the Korean peninsula, the average minimum depth to reach the East Sea Proper Water from surface water is 300 m and fluctuates between 250 m and 350 m throughout a year. Further studies could be needed for the utilization of cold water, such as the East Sea Proper Water for energy conversion.

• Journal of Internet Computing and Services
• /
• v.22 no.3
• /
• pp.27-35
• /
• 2021

With the development of the Internet, various IT technologies such as IoT, Cloud, etc. have been developed, and various systems have been built in countries and companies. Because these systems generate and share vast amounts of data, they needed a variety of systems that could detect threats to protect the critical data contained in the system, which has been actively studied to date. Typical techniques include anomaly detection and misuse detection, and these techniques detect threats that are known or exhibit behavior different from normal. However, as IT technology advances, so do technologies that threaten systems, and these methods of detection. Advanced Persistent Threat (APT) attacks national or companies systems to steal important information and perform attacks such as system down. These threats apply previously unknown malware and attack technologies. Therefore, in this paper, we propose a hybrid intrusion detection system that combines anomaly detection and misuse detection to detect unknown threats. Two detection techniques have been applied to enable the detection of known and unknown threats, and by applying machine learning, more accurate threat detection is possible. In misuse detection, we applied Classification based on Association Rule(CBA) to generate rules for known threats, and in anomaly detection, we used One-Class SVM(OCSVM) to detect unknown threats. Experiments show that unknown threat detection accuracy is about 94%, and we confirm that unknown threats can be detected.