• Journal of the Korea Society of Computer and Information
• /
• v.26 no.4
• /
• pp.1-9
• /
• 2021

In this paper, we propose a training algorithm of support vector machine (SVM) with a sensitive variable. Although machine learning models enable automatic decision making in the real world applications, regulations prohibit sensitive information from being used to protect privacy. In particular, the privacy protection of the legally protected attributes such as race, gender, and disability is compulsory. We present an efficient least square SVM (LSSVM) training algorithm using a fully homomorphic encryption (FHE) to protect a partial sensitive attribute. Our framework posits that data owner has both non-sensitive attributes and a sensitive attribute while machine learning service provider (MLSP) can get non-sensitive attributes and an encrypted sensitive attribute. As a result, data owner can obtain the encrypted model parameters without exposing their sensitive information to MLSP. In the inference phase, both non-sensitive attributes and a sensitive attribute are encrypted, and all computations should be conducted on encrypted domain. Through the experiments on real data, we identify that our proposed method enables to implement privacy-preserving sensitive LSSVM with FHE that has comparable performance with the original LSSVM algorithm. In addition, we demonstrate that the efficient sensitive LSSVM with FHE significantly improves the computational cost with a small degradation of performance.

• Journal of Korean Society on Water Environment
• /
• v.27 no.4
• /
• pp.425-432
• /
• 2011

To control non-point source pollution at a watershed scale, rainfall-runoff characteristics from forest watersheds should be investigated since the forest is the dominant land use in Korea. Long-term monitoring would be an ideal method. However, computer models have been utilized due to limitations in cost and labor in performing long-term monitoring at the watersheds. In this study, the Geo-spatial interface to the Water Erosion Prediction Project (GeoWEPP) model was evaluated for its runoff prediction from a coniferous forest dominant watersheds. The $R^2$ and the NSE for calibrated result comparisons were 0.77 and 0.63, validated result comparisons were 0.92, 0.89, respectively. These comparisons indicated that the GeoWEPP model can be used in evaluating rainfall-runoff characteristics. To estimate runoff changes from a coniferous forest watershed with various cover degree scenarios, ten cover degree scenarios (10%, 20%, 30%, 40%, 50%, 60%, 70%, 80%, 90%, 100%) were run using the calibrated GeoWEPP model. It was found that runoff increases with decrease in cover degree. Runoff volume was the highest ($206,218.66m^3$) at 10% cover degree, whereas the lowest ($134,074.58m^3$) at 100% cover degree due to changes in evapotranspiration under various cover degrees at the forest. As shown in this study, GeoWEPP model could be efficiently used to investigate runoff characteristics from the coniferous forest watershed and effects of various cover degree scenarios on runoff generation.

• The Journal of Bigdata
• /
• v.5 no.2
• /
• pp.17-27
• /
• 2020

District heating system supplies heat from low-cost high-efficiency heat production facilities to heat demand areas through a heat pipe network. For efficient heat supply system operation, it is important to accurately predict the heat demand within the region and optimize the heat production plan accordingly. In this study, a heat demand forecasting model is proposed considering real-time calorimeter information from local heat demands. Previous models considered ambient temperature and heat demand history data to predict future heat demands. To improve forecast accuracy, the proposed heat demand forecast model added big data from real-time calorimeters installed in the heat demands within the target region. By employing calorimeter information directly in the model, it is expected that the proposed forecast model is to reflect heat use pattern of each demand. Computational experiemtns based on the actual heat demand data shows that the forecast accuracy of the proposed model improved when the calorimeter big data is reflected.

• Journal of Convergence for Information Technology
• /
• v.12 no.4
• /
• pp.260-269
• /
• 2022

In this paper, We propose an anomaly detection model using deep neural network to automate the identification of outliers of the national air pollution measurement network data that is previously performed by experts. We generated training data by analyzing missing values and outliers of weather data provided by the Institute of Environmental Research and based on the BeatGAN model of the unsupervised learning method, we propose a new model by changing the kernel structure, adding the convolutional filter layer and the transposed convolutional filter layer to improve anomaly detection performance. In addition, by utilizing the generative features of the proposed model to implement and apply a retraining algorithm that generates new data and uses it for training, it was confirmed that the proposed model had the highest performance compared to the original BeatGAN models and other unsupervised learning model like Iforest and One Class SVM. Through this study, it was possible to suggest a method to improve the anomaly detection performance of proposed model while avoiding overfitting without additional cost in situations where training data are insufficient due to various factors such as sensor abnormalities and inspections in actual industrial sites.

• The Journal of the Korea Contents Association
• /
• v.22 no.7
• /
• pp.55-62
• /
• 2022

The perovskite solar cell is an active part of research in renewable energy fields such as solar energy, wind, hydroelectric power, marine energy, bioenergy, and hydrogen energy to replace fossil fuels such as oil, coal, and natural gas, which will gradually disappear as power demand increases due to the increase in use of the Internet of Things and Virtual environments due to the 4th industrial revolution. The perovskite solar cell is a solar cell device using an organic-inorganic hybrid material having a perovskite structure, and has advantages of replacing existing silicon solar cells with high efficiency, low cost solutions, and low temperature processes. In order to optimize the light absorption layer thin film predicted by the existing empirical method, reliability must be verified through device characteristics evaluation. However, since it costs a lot to evaluate the characteristics of the light-absorbing layer thin film device, the number of tests is limited. In order to solve this problem, the development and applicability of a clear and valid model using machine learning or artificial intelligence model as an auxiliary means for optimizing the light absorption layer thin film are considered infinite. In this study, to estimate the light absorption layer thin-film optimization of perovskite solar cells, the regression models of the support vector machine's linear kernel, R.B.F kernel, polynomial kernel, and sigmoid kernel were compared to verify the accuracy difference for each kernel function.

• Korean Association of Arts Management
• /
• no.58
• /
• pp.179-204
• /
• 2021

Not only the consumption trend after the COVID-19 pandemic but also low financial interest rates have stimulated people to invest artworks. With the recent noticeable growth, art investments that mainly conducted by younger generation through online platform can be characterized by a fractional ownership in art market which means several people share one piece of artwork. This study explores 4 fractional ownership platforms in the domestic art market including Art Together, Art & Guide, Tessa, and Pica projects, using a business model canvas that describes nine key elements: Customer Segments, Value Proposition, Channels, Customer Relationships, Revenue Streams, Key Resources, Key Activities, Key Partners and Cost Structure. The four cases have similar business models, but the details of revenue streams are different. The key sources of revenue are the profit and commission of the work. Thus, maximizing the profit margin of artworks is the core of revenue streams, so selecting and purchasing highly profitable artworks are significant. Based on the analysis, there are 3 suggestions to continue fractional ownership platform businesses in art market successfully. First, it is required to have a long-term perspective on art investments, as a way to diverse asset portfolio. Second, business confidence should be increased to maintain customer loyalty. Third, the role of platforms as competent experts is important.

• Journal of the Korea Society of Computer and Information
• /
• v.26 no.11
• /
• pp.21-31
• /
• 2021

As the COVID-19 pandemic rapidly changes healthcare around the globe, the need for smart healthcare that allows for remote diagnosis is increasing. The current classification of respiratory diseases cost high and requires a face-to-face visit with a skilled medical professional, thus the pandemic significantly hinders monitoring and early diagnosis. Therefore, the ability to accurately classify and diagnose respiratory sound using deep learning-based AI models is essential to modern medicine as a remote alternative to the current stethoscope. In this study, we propose a deep learning-based respiratory sound classification model using data collected from medical experts. The sound data were preprocessed with BandPassFilter, and the relevant respiratory audio features were extracted with Log-Mel Spectrogram and Mel Frequency Cepstral Coefficient (MFCC). Subsequently, a Parallel CNN network model was trained on these two inputs using stacking ensemble techniques combined with various machine learning classifiers to efficiently classify and detect abnormal respiratory sounds with high accuracy. The model proposed in this paper classified abnormal respiratory sounds with an accuracy of 96.9%, which is approximately 6.1% higher than the classification accuracy of baseline model.

• Knowledge Management Research
• /
• v.23 no.1
• /
• pp.89-109
• /
• 2022

Due to COVID-19 and soaring participation of individual investors, large-scale transactions exceeding system capacity limits have been reported frequently in the capital market. The capital market IT systems, which the impact of system failure is very critical, have encountered unexpectedly tremendous transactions in 2020, resulting in a sharp increase in system failures. Despite the fact that many companies maintained large-scale system capacity planning policies, recent transaction influx suggests that a new approach to capacity planning is required. Therefore, this study developed capital market IT system capacity planning models using machine learning techniques and analyzed those performances. In addition, the performance of the best proposed model was improved by using sentiment index that can promptly reflect the behavior of investors. The model uses empirical data including the COVID-19 period, and has high performance and stability that can be used in practice. In practical significance, this study maximizes the cost-efficiency of a company, but also presents optimal parameters in consideration of the practical constraints involved in changing the system. Additionally, by proving that the sentiment index can be used as a major variable in system capacity planning, it shows that the sentiment index can be actively used for various other forecasting demands.

• Journal of Industrial Convergence
• /
• v.20 no.8
• /
• pp.1-13
• /
• 2022

Although the number of venture start-ups has increased significantly, it is difficult to judge the success or failure based on short-term performance alone. The survival of a company cannot be guaranteed if it does not show sustainable growth prospects. As a growth factor for venture companies, the level of technology commercialization capability and competitive strategies are considered important. Recently, the emergence of innovative business models is creating new opportunities and driving the growth of numerous venture start-ups. This study tried to investigate the mediating effect of business model innovation in the relationship between technology commercialization capability, competitive strategy and the growth prospects of venture companies. For this, empirical analysis was conducted using the original data of the Research on the Precision Status of Venture Firms 2021. As a result, production, manufacturing, marketing capability, cost leadership and product differentiation had a positive(+) effect on growth prospects. The mediating effect of business model innovation between all factors except for manufacturing capacity and growth prospects was verified. This study expanded the scope of research by shedding new light on the factors influencing the long-term growth prospects of venture companies and revealing business model innovation as a new mediating variable. In future research, it is necessary to develop an objective measurement tool and to identify differences according to industrial characteristics.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.45-52
• /
• 2023

The power generation method using expensive diesel has operation problems such as high cost diesel generator and a lack of reserved power due to increase of power demand in some islands, requiring expansion of power generation facilities. To solve this problems, it is necessary to improve the efficiency of power generation facilities through an ORC(Organic Rankin Cycle) system application that uses waste heat as a heat source. Therefore, localized application technology of price competitive and highly reliable ORC power generation system is needed, and optimization technology of generators is having great effect, so this study performed two generator designs to get a high-efficiency generator with an optimized 30kW output. The comparison of simulation data for two designed models showed that a generator with SPM factor of 46.2% had an efficiency of 92.1% and a power ouput of about 23.2kW based on 12,000rpm, a generator with SPM factor of 44.46%, had a power output of 27.9kW and efficiency of 93.6% based on above rpm. For the verification of improved design model with SPM factor of 44.46%, the prototype test system with 110kW motor dynamometer was installed and got to the efficiency of 92.08% with conditions of the rated capacity 25kW at 12,000rpm, the test results of prototype generator showed the validity of generator design.