• Asia-pacific Journal of Multimedia Services Convergent with Art, Humanities, and Sociology
• /
• v.6 no.5
• /
• pp.367-377
• /
• 2016

The purpose of the projects for strengthening the Service Business Competitiveness, which had been sponsored by the Ministry of Trade, Industry and Energy, and managed by the NIPA, is to support for combining the whole business process of the SMEs with the business model considering the scientific aspects of the services, to enhance the productivity of them and to add the values of their activities. 5 organizations are selected in 2014, and 4 in 2015 as leading organizations for these projects. This study analyzed the efficiency of these projects using DEA. Throughout the analysis of the prior researches, this study used the amount of government-sponsored money as the input variable, and the number of new customer business, the sales revenue, and the number of new employment as the output variables. And the result of this analysis showed that the decision making unit 12, 15, and 21 was efficient. And from this study, we found out two more performance indicators such as, the number of new employment and the amount of sales revenue, besides the number of new customer businesses.

• Journal of Intelligence and Information Systems
• /
• v.29 no.2
• /
• pp.129-148
• /
• 2023

Bitcoin is a blockchain technology-based digital currency that has been recognized as a representative cryptocurrency and a financial investment asset. Due to its highly volatile nature, Bitcoin has gained a lot of attention from investors and the public. Based on this popularity, numerous studies have been conducted on price and trend prediction using machine learning and deep learning. This study employed LSTM (Long Short Term Memory) and CNN (Convolutional Neural Networks), which have shown potential for predictive performance in the finance domain, to enhance the classification accuracy in Bitcoin price trend prediction. XAI(eXplainable Artificial Intelligence) techniques were applied to the predictive model to enhance its explainability and interpretability by providing a comprehensive explanation of the model. In the empirical experiment, CNN was applied to technical indicators and Google trend data to build a Bitcoin price trend prediction model, and the CNN model using both technical indicators and Google trend data clearly outperformed the other models using neural networks, SVM, and LSTM. Then SHAP(Shapley Additive exPlanations) was applied to the predictive model to obtain explanations about the output values. Important prediction drivers in input variables were extracted through global interpretation, and the interpretation of the predictive model's decision process for each instance was suggested through local interpretation. The results show that our proposed research framework demonstrates both improved classification accuracy and explainability by using CNN, Google trend data, and SHAP.

• 한국체육학회지인문사회과학편
• /
• v.57 no.6
• /
• pp.123-134
• /
• 2018

The purpose of this study is to analyze the economic efficiency of the policy implemented by Ministry of Culture, Sports and Tourism on leading company in sport industry. The leading companies in sport industry are those who have a certain amount of sales in sport industry and the ones with potential to become global companies. Supporting areas include business advancement, overseas market development, and overseas PR marketing integration support. The research is performed by developing the equilibrium model composed of supply as well as demand and applying input-output analysis. The economic efficiency is estimated to in the form of changes in the sales of corporations and the ripple effect of the national economy. The results of the study are as follows. First, it is estimated that the sales growth rate of the company due to the implementation of the policy is from 3.74% to 5.19%. Second, the increase in sales reaches to a maximum of KRW 4,081 billion with a minimum of KRW 1,573 million, depending on the size of the company. Third, it is estimated that the production inducement effect for the national economy is from KRW 36 billion to KRW 93.4 billion. Fourth, the induced value added for the national economy is estimated to be at least KRW 11.3 billion, up to KRW 29.2 billion.

• The Journal of the Convergence on Culture Technology
• /
• v.9 no.4
• /
• pp.487-494
• /
• 2023

In this study, performance comparison was performed on R and TensorFlow, which are free deep learning tools. In the experiment, six types of deep neural networks were built using each tool, and the neural networks were trained using the 10-year Korean temperature dataset. The number of nodes in the input layer of the constructed neural network was set to 10, the number of output layers was set to 5, and the hidden layer was set to 5, 10, and 20 to conduct experiments. The dataset includes 3600 temperature data collected from Gangnam-gu, Seoul from March 1, 2013 to March 29, 2023. For performance comparison, the future temperature was predicted for 5 days using the trained neural network, and the root mean square error (RMSE) value was measured using the predicted value and the actual value. Experiment results shows that when there was one hidden layer, the learning error of R was 0.04731176, and TensorFlow was measured at 0.06677193, and when there were two hidden layers, R was measured at 0.04782134 and TensorFlow was measured at 0.05799060. Overall, R was measured to have better performance. We tried to solve the difficulties in tool selection by providing quantitative performance information on the two tools to users who are new to machine learning.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.6B
• /
• pp.597-603
• /
• 2006

The purpose of this study is to improve the short term rainfall forecast skill using neural network model that can deal with the non-linear behavior between satellite data and ground observation, and minimize the flood damage. To overcome the geographical limitation of Korean peninsula and get the long forecast lead time of 3 to 6 hour, the developed rainfall forecast model took satellite imageries and wide range AWS data. The architecture of neural network model is a multi-layer neural network which consists of one input layer, one hidden layer, and one output layer. Neural network is trained using a momentum back propagation algorithm. Flood was estimated using rainfall forecasts. We developed a dynamic flood inundation model which is associated with 1-dimensional flood routing model. Therefore the model can forecast flood aspect in a protected lowland by levee failure of river. In the case of multiple levee breaks at main stream and tributaries, the developed flood inundation model can estimate flood level in a river and inundation level and area in a protected lowland simultaneously.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.2D
• /
• pp.241-250
• /
• 2006

Although walking is an important transport mode which should be promoted, realistic studies about walking is not sufficient. Especially, due to the transportation planning oriented toward automobile, there is not realistic analysis method for walking in the Highway Capacity Manual. Therefore, in this study the fuzzy approximate reasoning was employed to build a model for the analysis of walkways service level. For the input variable the noise level and brightness as well as the pedestrian flow rate were employed and the output variable was the walking satisfaction degree. The fuzzy models were constructed for daytime and nighttime separately. The forecastability analysis for the models were conducted using $R^2$, MAE and MSE. The values of them for the daytime model are 0.802, 0.729 and 0.735 respectively and the values for nighttime are 0.893, 0.878 and 0.860 respectively, so it can be said that the models explain the real situation well. As a result of this study, it can be concluded that the noise level has stronger effects to walking satisfaction then the brightness in night.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.26 no.1B
• /
• pp.61-67
• /
• 2006

Various methods have been applied for the research to model the relationship between rainfall-runoff, which shows a strong nonlinearity. In particular, most researches to model the relationship between rainfall-runoff using artificial neural networks have used back propagation algorithm (BPA), Levenberg Marquardt (LV) and radial basis function (RBF). and They have been proved to be superior in representing the relationship between input and output showing strong nonlinearity and to be highly adaptable to rapid or significant changes in data. The theory of artificial neural networks is utilized not only for prediction but also for classifying the patterns of data and analyzing the characteristics of the patterns. Thus, the present study applied self?organizing map (SOM) based on Kohonen's network theory in order to classify the patterns of rainfall-runoff process and analyze the patterns. The results from the method proposed in the present study revealed that the method could classify the patterns of rainfall in consideration of irregular changes of temporal and spatial distribution of rainfall. In addition, according to the results from the analysis the patterns between rainfall-runoff, seven patterns of rainfall-runoff relationship with strong nonlinearity were identified by SOM.

• 지역과문화
• /
• v.6 no.2
• /
• pp.77-104
• /
• 2019

This study examines the efficiency of using local cultural resources in local governments. The study does so by DEA(Data Envelope Analysis) using data from the year 2017 for 17 local governments in Korea. In addition, this study tries to estimate environmental efficiency of local cultural resources. For this, the 'Total Efficiency' including the output variables related to the local cultural resource environment was analyzed. After than It compared the 'Total Efficiency' with the 'Utilization Efficiency', to estimate the 'Environmental Efficiency' of local cultural resources. The followings are results which are significant statistically. Firstly, it was evaluated that five of the 17 local governments utilized the local cultural resources efficiently. Secondly, it was result that the inefficiency of the other local governments was relatively influenced by the economies of scale than PTE(Pure Technical Efficiency). Thirdly, It has been confirmed that environmental aspects such as cultural properties and cultural infrastructure have a considerable impact on the increase or decrease of efficiency in local governments. The difference in the efficiency of local governments are influenced by the population density. In order to improve the efficiency in the future, it is necessary to adjust the appropriate level of input according to the local population estimate, which is a major consumer of the local cultural resource utilization. In addition, the local festivals and village festivals held by local governments should be checked to improve in quality by eliminating inefficiencies. Also, it should be considered of environmental factors together, when analyzing the efficiency of the local cultural resource in local governments.

• Journal of the Korea Society of Computer and Information
• /
• v.28 no.10
• /
• pp.247-256
• /
• 2023

This study was conducted with the purpose of suggesting alternatives for the efficient operation of senior day care facilities in 22 cities and counties in the Jeonnam region by analyzing the efficiency of senior day care facilities. The analysis data for the study used the National Health Insurance Corporation's long-term care insurance for the elderly (2022), the Input variables were the number of facilities, the number of workers, the number of affordable, and the number of senior long-term care insurance recipients and the Output variables were the the number of users. As a result of the analysis, CCR was most efficient in Goheung-gun, Gokseong-gun, Gwangyang-si, Boseong-gun, Yeongam-gun, and Jindo-gun, BCC was most efficient in Goheung-gun, Gokseong-gun, Gwangyang-si, Gurye-gun, Damyang-gun, Boseong-gun, and Jindo-gun, and SE was most efficient in that order: Jindo-gun, Gokseong-gun, and Gwangyang-si. It turned out to be a super efficient area. In the contribution analysis, the number of affordable and workers variables were found to be variables that had a large impact on efficiency contribution. In the improvement potential analysis, the number of facilities variable was found to be a variable that had a significant impact on efficiency. Therefore, for the efficient operation of senior day care facilities, we suggest adjusting supply and demand, such as the number of facilities and affordable, and suggest that training programs to strengthen the expertise of workers who contribute greatly are required.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.5
• /
• pp.15-30
• /
• 2023

Recently, generative models based on the Transformer architecture, such as ChatGPT, have been gaining significant attention. The Transformer architecture has been applied to various neural network models, including Google's BERT(Bidirectional Encoder Representations from Transformers) sentence generation model. In this paper, a method is proposed to create a text binary classification model for determining whether a comment on Korean movie review is positive or negative. To accomplish this, a pre-trained multilingual BERT sentence generation model is fine-tuned and transfer learned using a new Korean training dataset. To achieve this, a pre-trained BERT-Base model for multilingual sentence generation with 104 languages, 12 layers, 768 hidden, 12 attention heads, and 110M parameters is used. To change the pre-trained BERT-Base model into a text classification model, the input and output layers were fine-tuned, resulting in the creation of a new model with 178 million parameters. Using the fine-tuned model, with a maximum word count of 128, a batch size of 16, and 5 epochs, transfer learning is conducted with 10,000 training data and 5,000 testing data. A text sentiment binary classification model for Korean movie review with an accuracy of 0.9582, a loss of 0.1177, and an F1 score of 0.81 has been created. As a result of performing transfer learning with a dataset five times larger, a model with an accuracy of 0.9562, a loss of 0.1202, and an F1 score of 0.86 has been generated.