• The Transactions of The Korean Institute of Electrical Engineers
• /
• 제62권5호
• /
• pp.696-704
• /
• 2013

In this paper, we introduce the LED emotional lighting system realized with the aid of both intelligent algorithm and RGB LED combined with White LED. Generally, the illumination is known as a design factor to form the living place that affects human's emotion and action in the light- space as well as the purpose to light up the specific space. The LED emotional lighting system that can express emotional atmosphere as well as control the quantity of light is designed by using both RGB LED to form the emotional mood and W LED to get sufficient amount of light. RBFNNs is used as the intelligent algorithm and the network model designed with the aid of LED control parameters (viz. color coordinates (x and y) related to color temperature, and lux as inputs, RGBW current as output) plays an important role to build up the LED emotional lighting system for obtaining appropriate color space. Unlike conventional RBFNNs, Fuzzy C-Means(FCM) clustering method is used to obtain the fitness values of the receptive function, and the connection weights of the consequence part of networks are expressed by polynomial functions. Also, the parameters of RBFNN model are optimized by using PSO(Particle Swarm Optimization). The proposed LED emotional lighting can save the energy by using the LED light source and improve the ability to work as well as to learn by making an adequate mood under diverse surrounding conditions.

• Journal of Information Processing Systems
• /
• 제13권5호
• /
• pp.1243-1258
• /
• 2017

A new medical materials scheduling system and its modeling method for the complex rescue are presented. Different from other similar system, first both the BeiDou Satellite Communication System (BSCS) and the Special Fiber-optic Communication Network (SFCN) are used to collect the rescue requirements and the location information of disaster areas. Then all these messages will be displayed in a special medical software terminal. After that the bipartite graph models are utilized to compute the optimal scheduling of medical materials. Finally, all these results will be transmitted back by the BSCS and the SFCN again to implement a fast guidance of medical rescue. The sole drug scheduling issue, the multiple drugs scheduling issue, and the backup-scheme selection issue are all utilized: the Kuhn-Munkres algorithm is used to realize the optimal matching of sole drug scheduling issue, the spectral clustering-based method is employed to calculate the optimal distribution of multiple drugs scheduling issue, and the similarity metric of neighboring matrix is utilized to realize the estimation of backup-scheme selection issue of medical materials. Many simulation analysis experiments and applications have proved the correctness of proposed technique and system.

• Journal of Internet Computing and Services
• /
• 제20권1호
• /
• pp.1-10
• /
• 2019

Since big-data text mining extracts many features and data, clustering and classification can result in high computational complexity and low reliability of the analysis results. In particular, a term document matrix obtained through text mining represents term-document features, but produces a sparse matrix. We designed an advanced genetic algorithm (GA) to extract features in text mining for detection model. Term frequency inverse document frequency (TF-IDF) is used to reflect the document-term relationships in feature extraction. Through a repetitive process, a predetermined number of features are selected. And, we used the sparsity score to improve the performance of detection model. If a spam mail data set has the high sparsity, detection model have low performance and is difficult to search the optimization detection model. In addition, we find a low sparsity model that have also high TF-IDF score by using s(F) where the numerator in fitness function. We also verified its performance by applying the proposed algorithm to text classification. As a result, we have found that our algorithm shows higher performance (speed and accuracy) in attack mail classification.

• Proceedings of the Korea Water Resources Association Conference
• /
• 한국수자원학회 2015년도 학술발표회
• /
• pp.217-217
• /
• 2015

The objective of this study was mainly to evaluate the water resources potential of Lake Tana Basin (LTB) by using Soil and Water Assessment Tool (SWAT). From SWAT simulation of LTB, about 5236 km2 area of LTB is gauged watershed and the remaining 9878 km2 area is ungauged watershed. For calibration of model parameters, four gauged stations were considered namely: Gilgel Abay, Gummera, Rib, and Megech. The SWAT-CUP built-in techniques, particle swarm optimization (PSO) and generalized likelihood uncertainty estimation (GLUE) method was used for calibration of model parameters and PSO method were selected for the study based on its performance results in four gauging stations. However the level of sensitivity of flow parameters differ from catchment to catchment, the curve number (CN2) has been found the most sensitive parameters in all gauged catchments. To facilitate the transfer of data from gauged catchments to ungauged catchments, clustering of hydrologic response units (HRUs) were done based on physical similarity measured between gauged and ungauged catchment attributes. From SWAT land use/ soil use/slope reclassification of LTB, a total of 142 HRUs were identified and these HRUs are clustered in to 39 similar hydrologic groups. In order to transfer the optimized model parameters from gauged to ungauged catchments based on these clustered hydrologic groups, this study evaluates three parameter transfer schemes: parameters transfer based on homogeneous regions (PT-I), parameter transfer based on global averaging (PT-II), and parameter transfer by considering Gilgel Abay catchment as a representative catchment (PT-III) since its model performance values are better than the other three gauged catchments. The performance of these parameter transfer approach was evaluated based on values of Nash-Sutcliffe efficiency (NSE) and coefficient of determination (R2). The computed NSE values was found to be 0.71, 0.58, and 0.31 for PT-I, PT-II and PT-III respectively and the computed R2 values was found to be 0.93, 0.82, and 0.95 for PT-I, PT-II, and PT-III respectively. Based on the performance evaluation criteria, PT-I were selected for modelling ungauged catchments by transferring optimized model parameters from gauged catchment. From the model result, yearly average stream flow for all homogeneous regions was found 29.54 m3/s, 112.92 m3/s, and 130.10 m3/s for time period (1989 - 2005) for region-I, region-II, and region-III respectively.

• Journal of Advanced Navigation Technology
• /
• 제15권6호
• /
• pp.1015-1024
• /
• 2011

Mobile P2P protocols in ad-hoc networks have gained large attention recently. Although there has been much research on P2P algorithms for wired networks, existing P2P protocols are not suitable for mobile ad-hoc networks because they do not consider mobility of peers. This study proposes a new cluster-based P2P protocol for ad hoc networks which utilizes peer mobility. In typical cluster-based P2P algorithms, each cluster has a super peer and other peers of the cluster register their file list to the super peer. High mobility peers would cause a lot of file list registration traffic because they hand-off between clusters frequently. In the proposed scheme, while peers with low mobility behave in the same way as the peers of the typical cluster-based P2P schemes, peers with high mobility behave differently. They inform their entrance to the cluster region to the super peer but they do not register their file list to the super peer. When a peer wishes to find a file, it first searches the registered file list of the super peer and if fails, query message is broadcasted. We perform mathematical modeling, analysis and optimization of the proposed scheme regarding P2P traffic and associated routing traffic. Numerical results show that the proposed scheme performs much better than or similar to the typical cluster-based P2P scheme and flooding based Gnutella.

• Journal of the Korean Institute of Intelligent Systems
• /
• 제23권4호
• /
• pp.354-359
• /
• 2013

In this paper, we suggested the method for implementation of unsupervised nonlinear classification using Binary Harmony Search (BHS) algorithm, which is known as a optimization algorithm. Various algorithms have been suggested for classification of feature vectors from the process of machine learning for pattern recognition or EEG signal analysis processing. Supervised learning based support vector machine or fuzzy c-mean (FCM) based on unsupervised learning have been used for classification in the field. However, conventional methods were hard to apply nonlinear dataset classification or required prior information for supervised learning. We solved this problems with proposed classification method using heuristic approach which took the minimal Euclidean distance between vectors, then we assumed them as same class and the others were another class. For the comparison, we used FCM, self-organizing map (SOM) based on artificial neural network (ANN). KEEL machine learning datset was used for simulation. We concluded that proposed method was superior than other algorithms.

• Journal of Intelligence and Information Systems
• /
• 제23권2호
• /
• pp.107-122
• /
• 2017

Volatility in the stock market returns is a measure of investment risk. It plays a central role in portfolio optimization, asset pricing and risk management as well as most theoretical financial models. Engle(1982) presented a pioneering paper on the stock market volatility that explains the time-variant characteristics embedded in the stock market return volatility. His model, Autoregressive Conditional Heteroscedasticity (ARCH), was generalized by Bollerslev(1986) as GARCH models. Empirical studies have shown that GARCH models describes well the fat-tailed return distributions and volatility clustering phenomenon appearing in stock prices. The parameters of the GARCH models are generally estimated by the maximum likelihood estimation (MLE) based on the standard normal density. But, since 1987 Black Monday, the stock market prices have become very complex and shown a lot of noisy terms. Recent studies start to apply artificial intelligent approach in estimating the GARCH parameters as a substitute for the MLE. The paper presents SVR-based GARCH process and compares with MLE-based GARCH process to estimate the parameters of GARCH models which are known to well forecast stock market volatility. Kernel functions used in SVR estimation process are linear, polynomial and radial. We analyzed the suggested models with KOSPI 200 Index. This index is constituted by 200 blue chip stocks listed in the Korea Exchange. We sampled KOSPI 200 daily closing values from 2010 to 2015. Sample observations are 1487 days. We used 1187 days to train the suggested GARCH models and the remaining 300 days were used as testing data. First, symmetric and asymmetric GARCH models are estimated by MLE. We forecasted KOSPI 200 Index return volatility and the statistical metric MSE shows better results for the asymmetric GARCH models such as E-GARCH or GJR-GARCH. This is consistent with the documented non-normal return distribution characteristics with fat-tail and leptokurtosis. Compared with MLE estimation process, SVR-based GARCH models outperform the MLE methodology in KOSPI 200 Index return volatility forecasting. Polynomial kernel function shows exceptionally lower forecasting accuracy. We suggested Intelligent Volatility Trading System (IVTS) that utilizes the forecasted volatility results. IVTS entry rules are as follows. If forecasted tomorrow volatility will increase then buy volatility today. If forecasted tomorrow volatility will decrease then sell volatility today. If forecasted volatility direction does not change we hold the existing buy or sell positions. IVTS is assumed to buy and sell historical volatility values. This is somewhat unreal because we cannot trade historical volatility values themselves. But our simulation results are meaningful since the Korea Exchange introduced volatility futures contract that traders can trade since November 2014. The trading systems with SVR-based GARCH models show higher returns than MLE-based GARCH in the testing period. And trading profitable percentages of MLE-based GARCH IVTS models range from 47.5% to 50.0%, trading profitable percentages of SVR-based GARCH IVTS models range from 51.8% to 59.7%. MLE-based symmetric S-GARCH shows +150.2% return and SVR-based symmetric S-GARCH shows +526.4% return. MLE-based asymmetric E-GARCH shows -72% return and SVR-based asymmetric E-GARCH shows +245.6% return. MLE-based asymmetric GJR-GARCH shows -98.7% return and SVR-based asymmetric GJR-GARCH shows +126.3% return. Linear kernel function shows higher trading returns than radial kernel function. Best performance of SVR-based IVTS is +526.4% and that of MLE-based IVTS is +150.2%. SVR-based GARCH IVTS shows higher trading frequency. This study has some limitations. Our models are solely based on SVR. Other artificial intelligence models are needed to search for better performance. We do not consider costs incurred in the trading process including brokerage commissions and slippage costs. IVTS trading performance is unreal since we use historical volatility values as trading objects. The exact forecasting of stock market volatility is essential in the real trading as well as asset pricing models. Further studies on other machine learning-based GARCH models can give better information for the stock market investors.

• Journal of Intelligence and Information Systems
• /
• 제26권1호
• /
• pp.1-21
• /
• 2020

With the rapid development of artificial intelligence technology, various techniques have been developed to extract meaningful information from unstructured text data which constitutes a large portion of big data. Over the past decades, text mining technologies have been utilized in various industries for practical applications. In the field of business intelligence, it has been employed to discover new market and/or technology opportunities and support rational decision making of business participants. The market information such as market size, market growth rate, and market share is essential for setting companies' business strategies. There has been a continuous demand in various fields for specific product level-market information. However, the information has been generally provided at industry level or broad categories based on classification standards, making it difficult to obtain specific and proper information. In this regard, we propose a new methodology that can estimate the market sizes of product groups at more detailed levels than that of previously offered. We applied Word2Vec algorithm, a neural network based semantic word embedding model, to enable automatic market size estimation from individual companies' product information in a bottom-up manner. The overall process is as follows: First, the data related to product information is collected, refined, and restructured into suitable form for applying Word2Vec model. Next, the preprocessed data is embedded into vector space by Word2Vec and then the product groups are derived by extracting similar products names based on cosine similarity calculation. Finally, the sales data on the extracted products is summated to estimate the market size of the product groups. As an experimental data, text data of product names from Statistics Korea's microdata (345,103 cases) were mapped in multidimensional vector space by Word2Vec training. We performed parameters optimization for training and then applied vector dimension of 300 and window size of 15 as optimized parameters for further experiments. We employed index words of Korean Standard Industry Classification (KSIC) as a product name dataset to more efficiently cluster product groups. The product names which are similar to KSIC indexes were extracted based on cosine similarity. The market size of extracted products as one product category was calculated from individual companies' sales data. The market sizes of 11,654 specific product lines were automatically estimated by the proposed model. For the performance verification, the results were compared with actual market size of some items. The Pearson's correlation coefficient was 0.513. Our approach has several advantages differing from the previous studies. First, text mining and machine learning techniques were applied for the first time on market size estimation, overcoming the limitations of traditional sampling based- or multiple assumption required-methods. In addition, the level of market category can be easily and efficiently adjusted according to the purpose of information use by changing cosine similarity threshold. Furthermore, it has a high potential of practical applications since it can resolve unmet needs for detailed market size information in public and private sectors. Specifically, it can be utilized in technology evaluation and technology commercialization support program conducted by governmental institutions, as well as business strategies consulting and market analysis report publishing by private firms. The limitation of our study is that the presented model needs to be improved in terms of accuracy and reliability. The semantic-based word embedding module can be advanced by giving a proper order in the preprocessed dataset or by combining another algorithm such as Jaccard similarity with Word2Vec. Also, the methods of product group clustering can be changed to other types of unsupervised machine learning algorithm. Our group is currently working on subsequent studies and we expect that it can further improve the performance of the conceptually proposed basic model in this study.