• The KIPS Transactions:PartB
• /
• v.15B no.1
• /
• pp.25-36
• /
• 2008

In this paper, we present a robust hand recognition approach to sudden illumination changes. The proposed approach constructs a background model with respect to hue and hue gradient in HSI color space and extracts a foreground hand region from an input image using the background subtraction method. Eighteen features are defined for a hand pose and multi-class SVM(Support Vector Machine) approach is applied to learn and classify hand poses based on eighteen features. The proposed approach robustly extracts the contour of a hand with variations in illumination by applying the hue gradient into the background subtraction. A hand pose is defined by two Eigen values which are normalized by the size of OBB(Object-Oriented Bounding Box), and sixteen feature values which represent the number of hand contour points included in each subrange of OBB. We compared the RGB-based background subtraction, hue-based background subtraction and the proposed approach with sudden illumination changes and proved the robustness of the proposed approach. In the experiment, we built a hand pose training model from 2,700 sample hand images of six subjects which represent nine numerical numbers from one to nine. Our implementation result shows 92.6% of successful recognition rate for 1,620 hand images with various lighting condition using the training model.

• Journal of Intelligence and Information Systems
• /
• v.22 no.4
• /
• pp.177-192
• /
• 2016

Machine learning is a field of artificial intelligence. It refers to an area of computer science related to providing machines the ability to perform their own data analysis, decision making and forecasting. For example, one of the representative machine learning models is artificial neural network, which is a statistical learning algorithm inspired by the neural network structure of biology. In addition, there are other machine learning models such as decision tree model, naive bayes model and SVM(support vector machine) model. Among the machine learning models, we use SVM model in this study because it is mainly used for classification and regression analysis that fits well to our study. The core principle of SVM is to find a reasonable hyperplane that distinguishes different group in the data space. Given information about the data in any two groups, the SVM model judges to which group the new data belongs based on the hyperplane obtained from the given data set. Thus, the more the amount of meaningful data, the better the machine learning ability. In recent years, many financial experts have focused on machine learning, seeing the possibility of combining with machine learning and the financial field where vast amounts of financial data exist. Machine learning techniques have been proved to be powerful in describing the non-stationary and chaotic stock price dynamics. A lot of researches have been successfully conducted on forecasting of stock prices using machine learning algorithms. Recently, financial companies have begun to provide Robo-Advisor service, a compound word of Robot and Advisor, which can perform various financial tasks through advanced algorithms using rapidly changing huge amount of data. Robo-Adviser's main task is to advise the investors about the investor's personal investment propensity and to provide the service to manage the portfolio automatically. In this study, we propose a method of forecasting the Korean volatility index, VKOSPI, using the SVM model, which is one of the machine learning methods, and applying it to real option trading to increase the trading performance. VKOSPI is a measure of the future volatility of the KOSPI 200 index based on KOSPI 200 index option prices. VKOSPI is similar to the VIX index, which is based on S&P 500 option price in the United States. The Korea Exchange(KRX) calculates and announce the real-time VKOSPI index. VKOSPI is the same as the usual volatility and affects the option prices. The direction of VKOSPI and option prices show positive relation regardless of the option type (call and put options with various striking prices). If the volatility increases, all of the call and put option premium increases because the probability of the option's exercise possibility increases. The investor can know the rising value of the option price with respect to the volatility rising value in real time through Vega, a Black-Scholes's measurement index of an option's sensitivity to changes in the volatility. Therefore, accurate forecasting of VKOSPI movements is one of the important factors that can generate profit in option trading. In this study, we verified through real option data that the accurate forecast of VKOSPI is able to make a big profit in real option trading. To the best of our knowledge, there have been no studies on the idea of predicting the direction of VKOSPI based on machine learning and introducing the idea of applying it to actual option trading. In this study predicted daily VKOSPI changes through SVM model and then made intraday option strangle position, which gives profit as option prices reduce, only when VKOSPI is expected to decline during daytime. We analyzed the results and tested whether it is applicable to real option trading based on SVM's prediction. The results showed the prediction accuracy of VKOSPI was 57.83% on average, and the number of position entry times was 43.2 times, which is less than half of the benchmark (100 times). A small number of trading is an indicator of trading efficiency. In addition, the experiment proved that the trading performance was significantly higher than the benchmark.

• Journal of Advanced Marine Engineering and Technology
• /
• v.33 no.8
• /
• pp.1261-1267
• /
• 2009

The Direct Torque Control[DTC] controls torque and flux by restricting the flux and torque errors within respective hysteresis bands, and motor torque and flux are controlled by the stator voltage space vector using optimum inverter switching table. And the Current Error Compensation method is on the basis of compensating current difference between the induction motor and its numerical model, in which the identical stator voltage is supplied for both the actual motor and the model so that the gaps between stator currents of the two can be forced to decay to zero as time proceeds. Consequently, the rotor speed approaches to the model speed, namely, setting value and the system can control motor speed precisely. This paper proposes a new sensorless speed control of induction motor using DTC and Current Error Compensation, which requires neither shaft encoder, speed estimator nor PI controllers. And through computer simulation, confirm effectiveness of proposed method.

• Journal of KIISE
• /
• v.41 no.12
• /
• pp.1117-1125
• /
• 2014

Folksonomy data, which is derived from social tagging systems, is a useful source for understanding a user's intention and interest. Using the folksonomy data, it is possible to create an accurate user profile which can be utilized to build a personalized search system. However there are limitations in some of the traditional methods such as Vector Space Model(VSM) for user profiling and similarity computation. This paper suggests a novel method with graph-based user and document profile which uses the proximity information of query terms to improve personalized search. We demonstrate the performance of the suggested method by comparing its performance with several state-of-the-art VSM based personalization models in two different folksonomy datasets. The results show that the proposed model constantly outperforms the other state-of-the-art personalization models. Furthermore, the parameter sensitivity results show that the proposed model is parameter-free in that it is not affected by the idiosyncratic nature of datasets.

• Journal of KIISE
• /
• v.42 no.6
• /
• pp.748-754
• /
• 2015

This paper proposes a sequential state estimation model consisting of continuous and discrete variables, as a way of generalizing all discrete-state factorial HMM, and gives a design of gait motion model based on the idea. The discrete state variable implements a Markov chain that models the gait dynamics, and for each state of the Markov chain, we created a Gaussian process over the space of the continuous variable. The Markov chain controls the switching among Gaussian processes, each of which models the rotation or various views of a gait state. Then a particle filter-based algorithm is presented to give an approximate filtering solution. Given an input vector sequence presented over time, this finds a trajectory that follows a Gaussian process and occasionally switches to another dynamically. Experimental results show that the proposed model can provide a very intuitive interpretation of video-based gait into a sequence of poses and a sequence of posture states.

• Journal of KIISE:Software and Applications
• /
• v.30 no.1_2
• /
• pp.140-152
• /
• 2003

An XML document has a structure which may be irregular. It is difficult for end-users to comprehend the irregular document structure exactly. For these XML documents, an end-user has a difficulty in using structured query. Therefore, an end-user formulates no structured query or a query which has a little structure information. In this context, we propose new retrieval models which use the structured information for ranking and compensate the difference between user query structure and document structure. To ease with querying, we assume the independence among querying paths which represent structural constraints. Since this assumption makes degradation of the expression power of a query language, we also propose a model which overcome this problem. As there had been no test collections for XML documents, we made a small test collection from TIPSTER of the RTEC and experimented on this collection without a structured query, From this experiment, we showed that our models improve average precision about 67% over conventional Vector-Space model.

• Journal of Power Electronics
• /
• v.14 no.1
• /
• pp.92-104
• /
• 2014

To insure stable operation and eliminate twice torque ripple, a topology for a six phase permanent magnet synchronous generator (SP-PMSG) with a neutral point connected together was analyzed in this paper. By adopting an extended transformation matrix, the mathematic model of the space vector control was established. The voltage and torque equations were deduced while considering the third harmonic flux and inductance. In addition, the suppression third harmonic method and the closed loop control strategy were proposed. A comparison analysis indicates that the cooper loss minimum method and the current magnitude minimum method can meet different application requirements. The voltage compensation amount for each of the methods was deduced which also takes into account the third harmonic effect. A simulation and experimental result comparison validates the consistency through theoretical derivation. It can be seen that all of the two control strategies can meet the requirements of post-fault.

• 제어로봇시스템학회:학술대회논문집
• /
• 2003.10a
• /
• pp.1986-1989
• /
• 2003

This paper proposes the information retrieval improvement for the Web using the structure and hyperlinks of HTML documents along with user profile. The method bases on the rationale that terms appearing in different structure of documents may have different significance in identifying the documents. The method partitions the occurrence of terms in a document collection into six classes according to the tags in which particular terms occurred (such as Title, H1-H6 and Anchor). We use genetic algorithm to determine class importance values and expand user query. We also use this value in similarity computation and update user profile. Then a genetic algorithm is used again to select some terms from user profile to expand the original query. Lastly, the search engine uses the expanded query for searching and the results of the search engine are scored by similarity values between each result and the user profile. Vector space model is used and the weighting schemes of traditional information retrieval were extended to include class importance values. The tested results show that precision is up to 81.5%.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2003.09a
• /
• pp.455-458
• /
• 2003

The variety of document ranking algorithms have developed to provide efficient mining results for user's query on the web environment. The typical ranking algorithms are the Vector-Space Model based on the text, PsgeRank and HITS algorithms based on the hyperlink structures and other several improvement algorithms. All these are for the user's convenience and preference. However, these algorithms are usually developed on then Horizontal and non-hierarchial web environments and are not suitable for the hierarchial web environments such as enterprise and defense networks. Thus, we must consider the special environment factors in order to improve the ranking algorithms. In this paper, we analyze the several typical algorithms used by hyperlink structures on the web environment. We, then suggest a configuration of the hierarchical web environment and also give the relations between agents of the web mining system. Next, we propose an improved ranking algorithm suitable to this kind of special environments. The proposed algorithm is considered both the hyperlink structures of the documents and the location of the user of the hierarchical web.

• Phonetics and Speech Sciences
• /
• v.1 no.4
• /
• pp.127-132
• /
• 2009

The feature vectors which are used in conventional speaker recognition (SR) systems may have many correlations between their neighbors. To improve the performance of the SR, many researchers adopted linear transformation method like principal component analysis (PCA). In general, the linear transformation of the feature vectors is based on concatenated form of the static features and their dynamic features. However, the linear transformation which based on both the static features and their dynamic features is more complex than that based on the static features alone due to the high order of the features. To overcome these problems, we propose an efficient method that applies linear transformation and temporal information of the features to reduce complexity and improve the performance in speaker verification (SV). The proposed method first performs a linear transformation by PCA coefficients. The delta parameters for temporal information are then obtained from the transformed features. The proposed method only requires 1/4 in the size of the covariance matrix compared with adding the static and their dynamic features for PCA coefficients. Also, the delta parameters are extracted from the linearly transformed features after the reduction of dimension in the static features. Compared with the PCA and conventional methods in terms of equal error rate (EER) in SV, the proposed method shows better performance while requiring less storage space and complexity.