• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.6
• /
• pp.527-533
• /
• 2013

BCI (Brain-Computer Interface) is a system that transforms a subject's brain signal related to their intention into a control signal by classifying EEG (electroencephalograph) signals obtained during the imagination of movement of a subject's limbs. The BCI system allows us to control machines such as robot arms or wheelchairs only by imaging limbs. With the exact same experiment environment, activated brain regions of each subjects are totally different. In that case, a simple approach is to use as many channels as possible when measuring brain signals. However the problem is that using many channels also causes other problems. When applying a CSP (Common Spatial Pattern), which is an EEG extraction method, many channels cause an overfitting problem, and in addition there is difficulty using this technique for medical analysis. To overcome these problems, we suggest an optimal channel selection method using a BPSO (Binary Particle Swarm Optimization), BPSO with channel impact factor, and GA. This paper examined optimal selected channels among all channels using three optimization methods and compared the classification accuracy and the number of selected channels between BPSO, BPSO with channel impact factor, and GA by SVM (Support Vector Machine). The result showed that BPSO with channel impact factor selected 2 fewer channels and even improved accuracy by 10.17~11.34% compared with BPSO and GA.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.49 no.4
• /
• pp.42-53
• /
• 2012

In pattern recognition and machine learning society, classification has been a classical problem and the most widely researched area. Adaptive boosting also known as Adaboost has been successfully applied to binary classification problems. It is a kind of boosting algorithm capable of constructing a strong classifier through a weighted combination of weak classifiers. On the other hand, the PCA and LDA algorithms are the most popular linear feature extraction methods used mainly for dimensionality reduction. In this paper, the combination of Adaboost and feature extraction methods is proposed for efficient classification of two class data. Conventionally, in classification problems, the roles of feature extraction and classification have been distinct, i.e., a feature extraction method and a classifier are applied sequentially to classify input variable into several categories. In this paper, these two steps are combined into one resulting in a good classification performance. More specifically, each projection vector is treated as a weak classifier in Adaboost algorithm to constitute a strong classifier for binary classification problems. The proposed algorithm is applied to UCI dataset and FRGC dataset and showed better recognition rates than sequential application of feature extraction and classification methods.

• Journal of The Korean Society of Agricultural Engineers
• /
• v.64 no.1
• /
• pp.15-26
• /
• 2022

3D open-field farm model developed from UAV (Unmanned Aerial Vehicle) data could make crop monitoring easier, also could be an important dataset for various fields like remote sensing or precision agriculture. It is essential to separate crops from the non-crop area because labeling in a manual way is extremely laborious and not appropriate for continuous monitoring. We, therefore, made a 3D open-field farm model based on UAV images and developed a crop segmentation model using a supervised machine learning algorithm. We compared performances from various models using different data features like color or geographic coordinates, and two supervised learning algorithms which are SVM (Support Vector Machine) and KNN (K-Nearest Neighbors). The best approach was trained with 2-dimensional data, ExGR (Excess of Green minus Excess of Red) and z coordinate value, using KNN algorithm, whose accuracy, precision, recall, F1 score was 97.85, 96.51, 88.54, 92.35% respectively. Also, we compared our model performance with similar previous work. Our approach showed slightly better accuracy, and it detected the actual crop better than the previous approach, while it also classified actual non-crop points (e.g. weeds) as crops.

• Journal of Advanced Navigation Technology
• /
• v.27 no.1
• /
• pp.111-118
• /
• 2023

For the implementation of a smart factory, it is necessary to collect data by connecting various sensors and devices in the manufacturing environment and to diagnose or predict failures in production facilities through data analysis. In this paper, to predict the residual useful lifetime of milling insert used for machining products in CNC machine, weight k-NN algorithm, Decision Tree, SVR, XGBoost, Random forest, 1D-CNN, and frequency spectrum based on vibration signal are investigated. As the results of the paper, the frequency spectrum does not provide a reliable criterion for an accurate prediction of the residual useful lifetime of an insert. And the weighted k-nearest neighbor algorithm performed best with an MAE of 0.0013, MSE of 0.004, and RMSE of 0.0192. This is an error of 0.001 seconds of the remaining useful lifetime of the insert predicted by the weighted-nearest neighbor algorithm, and it is considered to be a level that can be applied to actual industrial sites.

• International conference on construction engineering and project management
• /
• 2020.12a
• /
• pp.463-481
• /
• 2020

Cutter suction dredgers (CSDs) are widely used in various dredging constructions such as channel excavation, wharf construction, and reef construction. During a CSD construction, the main operation is to control the swing speed of cutter to keep the slurry concentration in a proper range. However, the slurry concentration cannot be monitored in real-time, i.e., there is a "time-lag effect" in the log of slurry concentration, making it difficult for operators to make the optimal decision on controlling. Concerning this issue, a solution scheme that using real-time monitored indicators to predict current slurry concentration is proposed in this research. The characteristics of the CSD monitoring data are first studied, and a set of preprocessing methods are presented. Then we put forward the concept of "index class" to select the important indices. Finally, an ensemble learning algorithm is set up to fit the relationship between the slurry concentration and the indices of the index classes. In the experiment, log data over seven days of a practical dredging construction is collected. For comparison, the Deep Neural Network (DNN), Long Short Time Memory (LSTM), Support Vector Machine (SVM), Random Forest (RF), Gradient Boosting Decision Tree (GBDT), and the Bayesian Ridge algorithm are tried. The results show that our method has the best performance with an R² of 0.886 and a mean square error (MSE) of 5.538. This research provides an effective way for real-time predicting the slurry concentration of CSDs and can help to improve the stationarity and production efficiency of dredging construction.

• Journal of Intelligence and Information Systems
• /
• v.25 no.2
• /
• pp.39-55
• /
• 2019

Recently banks and large financial institutions have introduced lots of Robo-Advisor products. Robo-Advisor is a Robot to produce the optimal asset allocation portfolio for investors by using the financial engineering algorithms without any human intervention. Since the first introduction in Wall Street in 2008, the market size has grown to 60 billion dollars and is expected to expand to 2,000 billion dollars by 2020. Since Robo-Advisor algorithms suggest asset allocation output to investors, mathematical or statistical asset allocation strategies are applied. Mean variance optimization model developed by Markowitz is the typical asset allocation model. The model is a simple but quite intuitive portfolio strategy. For example, assets are allocated in order to minimize the risk on the portfolio while maximizing the expected return on the portfolio using optimization techniques. Despite its theoretical background, both academics and practitioners find that the standard mean variance optimization portfolio is very sensitive to the expected returns calculated by past price data. Corner solutions are often found to be allocated only to a few assets. The Black-Litterman Optimization model overcomes these problems by choosing a neutral Capital Asset Pricing Model equilibrium point. Implied equilibrium returns of each asset are derived from equilibrium market portfolio through reverse optimization. The Black-Litterman model uses a Bayesian approach to combine the subjective views on the price forecast of one or more assets with implied equilibrium returns, resulting a new estimates of risk and expected returns. These new estimates can produce optimal portfolio by the well-known Markowitz mean-variance optimization algorithm. If the investor does not have any views on his asset classes, the Black-Litterman optimization model produce the same portfolio as the market portfolio. What if the subjective views are incorrect? A survey on reports of stocks performance recommended by securities analysts show very poor results. Therefore the incorrect views combined with implied equilibrium returns may produce very poor portfolio output to the Black-Litterman model users. This paper suggests an objective investor views model based on Support Vector Machines(SVM), which have showed good performance results in stock price forecasting. SVM is a discriminative classifier defined by a separating hyper plane. The linear, radial basis and polynomial kernel functions are used to learn the hyper planes. Input variables for the SVM are returns, standard deviations, Stochastics %K and price parity degree for each asset class. SVM output returns expected stock price movements and their probabilities, which are used as input variables in the intelligent views model. The stock price movements are categorized by three phases; down, neutral and up. The expected stock returns make P matrix and their probability results are used in Q matrix. Implied equilibrium returns vector is combined with the intelligent views matrix, resulting the Black-Litterman optimal portfolio. For comparisons, Markowitz mean-variance optimization model and risk parity model are used. The value weighted market portfolio and equal weighted market portfolio are used as benchmark indexes. We collect the 8 KOSPI 200 sector indexes from January 2008 to December 2018 including 132 monthly index values. Training period is from 2008 to 2015 and testing period is from 2016 to 2018. Our suggested intelligent view model combined with implied equilibrium returns produced the optimal Black-Litterman portfolio. The out of sample period portfolio showed better performance compared with the well-known Markowitz mean-variance optimization portfolio, risk parity portfolio and market portfolio. The total return from 3 year-period Black-Litterman portfolio records 6.4%, which is the highest value. The maximum draw down is -20.8%, which is also the lowest value. Sharpe Ratio shows the highest value, 0.17. It measures the return to risk ratio. Overall, our suggested view model shows the possibility of replacing subjective analysts's views with objective view model for practitioners to apply the Robo-Advisor asset allocation algorithms in the real trading fields.

• Journal of Korea Multimedia Society
• /
• v.18 no.5
• /
• pp.610-619
• /
• 2015

*In this paper, we propose a real-time face tracking system using an adaptive face detector and a tracking algorithm. An image is divided into the regions of background and face candidate by a real-time updated skin color identifying system in order to accurately detect facial features. The facial characteristics are extracted using the five types of simple Haar-like features. The extracted features are reinterpreted by Principal Component Analysis (PCA), and the interpreted principal components are processed by Support Vector Machine (SVM) that classifies into facial and non-facial areas. The movement of the face is traced by Kalman filter and Mean shift, which use the static information of the detected faces and the differences between previous and current frames. The proposed system identifies the initial skin color and updates it through a real-time color detecting system. A similar background color can be removed by updating the skin color. Also, the performance increases up to 20% when the background color is reduced in comparison to extracting features from the entire region. The increased detection rate and speed are acquired by the usage of Kalman filter and Mean shift.

• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.6
• /
• pp.323-331
• /
• 2013

An extreme learning machine (ELM) is an efficient learning algorithm that is based on the generalized single, hidden-layer feed-forward networks (SLFNs), which perform well in classification applications. Many studies have demonstrated its superiority over the existing classical algorithms: support vector machine (SVM) and BP neural network. This paper presents a novel face recognition approach based on a multi-class project extreme learning machine (MPELM) classifier and 2D Gabor transform. First, all face image features were extracted using 2D Gabor filters, and the MPELM classifier was used to determine the final face classification. Two well-known face databases (CMU-PIE and ORL) were used to evaluate the performance. The experimental results showed that the MPELM-based method outperformed the ELM-based method as well as other methods.

• Journal of Korea Multimedia Society
• /
• v.20 no.8
• /
• pp.1395-1405
• /
• 2017

In this paper, we analyses heart beat data to identify subjects stress state (binary) using heart rate variability (HRV) features extracted from heart beat data of the subjects and implement supervised machine learning techniques to create the mental stress classifier. There are four steps need to be done: data acquisition, data processing (HRV analysis), features selection, and machine learning, before doing performance measurement. There are 56 features generated from the HRV Analysis module with several of them are selected (using own algorithm) after computing the Pearson Correlation Matrix (p-values). The results of the list of selected features compared with all features data are compared by its model error after training using several machine learning techniques: support vector machine, decision tree, and discriminant analysis. SVM model and decision tree model with using selected features shows close results compared to using all recording by only 1% difference. Meanwhile, the discriminant analysis differs about 5%. All the machine learning method used in this works have 90% maximum average accuracy.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.67 no.4
• /
• pp.569-577
• /
• 2018

In this paper, with the aid of information which is included within data, preprocessing algorithm-based black plastic classifier is designed. The slope and area of spectrum obtained by using laser induced breakdown spectroscopy(LIBS) are analyzed for each material and its ensuing information is applied as the input data of the proposed classifier. The slope is represented by the rate of change of wavelength and intensity. Also, the area is calculated by the wavelength of the spectrum peak where the material property of chemical elements such as carbon and hydrogen appears. Using informations such as slope and area, input data of the proposed classifier is constructed. In the preprocessing part of the classifier, Principal Component Analysis(PCA) and fuzzy transform are used for dimensional reduction from high dimensional input variables to low dimensional input variables. Characteristic analysis of the materials as well as the processing speed of the classifier is improved. In the condition part, FCM clustering is applied and linear function is used as connection weight in the conclusion part. By means of Particle Swarm Optimization(PSO), parameters such as the number of clusters, fuzzification coefficient and the number of input variables are optimized. To demonstrate the superiority of classification performance, classification rate is compared by using WEKA 3.8 data mining software which contains various classifiers such as Naivebayes, SVM and Multilayer perceptron.