• Journal of Intelligence and Information Systems
• /
• v.25 no.4
• /
• pp.53-65
• /
• 2019

Object tracking is one of important steps to achieve video-based surveillance systems. Object tracking is considered as an essential task similar to object detection and recognition. In order to perform object tracking, various machine learning methods (e.g., least-squares, perceptron and support vector machine) can be applied for different designs of tracking systems. In general, generative methods (e.g., principal component analysis) were utilized due to its simplicity and effectiveness. However, the generative methods were only focused on modeling the target object. Due to this limitation, discriminative methods (e.g., binary classification) were adopted to distinguish the target object and the background. Among the machine learning methods for binary classification, total error rate minimization can be used as one of successful machine learning methods for binary classification. The total error rate minimization can achieve a global minimum due to a quadratic approximation to a step function while other methods (e.g., support vector machine) seek local minima using nonlinear functions (e.g., hinge loss function). Due to this quadratic approximation, the total error rate minimization could obtain appropriate properties in solving optimization problems for binary classification. However, this total error rate minimization was based on a batch mode setting. The batch mode setting can be limited to several applications under offline learning. Due to limited computing resources, offline learning could not handle large scale data sets. Compared to offline learning, online learning can update its solution without storing all training samples in learning process. Due to increment of large scale data sets, online learning becomes one of essential properties for various applications. Since object tracking needs to handle data samples in real time, online learning based total error rate minimization methods are necessary to efficiently address object tracking problems. Due to the need of the online learning, an online learning based total error rate minimization method was developed. However, an approximately reweighted technique was developed. Although the approximation technique is utilized, this online version of the total error rate minimization could achieve good performances in biometric applications. However, this method is assumed that the total error rate minimization can be asymptotically achieved when only the number of training samples is infinite. Although there is the assumption to achieve the total error rate minimization, the approximation issue can continuously accumulate learning errors according to increment of training samples. Due to this reason, the approximated online learning solution can then lead a wrong solution. The wrong solution can make significant errors when it is applied to surveillance systems. In this paper, we propose an exactly reweighted technique to recursively update the solution of the total error rate minimization in online learning manner. Compared to the approximately reweighted online total error rate minimization, an exactly reweighted online total error rate minimization is achieved. The proposed exact online learning method based on the total error rate minimization is then applied to object tracking problems. In our object tracking system, particle filtering is adopted. In particle filtering, our observation model is consisted of both generative and discriminative methods to leverage the advantages between generative and discriminative properties. In our experiments, our proposed object tracking system achieves promising performances on 8 public video sequences over competing object tracking systems. The paired t-test is also reported to evaluate its quality of the results. Our proposed online learning method can be extended under the deep learning architecture which can cover the shallow and deep networks. Moreover, online learning methods, that need the exact reweighting process, can use our proposed reweighting technique. In addition to object tracking, the proposed online learning method can be easily applied to object detection and recognition. Therefore, our proposed methods can contribute to online learning community and object tracking, detection and recognition communities.

• FLOWER RESEARCH JOURNAL
• /
• v.16 no.1
• /
• pp.36-43
• /
• 2008

This purpose of this study was to examine the effect of planting density, growing medium and strength of a nutrient solution (National Horticultural Research Institute's nutrient solution: HRI's) on the growth and development of Oriental hybrid lily 'Le Reve' in a box cultivation. The planting density with 14, 18 and 22 bulbs had sprouting one day earlier than other treatments. Planting density of 22 bulbs flowered first, while six bulbs flowered the last, indicating that higher planting densities led earlier flowering. The increasing planting density increased stem length of cut flowers. On the other hand, cut flower quality was improved when the planting density was lower. The incidence of physiological disorders such as blasting was more frequent in planting density of 22, 18, and 14, indicating that higher planting densities caused higher incidences of physiological disorders. All planting densities except 22 bulbs displayed superior results in width, weight, number, and scale weight of the bulbs. Greater planting densities led to inferior bulb enlargement and an increased decomposition rate. pH decreased in all treatments after the bulb enlargement and decreased more as the planting density increased. Contents of P, K, Ca, and Mg increased, while contents of K and Ca decreased, as the planting density increased. The rice hull+coir (1:1, v/v) treatment was better than others, but did not show that much of a difference. Moreover, in bulbs enlargement after cut flower harvest, lily medium and perlite+peat moss treatments showed superior results, and decomposition rate was the greatest in the rice hull+coir (1:1, v/v) treatment. In the HRI's solution strength treatment from the period of flower bud emergence to flower harvest, higher solution strengths gave better cut flower quality in terns of length, weight, and number of flowers. The non-treated control and one third strength of a HRI's solution hastened flowering, indicating that lower strengths led to earlier flowering. According to the results of leaf analysis as affected by solution strength during the flower harvest, absorption rates of N and K were greater when the strength was higher, and Ca and Mg showed the same tendency. On the other hand, the absorption rate of P was the lowest in all treatments.

• Journal of the Korean Geotechnical Society
• /
• v.23 no.9
• /
• pp.5-16
• /
• 2007

The simple linear elastic-perfectly plastic model with soil parameters $s_u,\;E_u$ and n of undrained condition is usually applied to predict the displacement of a constructed diaphragm wall(DW) on soft soils during excavation. However, the application of this soil model for finite element analysis could not interpret the continued increment of the lateral displacement of the DW for the large and deep excavation area both during the elapsed time without activity of excavation and after finishing excavation. To study the characteristic behaviors of soil behind the DW during the periods without excavation, a series of tests on soft Bangkok clay samples are simulated in the same manner as stress condition of soil elements happening behind diaphragm wall by triaxial tests. Three kinds of triaxial tests are carried out in this research: $K_0$ consolidated undrained compression($CK_0U_C$) and $K_0$ consolidated drained/undrained unloading compression with periodic decrement of horizontal pressure($CK_0DUC$ and $CK_0UUC$). The study shows that the shear strength of series $CK_0DUC$ tests is equal to the residual strength of $CK_0UC$ tests. The Young's modulus determined at each decrement step of the horizontal pressure of soil specimen on $CK_0DUC$ tests decreases with increase in the deviator stress. In addition, the slope of Critical State Line of both $CK_0UC$ and $CK_0DUC$ tests is equal. Moreover, the axial and radial strain rates of each decrement of horizontal pressure step of $CK_0DUC$ tests are established with the function of time, a slope of critical state line and a ratio of deviator and mean effective stress. This study shows that the results of the unloading compression triaxial tests can be used to predict the diaphragm wall deflection during excavation.

• Journal of Intelligence and Information Systems
• /
• v.24 no.2
• /
• pp.111-124
• /
• 2018

This study aims to develop a classification model for predicting the occurrence of hyperlipidemia, one of the chronic diseases. Prior studies applying data mining techniques for predicting disease can be classified into a model design study for predicting cardiovascular disease and a study comparing disease prediction research results. In the case of foreign literatures, studies predicting cardiovascular disease were predominant in predicting disease using data mining techniques. Although domestic studies were not much different from those of foreign countries, studies focusing on hypertension and diabetes were mainly conducted. Since hypertension and diabetes as well as chronic diseases, hyperlipidemia, are also of high importance, this study selected hyperlipidemia as the disease to be analyzed. We also developed a model for predicting hyperlipidemia using SVM and meta learning algorithms, which are already known to have excellent predictive power. In order to achieve the purpose of this study, we used data set from Korea Health Panel 2012. The Korean Health Panel produces basic data on the level of health expenditure, health level and health behavior, and has conducted an annual survey since 2008. In this study, 1,088 patients with hyperlipidemia were randomly selected from the hospitalized, outpatient, emergency, and chronic disease data of the Korean Health Panel in 2012, and 1,088 nonpatients were also randomly extracted. A total of 2,176 people were selected for the study. Three methods were used to select input variables for predicting hyperlipidemia. First, stepwise method was performed using logistic regression. Among the 17 variables, the categorical variables(except for length of smoking) are expressed as dummy variables, which are assumed to be separate variables on the basis of the reference group, and these variables were analyzed. Six variables (age, BMI, education level, marital status, smoking status, gender) excluding income level and smoking period were selected based on significance level 0.1. Second, C4.5 as a decision tree algorithm is used. The significant input variables were age, smoking status, and education level. Finally, C4.5 as a decision tree algorithm is used. In SVM, the input variables selected by genetic algorithms consisted of 6 variables such as age, marital status, education level, economic activity, smoking period, and physical activity status, and the input variables selected by genetic algorithms in artificial neural network consist of 3 variables such as age, marital status, and education level. Based on the selected parameters, we compared SVM, meta learning algorithm and other prediction models for hyperlipidemia patients, and compared the classification performances using TP rate and precision. The main results of the analysis are as follows. First, the accuracy of the SVM was 88.4% and the accuracy of the artificial neural network was 86.7%. Second, the accuracy of classification models using the selected input variables through stepwise method was slightly higher than that of classification models using the whole variables. Third, the precision of artificial neural network was higher than that of SVM when only three variables as input variables were selected by decision trees. As a result of classification models based on the input variables selected through the genetic algorithm, classification accuracy of SVM was 88.5% and that of artificial neural network was 87.9%. Finally, this study indicated that stacking as the meta learning algorithm proposed in this study, has the best performance when it uses the predicted outputs of SVM and MLP as input variables of SVM, which is a meta classifier. The purpose of this study was to predict hyperlipidemia, one of the representative chronic diseases. To do this, we used SVM and meta-learning algorithms, which is known to have high accuracy. As a result, the accuracy of classification of hyperlipidemia in the stacking as a meta learner was higher than other meta-learning algorithms. However, the predictive performance of the meta-learning algorithm proposed in this study is the same as that of SVM with the best performance (88.6%) among the single models. The limitations of this study are as follows. First, various variable selection methods were tried, but most variables used in the study were categorical dummy variables. In the case with a large number of categorical variables, the results may be different if continuous variables are used because the model can be better suited to categorical variables such as decision trees than general models such as neural networks. Despite these limitations, this study has significance in predicting hyperlipidemia with hybrid models such as met learning algorithms which have not been studied previously. It can be said that the result of improving the model accuracy by applying various variable selection techniques is meaningful. In addition, it is expected that our proposed model will be effective for the prevention and management of hyperlipidemia.