• Proceedings of the KIEE Conference
• /
• 2005.10a
• /
• pp.136-138
• /
• 2005

The conventional self-tuning methods have the speed control problem of nonlinear BLDC motor which can't adapt against any kinds of noise or operation circumstances. In this paper, supposed to solve these problem to PI parameters controller algorithm using ANN. In the proposed algorithm, the parameters of the controller were adjusted to reduce by on-line system the error of the speed of BLDC motor. In this process, EBPA NN was constituted to an output error value of a BLDC motor and conspired an input and output. The performance of the self-tuning controller is compared with that of the PI controller tuned by conventional method(Z&N). The effectiveness of the proposed control method IS verified thought the Matlab Simulink.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.223-224
• /
• 2021

Recently, k-farthest neighbor (kFN) queries have not as much attention as k-nearest neighbor (kNN) queries. Therefore, this study considers moving k-farthest neighbor (MkFN) queries for spatial network databases. Given a positive integer k, a moving query point q, and a set of data points P, MkFN queries can constantly retrieve k data points that are farthest from the query point q. The challenge with processing MkFN queries in spatial networks is to avoid unnecessary or superfluous distance calculations between the query and associated data points. This study proposes a batch processing algorithm, called MOFA, to enable efficient processing of MkFN queries in spatial networks. MOFA aims to avoid dispensable distance computations based on the clustering of both query and data points. Moreover, a time complexity analysis is presented to clarify the effect of the clustering method on the query processing time. Extensive experiments using real-world roadmaps demonstrated the efficiency and scalability of the MOFA when compared with a conventional solution.

• ETRI Journal
• /
• v.42 no.1
• /
• pp.78-89
• /
• 2020

Human activity recognition (HAR) has become effective as a computer vision tool for video surveillance systems. In this paper, a novel biometric system that can detect human activities in 3D space is proposed. In order to implement HAR, joint angles obtained using an RGB-depth sensor are used as features. Because HAR is operated in the time domain, angle information is stored using the sliding kernel method. Haar-wavelet transform (HWT) is applied to preserve the information of the features before reducing the data dimension. Dimension reduction using an averaging algorithm is also applied to decrease the computational cost, which provides faster performance while maintaining high accuracy. Before the classification, a proposed thresholding method with inverse HWT is conducted to extract the final feature set. Finally, the K-nearest neighbor (k-NN) algorithm is used to recognize the activity with respect to the given data. The method compares favorably with the results using other machine learning algorithms.

• Science of Emotion and Sensibility
• /
• v.20 no.3
• /
• pp.169-180
• /
• 2017

Individuals with high trait anxiety try to suppress their anger expression, thus there are limits in measuring their anger using subjective behavioral evaluation. In order to overcome this limitation, this study attempted to identify the difference in the autonomic nervous system responses induced by anger in individuals with high trait anxiety. Participants were divided into two groups, anxiety and control groups. Electrocardiogram (ECG), respiration (RESP), electrodermal activity (EDA), and skin temperature (SKT) were measured while participants were presented with an anger-inducing stimulus. Heart rate (HR), standard deviation of NN interval (SDNN), root mean square of successive difference (RMSSD), low frequency (LF), high frequency (HF), LF/HF ratio, respiration rate (RR), skin conductance level (SCL), and maximum skin temperature (maxSKT) were calculated before and after presenting the stimulus. Anxiety group reported greater anger by the anger-inducing stimulus compared to the control group. Anxiety group also showed significant increase in SDNN and LF, and decrease in HF, LF/HF ratio, and RR. These results suggest that the autonomic nervous system responses may be used as objective indicators of anger experiences in individuals with high trait anxiety.

• Science of Emotion and Sensibility
• /
• v.14 no.2
• /
• pp.269-278
• /
• 2011

This paper illustrates the inter-relationship between the theta/alpha ratio of the EEG signal and multiple HRV related parameters associated with the cardiovascular system response during event-related stimuli. Both EEG and PPG signals were simultaneously recorded in 21 healthy subjects. All subjects had their attention focused on the CNT program for nine minutes. Time-frequency analysis was applied to the EEG and PPG signals. The theta/alpha ratio was extracted from the EEG results, and the HRV features, including beat interval(1), SDNN(2), RMSSD(3), NN50(4), LF(5), HF(6), and LFIHF(7), were extracted from the PPG. Through multiple linear regression, the relationship ($R^2$) between the multiple combined features and the theta/alpha rhythm was identified. As a result, the combinations of $R^2$($R^2=0.253$; seven dimensions) and the theta/alpha ratio indicated a higher inter-relationship value than those of other combinations. The combinations of features that were greater than three dimensions, based on {SDNN(2), HF(6)}, generally showed higher $R^2$ value. We demonstrate that the high dimensional combinations had a higher correlation than did the low dimensional combinations.

• Journal of KIISE:Software and Applications
• /
• v.35 no.9
• /
• pp.562-571
• /
• 2008

For the purpose of building domain ontology, this paper proposes a methodology for building core ontology first, and then enriching the core ontology with the concepts and relations in the domain thesaurus. First, the top-level concept taxonomy of the core ontology is built using domain dictionary and general domain thesaurus. Then, the concepts of the domain thesaurus are classified into top-level concepts in the core ontology, and relations between broader terms (BT) - narrower terms (NT) and related terms (RT) are classified into semantic relations defined for the core ontology. To classify concepts, a two-step approach is adopted, in which a frequency-based approach is complemented with a similarity-based approach. To classify relations, two techniques are applied: (i) for the case of insufficient training data, a rule-based module is for identifying isa relation out of non-isa ones; a pattern-based approach is for classifying non-taxonomic semantic relations from non-isa. (ii) For the case of sufficient training data, a maximum-entropy model is adopted in the feature-based classification, where k-NN approach is for noisy filtering of training data. A series of experiments show that performances of the proposed systems are quite promising and comparable to judgments by human experts.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.10
• /
• pp.207-216
• /
• 2013

The aim of this study is to design a classifier for sleep stage analysis and select important feature set which shows sleep stage well based on physiological signals during sleep. Sleep has a significant effect on the quality of human life. When people undergo lack of sleep or sleep-related disease, they are likely to reduced concentration and cognitive impairment affects, etc. Therefore, there are a lot of research to analyze sleep stage. In this study, after acquisition physiological signals during sleep, we do pre-processing such as filtering for extracting features. The features are used input for the new combination algorithm using genetic algorithm(GA) and neural networks(NN). The algorithm selects features which have high weights to classify sleep stage. As the result of this study, accuracy of the algorithm is up to 90.26% with electroencephalography(EEG) signal and electrocardiography(ECG) signal, and selecting features are alpha and delta frequency band power of EEG signal and standard deviation of all normal RR intervals(SDNN) of ECG signal. We checked the selected features are well shown that they have important information to classify sleep stage as doing repeating the algorithm. This research could use for not only diagnose disease related to sleep but also make a guideline of sleep stage analysis.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.50 no.11
• /
• pp.206-216
• /
• 2013

The emotion plays a critical role in human's daily life including learning, action, decision and communication. In this paper, emotion discrimination classifier is designed to reduce system complexity through reduced selection of dominant features from biosignals. The photoplethysmography(PPG), skin temperature, skin conductance, fontal and parietal electroencephalography(EEG) signals were measured during 4 types of movie watching associated with the induction of neutral, sad, fear joy emotions. The genetic algorithm with support vector machine(SVM) based fitness function was designed to determine dominant features among 24 parameters extracted from measured biosignals. It shows maximum classification accuracy of 96.4%, which is 17% higher than that of SVM alone. The minimum error features selected are the mean and NN50 of heart rate variability from PPG signal, the mean of PPG induced pulse transit time, the mean of skin resistance, and ${\delta}$ and ${\beta}$ frequency band powers of parietal EEG. The combination of parietal EEG, PPG, and skin resistance is recommendable in high accuracy instrumentation, while the combinational use of PPG and skin conductance(79% accuracy) is affordable in simplified instrumentation.

• Proceedings of the Korean Society of Plant Pathology Conference
• /
• 2003.10a
• /
• pp.66.1-66
• /
• 2003

The aim of this study was to characterize the interactions of rice and Burkholderia glumae, a causal agent of bacterial grain rot of rice, at molecular levels using whole genomic sequences and to identify genes important for pathogenicity and symptom development. To do these, we sequenced whole genome of the bacterium and constructed cosmid clone profiles. We generated pools of mutants using various transposons and determined mutation sites by sequencing rescued plasmids. We focused on studying toxoflavin biosynthetic genes, quorum sensing regulation, and Hrp type III protein secretion systems. We found that two possible operons consisting of five genes are involved in toxoflavin biosynthesis and their expression is regulated by quorum sensing and LysR-type regulator, ToxR. We have isolated the nn PAI of B. glumae and characterized by mutational analyses. The hrp cluster resembled most the putative Type III secretion systems of B. pseudomallei, which is the causative agent of melioidosis, a serious disease of man and animals. The Hrp PAI core region showed high similarity to that of Ralstonia solanacearum and Xanthomonas campestris, however some aspects were dissimilar.

• Journal of Information Processing Systems
• /
• v.16 no.2
• /
• pp.406-420
• /
• 2020

In order to make up the deficiencies of the existing research results which cannot effectively deal with the nearest neighbor query based on the line segments in obstacle space, the k nearest neighbor query method of line segment in obstacle space is proposed and the STA_OLkNN algorithm under the circumstance of static obstacle data set is put forward. The query process is divided into two stages, including the filtering process and refining process. In the filtration process, according to the properties of the line segment Voronoi diagram, the corresponding pruning rules are proposed and the filtering algorithm is presented. In the refining process, according to the relationship of the position between the line segments, the corresponding distance expression method is put forward and the final result is obtained by comparing the distance. Theoretical research and experimental results show that the proposed algorithm can effectively deal with the problem of k nearest neighbor query of the line segment in the obstacle environment.