• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.11
• /
• pp.998-1003
• /
• 2013

This study proposes an adaptive control algorithm for lateral motion of a UGV (Unmanned Ground Vehicle) using an NN (Neural Networks). The lateral motion of the UGV can be corrupted with various uncertainties such as side slip. In order to compensate the performance degradation of the UGV under various uncertainties, an NN-based adaptive control is designed by utilizing a virtual control concept. Since both the drift and input gain terms are uncertain, the proposed method adapts the whole terms related to the difference between the nominal and real systems. To avoid a singularity problem with the adaptive control, the affine property of the UGV dynamic model is utilized and the overall closed-loop stability is analyzed rigorously. Finally, numerical simulations using Carsim are performed to validate the effectiveness of the proposed scheme.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2010.05a
• /
• pp.927-930
• /
• 2010

Recently, continuous k-nearest neighbor query(CkNN) which is defined as a query to find the nearest points of interest to all the points on a given path is widely used in the LBS(Location Based Service) and ITS(Intelligent Transportation System) applications. It is necessary to acquire results quickly in the above applications and be applicable to spatial network databases. This paper proposes a new method to search nearest POIs(Point Of Interest) for moving query objects on the spatial networks. The method produces a set of split points and their corresponding k-POIs as results. There is no order between the POIs. The analysis show that the proposed method outperforms the existing methods.

• Journal of Information Technology Applications and Management
• /
• v.15 no.2
• /
• pp.51-65
• /
• 2008

The purpose of this paper is introducing WiFi based EKF(Extended Kalman Filter) method for indoor positioning. The advantages of our EKF method include: 1) Any special equipment dedicated for positioning is not required. 2) implementation of EKF does not require off-line phase of fingerprinting methods. 3) The EKF effectively minimizes squared deviation of the trilateration method. In order to experimentally prove the advantages of our method, we implemented indoor positioning systems making use of the K-NN(K Nearest Neighbors), Bayesian, decision tree, trilateration, and our EKF methods. Our experimental results show that the average-errors of K-NN, Bayesian and decision tree methods are all close to 2.4 meters whereas the average errors of trilateration and EKF are 4.07 meters and 3.528 meters, respectively. That is, the accuracy of our EKF is a bit inferior to those of fingerprinting methods. Even so, our EKF is accurate enough to be used for practical indoor LBS systems. Moreover, our EKF is easier to implement than fingerprinting methods because it does not require off-line phase.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.7
• /
• pp.2568-2584
• /
• 2015

Spectral clustering has become one of the most popular clustering approaches in recent years. Similarity graph constructed on the data is one of the key factors that influence the performance of spectral clustering. However, the similarity graphs constructed by existing methods usually contain some unreliable edges. To construct reliable similarity graph for spectral clustering, an efficient method based on Markov random walk (MRW) is proposed in this paper. In the proposed method, theMRW model is defined on the raw k-NN graph and the neighbors of each sample are determined by the probability of the MRW. Since the high order transition probabilities carry complex relationships among data, the neighbors in the graph determined by our proposed method are more reliable than those of the existing methods. Experiments are performed on the synthetic and real-world datasets for performance evaluation and comparison. The results show that the graph obtained by our proposed method reflects the structure of the data better than those of the state-of-the-art methods and can effectively improve the performance of spectral clustering.

• The Journal of Internal Korean Medicine
• /
• v.29 no.3
• /
• pp.778-786
• /
• 2008

Objectives : This study was to investigate the short time effect of caffeine on heart rate variability(HRV) and the effect of Neiguan(PC6) acupuncture stimulation on HRV. Methods : 27 healthy adult volunteers were randomly allocated to two groups: Neiguan group (N=13) or placebo group (N=14). The study was carried out under a randomized double-blinded placebo-controlled trial method. Each group orally received the same tablets with 200 mg caffeine. After 1 hour, acupuncture was applied to the Neiguan(PC6) points for the Neiguan group, and for the placebo group was applied to a non-acupuncture point. Both groups were estimated with HRV 3 times, before and after caffeine ingestion, 20 minutes after acupuncture stimulation. Results : After taking caffeine, pulse rate, mean-HRV, and pNN50(the proportion derived by dividing NN50 by the total number of NN intervals) decreased, SDNN(standard deviation of all normal-to-normal (NN) intervals), RMSSD (the root square of successive differences), TP log, HF(high frequency), and HRV index was increased. There were significant changes to the autonomic nervous system after taking caffeine. There were no significant differences between the two groups after acupuncture at Neiguan. Conclusion : Caffeine could induce general activation of the autonomic nervous system. Neiguan acupuncture stimulation may not have significant influence on the autonomic nervous system.

• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.43 no.6 s.312
• /
• pp.1-9
• /
• 2006

For the indoor positioning, wireless fingerprinting is most favorable because fingerprinting is most accurate among the techniques for wireless network based indoor positioning which does not require any special equipments dedicated for positioning. The deployment of a fingerprinting method consists of off-line phase and on-line phase. Off-line phase is not a time critical procedure, but on-line phase is indeed a time-critical procedure. If it is too slow then the user's location can be changed while it is calculating and the positioning method would never be accurate. Even so there is no research of improving efficiency of on-line phase of wireless fingerprinting. This paper proposes a decision-tree method for wireless fingerprinting and performs comparative analysis of the fingerprinting techniques including K-NN, Bayesian and our decision-tree.

• Journal of Korean Society for Atmospheric Environment
• /
• v.22 no.5
• /
• pp.614-626
• /
• 2006

Using the data of three environmental monitoring sites in Pohang area(KME112, KME113, and KME114), statistical forecasting models of the daily maximum and mean values of PM10 have been developed. Since the distributions of the daily maximum and mean PM10 values are skewed, which are similar to the Weibull distribution, these values were log-transformed to increase prediction accuracy by approximating the normal distribution. Three statistical forecasting models, which are regression, neural networks(NN) and support vector regression(SVR), were built using the log-transformed response variables, i.e., log(max(PM10)) or log(mean (PM10)). Also, the forecasting models were validated by the measure of RMSE, CORR, and IOA for the model comparison and accuracy. The improvement rate of IOA before and after the log-transformation in the daily maximum PM10 prediction was 12.7% for the regression and 22.5% for NN. In particular, 42.7% was improved for SVR method. In the case of the daily mean PM10 prediction, IOA value was improved by 5.1% for regression, 6.5% for NN, and 6.3% for SVR method. As a conclusion, SVR method was found to be performed better than the other methods in the point of the model accuracy and fitness views.

• Maxillofacial Plastic and Reconstructive Surgery
• /
• v.18 no.4
• /
• pp.570-593
• /
• 1996

This study was intended to perform the influence of condyle positional change after surgical correction of skeletal Class III malocclusion after BSSRO in 20 patients(males 9, females 11) using computed tomogram that were taken in centric occlusion before, immediate, and long term after surgery and lateral cephalogram that were taken in centric occlusion before, 7 days within the period intermaxillary fixation, 24hour after removing intermaxillary fixation and long term after surgery. 1. Mean intercondylar distance was $84.45{\pm}4.01mm$ and horizontal long axis of condylar angle was $11.89{\pm}5.19^{\circ}$on right, $11.65{\pm}2.09^{\circ}$on left side and condylar lateral poles were located about 12mm and medial poles about 7mm from reference line(AA') on the axial tomograph. Mean intercondylar distance was $84.43{\pm}3.96mm$ and vertical axis angle of condylar angle was $78.72{\pm}3.43^{\circ}$on right, $78.09{\pm}6.12^{\circ}$on left. 2. No statistical significance was found on the condylar change(T2C-T1C) but it had definitive increasing tendency. There was significant decreasing of the distance between both condylar pole and the AA'(p<0.05) during the long term(TLC-T2C). 3. On the lateral cephalogram, no statistical significance was found between immediate after surgery and 24 hours after the removing of intermaxillary fixation but only the lower incisor tip moved forward about 0.33mm(p<0.05). Considering individual relapse rate, mean relapse rate was 1.2% on L1, 5.0% on B, 2.0% on Pog, 9.1% on Gn, 10.3% on Me(p<0.05). 4. There was statistical significance on the influence of the mandibular set-back to the total mandibular relapse(p<0.05). 5. There was no statistical significance on the influence of the mandibular set-back(T2-T1) to the condylar change(T2C-T1C), the condylar change(T2C-T1C, TLC-T2C) to the mandibular total relapse, the pre-operative condylar position to the condylar change(T2C-T1C, TLC-T2C), the pre-operative mandibular posture to the condylar change(T2C-T1C, TLC-T2C)(p>0.05). 6. The result of multiple regression analysis on the influence of the pre-operative condylar position to the total mandibular relapse revealed that the more increasing of intercondylar distance and condylar vertical axis angle and decreasing of condyalr head long axis angle, the more increasing of mandibular horizontal relapse(L1,B,Pog,Gn,Me) on the right side condyle. The same result was founded in the case of horizontal relapse(L1,Me) on the left side condyle.(p<0.05). 7. The result of multiple regression analysis on the influence of the pre-operative condylar position to the pre-operative mandibular posture revealed that the more increasing of intercondylar distance and condylar vertical axis angle and decreasing of condylar head long axis angle, the more increasing of mandibular vertical length on the right side condyle. and increasing of vertical lengh & prognathism on the left side condyle(p<0.05). 8. The result of simple regression analysis on the influence of the pre-operative mandibular posture to the mandibular total relapse revealed that the more increasing of prognathism, the more increasing of mandibular total relapse in B and the more increasing of over-jet the more increasing of mandibular total relapse(p<0.05). Consequently, surgical mandibular repositioning was not significantly influenced to the change of condylar position with condylar reposition method.

• Journal of the Korean BIBLIA Society for library and Information Science
• /
• v.22 no.2
• /
• pp.5-25
• /
• 2011

This study aims to identify the most effective statistical feature selecting method and context window size for word sense disambiguation using supervised methods. In this study, features were selected by four different methods: information gain, document frequency, chi-square, and relevancy. The result of weight comparison showed that identifying the most appropriate features could improve word sense disambiguation performance. Information gain was the highest. SVM classifier was not affected by feature selection and showed better performance in a larger feature set and context size. Naive Bayes classifier was the best performance on 10 percent of feature set size. kNN classifier on under 10 percent of feature set size. When feature selection methods are applied to word sense disambiguation, combinations of a small set of features and larger context window size, or a large set of features and small context windows size can make best performance improvements.

• Proceedings of the KIEE Conference
• /
• 2001.07d
• /
• pp.2123-2125
• /
• 2001

In thermal power plant, the efficiency of a combined power plant with a gas turbine increases, exceeding 50%, while the efficiency of traditional steam turbine plants is approximately 35% to 40%. Up to the present time, the PID controller has been used to operate this system. However, it is very difficult to achieve an optimal PID gain without any experience, since the gain of the PID controller has to be manually tuned by trial and error procedures. This paper focuses on the neural network tuning of the 2-DOF PID controller with a separated 2-DOF parameter (NN-Tuning 2-DOF PID controller), for optimal control of the Gun-san gas turbine generating plant in Seoul. Korea. In order to attain optimal control, transfer function and operating data from start-up, running, and stop procedures of the Gun-san gas turbine have been acquired, and a designed controller has been applied to this system. The results of the NN-Tuning 2-DOF PID are compared with the PID controller and the conventional 2-DOF PID controller tuned by the Ziegler-Nichols method through experimentation. The experimental results of the NN-Tuning 2-DOF PID controller represent a more satisfactory response than those of the previously-mentioned two controller.