• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.8
• /
• pp.3657-3682
• /
• 2018

This paper presents a Bluetooth and pedestrian dead reckoning (PDR)-based indoor fusion localization approach (BtPDR) using smartphones. A Bluetooth and PDR-based indoor fusion localization approach can localize the initial position of a smartphone with the received signal strength (RSS) of Bluetooth. While a smartphone is moving, BtPDR can track its position by fusing the localization results of PDR and Bluetooth RSS. In addition, BtPDR can adaptively modify the parameters of PDR. The contributions of BtPDR include: a Bluetooth RSS-based Probabilistic Voting (BRPV) localization mechanism, a probabilistic voting-based Bluetooth RSS and PDR fusion method, and a heuristic search approach for reducing the complexity of BRPV. The experiment results in a real scene show that the average positioning error is < 2m, which is considered adequate for indoor location-based service applications. Moreover, compared to the traditional PDR method, BtPDR improves the location accuracy by 42.6%, on average. Compared to state-of-the-art Wireless Local Area Network (WLAN) fingerprint + PDR-based fusion indoor localization approaches, BtPDR has better positioning accuracy and does not need the same offline workload as a fingerprint algorithm.

• Journal of Power Electronics
• /
• v.17 no.3
• /
• pp.695-703
• /
• 2017

In order to satisfy the urgent requirements for the overheating protection of induction motors, an approach that can be used to identify motor temperature has been proposed based on the rotor slots harmonic (RSH) in this paper. One method to accomplish this is to improve the calculation efficiency of the RSH by predicting the stator winding distribution harmonic order by analyzing the harmonics spectrum. Another approach is to increase the identification accuracy of the RSH by suppressing the influence of voltage flashes or current surges during temperature estimation based on model predictive control (MPC). First, an analytical expression of the stator inductance is extracted from a steady-state positive sequence motor equivalent circuit model developed from the rotor flux field orientation. Then a procedure that applies MPC for reducing the identification error of the rotor temperature caused by voltage sag or swell of the power system is given. Due to this work, the efficiency and accuracy of the RSH have been significantly improved and validated our experiments. This work can serves as a reference for the on-line temperature monitoring and overheating protection of an induction motor.

• Journal of Institute of Control, Robotics and Systems
• /
• v.13 no.10
• /
• pp.962-969
• /
• 2007

In this paper, an approach is developed for relative state estimation of satellite formation flying. To estimate relative states of two satellites, the Extended Kalman Filter Algorithm is adopted with the relative distance and speed between two satellites and attitude of satellite for measurements. Numerical simulations are conducted under two circumstances. The first one presents both chief and deputy satellites are orbiting a circular reference orbit around a perfectly spherical Earth model with no disturbing acceleration, in which the elementary relative orbital motion is taken into account. In reality, however, the Earth is not a perfect sphere, but rather an oblate spheroid, and both satellites are under the effect of $J_2$ geopotential disturbance, which causes the relative distance between two satellites to be on the gradual increase. A near-Earth orbit decays as a result of atmospheric drag. In order to remove the modeling error, the second scenario incorporates the effect of the $J_2$ geopotential force, and the atmospheric drag, and the eccentricity in satellite orbit are also considered.

• International Journal of Control, Automation, and Systems
• /
• v.4 no.4
• /
• pp.448-455
• /
• 2006

This paper deals with the observer design problem for a class of state-delayed nonlinear systems with or without time-varying norm-bounded parameter uncertainty. The nonlinearities under consideration are assumed to satisfy the global Lipschitz conditions and appear in both the state and measured output equations. The problem we address is the design of a nonlinear observer such that the resulting error system is globally asymptotically stable. For the case when there is no parameter uncertainty, a sufficient condition for the solvability of this problem is derived in terms of linear matrix inequalities and the explicit formula of a desired observer is given. Based on this, the robust observer design problem for the case when parameter uncertainties appear is considered and the solvability condition is also given. Both of the solvability conditions obtained in this paper are delay-dependent. A numerical example is provided to demonstrate the applicability of the proposed approach.

• Journal of Digital Convergence
• /
• v.13 no.1
• /
• pp.243-248
• /
• 2015

Recognition model is not defined when you configure a model, Been added to the model after model building awareness, Model a model of the clustering due to lack of recognition models are generated by modeling is causes the degradation of the recognition rate. In order to improve decision tree state tying modeling using parameter estimation of Bayesian method. The parameter estimation method is proposed Bayesian method to navigate through the model from the results of the decision tree based on the tying state according to the maximum probability method to determine the recognition model. According to our experiments on the simulation data generated by adding noise to clean speech, the proposed clustering method error rate reduction of 1.29% compared with baseline model, which is slightly better performance than the existing approach.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.308-310
• /
• 2022

With the rise of the Al wave, task-oriented dialogue systems have become one of the popular research directions in academia and industry. Currently, task-oriented dialogue systems mainly adopt pipelined form, which mainly includes natural language understanding, dialogue state decision making, dialogue state tracking and natural language generation. However, pipelining is prone to error propagation, so many task-oriented dialogue systems in the market are only for single-round dialogues. Usually single- domain dialogues have relatively accurate semantic understanding, while they tend to perform poorly on multi-domain, multi-round dialogue datasets. To solve these issues, we developed a paddle-based multi-domain task-oriented Chinese dialogue system. It is based on NEZHA-base pre-training model and CrossWOZ dataset, and uses intention recognition module, dichotomous slot recognition module and NER recognition module to do DST and generate replies based on rules. Experiments show that the dialogue system not only makes good use of the context, but also effectively addresses long-term dependencies. In our approach, the DST of dialogue tracking state is improved, and our DST can identify multiple slotted key-value pairs involved in the discourse, which eliminates the need for manual tagging and thus greatly saves manpower.

• Journal of Computational Design and Engineering
• /
• v.2 no.4
• /
• pp.206-217
• /
• 2015

This paper presents a complete S-shape feed rate scheduling approach (CSFA) with confined jerk, acceleration and command feed rate for parametric tool path. For a Non-Uniform Rational B-Spline (NURBS) tool path, the critical points of the tool path where the radius of curvature reaches extreme values are found firstly. Then, the NURBS curve is split into several NURBS sub-curves or blocks by the critical points. A bidirectional scanning strategy with the limitations of chord error, normal/tangential acceleration/jerk and command feed rate is employed to make the feed rate at the junctions between different NURBS blocks continuous. To improve the efficiency of the feed rate scheduling, the NURBS block is classified into three types: short block, medium block and long block. The feed rate profile corresponding to each NURBS block is generated according to the start/end feed rates and the arc length of the block and the limitations of tangential acceleration/jerk. In addition, two compensation strategies are proposed to make the feed rate more continuous and the arc increment more precise. Once the feed rate profile is determined, a second-order Taylor's expansion interpolation method is applied to generate the position commands. Finally, experiments with two free-form NURBS curves are conducted to verify the applicability and accuracy of the proposed method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.63 no.9
• /
• pp.1286-1293
• /
• 2014

Typically, studies through the simulation system have been progressed, because the evaluation of the driver's arousal state about the service of a actual train has risk of safety for the driver. When configured event same as the real in simulation system, the ability to cope with an accident situation may be the same each other. But the difference in the state of tension or arousal will occur. In this study, requested to cooperate with the railways in order to escape from these constraints, and the target of the experiment was to real engineer service. I was set about experiment when the train was stopped as safe as possible. As a result, the beta wave of EEG signals that representing complex calculations or anxiety is increased rapidly on the basis of a flag station from at the time of departure. The size of the electrodermal activity signal in response to movement of the body gave a noticeable. In terms of HRV, if the train approach a flag station gradually and the R-R interval is narrowed. So that the driver can be estimated as arousal state. In accordance with this study, if the quantitative standard of arousal state be based on the driver's biosignals will provide, it will be able to take advantage of development the system that would prevent train accidents caused by human error.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.8
• /
• pp.702-708
• /
• 2013

Underwater TRN (Underwater Terrain Referenced Navigation) estimates an underwater vehicle state by measuring a distance between the vehicle and undersea terrain, and comparing it with the known terrain database. TRN belongs to absolute navigation methods, which are used to compensate a drift error of dead reckoning measurements such as IMU (Inertial Measurement Unit) or DVL (Doppler Velocity Log). However, underwater TRN is different to other absolute methods such as USBL (Ultra-Short Baseline) and LBL (Long Baseline), because TRN is independent of the external environment. As a magnetic-field-based navigation, TRN is a kind of geophysical navigation. This paper develops an EKF (Extended Kalman Filter) formulation for underwater TRN. A filter propagation part is composed by an inertial navigation system, and a filter update is executed with echo-sounder measurement. For large-initial-error cases, an adaptive EKF approach is also presented, to keep the filter be stable. At the end, simulation studies are given to verify the performance of the proposed TRN filter. With simplified sensor and terrain database models, the simulation results show that the underwater TRN could support conventional underwater navigation methods.

• Atmosphere
• /
• v.17 no.4
• /
• pp.327-337
• /
• 2007

In this study, we examined the new ensemble training approach to reduce the systematic error and improve prediction skill of wind by using the Short-range Ensemble prediction system (SENSE), which is the mesoscale multi-model ensemble prediction system. The SENSE has 16 ensemble members based on the MM5, WRF ARW, and WRF NMM. We evaluated the skill of surface wind prediction compared with AWS (Automatic Weather Station) observation during the summer season (June - August, 2006). At first stage, the correction of initial state for each member was performed with respect to the observed values, and the corrected members get the training stage to find out an adaptive weight function, which is formulated by Root Mean Square Vector Error (RMSVE). It was found that the optimal training period was 1-day through the experiments of sensitivity to the training interval. We obtained the weighted ensemble average which reveals smaller errors of the spatial and temporal pattern of wind speed than those of the simple ensemble average.