• Proceedings of the KIEE Conference
• /
• summer
• /
• pp.1251-1253
• /
• 2004

This paper is proposed a fuzzy neural network controller based on the vector controlled surface permanent magnet synchronous motor(SPMSM) drive system. The hybrid combination of neural network and fuzzy control will produce a powerful representation flexibility and numerical processing capability. Also, this paper is proposed speed control of SPMSM using neuro-fuzzy control(NFC) and estimation of speed using artificial neural network(ANN) Controller. The back propagation neural network technique is used to provide a real time adaptive estimation of the motor speed. The error between the desired state variable and the actual one is back-propagated to adjust the rotor speed, so that the actual state variable will coincide with the desired one. The back propagation mechanism is easy to derive and the estimated speed tracks precisely the actual motor speed. This paper is proposed the theoretical analysis as well as the simulation results to verify the effectiveness of the new method.

• Proceedings of the KIEE Conference
• /
• 1999.07g
• /
• pp.2923-2925
• /
• 1999

The objective of camera calibration is to determine the internal optical characteristics of camera and 3D position and orientation of camera with respect to the real world. Calibration procedure applicable to general purpose cameras and lenses. The general method to revise the accuracy rate of calibration is using mathematical distortion of lens. The effective og calibration show big difference in proportion to distortion of camera lens. In this paper, we propose the method which calibration distortion model by using neural network. The neural network model implicity contains all the distortion model. We can predict the high accuracy of calibration method proposed in this paper. Neural network can set properly the distortion model which has difficulty to estimate exactly in general method. The performance of the proposed neural network approach is compared with the well-known Tsai's two stage method in terms of calibration errors. The results show that the proposed approach gives much more stable and acceptabke calibration error over Tsai's two stage method regardless of camera resolution and camera angle.

• Journal of the Institute of Convergence Signal Processing
• /
• v.6 no.1
• /
• pp.45-52
• /
• 2005

Dynamic neural networks have been applied to diverse fields requiring temporal signal processing. This paper describes system identification using the hybrid neural network, composed of locally(LRNN) and globally recurrent neural networks(GRNN) to improve dynamics of multilayered recurrent networks(RNN). The structure of the hybrid nework combines IIR-MLP as LRNN and Elman RNN as GRNN. The hybrid network is evaluated in linear and nonlinear system identification, and compared with Elman RNN and IIR-MLP networks for the relative comparison of its performance. Simulation results show that the hybrid network performs better with respect to the convergence and accuracy, indicating that it can be a more effective network than conventional multilayered recurrent networks in system identification.

• Transactions of the Korean Society of Mechanical Engineers
• /
• v.18 no.1
• /
• pp.1-11
• /
• 1994

This paper presents an intelligent robotic control method for chamferless parts mating by integrating fuzzy control and neural network. The successful assembly task requires an extremely high position accuracy and a good knowledge of mating parts. However, conventional assembly method alone makes it difficult to achieve satisfactory assembly performance because of the complexity and the uncertainties of the process and its environments such as not only the limitation of the devices performing the assembly but also imperfect knowledge of the parts being assembled. To cope with these problems, an intelligent robotic assembly method is proposed, which is composed of fuzzy controller and learning mechanism based upon neural net. In this method, fuzzy controller copes with the complexity and the uncertainties of the assembly process, while neural network enhances the assembly scheme so as to learn fuzzy rules from experience and adapt to changes in environment of uncertainty and imprecision. The performance of the proposed assembly scheme is evaluted through a series of experiments using SCARA robot. The results show that the proposed control method can be effectively applied to chamferless precision parts mating.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.11 no.5
• /
• pp.915-920
• /
• 2007

Using the existing algorithms that estimate the background noise, the detection probability for the week tonals is low and for the even week tonals, there is a limit not detected. Therefore it is required to algorithms which can improve the performance of the tonal extraction. Recently, many researches using artificial neural networks in sonar signal processing are performed. We propose a neural network with double feedback that can remove automatically the background noise and detect the even week tonals buried in background noise, therefore not detected by growing the week tonals lastingly for a certain time. For the real underwater target, experiments for the tonal extraction are performed by using the existing algorithms that estimate the background noise and the proposed neural network. As a result of the experiment, a method using the proposed neural network showed the better performance of the tonal extraction in comparison with the existing algorithms.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.18 no.9
• /
• pp.52-57
• /
• 2019

The key technology of the fourth industrial revolution is artificial intelligence and machine learning. In this study, FMEA was performed on fuel pumps used as key items in most systems to identify major failure components, and artificial neural networks were built using big data. The main failure mode of the fuel pump identified by the test was coil damage due to overheating. Based on the artificial neural network built, machine learning was conducted to predict the failure and the mean error rate was 4.9% when the number of hidden nodes in the artificial neural network was three and the temperature increased to $140^{\circ}C$ rapidly.

• Smart Structures and Systems
• /
• v.15 no.1
• /
• pp.227-244
• /
• 2015

This study develops a two stage procedure to identify the structural damage based on the optimized artificial neural networks. Initially, the modal strain energy index (MSEI) is established to extract the damaged elements and to reduce the computational time. Then the genetic algorithm (GA) and artificial neural networks (ANNs) are combined to detect the damage severity. The input of the network is modal strain energy index and the output is the flexural stiffness of the beam elements. The principal component analysis (PCA) is utilized to reduce the input variants of the neural network. By using the genetic algorithm to optimize the parameters, the ANNs can significantly improve the accuracy and convergence of the damage identification. The influence of noise on damage identification results is also studied. The simulation and experiment on beam structures shows that the adaptive parameter selection neural network can identify the damage location and severity of beam structures with high accuracy.

• The Korean Journal of Physiology and Pharmacology
• /
• v.23 no.2
• /
• pp.131-139
• /
• 2019

Manually reviewing electroencephalograms (EEGs) is labor-intensive and demands automated seizure detection systems. To construct an efficient and robust event detector for experimental seizures from continuous EEG monitoring, we combined spectral analysis and deep neural networks. A deep neural network was trained to discriminate periodograms of 5-sec EEG segments from annotated convulsive seizures and the pre- and post-EEG segments. To use the entire EEG for training, a second network was trained with non-seizure EEGs that were misclassified as seizures by the first network. By sequentially applying the dual deep neural networks and simple pre- and post-processing, our autodetector identified all seizure events in 4,272 h of test EEG traces, with only 6 false positive events, corresponding to 100% sensitivity and 98% positive predictive value. Moreover, with pre-processing to reduce the computational burden, scanning and classifying 8,977 h of training and test EEG datasets took only 2.28 h with a personal computer. These results demonstrate that combining a basic feature extractor with dual deep neural networks and rule-based pre- and post-processing can detect convulsive seizures with great accuracy and low computational burden, highlighting the feasibility of our automated seizure detection algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.12
• /
• pp.4664-4681
• /
• 2020

Modulation recognition (MR) plays a key role in cognitive radar, cognitive radio, and some other civilian and military fields. While existing methods can identify the signal modulation type by extracting the signal characteristics, the quality of feature extraction has a serious impact on the recognition results. In this paper, an end-to-end MR method based on long short-term memory (LSTM) and the gated recurrent unit (GRU) is put forward, which can directly predict the modulation type from a sampled signal. Additionally, the sliding window method is applied to fast-changing mixed-modulation signals for which the signal modulation type changes over time. The recognition accuracy on training datasets in different SNR ranges and the proportion of each modulation method in misclassified samples are analyzed, and it is found to be reasonable to select the evenly-distributed and full range of SNR data as the training data. With the improvement of the SNR, the recognition accuracy increases rapidly. When the length of the training dataset increases, the neural network recognition effect is better. The loss function value of the neural network decreases with the increase of the training dataset length, and then tends to be stable. Moreover, when the fast-changing period is less than 20ms, the error rate is as high as 50%. As the fast-changing period is increased to 30ms, the error rates of the GRU and LSTM neural networks are less than 5%.

• Journal of Information Processing Systems
• /
• v.18 no.1
• /
• pp.115-129
• /
• 2022

Adopting Internet of Things (IoT)-based technologies in smart homes helps users analyze home appliances electricity consumption for better overall cost monitoring. The IoT application like smart home system (SHS) could suffer from large missing values gaps due to several factors such as security attacks, sensor faults, or connection errors. In this paper, a novel framework has been proposed to predict large gaps of missing values from the SHS home appliances electricity consumption time-series datasets. The framework follows a series of steps to detect, predict and reconstruct the input time-series datasets of missing values. A hybrid convolutional neural network-long short term memory (CNN-LSTM) neural network used to forecast large missing values gaps. A comparative experiment has been conducted to evaluate the performance of hybrid CNN-LSTM with its single variant CNN and LSTM in forecasting missing values. The experimental results indicate a performance superiority of the CNN-LSTM model over the single CNN and LSTM neural networks.