• ETRI Journal
• /
• v.43 no.3
• /
• pp.538-548
• /
• 2021

This paper proposes an approach to improve the performance of no-reference video quality assessment for sports videos with dynamic motion scenes using an efficient spatiotemporal model. In the proposed method, we divide the video sequences into video blocks and apply a 3D shearlet transform that can efficiently extract primary spatiotemporal features to capture dynamic natural motion scene statistics from the incoming video blocks. The concatenation of a deep residual bidirectional gated recurrent neural network and logistic regression is used to learn the spatiotemporal correlation more robustly and predict the perceptual quality score. In addition, conditional video block-wise constraints are incorporated into the objective function to improve quality estimation performance for the entire video. The experimental results show that the proposed method extracts spatiotemporal motion information more effectively and predicts the video quality with higher accuracy than the conventional no-reference video quality assessment methods.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.337-351
• /
• 2021

Automatically recognizing facial expressions in video sequences is a challenging task because there is little direct correlation between facial features and subjective emotions in video. To overcome the problem, a video facial expression recognition method using spatiotemporal recurrent neural network and feature fusion is proposed. Firstly, the video is preprocessed. Then, the double-layer cascade structure is used to detect a face in a video image. In addition, two deep convolutional neural networks are used to extract the time-domain and airspace facial features in the video. The spatial convolutional neural network is used to extract the spatial information features from each frame of the static expression images in the video. The temporal convolutional neural network is used to extract the dynamic information features from the optical flow information from multiple frames of expression images in the video. A multiplication fusion is performed with the spatiotemporal features learned by the two deep convolutional neural networks. Finally, the fused features are input to the support vector machine to realize the facial expression classification task. The experimental results on cNTERFACE, RML, and AFEW6.0 datasets show that the recognition rates obtained by the proposed method are as high as 88.67%, 70.32%, and 63.84%, respectively. Comparative experiments show that the proposed method obtains higher recognition accuracy than other recently reported methods.

• Journal of Power Electronics
• /
• v.13 no.1
• /
• pp.139-160
• /
• 2013

In this paper, an intelligent robust control system (IRCS) for precision tracking control of permanent-magnet synchronous motor (PMSM) servo drives is proposed. The IRCS comprises a recurrent wavelet-based interval type-2 fuzzy-neural-network controller (RWIT2FNNC), an RWIT2FNN estimator (RWIT2FNNE) and a compensated controller. The RWIT2FNNC combines the merits of a self-constructing interval type-2 fuzzy logic system, a recurrent neural network and a wavelet neural network. Moreover, it performs the structure and parameter-learning concurrently. The RWIT2FNNC is used as the main tracking controller to mimic the ideal control law (ICL) while the RWIT2FNNE is developed to approximate an unknown dynamic function including the lumped parameter uncertainty. Furthermore, the compensated controller is designed to achieve $L_2$ tracking performance with a desired attenuation level and to deal with uncertainties including approximation errors, optimal parameter vectors and higher order terms in the Taylor series. Moreover, the adaptive learning algorithms for the compensated controller and the RWIT2FNNE are derived by using the Lyapunov stability theorem to train the parameters of the RWIT2FNNE online. A computer simulation and an experimental system are developed to validate the effectiveness of the proposed IRCS. All of the control algorithms are implemented on a TMS320C31 DSP-based control computer. The simulation and experimental results confirm that the IRCS grants robust performance and precise response regardless of load disturbances and PMSM parameters uncertainties.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.10
• /
• pp.149-157
• /
• 1994

A method of applying a recurrent backpropagation network to identifying or modelling a dynamic system is proposed. After the recurrent backpropagation network having both the characteristicsof interpolative network and associative network is applied to XOR problem, a new model of recurrent backpropagation network is proposed and compared with the original recurrent backpropagation network by applying them to XOR problem. based on the observation thata function can be approximated with polynomials to arbitrary accuracy, the new model is developed so that it may generate higher-order terms in the internal states Moreover, it is shown that the new network is succesfully applied to recognizing noisy patterns of numbers.

• Journal of the Institute of Electronics Engineers of Korea SC
• /
• v.37 no.4
• /
• pp.22-27
• /
• 2000

In this paper, new neural network called dynamic multidimensional wavelet neural network (DMWNN) is proposed. The resulting network from wavelet theory provides a unique and efficient representation of the given function. Also the proposed DMWNN have ability to store information for later use. Therefore it can represent dynamic mapping and decreases the dimension of the inputs needed for network. This feature of DMWNN can compensate for the weakness of diagonal recurrent neural network(DRNN) and feedforward wavelet neural network(FWNN). The efficacy of this type of network is demonstrated through experimental results.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.34 no.3C
• /
• pp.257-267
• /
• 2009

This paper presents a training method for neural networks and the employment of MSE (mean scare error) values as the basis of a decision regarding the identity claim of a speaker in a recurrent neural networks based speaker verification system. Recurrent neural networks (RNNs) are employed to capture temporally dynamic characteristics of speech signal. In the process of supervised learning for RNNs, target outputs are automatically generated and the generated target outputs are made to represent the temporal variation of input speech sounds. To increase the capability of discriminating between the true speaker and an impostor, a discriminative training method for RNNs is presented. This paper shows the use and the effectiveness of the MSE value, which is obtained from the Euclidean distance between the target outputs and the outputs of networks for test speech sounds of a speaker, as the basis of speaker verification. In terms of equal error rates, results of experiments, which have been performed using the Korean speech database, show that the proposed speaker verification system exhibits better performance than a conventional hidden Markov model based speaker verification system.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.60 no.9
• /
• pp.1700-1707
• /
• 2011

Interior permanent magnet synchronous motor(IPMSM) adjustable speed drives offer significant advantages over induction motor drives in a wide variety of industrial applications such as high power density, high efficiency, improved dynamic performance and reliability. Since the fuzzy neural network(FNN) is recognized general approximate method to control non-linearities and uncertainties, the development of FNN control systems have also grown rapidly. The FNN controller is compounded of fuzzy and neural network. It has an advantage that is the robustness of fuzzy control and the ability to adapt of neural network. However, the FNN has static problem due to their feed-forward network structure. This paper proposes high performance speed control of IPMSM drive using the recurrent FNN(RFNN) which improved conventional FNN controller. The RFNN has excellent dynamic response characteristics because of it has internally feed-back structure. Also, this paper proposes speed estimation of IPMSM drive using ANN. The proposed method is analyzed and compared to conventional FNN controller in various operating condition such as parameter variation, steady and transient states etc.

• The Journal of the Acoustical Society of Korea
• /
• v.18 no.6
• /
• pp.3-8
• /
• 1999

In this paper, we propose a new active noise control system that cancels the only noise signal from the mixture selectively. A blind source separation realized by a dynamic recurrent neural network is used as a preprocessor of the active noise control system and separates the desired signal and the noise signal. The active noise control system adaptively generates an anti-noise signal to remove the only noise signal separated by the blind source separation. Computer simulation results show that the proposed scheme is effective to construct a selective attention system.

• The Journal of the Acoustical Society of Korea
• /
• v.23 no.4E
• /
• pp.112-119
• /
• 2004

This paper presents a method for the automatic recognition of pitch accents with no prior knowledge about the phonetic content of the signal (no knowledge of word or phoneme boundaries or of phoneme labels). The recognition algorithm used in this paper is a time-delay recurrent neural network (TDRNN). A TDRNN is a neural network classier with two different representations of dynamic context: delayed input nodes allow the representation of an explicit trajectory F0(t), while recurrent nodes provide long-term context information that can be used to normalize the input F0 trajectory. Performance of the TDRNN is compared to the performance of a MLP (multi-layer perceptron) and an HMM (Hidden Markov Model) on the same task. The TDRNN shows the correct recognition of $91.9{\%}\;of\;pitch\;events\;and\;91.0{\%}$ of pitch non-events, for an average accuracy of $91.5{\%}$ over both pitch events and non-events. The MLP with contextual input exhibits $85.8{\%},\;85.5{\%},\;and\;85.6{\%}$ recognition accuracy respectively, while the HMM shows the correct recognition of $36.8{\%}\;of\;pitch\;events\;and\;87.3{\%}$ of pitch non-events, for an average accuracy of $62.2{\%}$ over both pitch events and non-events. These results suggest that the TDRNN architecture is useful for the automatic recognition of pitch accents.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.56 no.5
• /
• pp.966-972
• /
• 2007

This paper presents position control of nonlinear three-dimensional crane systems using neural network approach. Such crane system generally includes very complicated characteristic dynamics and mechanical framework such that its mathematical model is expressed by strong nonlinearity. This leads difficulty in control design for the systems. We linearize the nonlinear system model to construct PID control applying well-known linear control theory and then neural network is utilized to compensate system perturbation due to linearization. Thus, control input of the crane system is composed of nominal PID and neural output signals respectively. Our method illustrates simple design procedure, but system perturbation and modelling error are overcome through a neural compensator. As well. adaptive neural control is constructed from online learning. Computer simulation demonstrates our control approach is superior to the classic control systems.