• Proceedings of the KIEE Conference
• /
• 2004.07d
• /
• pp.2432-2434
• /
• 2004

In this paper, we present a novel approach for the structure of Fuzzy Neural Network(FNN) based on wavelet function and apply this network structure to the solution of the tracking problem for mobile robots. Generally, the wavelet fuzzy model(WFM) has the advantage of the wavelet transform by constituting fuzzy basis function(FBF) and the conclusion part to equalize the linear combination of FBF with the linear combination of wavelet functions. However, it is very difficult to identify the fuzzy rules and to tune the membership functions of the fuzzy reasoning mechanism. Neural networks, on the other hand, utilize their learning capability for automatic identification and tuning. Therefore, we design a wavelet based FNN structure(WFNN) that merges these advantages of neural network, fuzzy model and wavelet. To verify the efficiency of our network structure, we evaluate the tracking performance for mobile robot and compare it with those of the FNN and the WFM.

• 제어로봇시스템학회:학술대회논문집
• /
• 1989.10a
• /
• pp.1129-1134
• /
• 1989

In this paper, we propose a neural network for learning to control semi-linear dynamical systems. The network is a composite system of four three-layer backpropagation subnetworks, and is able to control inverted pendulums better than systems based on modern control theory at least in some ranges of parameters. Three of the four subnetworks in our network system process angles, velocities, and positions of a moving inverted pendulum, respectively. The outputs from those three subnetworks are input to the remaining subnetwork that makes control decisions. Each of the four subnetworks learns connection weights independently by backpropagation algorithms. Teaching signals are given by the human operator. Also, input signals are generated by the human operator, but they are converted by preprocessors to actual input data for the three subnetworks except for the network for control decisions. The whole system is implemented on both of 16 bit personal computers and 32 bit workstations. First, we briefly provide the research background and the inverted pendulum problem itself, followed by the description of our composite neural network model. Next, some results from the simulation are given, which are subsequently compared with the results from a control system based on modern control theory. Then, some discussions and conclusion follow.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.8
• /
• pp.3789-3808
• /
• 2017

This paper studies a multi-antenna wireless relay network in the presence of a jammer. In this network, the source node transmits signals to the destination node through a multi-antenna relay node which adopts the amplify-and-forward scheme, and the jammer attempts to inject additive signals on all antennas of the relay node. With the linear beamforming scheme at the relay node, this network can be modeled as an equivalent Gaussian arbitrarily varying channel (GAVC). Based on this observation, we deduce the mathematical closed-forms of the capacities for two special cases and the suboptimal achievable rate for the general case, respectively. To reduce complexity, we further propose an optimal structure of the beamforming matrix. In addition, we present a second order cone programming (SOCP)-based algorithm to efficiently compute the optimal beamforming matrix so as to maximize the transmission rate between the source and the destination when the perfect channel state information (CSI) is available. Our numerical simulations show significant improvements of our propose scheme over other baseline ones.

• Phonetics and Speech Sciences
• /
• v.13 no.1
• /
• pp.45-51
• /
• 2021

End-to-end (E2E) automatic speech recognition (ASR) has achieved promising performance gains with the introduced self-attention network, Transformer. However, due to training time and the number of hyperparameters, finding the optimal hyperparameter set is computationally expensive. This paper investigates the impact of hyperparameters in the Transformer network to answer two questions: which hyperparameter plays a critical role in the task performance and training speed. The Transformer network for training has two encoder and decoder networks combined with Connectionist Temporal Classification (CTC). We have trained the model with Wall Street Journal (WSJ) SI-284 and tested on devl93 and eval92. Seventeen hyperparameters were selected from the ESPnet training configuration, and varying ranges of values were used for experiments. The result shows that "num blocks" and "linear units" hyperparameters in the encoder and decoder networks reduce Word Error Rate (WER) significantly. However, performance gain is more prominent when they are altered in the encoder network. Training duration also linearly increased as "num blocks" and "linear units" hyperparameters' values grow. Based on the experimental results, we collected the optimal values from each hyperparameter and reduced the WER up to 2.9/1.9 from dev93 and eval93 respectively.

• Journal of Information Technology Applications and Management
• /
• v.27 no.6
• /
• pp.181-196
• /
• 2020

Based on the resource-based perspective, this study seeks to understand the relationship between the organizational slack and innovation, and to demonstrate that there exists a difference in the influence of the organizational slack according to the type of innovation by dividing the types of innovation into exploratory and exploitative innovations. They also want to understand the role that network diversity plays in the relationship between organizational slack and innovation. For this purpose, hypothesis and research models were presented based on resource-based perspectives and empirical analysis was conducted on 171 companies. The analysis confirmed that the impact of organizational slack on exploitative innovation is linear, not non-linear, as expected. In other words, the more resources available, the more productive the enterprise is, and the more resources available to the organization have a positive impact on the innovation. On the other hand, exploratory innovation represented an inverse U-shaped relationship between organizational slack and nonlinearity as expected. The control effect of network diversity was only seen in the relationship between organizational slack and exploratory innovation. Through this study, it provides implications such as the importance of network diversity, which is a relationship between companies, and the difference in the utilization of organizational slack according to the type of innovation.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.1
• /
• pp.334-349
• /
• 2022

The effectiveness of Wi-Fi networks is greatly influenced by the optimization of contention window (CW) parameters. Unfortunately, the conventional approach employed by IEEE 802.11 wireless networks is not scalable enough to sustain consistent performance for the increasing number of stations. Yet, it is still the default when accessing channels for single-users of 802.11 transmissions. Recently, there has been a spike in attempts to enhance network performance using a machine learning (ML) technique known as reinforcement learning (RL). Its advantage is interacting with the surrounding environment and making decisions based on its own experience. Deep RL (DRL) uses deep neural networks (DNN) to deal with more complex environments (such as continuous state spaces or actions spaces) and to get optimum rewards. As a result, we present a new approach of CW control mechanism, which is termed as contention window threshold (CW_Threshold). It uses the DRL principle to define the threshold value and learn optimal settings under various network scenarios. We demonstrate our proposed method, known as a smart exponential-threshold-linear backoff algorithm with a deep Q-learning network (SETL-DQN). The simulation results show that our proposed SETL-DQN algorithm can effectively improve the throughput and reduce the collision rates.

• International Journal of Computer Science & Network Security
• /
• v.23 no.11
• /
• pp.21-31
• /
• 2023

In this paper, we focused on the problem of evaluating multi-class classification accuracy and simulation of multiple classifier performance metrics. Multi-class classifiers for sentiment analysis involved many challenges, whereas previous research narrowed to the binary classification model since it provides higher accuracy when dealing with text data. Thus, we take inspiration from the non-linear Support Vector Machine to modify the algorithm by embedding dynamic hyperplanes representing multiple class labels. Then we analyzed the performance of multi-class classifiers using macro-accuracy, micro-accuracy and several other metrics to justify the significance of our algorithm enhancement. Furthermore, we hybridized Enhanced Convolution Neural Network (ECNN) with Dynamic Support Vector Machine (DSVM) to demonstrate the effectiveness and efficiency of the classifier towards multi-class text data. We performed experiments on three hybrid classifiers, which are ECNN with Binary SVM (ECNN-BSVM), and ECNN with linear Multi-Class SVM (ECNN-MCSVM) and our proposed algorithm (ECNNDSVM). Comparative experiments of hybrid algorithms yielded 85.12 % for single metric accuracy; 86.95 % for multiple metrics on average. As for our modified algorithm of the ECNN-DSVM classifier, we reached 98.29 % micro-accuracy results with an f-score value of 98 % at most. For the future direction of this research, we are aiming for hyperplane optimization analysis.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.26 no.1
• /
• pp.10-21
• /
• 2023

For various target tracking applications, it is well known that the Kalman filter is the optimal estimator(in the minimum mean-square sense) to predict and estimate the state(position and/or velocity) of linear dynamical systems driven by Gaussian stochastic noise. In the case of nonlinear systems, Extended Kalman filter(EKF) and/or Unscented Kalman filter(UKF) are widely used, which can be viewed as approximations of the(linear) Kalman filter in the sense of the conditional expectation. However, to implement EKF and UKF, the exact dynamical model information and the statistical information of noise are still required. In this paper, we propose the recurrent neural-network based Kalman filter, where its Kalman gain is obtained via the proposed GRU-LSTM based neural-network framework that does not need the precise model information as well as the noise covariance information. By the proposed neural-network based Kalman filter, the state estimation performance is enhanced in terms of the tracking error, which is verified through various linear and nonlinear tracking problems with incomplete model and statistical covariance information.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.4
• /
• pp.305-312
• /
• 2023

Physics-Informed Neural Network (PINN) is used to invert bubble size distributions from attenuation losses. By considering a linear system for the bubble population inversion, Adaptive Learned Iterative Shrinkage Thresholding Algorithm (Ada-LISTA), which has been solved linear systems in image processing, is used as a neural network architecture in PINN. Furthermore, a regularization based on the linear system is added to a loss function of PINN and it makes a PINN have better generalization by a solution satisfying the bubble physics. To evaluate an uncertainty of bubble estimation, deep ensemble is adopted. 20 Ada-LISTAs with different initial values are trained using the same training dataset. During test with attenuation losses different from those in the training dataset, the bubble size distribution and corresponding uncertainty are indicated by average and variance of 20 estimations, respectively. Deep ensemble Ada-LISTA demonstrate superior performance in inverting bubble size distributions than the conventional convex optimization solver of CVX.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1162-1167
• /
• 2004

This paper presents the design methodology of digital fuzzy controller(DFC) for the systems with time-delay. We propose the fuzzy feedback controller whose output is delayed with unit sampling period and predicted. The analysis and the design problem considering time-delay become easy because the proposed controller is syncronized with the sampling time. The stabilization problem of the digital fuzzy system with time-delay is solved by linear matrix inequality(LMI) theory. Convex optimization techniques are utilized to solve the stable feedback gains and a common Lyapunov function for designed fuzzy control system. To show the effectiveness the proposed control scheme, the network control example is presented.