• The Journal of Korea Robotics Society
• /
• v.19 no.2
• /
• pp.139-148
• /
• 2024

In this paper, we propose a two-degree-of-freedom snake robot head system and an I-PID (Intelligent Proportional-Integral-Derivative)-based controller utilizing RBF (Radial Basis Function) neural network and adaptive robust terms as a control strategy to reduce rotation occurring in the snake robot head. This study proposes a two-degree-of-freedom snake robot head system to avoid complex snake robot dynamics. This system has a control system independent of the snake robot. Subsequently, it utilizes an I-PID controller to implement a control system that can effectively manage rotation at the snake robot head, the robot's nonlinearity, and disturbances. To compensate for the time delay estimation errors occurring in the I-PID control system, an RBF neural network is integrated. Additionally, an adaptive robust term is designed and integrated into the control system to enhance robustness and generate control inputs responsive to signal changes. The proposed controller satisfies stability according to Lyapunov's theory. The proposed control strategy was tested using a 9-degreeof-freedom snake robot. It demonstrates the capability to reduce rotation in Lateral undulation, Rectilinear, and Sidewinding locomotion.

• Proceedings of the Acoustical Society of Korea Conference
• /
• 1992.06a
• /
• pp.61-65
• /
• 1992

This paper presents a study on Neural Networks for Phoneme Recognition and performs phoneme recognition using TDNN(Time Delay Neural Network). Also, this paper proposes new training algorithm for speech recognition using neural nets that proper to large scale TDNN. Because phoneme recognition is indispensable for continuous speech recognition, this paper uses TDNN to get accurate recognition result of phoneme. And this paper proposes new training algorithm that can converge TDNN to optimal state regardless of the number of phoneme to be recognized. The result of recognition on three phoneme classes shows recognition rate of 9.1%. And this paper proves that proposed algorithm is a efficient method for high performance and reducing convergence time.

• Journal of information and communication convergence engineering
• /
• v.21 no.3
• /
• pp.198-207
• /
• 2023

Responding to changes in artificial intelligence models and the data environment is crucial for increasing data-learning accuracy and inference stability of industrial applications. A learning model that is overfitted to specific training data leads to poor learning performance and a deterioration in flexibility. Therefore, an early stopping technique is used to stop learning at an appropriate time. However, this technique does not consider the homogeneity and independence of the data collected by heterogeneous nodes in a differential network environment, thus resulting in low learning accuracy and degradation of system performance. In this study, the generalization performance of neural networks is maximized, whereas the effect of the homogeneity of datasets is minimized by achieving an accuracy of 99.7%. This corresponds to a decrease in delay time by a factor of 2.33 and improvement in performance by a factor of 2.5 compared with the conventional method.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.483-489
• /
• 2020

This paper proposes acoustic model training using self-attention for low-resource speech recognition. In low-resource speech recognition, it is difficult for acoustic model to distinguish certain phones. For example, plosive /d/ and /t/, plosive /g/ and /k/ and affricate /z/ and /ch/. In acoustic model training, the self-attention generates attention weights from the deep neural network model. In this study, these weights handle the similar pronunciation error for low-resource speech recognition. When the proposed method was applied to Time Delay Neural Network-Output gate Projected Gated Recurrent Unit (TNDD-OPGRU)-based acoustic model, the proposed model showed a 5.98 % word error rate. It shows absolute improvement of 0.74 % compared with TDNN-OPGRU model.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• v.3 no.1
• /
• pp.105-111
• /
• 2003

This paper is researching the storing of 40 different kinds of conditions. Such as, car speed, delay in starting time and the volume of cars in traffic. Through the use of a central nervous networking system or AI, using 10 different intersecting roads. We will improve the green traffic light. And allow more cars to easily flow through the intersections. Now days, with increasing many vehicles on restricted roads, the conventional traffic light creates prove startup-delay time and end-lag-time. The conventional traffic light loses the function of optimal cycle. And so, 30-45% of conventional traffic cycle is not matched to the present traffic cycle. In this paper proposes electro sensitive traffic light using fuzzy look up table method which will reduce the average vehicle waiting time and improve average vehicle speed. Computer simulation results prove that reducing the average vehicle waiting time which proposed considering passing vehicle length for optimal traffic cycle is better than fixed signal method which dosen't consider vehicle length.

• The Journal of the Acoustical Society of Korea
• /
• v.16 no.2E
• /
• pp.32-37
• /
• 1997

This paper proposes a isolated speech recognition method of Korean digits using a TDNN(Time Delay Neural Network) which is able to recognizc time-varying speech properties. We also make an investigation of effect on network parameter of TDNN ; hidden layers and time-delays. TDNNs in our experiments consist of 2 and 3 hidden layers and have several time-delays. From experiment result, TDNN structure which has 2 hidden-layers, gives a good result for speech recognition of Korean digits. Mis-recognition by time-delays can be improved by changing TDNN structures and mis-recognition separated from time-delays can be improved by changing input patterns.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.38 no.5
• /
• pp.671-683
• /
• 2018

The flood damage caused by heavy rains in urban watershed is increasing, and, as evidenced by many previous studies, urban flooding usually exceeds the water capacity of drainage networks. The flood on the area which considerably urbanized and densely populated cause serious social and economic damage. To solve this problem, deterministic and probabilistic studies have been conducted for the prediction flooding in urban areas. However, it is insufficient to obtain lead times and to derive the prediction results for the flood volume in a short period of time. In this study, IDNN, TDNN and NARX were compared for real-time flood prediction based on urban runoff analysis to present the optimal real-time urban flood prediction technique. As a result of the flood prediction with rainfall event of 2010 and 2011 in Gangnam area, the Nash efficiency coefficient of the input delay artificial neural network, the time delay neural network and nonlinear autoregressive network with exogenous inputs are 0.86, 0.92, 0.99 and 0.53, 0.41, 0.98 respectively. Comparing with the result of the error analysis on the predicted result, it is revealed that the use of nonlinear autoregressive network with exogenous inputs must be appropriate for the establishment of urban flood response system in the future.

• Smart Media Journal
• /
• v.6 no.3
• /
• pp.41-48
• /
• 2017

Event detection using social media has been widespread since social network services have been an active communication channel for connecting with others, diffusing news message. Especially, the real-time characteristic of social media has created the opportunity for supporting for real-time applications/systems. Social network such as Twitter is the potential data source to explore useful information by mining messages posted by the user community. This paper proposed a novel system for temporal event detection by analyzing social data. As a result, this information can be used by first responders, decision makers, or news agents to gain insight of the situation. The proposed approach takes advantages of deep learning methods that play core techniques on the main tasks including informative data identifying from a noisy environment and temporal event detection. The former is the responsibility of Convolutional Neural Network model trained from labeled Twitter data. The latter is for event detection supported by Recurrent Neural Network module. We demonstrated our approach and experimental results on the case study of earthquake situations. Our system is more adaptive than other systems used traditional methods since deep learning enables to extract the features of data without spending lots of time constructing feature by hand. This benefit makes our approach adaptive to extend to a new context of practice. Moreover, the proposed system promised to respond to acceptable delay within several minutes that will helpful mean for supporting news channel agents or belief plan in case of disaster events.

• Proceedings of the IEEK Conference
• /
• 2000.06e
• /
• pp.47-50
• /
• 2000

In this paper, we propose PID type direct control method using single neuron neural network. The proposed method has an output error and 2 time-delay as inputs and is designed to have input weights composed of P, I, D parameters to be controlled through teaming. We could verify the better performance of this system than the conventional method through simulations. And the reduced calculation, due to single neuron, makes it possible the real time processing, and the simple implementation.

• Environmental Engineering Research
• /
• v.21 no.4
• /
• pp.333-340
• /
• 2016

An Artificial Neural Network including a Radial Basis Function (RBF) and a Time Delay Neural Network (TDNN) was used to predict total dissolved solid (TDS) in the river Zayanderud. Water quality parameters in the river for ten years, 2001-2010, were prepared from data monitored by the Isfahan Regional Water Authority. A factor analysis was applied to select the inputs of water quality parameters, which obtained total hardness, bicarbonate, chloride and calcium. Input data to the neural networks were pH, $Na^+$, $Mg^{2+}$, Carbonate ($CO{_3}^{-2}$), $HCO{_3}^{-1}$, $Cl^-$, $Ca^{2+}$ and Total hardness. For learning process 5-fold cross validation were applied. In the best situation, the TDNN contained 2 hidden layers of 15 neurons in each of the layers and the RBF had one hidden layer with 100 neurons. The Mean Squared Error and the Mean Bias Error for the TDNN during the training process were 0.0006 and 0.0603 and for the RBF neural network the mentioned errors were 0.0001 and 0.0006, respectively. In the RBF, the coefficient of determination ($R^2$) and the index of agreement (IA) between the observed data and predicted data were 0.997 and 0.999, respectively. In the TDNN, the $R^2$ and the IA between the actual and predicted data were 0.957 and 0.985, respectively. The results of sensitivity illustrated that $Ca^{2+}$ and $SO{_4}^{2-}$ parameters had the highest effect on the TDS prediction.