• The Transactions of the Korean Institute of Electrical Engineers D
• /
• v.53 no.12
• /
• pp.834-838
• /
• 2004

This paper proposes an algorithm for EEG pattern classification using the Multi-template method, which is a kind of speaker adaptation method for speech signal processing. 10-channel EEG signals are collected in various environments. The linear prediction coefficients of the EEGs are extracted as the feature parameter of human sensibility. The human sensibility classification algorithm is developed using neural networks. Using EEGs of comfortable or uncomfortable seats, the proposed algorithm showed about 75% of classification performance in subject-independent test. In the tests using EEG signals according to room temperature and humidity variations, the proposed algorithm showed good performance in tracking of pleasantness changes and the subject-independent tests produced similar performances with subject-dependent ones.

• International Journal of Naval Architecture and Ocean Engineering
• /
• v.13 no.1
• /
• pp.848-857
• /
• 2021

This paper proposes an efficient approach based on a machine learning technique to predict the local stresses on mooring chain links. Three-link and multi-link finite element analyses were conducted for a target chain link of D107 with steel grade R4; 24,000 and 8000 analyses were performed, respectively. Two serial Artificial Neural Network (ANN) models based on a deep multi-layer perceptron technique were developed. The first ANN model corresponds to multi-link analyses, where the input neurons were the tension force and angle and the output neurons were the interlink angles. The second ANN model corresponds to the three-link analyses with the input neurons of the tension force, interlink angle, and the local stress positions, and the output neurons of the local stress. The predicted local stresses for the untrained cases were reliable compared to the numerical simulation results.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.192-198
• /
• 2024

This paper investigates the application of multi-agent deep reinforcement learning in the fighting game Samurai Shodown using Proximal Policy Optimization (PPO) and Advantage Actor-Critic (A2C) algorithms. Initially, agents are trained separately for 200,000 timesteps using Convolutional Neural Network (CNN) and Multi-Layer Perceptron (MLP) with LSTM networks. PPO demonstrates superior performance early on with stable policy updates, while A2C shows better adaptation and higher rewards over extended training periods, culminating in A2C outperforming PPO after 1,000,000 timesteps. These findings highlight PPO's effectiveness for short-term training and A2C's advantages in long-term learning scenarios, emphasizing the importance of algorithm selection based on training duration and task complexity. The code can be found in this link https://github.com/Lexer04/Samurai-Shodown-with-Reinforcement-Learning-PPO.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.48-56
• /
• 2023

The technology of Three-dimensional human posture estimation is used in sports, motion recognition, and special effects of video media. Among various methods for this, multi-view 3D human pose estimation is essential for precise estimation even in complex real-world environments. But Existing models for multi-view 3D human posture estimation have the disadvantage of high order of time complexity as they use 3D feature maps. This paper proposes a method to extend an existing monocular viewpoint multi-frame model based on Transformer with lower time complexity to 3D human posture estimation for multi-viewpoints. To expand to multi-viewpoints our proposed method first generates an 8-dimensional joint coordinate that connects 2-dimensional joint coordinates for 17 joints at 4-vieiwpoints acquired using the 2-dimensional human posture detector, CPN(Cascaded Pyramid Network). This paper then converts them into 17×32 data with patch embedding, and enters the data into a transformer model, finally. Consequently, the MLP(Multi-Layer Perceptron) block that outputs the 3D-human posture simultaneously updates the 3D human posture estimation for 4-viewpoints at every iteration. Compared to Zheng[5]'s method the number of model parameters of the proposed method was 48.9%, MPJPE(Mean Per Joint Position Error) was reduced by 20.6 mm (43.8%) and the average learning time per epoch was more than 20 times faster.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.11 no.1
• /
• pp.73-80
• /
• 2016

The Car License Plate Recognition(: CLPR) is required in searching the hit-and-run car, measuring the traffic density, investigating the traffic accidents as well as in pursuing vehicle crimes according to the increasing in number of vehicles. The captured images on the real environment of the CLPR is contaminated not only by snow and rain, illumination changes, but also by the geometrical distortion due to the pose changes between camera and car at the moment of image capturing. We propose homographic transformation and intensity histogram of vertical image projection so as to transform the distorted input to the original image and cluster the character and number, respectively. Especially, in this paper, the Multilayer Perceptron Algorithm(: MLP) in the CLPR is used to not only recognize the charcters and car license plate, but also determine the optimized ratio among the number of input, hidden and output layers by the real experimental result.

• Proceedings of the IEEK Conference
• /
• 2008.06a
• /
• pp.681-682
• /
• 2008

This paper propose skin color detection that uses MLP(Multi Layer Perceptron) and multiple color models. The proposed method reduces weight of MLP by partial connection between input layer and hidden layer based on color models, and the using color models are RGB model and YCbCr model. The experimental result for proposed method showed 94% classification rate of skin and non-skin pixels with 32% decrease in the number of weight compare to general MLP on the average.

• Proceedings of the Computational Structural Engineering Institute Conference
• /
• 2000.04b
• /
• pp.271-276
• /
• 2000

Optimal neuro-control algorithm is extended to the control of a multi-degree-of-freedom structure. An active mass driver(AMD) system on the top roof used as a controller. The control signals are made by a multi-layer perceptron(MLP) which is trained by minimizing a sub-optimal performance index. The performance index is a function of both the output responses and the control signals. Structure having nonlinear hysteretic behavior is also trained and controlled by using proposed control algorithm. Bothe the time delay effect and the dynamics of hydraulic actuator are included in the simulation. Example shows that optimal neuro-control algorithm can be applicable to the multi-degree of freedom structures.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2000.06a
• /
• pp.286-290
• /
• 2000

Optimal neuro-control algorithm is extended to the control of a multi-degree-of-freedom structure. An active mass driver(AMD) system on the top roof is used as an exciter. The control signals are made by a multi-layer perceptron(MLP) which is trained by minimizing a sub-optimal performance index. The performance index is a function of both the output responses and the control signals. Structure having nonlinear hysteretic behavior is also trained and controlled by using proposed control algorithm. In training neuro-controller, emulator neural network is not used. Instead, sensitivity-test data are used. Therefore, only one neural network is used for the control system. Both the time delay effect and the dynamics of hydraulic actuator are included in the simulation. Example shows that optimal neuro-control algorithm can be applicable to the multi-degree of freedom structures.

• 제어로봇시스템학회:학술대회논문집
• /
• 2004.08a
• /
• pp.1319-1323
• /
• 2004

In this paper, a problem of Thai sign language recognition using a neural network is considered. The paper addresses the problem in classifying certain signs conveying quantitative meaning, e.g., large or small. By treating those signs corresponding to different quantities as derived from different classes, the recognition error rate of the standard multi-layer Perceptron increases if the precision in recognizing different quantities is increased. This is due the fact that, to increase the quantitative recognition precision of those signs, the number of (increasingly similar) classes must also be increased. This leads to an increase in false classification. The problem is due to misinterpreting the amount of quantity the quantitative signs convey. In this paper, instead of treating those signs conveying quantitative attribute of the same quantity type (such as 'size' or 'amount') as derived from different classes, here they are considered instances of the same class. Those signs of the same quantity type are then further divided into different subclasses according to the level of quantity each sign is associated with. By using this two-level classification, false classification among main gesture classes is made independent to the level of precision needed in recognizing different quantitative levels. Moreover, precision of quantitative level classification can be made higher during the recognition phase, as compared to that used in the training phase. A standard multi-layer Perceptron with a back propagation learning algorithm was adapted in the study to implement this two-level classification of quantitative gesture signs. Experimental results obtained using an electronic glove measurement of hand postures are included.

• Journal of Aerospace System Engineering
• /
• v.13 no.6
• /
• pp.17-25
• /
• 2019

PHM (Prognostics and Health Management) of aircraft engines is applied to predict the remaining useful life before failure or the lifetime limit. There are two methods to establish a predictive model for this: The physics-based method and the data-driven method. The physics-based method is more accurate and requires less data, but its application is limited because there are few models available. In this study, the data-driven method is applied, in which a multi-layer perceptron based neural network algorithms is applied for the life prediction. The neural network is trained using the data sets virtually made by the C-MAPSS code developed by NASA. After training the model, it is applied to the test data sets, in which the confidence interval of the remaining useful life is predicted and validated by the actual value. The performance of proposed method is compared with previous studies, and the favorable accuracy is found.