• KIPS Transactions on Software and Data Engineering
• /
• v.8 no.1
• /
• pp.19-26
• /
• 2019

In this paper, the classification performance of learning algorithms is compared for TAB digit recognition. The TAB digits that are segmented from TAB musical notes contain TAB lines and musical symbols. The labeling method and non-linear filter are designed and applied to extract fret digits only. The shift operation of the 4 directions is applied to generate more data. The selected models are Bayesian classifier, support vector machine, prototype based learning, multi-layer perceptron, and convolutional neural network. The result shows that the mean accuracy of the Bayesian classifier is about 85.0% while that of the others reaches more than 99.0%. In addition, the convolutional neural network outperforms the others in terms of generalization and the step of the data preprocessing.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2014.10a
• /
• pp.342-345
• /
• 2014

Network intrusion detection system based on machine learning methods is quite dependent on the selected features in terms of accuracy and efficiency. Nevertheless, choosing the optimal combination of features from generally used features to detect network intrusion requires extensive computing resources. For instance, the number of possible feature combinations from given n features is $2^n-1$. In this paper, to tackle this problem we propose a optimal feature selection algorithm. Proposed algorithm is based on the local search algorithm, one of representative meta-heuristic algorithm for solving optimization problem. In addition, the accuracy of clusters which obtained using selected feature components and k-means clustering algorithm is adopted to evaluate a feature assembly. In order to estimate the performance of our proposed algorithm, comparing with a method where all features are used on NSL-KDD data set and multi-layer perceptron.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2009.10a
• /
• pp.731-734
• /
• 2009

In this paper, we propose the method the vehicle color recognizing in the image including a vehicle. In an image, the color feature vector of a vehicle is extracted and by using the backpropagation learning algorithm, that is the multi-layer perceptron, the recognized vehicle color. By using the RGB and HSI color model the feature vector used as the input of the backpropagation learning algorithm is the feature of the color used as the input of the neural network. The color of a vehicle recognizes as the white, the silver color, the black, the red, the yellow, the blue, and the green among the color of the vehicle most very much found out as 7 colors. By using the image including a vehicle for the performance evaluation of the method proposing, the color recognition performance was experimented.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.26 no.3
• /
• pp.333-340
• /
• 2022

The COVID-19 has made everyone anxious and people need to keep their distance. It is necessary to conduct collective assessment and screening of college students' mental health in the opening season of every year. This study uses and trains a multi-layer perceptron neural network model for deep learning to identify facial emotions. After the training, real pictures and videos were input for face detection. After detecting the positions of faces in the samples, emotions were classified, and the predicted emotional results of the samples were sent back and displayed on the pictures. The results show that the accuracy is 93.2% in the test set and 95.57% in practice. The recognition rate of Anger is 95%, Disgust is 97%, Happiness is 96%, Fear is 96%, Sadness is 97%, Surprise is 95%, Neutral is 93%, such efficient emotion recognition can provide objective data support for capturing negative. Deep learning emotion recognition system can cooperate with traditional psychological activities to provide more dimensions of psychological indicators for health.

• Geomechanics and Engineering
• /
• v.28 no.4
• /
• pp.385-396
• /
• 2022

The accurate determination of the subgrade reaction modulus (K_s) of soil is an important factor for geotechnical engineers. This study estimated the K_s of soft soil improved with floating deep cement mixing (DCM) columns. A novel prediction model was developed that emphasizes the accuracy of identifying the most significant parameters of K_s. Several multi-layer perceptron (MLP) models that were trained using the Levenberg Marquardt (LM) backpropagation method were developed to estimate K_s. The models were trained using a reliable database containing the results of 36 physical modelling tests. The input parameters were the undrained shear strength of the DCM columns, undrained shear strength of soft soil, area improvement ratio and length-to-diameter ratio of the DCM columns. Grey wolf optimization (GWO) was coupled with the MLPs to improve the performance indices of the MLPs. Sensitivity tests were carried out to determine the importance of the input parameters for prediction of K_s. The results showed that both the MLP-LM and MLP-GWO methods showed high ability to predict K_s. However, it was shown that MLP-GWO (R = 0.9917, MSE = 0.28 (MN/m²/m)) performed better than MLP-LM (R =0.9126, MSE =6.1916 (MN/m²/m)). This proves the greater reliability of the proposed hybrid model of MLP-GWO in approximating the subgrade reaction modulus of soft soil improved with floating DCM columns. The results revealed that the undrained shear strength of the soil was the most effective factor for estimation of K_s.

• Journal of Korean Society for Quality Management
• /
• v.50 no.4
• /
• pp.701-716
• /
• 2022

Purpose: This study aims to predict the dry cargo transportation market economy. The subject of this study is the BDI (Baltic Dry Index) time-series, an index representing the dry cargo transport market. Methods: In order to increase the accuracy of the BDI time-series, we have pre-processed the original time-series via time-series decomposition and data augmentation techniques and have used them for ANN learning. The ANN algorithms used are Multi-Layer Perceptron (MLP), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM) to compare and analyze the case of learning and predicting by applying time-series decomposition and data augmentation techniques. The forecast period aims to make short-term predictions at the time of t+1. The period to be studied is from '22. 01. 07 to '22. 08. 26. Results: Only for the case of the MAPE (Mean Absolute Percentage Error) indicator, all ANN models used in the research has resulted in higher accuracy (1.422% on average) in multivariate prediction. Although it is not a remarkable improvement in prediction accuracy compared to uni-variate prediction results, it can be said that the improvement in ANN prediction performance has been achieved by utilizing time-series decomposition and data augmentation techniques that were significant and targeted throughout this study. Conclusion: Nevertheless, due to the nature of ANN, additional performance improvements can be expected according to the adjustment of the hyper-parameter. Therefore, it is necessary to try various applications of multiple learning algorithms and ANN optimization techniques. Such an approach would help solve problems with a small number of available data, such as the rapidly changing business environment or the current shipping market.

• The Journal of Korea Robotics Society
• /
• v.17 no.4
• /
• pp.463-476
• /
• 2022

In this paper, we propose a table tennis posture classification system using a cooperative robot to develop a table tennis robot that can be trained like a real game. The most ideal table tennis robot would be a robot with a high joint driving speed and a high degree of freedom. Therefore, in this paper, we intend to use a cooperative robot with sufficient degrees of freedom to develop a robot that can be trained like a real game. However, cooperative robots have the disadvantage of slow joint driving speed. These shortcomings are expected to be overcome through quick recognition. Therefore, in this paper, we try to quickly classify the opponent's posture to overcome the slow joint driving speed. To this end, learning about dynamic postures was conducted using image data as input, and finally, three classification models were created and comparative experiments and evaluations were performed on the designated dynamic postures. In conclusion, comparative experimental data demonstrate the highest classification accuracy and fastest classification speed in classification models using MLP (Multi-Layer Perceptron), and thus demonstrate the validity of the proposed algorithm.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.1
• /
• pp.29-38
• /
• 2023

Although the biosignal is the best way to represent the human condition, it is difficult to acquire the biosignal of a driver driving for detecting driver's condition. As one of the methods to overcome this limitation, this paper proposes a driving stress monitoring system based on information provided by OBD-II(on-board diagnostics version II). The driving information and EDA(Electrodermal activity) data are obtained through the OBD-II scanner and E4 wristband, respectively. EDA data is used as ground truth to distinguish whether driver is stressed or not. MLP(multi-layer perceptron) neural network is used as a model to detect driving stress and is trained using driving data for about a month. To evaluate the proposed system, we used about 1 hour of driving data and the accuracy is 92%.

• The Journal of the Acoustical Society of Korea
• /
• v.42 no.1
• /
• pp.67-74
• /
• 2023

The images acquired from the speaker's mouth region revealed the unique patterns according to the corresponding voices. By using this principle, the several methods were proposed in which speech signals were recognized or synthesized from the images acquired at the speaker's lower face. In this study, an image-based speech synthesis method was proposed in which the depth images were cooperatively used. Since depth images yielded depth information that cannot be acquired from optical image, it can be used for the purpose of supplementing flat optical images. In this paper, the usefulness of depth images from the perspective of speech synthesis was evaluated. The validation experiment was carried out on 60 Korean isolated words, it was confirmed that the performance in terms of both subjective and objective evaluation was comparable to the optical image-based method. When the two images were used in combination, performance improvements were observed compared with when each image was used alone.

• Smart Media Journal
• /
• v.11 no.1
• /
• pp.58-66
• /
• 2022

As Internet technology develops, SNS users are increasing. As SNS becomes popular, SNS-type crimes using the influence and anonymity of social networks are increasing day by day. In this paper, we propose a fake account classification method that applies machine learning and deep learning to statistical and image data for fake accounts classification. SNS account data used for training was collected by itself, and the collected data is based on statistical data and image data. In the case of statistical data, machine learning and multi-layer perceptron were employed to train. Furthermore in the case of image data, a convolutional neural network (CNN) was utilized. Accordingly, it was confirmed that the overall performance of account classification was significantly meaningful.