• Journal of the Institute of Electronics Engineers of Korea CI
• /
• v.37 no.2
• /
• pp.31-43
• /
• 2000

This paper presents a novel algorithm lot extraction of the eye and mouth fields (facial features) from 2D gray level face images. First of all, it has been found that Eigenfeatures, derived from the eigenvalues and the eigenvectors of the binary edge data set constructed from the eye and mouth fields are very good features to locate these fields. The Eigenfeatures, extracted from the positive and negative training samples for the facial features, ate used to train a MultiLayer Perceptron(MLP) whose output indicates the degree to which a particular image window contains the eye or the mouth within itself. Second, to ensure robustness, the ensemble network consisting of multiple MLPs is used instead of a single MLP. The output of the ensemble network becomes the average of the multiple locations of the field each found by the constituent MLPs. Finally, in order to reduce the computation time, we extracted the coarse search region lot eyes and mouth by using prior information on face images. The advantages of the proposed approach includes that only a small number of frontal faces are sufficient to train the nets and furthermore, lends themselves to good generalization to non-frontal poses and even to other people's faces. It was also experimentally verified that the proposed algorithm is robust against slight variations of facial size and pose due to the generalization characteristics of neural networks.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.2
• /
• pp.149-162
• /
• 2005

This paper suggest a way to detect a specific wanted figure in public places such as subway stations and banks by comparing color face images extracted from the real time CCTV with the face images of designated specific figures. Assuming that the characteristic of the surveillance camera allows the face information in screens to change arbitrarily and to contain information on numerous faces, the accurate detection of the face area was focused. To solve this problem, the normalization work using subsampling with $20{\times}20$ pixels on arbitrary face images, which is based on the Perceptron Neural Network model suggested by R. Rosenblatt, created the effect of recogning the whole face. The optimal linear filter and the histogram shaper technique were employed to minimize the outside interference such as lightings and light. The addition operation of the egg-shaped masks was added to the pre-treatment process to minimize unnecessary work. The images finished with the pre-treatment process were divided into three reception fields and the information on the specific location of eyes, nose, and mouths was determined through the neural network. Furthermore, the precision of results was improved by constructing the three single-set network system with different initial values in a row.

• Journal of KIISE:Software and Applications
• /
• v.30 no.5_6
• /
• pp.540-549
• /
• 2003

In collaborative recommendation two models are generally used: the user model and the article model. A user model learns correlation between users preferences and recommends an article based on other users preferences for the article. Similarly, an article model learns correlation between preferences for articles and recommends an article based on the target user's preference for other articles. In this paper, we investigates various combination methods of the user model and the article model for better recommendation performance. They include simple sequential and parallel methods, perceptron, multi-layer perceptron, fuzzy rules, and BKS. We adopt the multi-layer perceptron for training each of the user and article models. The multi-layer perceptron has several advantages over other methods such as the nearest neighbor method and the association rule method. It can learn weights between correlated items and it can handle easily both of symbolic and numeric data. The combined models outperform any of the basic models and our experiments show that the multi-layer perceptron is the most efficient combination method among them.

• The Journal of the Acoustical Society of Korea
• /
• v.20 no.4
• /
• pp.48-53
• /
• 2001

In this paper, selectively attentive learning method has been proposed to improve the learning speed of multilayer Perceptron based on the error backpropagation algorithm. Three attention criterions are introduced to effectively determine which set of input patterns is or which portion of network is attended to for effective learning. Such criterions are based on the mean square error function of the output layer and class-selective relevance of the hidden nodes. The acceleration of learning time is achieved by lowering the computational cost per iteration. Effectiveness of the proposed method is demonstrated in a speaker adaptation task of isolated word recognition system. The experimental results show that the proposed selective attention technique can reduce the learning time more than 60% in an average sense.

• Journal of the Korea Convergence Society
• /
• v.10 no.4
• /
• pp.17-23
• /
• 2019

In this paper, quality control (QC) is applied to each meteorological element of weather data collected from seven IoT sensors such as temperature. In addition, we propose a method for estimating the data regarded as error by means of machine learning. The collected meteorological data was linearly interpolated based on the basic QC results, and then machine learning-based QC was performed. Support vector regression, decision table, and multilayer perceptron were used as machine learning techniques. We confirmed that the mean absolute error (MAE) of the machine learning models through the basic QC is 21% lower than that of models without basic QC. In addition, when the support vector regression model was compared with other machine learning methods, it was found that the MAE is 24% lower than that of the multilayer neural network and 58% lower than that of the decision table on average.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.2
• /
• pp.81-86
• /
• 2022

Given that time series are used in various fields, such as finance, IoT, and manufacturing, data analytical methods for accurate time-series forecasting can serve to increase operational efficiency. Among time-series analysis methods, multi-horizon forecasting provides a better understanding of data because it can extract meaningful statistics and other characteristics of the entire time-series. Furthermore, time-series data with exogenous information can be accurately predicted by using multi-horizon forecasting methods. However, traditional deep learning-based models for time-series do not account for the heterogeneity of inputs. We proposed an improved time-series predicting method, called the temporal fusion transformer method, which combines multi-horizon forecasting with interpretable insights into temporal dynamics. Various real-world data such as stock prices, fine dust concentrates and electricity consumption were considered in experiments. Experimental results showed that our temporal fusion transformer method has better time-series forecasting performance than existing models.

• Journal of Sensor Science and Technology
• /
• v.8 no.1
• /
• pp.45-52
• /
• 1999

In this raper, an enhanced learning method is proposed for improving the learning speed of the error back propagation learning algorithm. In order to cope with the premature saturation phenomenon at the initial learning stage, a variation scheme of active functions is introduced by using higher order functions, which does not need much increase of computation load. It naturally changes the learning rate of inter-connection weights to a large value as the derivative of sigmoid function abnormally decrease to a small value during the learning epoch. Also, we suggest the hybrid learning method incorporated the proposed method with the momentum training algorithm. Computer simulation results show that the proposed learning algorithm outperforms the conventional methods such as momentum and delta-bar-delta algorithms.

• Journal of Korea Water Resources Association
• /
• v.55 no.11
• /
• pp.903-911
• /
• 2022

Groundwater, one of the resources for supplying water, fluctuates in water level due to various natural factors. Recently, research has been conducted to predict fluctuations in groundwater levels using Artificial Neural Network (ANN). Previously, among operators in ANN, Gradient Descent (GD)-based Optimizers were used as Optimizer that affect learning. GD-based Optimizers have disadvantages of initial correlation dependence and absence of solution comparison and storage structure. This study developed Gradient Descent combined with Harmony Search (GDHS), a new Optimizer that combined GD and Harmony Search (HS) to improve the shortcomings of GD-based Optimizers. To evaluate the performance of GDHS, groundwater level at Icheon Yullhyeon observation station were learned and predicted using Multi Layer Perceptron (MLP). Mean Squared Error (MSE) and Mean Absolute Error (MAE) were used to compare the performance of MLP using GD and GDHS. Comparing the learning results, GDHS had lower maximum, minimum, average and Standard Deviation (SD) of MSE than GD. Comparing the prediction results, GDHS was evaluated to have a lower error in all of the evaluation index than GD.

• Geotechnical Engineering
• /
• v.10 no.3
• /
• pp.79-96
• /
• 1994

A tunnel design expert system entitled NESTED is developed using the artificial neural network. The expert system includes three neural network computer models designed for the stability assessment of underground openings and the estimation of correlation between the RMR and Q systems. The expert system consists of the three models and the computerized rock mass classification programs that could be driven under the same user interface. As the structure of the neural network, a multi -layer neural network which adopts an or ror back-propagation learning algorithm is used. To set up its knowledge base from the prior case histories, an engineering database which can control the incomplete and erroneous information by learning process is developed. A series of experiments comparing the results of the neural network with the actual field observations have demonstrated the inferring capabilities of the neural network to identify the possible failure modes and the support timing. The neural network expert system thus complements the incomplete geological data and provides suitable support recommendations for preliminary design of tunnels in rock masses.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.40 no.9
• /
• pp.1731-1733
• /
• 2015

Since electroencephalogram(EEG) has non-linear and non-stationary properties, it is effective to analyze the characteristic of EEG with time-frequency method rather than spectrum method. In this letter, we propose the modified drowsiness detection system using discrete wavelet transform combined with errors-in-variables and multilayer perceptron methods. For the comparison of the proposed scheme with the previous one, the state 'others' is added to the previous states of drivers: 'alertness,' 'transition,' and 'drowsiness.' From the computer simulation using machine learning, we confirm that the proposed scheme outperforms the previous one for some conditions.