• Journal of the Semiconductor & Display Technology
• /
• v.20 no.3
• /
• pp.131-135
• /
• 2021

Numbers of studies related to optimization of design of organic light emitting diodes(OLED) through machine learning are increasing. We propose the generative method of the image to assess the performance of the device combining with machine learning technique. Principle parameter regarding dark spot growth mechanism of the OLED can be the key factor to determine the long-time performance. Captured images from actual device and randomly generated images at specific time and initial pinhole state are fed into the deep neural network system. The simulation reinforced by the machine learning technique can predict the device parameters accurately and faster. Similarly, the inverse design using multiple layer perceptron(MLP) system can infer the initial degradation factors at manufacturing with given device parameter to feedback the design of manufacturing process.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.4
• /
• pp.126-129
• /
• 2020

We introduce a lifetime assessment technique using deep learning algorithm with complex electrical parameters such as resistivity, permittivity, impedance parameters as integrated indicators for predicting the degradation of the organic molecules. The evaluation system consists of fully automated in-situ measurement system and multiple layer perceptron learning system with five hidden layers and 1011 perceptra in each layer. Prediction accuracies are calculated and compared depending on the physical feature, learning hyperparameters. 62.5% of full time-series data are used for training and its prediction accuracy is estimated as r-square value of 0.99. Remaining 37.5% of the data are used for testing with prediction accuracy of 0.95. With k-fold cross-validation, the stability to the instantaneous changes in the measured data is also improved.

• The Journal of Korea Robotics Society
• /
• v.12 no.2
• /
• pp.206-216
• /
• 2017

This paper proposes a method to simultaneously estimate two degrees of freedom in wrist forces (extension - flexion, adduction - abduction) and one degree of freedom in grasping forces using Electromyography (EMG) signals of the forearms. To correlate the EMG signals with the forces, we applied a multi - layer perceptron(MLP), which is a machine learning method, and used the characteristics of the muscles constituting the forearm to generate learning data. Through the experiments, the similarity between the MLP target value and the estimated value was investigated by applying the coefficient of determination ($R^2$) and root mean square error (RMSE) to evaluate the performance of the proposed method. As a result, the $R^2$ values with respect to the wrist flexion-extension, adduction - abduction and grasping forces were 0.79, 0.73 and 0.78 and RMSE were 0.12, 0.17, 0.13 respectively.

• The Transactions of the Korean Institute of Electrical Engineers
• /
• v.40 no.8
• /
• pp.782-791
• /
• 1991

In the fields of pattern recognition such as speech recognition, several new techniques using Artifical Neural network Models have been proposed and implemented. In particular, the Multilayer Perception Model has been shown to be effective in static speech pattern recognition. But speech has dynamic or temporal characteristics and the most important point in implementing speech recognition systems using Artificial Neural Network Models for continuous speech is the learning of dynamic characteristics and the distributed cues and contextual effects that result from temporal characteristics. But Recurrent Multilayer Perceptron Model is known to be able to learn sequence of pattern. In this paper, the results of applying the Recurrent Model which has possibilities of learning tedmporal characteristics of speech to phoneme recognition is presented. The test data consist of 144 Vowel+ Consonant + Vowel speech chains made up of 4 Korean monothongs and 9 Korean plosive consonants. The input parameters of Artificial Neural Network model used are the FFT coefficients, residual error and zero crossing rates. The Baseline model showed a recognition rate of 91% for volwels and 71% for plosive consonants of one male speaker. We obtained better recognition rates from various other experiments compared to the existing multilayer perceptron model, thus showed the recurrent model to be better suited to speech recognition. And the possibility of using Recurrent Models for speech recognition was experimented by changing the configuration of this baseline model.

• Journal of Institute of Control, Robotics and Systems
• /
• v.19 no.11
• /
• pp.1022-1028
• /
• 2013

It is well knowns that based on the CSP (Common Spatial Pattern) algorithm, the linear projection of an EEG (Electroencephalography) signal can be made to spaces that optimize the discriminant between two patterns. Sharing disadvantages from linear time invariant systems, CSP suffers from the non-stationary nature of EEGs causing the performance of the classification in a BCI (Brain-Computer Interface) system to drop significantly when comparing the training data and test data. The author has suggested a simple idea based on the parallel model of CSP filters to improve the performance of BCI systems. The model was tested with a simple CSP algorithm (without any elaborate regularizing methods) and a perceptron learning algorithm as a classifier to determine the improvement of the system. The simulation showed that the parallel model could improve classification performance by over 10% compared to conventional CSP methods.

• Journal of Information Processing Systems
• /
• v.12 no.3
• /
• pp.436-454
• /
• 2016

This research presents the battery discharge rate models for the energy consumption of mobile phone batteries based on machine learning by taking into account three usage patterns of the phone: the standby state, video playing, and web browsing. We present the experimental design methodology for collecting data, preprocessing, model construction, and parameter selections. The data is collected based on the HTC One X hardware platform. We considered various setting factors, such as Bluetooth, brightness, 3G, GPS, Wi-Fi, and Sync. The battery levels for each possible state vector were measured, and then we constructed the battery prediction model using different regression functions based on the collected data. The accuracy of the constructed models using the multi-layer perceptron (MLP) and the support vector machine (SVM) were compared using varying kernel functions. Various parameters for MLP and SVM were considered. The measurement of prediction efficiency was done by the mean absolute error (MAE) and the root mean squared error (RMSE). The experiments showed that the MLP with linear regression performs well overall, while the SVM with the polynomial kernel function based on the linear regression gives a low MAE and RMSE. As a result, we were able to demonstrate how to apply the derived model to predict the remaining battery charge.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.33 no.8B
• /
• pp.707-718
• /
• 2008

The methodology of classifying traffics is changing from payload based or port based to machine learning based in order to overcome the dynamic changes of application's characteristics. However, current state of traffic classification using machine learning (ML) algorithms is ongoing under the offline environment. Specifically, most of the current works provide results of traffic classification using cross validation as a test method. Also, they show classification results based on traffic flows. However, these traffic classification results are not useful for practical environments of the network traffic monitoring. This paper compares the classification results using cross validation with those of using split validation as the test method. Also, this paper compares the classification results based on flow to those based on bytes. We classify network traffics by using various feature sets and machine learning algorithms such as J48, REPTree, RBFNetwork, Multilayer perceptron, BayesNet, and NaiveBayes. In this paper, we find the best feature sets and the best ML algorithm for classifying traffics using the split validation.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.179-186
• /
• 2023

For the future prosperity of any society, the sound growth of children is essential. Autism Spectrum Disorder (ASD) is a neurobehavioral disorder which has an impact on social interaction of autistic child and has an undesirable effect on his learning, speaking, and responding skills. These children have over or under sensitivity issues of touching, smelling, and hearing. Its symptoms usually appear in the child of 4- to 11-year-old but parents did not pay attention to it and could not detect it at early stages. The process to diagnose in recent time is clinical sessions that are very time consuming and expensive. To complement the conventional method, machine learning techniques are being used. In this way, it improves the required time and precision for diagnosis. We have applied TFLite model on image based dataset to predict the autism based on facial features of child. Afterwards, various machine learning techniques were trained that includes Logistic Regression, KNN, Gaussian Naïve Bayes, Random Forest and Multi-Layer Perceptron using Autism Spectrum Quotient (AQ) dataset to improve the accuracy of the ASD detection. On image based dataset, TFLite model shows 80% accuracy and based on AQ dataset, we have achieved 100% accuracy from Logistic Regression and MLP models.

• The Journal of Bigdata
• /
• v.6 no.2
• /
• pp.39-49
• /
• 2021

Recently, large and diverse weather data are being collected by sensors from various sources. Efforts to predict the concentration of fine dust through machine learning are being made everywhere, and this study intends to compare PM10 and PM2.5 prediction models using data from 840 outdoor air meters installed throughout the city. Information can be provided in real time by predicting the concentration of fine dust after 5 minutes, and can be the basis for model development after 10 minutes, 30 minutes, and 1 hour. Data preprocessing was performed, such as noise removal and missing value replacement, and a derived variable that considers temporal and spatial variables was created. The parameters of the model were selected through the response surface method. XGBoost, Random Forest, and Deep Learning (Multilayer Perceptron) are used as predictive models to check the difference between fine dust concentration and predicted values, and to compare the performance between models.

• The Journal of the Acoustical Society of Korea
• /
• v.28 no.1
• /
• pp.32-43
• /
• 2009

In this paper, we improve the performance of cardiac disorder classification by continuous heart sound signals using automatic segmentation and extreme learning machine (ELM). The accuracy of the conventional cardiac disorder classification systems degrades because murmurs and click sounds contained in the abnormal heart sound signals cause incorrect or missing starting points of the first (S1) and the second heart pulses (S2) in the automatic segmentation stage, In order to reduce the performance degradation due to segmentation errors, we find the positions of the S1 and S2 pulses, modify them using the time difference of S1 or S2, and extract a single period of heart sound signals. We then obtain a feature vector consisting of the mel-scaled filter bank energy coefficients and the envelope of uniform-sized sub-segments from the single-period heart sound signals. To classify the heart disorders, we use ELM with a single hidden layer. In cardiac disorder classification experiments with 9 cardiac disorder categories, the proposed method shows the classification accuracy of 81.6% and achieves the highest classification accuracy among ELM, multi-layer perceptron (MLP), support vector machine (SVM), and hidden Markov model (HMM).