• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.4
• /
• pp.1123-1146
• /
• 2023

In South Korea, there have been many studies on efficient building-energy management using renewable energy facilities in single zero-energy houses or buildings. However, such management was limited due to spatial and economic problems. To realize a smart zero-energy city, studying efficient energy integration for the entire city, not just for a single house or building, is necessary. Therefore, this study was conducted in the eco-friendly energy town of Chungbuk Innovation City. Chungbuk successfully realized energy independence by converging new and renewable energy facilities for the first time in South Korea. This study analyzes energy data collected from public buildings in that town every minute for a year. We propose a smart city building-energy management model based on the results that combine various renewable energy sources with grid power. Supervised learning can determine when it is best to sell surplus electricity, or unsupervised learning can be used if there is a particular pattern or rule for energy use. However, it is more appropriate to use reinforcement learning to maximize rewards in an environment with numerous variables that change every moment. Therefore, we propose a power distribution algorithm based on reinforcement learning that considers the sales of Energy Storage System power from surplus renewable energy. Finally, we confirm through economic analysis that a 10% saving is possible from this efficiency.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.6
• /
• pp.1103-1108
• /
• 2023

In this paper, we propose a new algorithm for attenuating the background noises in acoustic signal. This algorithm improves the noise attenuation performance by using the FNN(: Full-connected Neural Network) deep learning algorithm instead of the existing adaptive filter after wavelet transform. After wavelet transforming the input signal for each short-time period, noise is removed from a single input audio signal containing noise by using a 1024-1024-512-neuron FNN deep learning model. This transforms the time-domain voice signal into the time-frequency domain so that the noise characteristics are well expressed, and effectively predicts voice in a noisy environment through supervised learning using the conversion parameter of the pure voice signal for the conversion parameter. In order to verify the performance of the noise reduction system proposed in this study, a simulation program using Tensorflow and Keras libraries was written and a simulation was performed. As a result of the experiment, the proposed deep learning algorithm improved Mean Square Error (MSE) by 30% compared to the case of using the existing adaptive filter and by 20% compared to the case of using the STFT(: Short-Time Fourier Transform) transform effect was obtained.

• The KIPS Transactions:PartB
• /
• v.9B no.2
• /
• pp.139-146
• /
• 2002

The robot soccer simulation game is a dynamic multi-agent environment. In this paper we suggest a new reinforcement learning approach to each agent's dynamic positioning in such dynamic environment. Reinforcement learning is the machine learning in which an agent learns from indirect, delayed reward an optimal policy to choose sequences of actions that produce the greatest cumulative reward. Therefore the reinforcement learning is different from supervised learning in the sense that there is no presentation of input-output pairs as training examples. Furthermore, model-free reinforcement learning algorithms like Q-learning do not require defining or learning any models of the surrounding environment. Nevertheless these algorithms can learn the optimal policy if the agent can visit every state-action pair infinitely. However, the biggest problem of monolithic reinforcement learning is that its straightforward applications do not successfully scale up to more complex environments due to the intractable large space of states. In order to address this problem, we suggest Adaptive Mediation-based Modular Q-Learning (AMMQL) as an improvement of the existing Modular Q-Learning (MQL). While simple modular Q-learning combines the results from each learning module in a fixed way, AMMQL combines them in a more flexible way by assigning different weight to each module according to its contribution to rewards. Therefore in addition to resolving the problem of large state space effectively, AMMQL can show higher adaptability to environmental changes than pure MQL. In this paper we use the AMMQL algorithn as a learning method for dynamic positioning of the robot soccer agent, and implement a robot soccer agent system called Cogitoniks.

• Journal of the Korea Convergence Society
• /
• v.8 no.1
• /
• pp.25-34
• /
• 2017

With the recent spread of smartphones and the introduction of web services, online users can access large-scale content regardless of time or place. However, users have had trouble finding the content they wanted among large-scale content. To solve this problem, user modeling and content recommendation system have been actively studied in various fields. However, in spite of active changes in senior groups according to the changes in information environment, research on user modeling and content recommendation system focused on senior groups are insufficient. In this paper, we propose a method of modeling smart senior based on their preference, and further develop a smart senior classification model using machine learning methods. As a result, we can not only grasp the preferences of smart seniors, but also develop a smart senior classification model, which is the foundation for the research of a recommendation system which will provide the activities and contents most suitable for senior groups.

• Journal of Convergence for Information Technology
• /
• v.7 no.1
• /
• pp.55-60
• /
• 2017

In order to provide intelligent services without human intervention in the Internet of Things environment, it is necessary to analyze the big data generated by the IoT device and learn the normal pattern, and to predict the abnormal symptoms such as faulty or malfunction based on the learned normal pattern. The purpose of this study is to implement a machine learning model that can predict product failure by analyzing big data generated in various devices of product process. The machine learning model uses the big data analysis tool R because it needs to analyze based on existing data with a large volume. The data collected in the product process include the information about product faulty, so supervised learning model is used. As a result of the study, I classify the variables and variable conditions affecting the product failure, and proposed a prediction model for the product failure based on the decision tree. In addition, the predictive power of the model was significantly higher in the conformity and performance evaluation analysis of the model using the ROC curve.

• Journal of KIISE
• /
• v.44 no.12
• /
• pp.1275-1281
• /
• 2017

The supervised learning approach is suitable for classification of insulting sentences, but pre-decided training sentences are necessary. Since a Character-level Convolution Neural Network is robust for each character, so is appropriate for classifying abusive sentences, however, has a drawback that demanding a lot of training sentences. In this paper, we propose transfer learning method that reusing the trained filters in the real classification process after the filters get the characteristics of offensive words by generated abusive/normal pair of sentences. We got higher performances of the classifier by decreasing the effects of data shortage and class imbalance. We executed experiments and evaluations for three datasets and got higher F1-score of character-level CNN classifier when applying transfer learning in all datasets.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.15 no.3
• /
• pp.513-520
• /
• 2020

Recently, the development of a vision inspection system using machine learning has become more active. This study seeks to develop a defect inspection model using machine learning. Defect detection problems for images correspond to classification problems, which are the method of supervised learning in machine learning. In this study, defect detection models are developed based on algorithms that automatically extract features and algorithms that do not extract features. One-dimensional CNN and two-dimensional CNN are used as algorithms for automatic extraction of features, and MLP and SVM are used as algorithms for non-extracting features. A defect detection model is developed based on four models and their accuracy and AUC compare based on AUC. Although image classification is common in the development of models using CNN, high accuracy and AUC is achieved when developing SVM models by converting pixels from images into RGB values in this study.

• Journal of Korea Water Resources Association
• /
• v.33 no.4
• /
• pp.505-515
• /
• 2000

THe purpose of this study is to forecast of runoff hydrographs according to rainfall event in a stream. The neural network theory as a hydrologic blackbox model is used to solve hydrological problems. The Back-Propagation(BP) algorithm by the Levenberg-Marquardt(LM) techniques and Radial Basis Function(RBF) network in Neural Network(NN) models are used. Runoff hydrograph is forecasted in Bocheongstream basin which is a IHP the representative basin. The possibility of a simulation for runoff hydrographs about unlearned stations is considered. The results show that NN models are performed to effective learning for rainfall-runoff process of hydrologic system which involves a complexity and nonliner relationships. The RBF networks consist of 2 learning steps. The first step is an unsupervised learning in hidden layer and the next step is a supervised learning in output layer. Therefore, the RBF networks could provide rather time saved in the learning step than the BP algorithm. The peak discharge both BP algorithm and RBF network model in the estimation of an unlearned are a is trended to observed values.

• Healthcare Informatics Research
• /
• v.24 no.4
• /
• pp.309-316
• /
• 2018

Objectives: Both the valence and arousal components of affect are important considerations when managing mental healthcare because they are associated with affective and physiological responses. Research on arousal and valence analysis, which uses images, texts, and physiological signals that employ deep learning, is actively underway; research investigating how to improve the recognition rate is needed. The goal of this research was to design a deep learning framework and model to classify arousal and valence, indicating positive and negative degrees of emotion as high or low. Methods: The proposed arousal and valence classification model to analyze the affective state was tested using data from 40 channels provided by a dataset for emotion analysis using electrocardiography (EEG), physiological, and video signals (the DEAP dataset). Experiments were based on 10 selected featured central and peripheral nervous system data points, using long short-term memory (LSTM) as a deep learning method. Results: The arousal and valence were classified and visualized on a two-dimensional coordinate plane. Profiles were designed depending on the number of hidden layers, nodes, and hyperparameters according to the error rate. The experimental results show an arousal and valence classification model accuracy of 74.65 and 78%, respectively. The proposed model performed better than previous other models. Conclusions: The proposed model appears to be effective in analyzing arousal and valence; specifically, it is expected that affective analysis using physiological signals based on LSTM will be possible without manual feature extraction. In a future study, the classification model will be adopted in mental healthcare management systems.

• Journal of Korea Trade
• /
• v.25 no.5
• /
• pp.110-128
• /
• 2021

Purpose - The essential purpose of this study is to analyze the possibility of substitution of an individual job resulting from technological development represented by the 4th Industrial Resolution, considering the different effects of digital transformation on the labor market. Design/methodology - In order to estimate the substitution probability, this study used two data sets which the job characteristics data for individual occupations provided by KEIS and the information on occupational status of substitution provided by Frey and Osborne(2013). In total, 665 occupations were considered in this study. Of these, 80 occupations had data with labels of substitution status. The primary goal of estimation was to predict the degree of substitution for 607 of 665 occupations (excluding 58 with markers). It utilized three methods a principal component analysis, an unsupervised learning methodology of machine learning, and Ridge and Lasso from supervised learning methodology. After extracting significant variables based on the three methods, this study carried out logistics regression to estimate the probability of substitution for each occupation. Findings - The probability of substitution for other occupational groups did not significantly vary across individual models, and the rank order of the probabilities across occupational groups were similar across models. The mean of three methods of substitution probability was analyzed to be 45.3%. The highest value was obtained using the PCA method, and the lowest value was derived from the LASSO method. The average substitution probability of the trading industry was 45.1%, very similar to the overall average. Originality/value - This study has a significance in that it estimates the job substitution probability using various machine learning methods. The results of substitution probability estimation were compared by industry sector. In addition, This study attempts to compare between trade business and industry sector.