• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.2
• /
• pp.61.1-61.1
• /
• 2017

As the application of deep-learning methods has been succeeded in various fields, they have a high potential to be applied to space weather forecasting. Convolutional neural network, one of deep learning methods, is specialized in image recognition. In this study, we apply the AlexNet architecture, which is a winner of Imagenet Large Scale Virtual Recognition Challenge (ILSVRC) 2012, to the forecast of daily solar flare occurrence using the MatConvNet software of MATLAB. Our input images are SOHO/MDI, EIT $195{\AA}$, and $304{\AA}$ from January 1996 to December 2010, and output ones are yes or no of flare occurrence. We consider other input images which consist of last two images and their difference image. We select training dataset from Jan 1996 to Dec 2000 and from Jan 2003 to Dec 2008. Testing dataset is chosen from Jan 2001 to Dec 2002 and from Jan 2009 to Dec 2010 in order to consider the solar cycle effect. In training dataset, we randomly select one fifth of training data for validation dataset to avoid the over-fitting problem. Our model successfully forecasts the flare occurrence with about 0.90 probability of detection (POD) for common flares (C-, M-, and X-class). While POD of major flares (M- and X-class) forecasting is 0.96, false alarm rate (FAR) also scores relatively high(0.60). We also present several statistical parameters such as critical success index (CSI) and true skill statistics (TSS). All statistical parameters do not strongly depend on the number of input data sets. Our model can immediately be applied to automatic forecasting service when image data are available.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.3
• /
• pp.70-77
• /
• 2017

Recently, Internet of Things (IoT) and deep learning techniques have affected video surveillance systems in various ways. The surveillance features that perform detection, tracking, and classification of specific objects in Closed Circuit Television (CCTV) video are becoming more intelligent. This paper presents real-time algorithm that can run in a PC environment using only a low power CPU. Traditional tracking algorithms combine background modeling using the Gaussian Mixture Model (GMM), Hungarian algorithm, and a Kalman filter; they have relatively low complexity but high detection errors. To supplement this, deep learning technology was used, which can be trained from a large amounts of data. In particular, an SRGB(Sequential RGB)-3 Layer CNN was used on tracked objects to emphasize the features of moving people. Performance evaluation comparing the proposed algorithm with existing ones using HOG and SVM showed move-in and move-out error rate reductions by 7.6 % and 9.0 %, respectively.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.7
• /
• pp.1114-1124
• /
• 2015

In this paper, precipitation / non-precipitation pattern classification of meteorological radar data is conducted by using neuro-fuzzy algorithm. Structure expression of meteorological radar data information is analyzed in order to effectively classify precipitation and non-precipitation. Also diverse input variables for designing pattern classifier could be considered by exploiting the quantitative as well as qualitative characteristic of meteorological radar data information and then each characteristic of input variables is analyzed. Preferred pattern classifier can be designed by essential input variables that give a decisive effect on output performance as well as model architecture. As the proposed model architecture, neuro-fuzzy algorithm is designed by using FCM-based radial basis function neural network(RBFNN). Two parts of classifiers such as instance classifier part and echo classifier part are designed and carried out serially in the entire system architecture. In the instance classifier part, the pattern classifier identifies between precipitation and non-precipitation data. In the echo classifier part, because precipitation data information identified by the instance classifier could partially involve non-precipitation data information, echo classifier is considered to classify between them. The performance of the proposed classifier is evaluated and analyzed when compared with existing QC method.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.61 no.11
• /
• pp.1758-1764
• /
• 2012

A large number of wire rope has been used in various inderstiries as Cranes and Elevators from expanding the scale of the industrial market. But now, the management of wire rope is used as manually operated by rope replacement from over time or after the accident.It is caused to major accidents as well as economic losses and personal injury. Therefore its time to need periodic fault diagnosis of wire rope or supply of real-time monitoring system. Currently, there are several methods has been reported for fault diagnosis method of the wire rope, to find out the feature point from extracting method is becoming more common compared to time wave and model-based system. This method has implemented a deterministic modeling like the observer and neural network through considering the state of the system as a deterministic signal. However, the out-put of real system has probability characteristics, and if it is used as a current method on this system, the performance will be decreased at the real time. And if the random noise is occurred from unstable measure/experiment environment in wire rope system, diagnostic criterion becomes unclear and accuracy of diagnosis becomes blurred. Thus, more sophisticated techniques are required rather than deterministic fault diagnosis algorithm. In this paper, we developed the fault diagnosis of the wire rope using probability density estimation techniques algorithm. At first, The steady-state wire rope fault signal detection is defined as the probability model through probability distribution estimate. Wire rope defects signal is detected by a hall sensor in real-time, it is estimated by proposed probability estimation algorithm. we judge whether wire rope has defection or not using the error value from comparing two probability distribution.

• Journal of Korea Water Resources Association
• /
• v.37 no.6
• /
• pp.449-460
• /
• 2004

The purpose of this study is to test the applicability of neuro-fuzzy system for monthly dam inflow forecasts by using weather forecasting information. The neuro-fuzzy algorithm adopted in this study is the ANFIS(Adaptive neuro-fuzzy Inference System) in which neural network theory is combined with fuzzy theory. The ANFIS model can experience the difficulties in selection of a control rule by a space partition because the number of control value increases rapidly as the number of fuzzy variable increases. In an effort to overcome this drawback, this study used the subtractive clustering which is one of fuzzy clustering methods. Also, this study proposed a method for converting qualitative weather forecasting information to quantitative one. ANFIS for monthly dam inflow forecasts was tested in cases of with or without weather forecasting information. It can be seen that the model performances obtained from the use of past observed data and future weather forecasting information are much better than those from past observed data only.

• Journal of Internet Computing and Services
• /
• v.20 no.6
• /
• pp.65-72
• /
• 2019

Data augmentation is a method that increases the amount of data through various algorithms based on a small amount of sample data. When machine learning and deep learning techniques are used to solve real-world problems, there is often a lack of data sets. The lack of data is at greater risk of underfitting and overfitting, in addition to the poor reflection of the characteristics of the set of data when learning a model. Thus, in this paper, through the layer-wise data augmenting method at each layer of deep neural network, the proposed method produces augmented data that is substantially meaningful and shows that the method presented by the paper through experimentation is effective in the learning of the model by measuring whether the method presented by the paper improves classification accuracy.

• Journal of the Institute of Convergence Signal Processing
• /
• v.20 no.4
• /
• pp.226-231
• /
• 2019

A WTCI is an important criteria for evaluating an mount of patient's tongue coating in tongue diagnosis. However, Previous WTCI tongue coating evaluation methods is a most of quantitatively measuring ration of the extracted tongue coating region and tongue body region, which has a non-objective measurement problem occurring by exposure conditions of tongue image or the recognition performance of tongue coating. Therefore, a WTCI based on deep learning is proposed for classifying an amount of tonger coating in this paper. This is applying the AI deep learning method using big data. to WTCI for evaluating an amount of tonger coating. In order to verify the effectiveness performance of the deep learning in tongue coating evaluating method, we classify the 3 types class(no coating, some coating, intense coating) of an amount of tongue coating by using CNN model. As a results by testing a building the tongue coating sample images for learning and verification of CNN model, proposed method is showed 96.7% with respect to the accuracy of classifying an amount of tongue coating.

• Journal of Korean Society of Environmental Engineers
• /
• v.37 no.1
• /
• pp.1-6
• /
• 2015

The purpose of this study is to suggest the effective operation method by developing prediction model for the gas production rate, an indicator of the effectiveness of anaerobic digestion tank, using data mining. At the result, gas production estimate model is developed by using ANN within 10% error. It is expected to help operation of anaerobic digestion by suggesting selected parameter. Meanwhile case based reasoning is applied to develop dewatering cake management technology. Case based reasoning uses the most similar examples of past when a new problem occurs, therefore in this study, management measures are developed that proposes dewatering cake minimization with the minimum change by applying the case based reasoning to sludge disposal process.

• Journal of Digital Convergence
• /
• v.16 no.10
• /
• pp.205-212
• /
• 2018

With the development of high performance CPU / GPU, artificial intelligence algorithms such as deep neural networks, and a large amount of data, machine learning has been extended to various applications. In particular, a large amount of data collected from the Internet of Things, social network services, web pages, and public data is accelerating the use of machine learning. Learning data sets for machine learning exist in various formats according to application fields and data types, and thus it is difficult to effectively process data and apply them to machine learning. Therefore, this paper studied a method for building a learning data set for machine learning in accordance with standardized procedures. This paper first analyzes the requirement of learning data set according to problem types and data types. Based on the analysis, this paper presents the reference model to build learning data set for machine learning applications. This paper presents the target standardization organization and a standard development strategy for building learning data set.

• The Transactions of the Korean Institute of Electrical Engineers P
• /
• v.59 no.3
• /
• pp.279-287
• /
• 2010

Interior permanent magnet synchronous motor(IPMSM) adjustable speed drives offer significant advantages over induction motor drives in a wide variety of industrial applications such as high power density, high efficiency, improved dynamic performance and reliability. This paper proposes efficiency optimization control of IPMSM drive using adaptive fuzzy learning controller(AFLC). In order to optimize the efficiency the loss minimization algorithm is developed based on motor model and operating condition. The d-axis armature current is utilized to minimize the losses of the IPMSM in a closed loop vector control environment. The design of the current based on adaptive fuzzy control using model reference and the estimation of the speed based on neural network using ANN controller. The controllable electrical loss which consists of the copper loss and the iron loss can be minimized by the optimal control of the armature current. The minimization of loss is possible to realize efficiency optimization control for the proposed IPMSM. The optimal current can be decided according to the operating speed and the load conditions. This paper considers the design and implementation of novel technique of high performance speed control for IPMSM using AFLC. Also, this paper proposes speed control of IPMSM using AFLC1, current control of AFLC2 and AFLC3, and estimation of speed using ANN controller. The proposed control algorithm is applied to IPMSM drive system controlled AFLC, the operating characteristics controlled by efficiency optimization control are examined in detail.