• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1243-1249
• /
• 2019

People who gathered to enjoy a specific event or content are called audiences or spectators, and show various propensity according to the characteristics of the crowd. Although there is such a difference, in general, the number of attendance is directly related to the business aspect, which enables stable financial operation for the sale of contents through various incomes, such as the admission fee and the use of other facilities. Therefore, prediction of audience can be used as a major factor in marketing and budgeting strategies. In this study, we review several existing models for predicting the number of attendance and propose an efficient machine learning model. In addition, we studied daily attendance prediction and abnormal attendance prediction using combine DNN(Deep Neural Network) and RF(Random Forest) model.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.16 no.4
• /
• pp.449-453
• /
• 2006

This paper wishes to present way that can take advantage of parts information of image drawing for efficient maintenance management of facilities efficiently. Information for parts that compose facilities to facilities design drawing has been expressed, and legend character has been written to divide each parts. This paper applies Artificial Intelligence techniques for legend character cognition of image drawing. Finally, apply artificial intelligence techniques to drawing management system to evaluate efficiency of method that propose in this paper that see.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.13 no.1
• /
• pp.45-50
• /
• 2003

Recently, robots technique has been developed remarkably. Emotion recognition is necessary to make an intimate robot. This paper shows the simulator and simulation result which recognize or classify emotions by learning pitch pattern. Also, because the pitch is not sufficient for recognizing emotion, we added acoustic elements. For that reason, we analyze the relation between emotion and acoustic elements. The simulator is composed of the DRNN(Dynamic Recurrent Neural Network), Feature extraction. DRNN is a learning algorithm for pitch pattern.

• Transactions on Control, Automation and Systems Engineering
• /
• v.3 no.4
• /
• pp.223-228
• /
• 2001

We have been developed an intelligent mobile robot with an artificial olfactory function to recognize odours and to track odour source location. This mobile robot also has ben installed an engine for speech recognition and synthesis and is controlled by wireless communication. An artificial olfactory system based on array of 7 gas sensors has been installed in the mobile robot for odour recognition, and 11 gas sensors also are located in the obttom of robot to track odour sources. 3 optical sensors are also in cluded in the intelligent mobile robot, which is driven by 2 D. C. motors, for clash avoidance in a way of direction toward an odour source. Throughout the experimental trails, it is confirmed that the intelligent mobile robot is capable of not only the odour recognition using artificial neural network algorithm, but also the tracking odour source using the step-by-step approach method. The preliminary results are promising that intelligent mobile robot, which has been developed, is applicable to service robot system for environmental monitoring, localization of odour source, odour tracking of hazardous areas etc.

• Journal of the Institute of Electronics Engineers of Korea TC
• /
• v.43 no.9 s.351
• /
• pp.25-31
• /
• 2006

In this paper, a fatality model of car accident using data mining is proposed with the goal of reducing fatality of traffic accident. The analysis results with a proposed fatality model are utilized to improve a technology and environment for driving. For this, traffic accident data are collected, a data mining algorithm is applied to this data, and then, a fatality model of car accident is developed based on the analysis. The training data as well as test data are utilized to develop the fatality model. The important factors to cause fatality in traffic accidents can be investigated using the model. If these factors are taken into account in traffic policies and driving environment, it is expected that the fatality rate of traffic accident can be reduced hereafter.

• Journal of the Institute of Electronics Engineers of Korea TE
• /
• v.39 no.4
• /
• pp.370-378
• /
• 2002

Fuzzy inference which combines numerical data and linguistic data has been used to design adaptive filter algorithms. In adaptive IIR filter design, the fuzzy prefilter is taken account, and applied to both direct and lattice structure. As for the fuzzy inference of the fuzzy filter, the Sugeno's method is employed. As membership functions and inference rules are recursively generated through neural network, the accuracy can be improved. The proposed adaptive algorithm, adaptive IIR filter with fuzzy prefilter, has been applied to adaptive system identification for the purposed of performance test. The evaluations have been carried out with viewpoints of convergence property and tracking properties of the parameter estimation. As a result, the faster convergence and the better coefficients tracking performance than those of the conventional algorithm are shown in case of direct structures.

• Proceedings of the Korean Association of Geographic Inforamtion Studies Conference
• /
• 2010.06a
• /
• pp.283-284
• /
• 2010

강우가 있을 때 토양수분은 증가하여 지표온도의 상승을 억제하고, 강우와 증발산을 통해 토양수분은 대기와 지형을 연결하는 중요한 상태변수(Yoo et al., 2001)가 된다. 이에 따라 물순환의 이해와 적절한 모형의 개발을 위해서는 강우 및 토양수분의 원격측정이 필수적일 뿐 아니라 관측 격자 내에서 일어나는 변화도에 대한 이해가 필요하다(김광섭 외, 2004). 따라서 본 연구에서는 인공위성 원격탐사 자료와 지형자료, 기상관측 자료와 같은 가용자료와 신경망(Neural Network) 모형을 이용하여 우리나라의 토양수분 분포도를 작성하고자 한다. 우선 신뢰도 높은 토양수분 관측자료를 가진 용담댐유역(6개 지점)에 대하여 전체적인 토양수분의 거동을 파악하여 토양수분 추정 모형의 적용 가능성을 확인하였다 이를 사용해서 용담댐 유역의 토양수분 분포와 우리나라 전역에 대한 토양수분 분포도를 추정하고자 한다. 신뢰할 수 있는 지상관측 토양수분 관측치가 다양한 지상조건에 대하여 존재하지 않는 한계에도 불구하고 제시된 토양수분추정 방법은 제한된 가용자료를 사용한 우리나라 전역의 토양수분 추정에 있어 합리적인 접근법이라 판단된다.

• The Bulletin of The Korean Astronomical Society
• /
• v.42 no.2
• /
• pp.60.2-61
• /
• 2017

A Convolutional Neural Network(CNN) is one of the well-known deep-learning methods in image processing and computer vision area. In this study, we apply CNN to two kinds of flare forecasting models: flare classification and occurrence. For this, we consider several pre-trained models (e.g., AlexNet, GoogLeNet, and ResNet) and customize them by changing several options such as the number of layers, activation function, and optimizer. Our inputs are the same number of SOHO)/MDI images for each flare class (None, C, M and X) at 00:00 UT from Jan 1996 to Dec 2010 (total 1600 images). Outputs are the results of daily flare forecasting for flare class and occurrence. We build, train, and test the models on TensorFlow, which is well-known machine learning software library developed by Google. Our major results from this study are as follows. First, most of the models have accuracies more than 0.7. Second, ResNet developed by Microsoft has the best accuracies : 0.77 for flare classification and 0.83 for flare occurrence. Third, the accuracies of these models vary greatly with changing parameters. We discuss several possibilities to improve the models.

• Physical Therapy Korea
• /
• v.22 no.2
• /
• pp.70-80
• /
• 2015

The spinal cord is highly complex, consisting of a specialized neural network that comprised both neuronal and non-neuronal cells. Any kind of injury and/or insult to the spinal cord leads to a series of damaging events resulting in motor and/or sensory deficits below the level of injury. As a result, muscle paralysis (or paresis) leading to muscle atrophy or shrinking of the muscle along with changes in muscle fiber type, and contractile properties have been observed. Traditionally, histology had been used as a gold standard to characterize spinal cord injury (SCI)-induced adaptation in spinal cord and skeletal muscle. However, histology measurements is invasive and cannot be used for longitudinal analysis. Therefore, the use of conventional magnetic resonance imaging (MRI) is promoted to be used as an alternative non-invasive method, which allows the repeated measurements over time and secures the safety against radiation by using radiofrequency pulse. Currently, many of pathological changes and adaptations occurring after SCI can be measured by MRI methods, specifically 3-dimensional MRI with the advanced diffusion tensor imaging technique. Both techniques have shown to be sensitive in measuring morphological and structural changes in skeletal muscle and the spinal cord.

• Proceedings of the Korean Society for Bioinformatics Conference
• /
• 2004.11a
• /
• pp.244-249
• /
• 2004

There have been many attempts to predict the secondary structure content of a protein from its primary sequence, which serves as the first step in a series of bioinformatics processes to gain knowledge of the structure and function of a protein. Most of them assumed that prediction relying on the information of the amino acid composition of a protein can be successful. Several approaches expanded the amount of information by including the pair amino acid composition of two adjacent residues. Recent methods achieved a remarkable improvement in prediction accuracy by using this expanded composition information. The overall average errors of two successful methods were 6.1% and 3.4%. This work was motivated by the observation that evolutionarily related proteins share the similar structure. After manipulating the values of the frequency matrix obtained by running PSI-BLAST, inputs of an artificial neural network were constructed by taking the ratio of the amino acid composition of the evolutionarily related proteins with a query protein to the background probability. Although we did not utilize the expanded composition information of amino acid pairs, we obtained the comparable accuracy, with the overall average error being 3.6%.