• The Korean Journal of Applied Statistics
• /
• v.27 no.7
• /
• pp.1257-1268
• /
• 2014

Since the introduction of KTX (Korea Tranin eXpress) in Korea reilway market, number of passengers using KTX has been greatly increased in the market. Thus, demand forecasting for KTX passengers has been played a importantant role in the train operation and management. In this paper, we study several time series models and compare the models based on considering special days and others. We used the MAPE (Mean Absolute Percentage Errors) to compare the performance between the models and we showed that the Reg-AR-GARCH model outperformanced other models in short-term period such as one month. In the longer periods, the Reg-ARMA model showed best forecasting accuracy compared with other models.

• Hwankyungkyoyuk
• /
• v.14 no.2
• /
• pp.95-105
• /
• 2001

Out-door learning activity in environmental education has been emphasized as an effective method in environmental education since the aims of environmental education emphasize students'value, attitude, actions as well as knowledge. In order to implement successfully out-door learning activity in environmental education classrooms, teachers'perceptions to environmental problems and experiences at fields are essential. An environmental education network among the metropolitan city and provincial office of education, nongovernmental organization of environmental movement and education and university was established and a teachers'in-service training program of out-door learning centered environmental education was implemented. The program was developed in order to 1) connect environmental education with the regional environmental situations, 2) provide teachers with opportunities to participate in an out-door learning program, and 3) train teachers to be environmental education leaders of out-door learning. For evaluation of the program, responses of participants to questionnaire were analyzed. Most of teachers responded that their perception of environment was changed positively after the participation in the program. This study suggested that a future planning of a teachers'in-service training program of out-door learning centered environmental education should be developed in considerations of arranging enough hours for out-door learning at regional environmental sites, applying performance assessment, providing teachers with multiple opportunities with programs in different levels including enriched programs, and establishing an environmental education network among nongovernmental organization of environment movement and education, university, and local offices and department of education.

• The Journal of the Acoustical Society of Korea
• /
• v.11 no.1
• /
• pp.22-34
• /
• 1992

There exists a transform trellis code that is optimal for stationary Gaussian sources and the squared-error distortion measure at all rates. In this paper, we train an asymptotically optimal version of such a code to obtain one which is matched better to the statistics of real world data. The training algorithm uses the M algorithm to search the trellis codebook and the LBG algorithm to update the trellis codebook. We investigate the trained transform trellis coding scheme for the first-order AR(autoregressive) Gaussian source whose correlation coefficient is 0.9 and actual speech sentences. For the first-order AR source, the achieved SNR for the test sequence is from 0.6 to 1.4 dB less than the maximum achievable SNR as given by Shannon's rate-distortion function for this source, depending on the rate and surpasses all previous known results for this source. For actual speech data, to achieve improved performance, we use window functions and gain adaptation at rate 1.0 bits/sample.

• The Journal of the Institute of Internet, Broadcasting and Communication
• /
• v.19 no.6
• /
• pp.227-233
• /
• 2019

Recently, along with the recent development of deep learning technique, neural networks are achieving success in computer vision filed. Convolutional neural network have shown outstanding performance in not only for a simple image classification task, but also for tasks with high difficulty such as object segmentation and detection. However many such deep learning models are based on supervised-learning, which requires more annotation labels than image-level label. Especially image semantic segmentation model requires pixel-level annotations for training, which is very. To solve these problems, this paper proposes a weakly-supervised semantic segmentation method which requires only image level label to train network. Existing weakly-supervised learning methods have limitations in detecting only specific area of object. In this paper, on the other hand, we use multi-classifier deep learning architecture so that our model recognizes more different parts of objects. The proposed method is evaluated using VOC 2012 validation dataset.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.144-150
• /
• 2017

Recently, deep learning is used for intelligent processing and accuracy improvement of data. It is formed calculation model composed of multi data processing layer that train the data representation through an abstraction of the various levels. A category of deep learning, convolution neural network is utilized in various research fields, which are human pose estimation, face recognition, image classification, speech recognition. When using the deep layer and lots of class, CNN that show a good performance on image classification obtain higher classification rate but occur the overfitting problem, when using a few data. So, we design the training network based on convolution neural network and trained our image data set for object classification in few class problem. The experiment show the higher classification rate of 7.06% in average than the previous networks designed to classify the object in 1000 class problem.

• Journal of IKEEE
• /
• v.12 no.1
• /
• pp.65-74
• /
• 2008

One of the popular methods used for pattern classification is the MBR (Memory-Based Reasoning) algorithm. Since it simply computes distances between a test pattern and training patterns or hyperplanes stored in memory, and then assigns the class of the nearest training pattern, it is notorious for memory usage and can't learn additional information from new data. In order to overcome this problem, we propose an incremental learning algorithm (iMPA). iMPA divides the entire pattern space into fixed number partitions, and generates representatives from each partition. Also, due to the fact that it can not learn additional information from new data, we present iMPA which can learn additional information from new data and not require access to the original data, used to train. Proposed methods have been successfully shown to exhibit comparable performance to k-NN with a lot less number of patterns and better result than EACH system which implements the NGE theory using benchmark data sets from UCI Machine Learning Repository.

• Journal of Korean Society of Forest Science
• /
• v.109 no.1
• /
• pp.23-30
• /
• 2020

The use of increased computing power, machine learning, and deep learning techniques have dramatically increased in various sectors. In particular, image detection algorithms are broadly used in forestry and remote sensing areas to identify forest types and tree species. However, in South Korea, machine learning has rarely, if ever, been applied in forestry image detection, especially to classify tree species. This study integrates the application of machine learning and forest image detection; specifically, we compared the ability of two machine learning data collection methods, namely image data captured by forest experts (D1) and web-crawling (D2), to automate the classification of five trees species. In addition, two methods of characterization to train/test the system were investigated. The results indicated a significant difference in classification accuracy between D1 and D2: the classification accuracy of D1 was higher than that of D2. In order to increase the classification accuracy of D2, additional data filtering techniques were required to reduce the noise of uncensored image data.

• Transactions of the Korean Society for Noise and Vibration Engineering
• /
• v.18 no.5
• /
• pp.558-563
• /
• 2008

Vibration/shock affects biggest taking a train subtraction of vehicle and durability decline. Therefore, absorber is used for vibration/shock isolation and various qualities of the material and design are applied to isolation. This paper proposes vibration/shock absorber that applies 'Disc' spring. Through comparison with 'Disc' spring that has nonlinearity and coil spring that is having linearity, see effect that nonlinearity of isolation gets in vibration/shock Isolation. Coil spring and 'Disc' spring are non-linear numerical analysis and simulation through theory for this, get and investigate comparison result through an experiment finally. Expressed and formulated shock through 'Runge-Kutta' method/impact response to nonlinear-vibration-equation of 1 degree of freedom for numerical analysis. Double half sine pulse of excitation used and analyzed result through spectrum response analysis here. Response of disc spring is compared to response of coil spring by changing $h_o/t$ ratio with computer simulation and the usage of disc spring is increased through analysis of effect of design factors. The purpose of this paper is that the shock response of disc spring is calculated through numerical simulation and to design the optimal absorber under the limited condition. And then, the isolation effect was analyzed through the shock test.

• Proceedings of the Korean Society for Noise and Vibration Engineering Conference
• /
• 2008.04a
• /
• pp.990-993
• /
• 2008

Vibration/shock affects biggest taking a train subtraction of vehicle and durability decline. Therefore, absorber is used for vibration/shock isolation and various qualities of the material and design are applied to isolation. This paper proposes vibration/shock absorber that applies 'Disc'spring. Through comparison with 'Disc' spring that has nonlinearity and coil spring that is having linearity, see effect that nonlinearity of isolation gets in vibration/shock isolation. Coil spring and 'Disc' spring are non-linear numerical analysis and simulation through theory for this, get and investigate comparison result through an experiment finally. Expressed and formulated shock through 'Runge-Kutta' method/impact response to nonlinear-vibration-equation of 1 degree of freedom for numerical analysis. Double half sine pulse of excitation used and analyzed result through spectrum response analysis here. Response of disc spring is compared to response of coil spring by changing ho/t ratio with computer simulation and the usage of disc spring is increased through analysis of effect of design factors. The purpose of this paper is that the shock response of disc spring is calculated through numerical simulation and to design the optimal absorber under the limited condition. And then, the isolation effect was analyzed through the shock test.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.48 no.2
• /
• pp.102-108
• /
• 2011

The existing vessels lighting control system has several problems, which are complexity of construction and high cost of establishment and maintenance. In this paper, We designed low cost and high performance lighting control system at digital vessel environment. We proposed a system which recognize the user's emotions after obtaining the biological informations about user's bio information(pulse sensor, blood pressure sensor, blood sugar sensor etc) through wireless sensors controls the LED Lights. This system classified emotions using backpropagation algorithm. We chose 3,000 data sets to train the backpropagation algorithm. As a result, obtained about 88.7% accuracy. And the classified emotions find the most appropriate point in the method of controlling the waves or frequencies to the red, green, blue LED Lamp comparing with the 20-color-emotion models in the HP's 'The meaning of color' and control the brightness or contrast of the LED Lamp. In this method, the system saved about 20% of the electricity consumed.