• Journal of Korea Multimedia Society
• /
• v.13 no.11
• /
• pp.1643-1656
• /
• 2010

It is necessary to develop a system to judge inferiority of goods to minimize the loss at small factories in which produces various kinds of goods with small amounts. That system can be developed based on HTM theory. HTM is a model to apply the operation principles of the neocortex in human brain to the machine learning. We have to build the trained HTM network to use the HTM-based machine learning system. It requires the knowledge for the HTM theory. This paper presents the design and implementation of the training system to support the development of HTM networks which recognize the molding parts to judge its badness. This training system allows field technicians to train the HTM network with high accuracy without the knowledge of the HTM theory. It also can be applied to any kind of the HTM-based judging systems for molding parts.

• KIISE Transactions on Computing Practices
• /
• v.24 no.3
• /
• pp.138-144
• /
• 2018

A video is a vivid medium similar to human's visual-linguistic experiences, since it can inculcate a sequence of situations, actions or dialogues that can be told as a story. In this study, we propose story learning/regeneration frameworks from videos with successive event order supervision for contextual coherence. The supervision induces each episode to have a form of trajectory in the latent space, which constructs a composite representation of ordering and semantics. In this study, we incorporated the use of kids videos as a training data. Some of the advantages associated with the kids videos include omnibus style, simple/explicit storyline in short, chronological narrative order, and relatively limited number of characters and spatial environments. We build the encoder-decoder structure with successive event order embedding, and train bi-directional LSTMs as sequence models considering multi-step sequence prediction. Using a series of approximately 200 episodes of kids videos named 'Pororo the Little Penguin', we give empirical results for story regeneration tasks and SEOE. In addition, each episode shows a trajectory-like shape on the latent space of the model, which gives the geometric information for the sequence models.

• Journal of the Korea Computer Industry Society
• /
• v.2 no.11
• /
• pp.1483-1494
• /
• 2001

In this rapidly changing information society, the needs for professional technicians in IT-related industrial fields are increasing, but the supplies of such men are not enough. A well-designed educational program is required in order to produce outstanding technicians in this up-to-date information-centered industrial environment. It is widely recognized that the educational program of two-year level college today should be improved because it has been mainly oriented to train or exercise short-term skills with a few basic theory. With this educational program, it is not easy to achieve the original educational goal to cultivate and to produce the specialists to be equipped with both technological and intellectual skills. Therefore, new three-year academic educational program is expected to accomplish that goal. This paper is aimed to offer a model of a new educational program on three-year academic system, which would help to meet IT industry's requirements.

• Journal of Korean Society of Environmental Engineers
• /
• v.33 no.12
• /
• pp.893-899
• /
• 2011

The occurrence of THMs, the characteristics of THMs formation and removal of THMs were investigated. The treatment train of M plant consists of prechlorination, flocculation, sedimentation, filtration, ozonation, activated carbon and postchlorination. The study of THM formation indicated that about 92% of the THMs were formed in the flocculation/sedimentation/filtration process which affected by prechlorination. The formation of THMs was highly correlated to $KMnO_4$ consumption and water temperature in raw water. The regression model had showed 0.72~0.80 of determination coefficient so it could be used to predict the amount of THMs formation in finished water. Compared to the prechlorination process, the THMs formation was reduced in interchlorination process. With the addition of PAC, fewer THMs were formed in PAC-chlorination process than in chlorination-PAC process. Our results showed that air stripping could be used to remove the existing THMs.

• Journal of the Korean Society for Railway
• /
• v.15 no.1
• /
• pp.17-22
• /
• 2012

Installation of screen doors at platform ensures safety of passengers by separating platform from tracks. Besides, it reduces drought and air pressure caused by train conserves heating and cooling energy in the station. In order to guarantee safety of platform screen doors, design considering evaluation of wind pressure requires. In this study, Sosa station, semisealed screen door and EMU are analyzed to estimate the wind pressure of platform screen doors model. Also Sosa station is influenced by climatic condition because it exposed to outside. Therefore, analysis on the wind pressure of platform screen doors is performed under the worst weather condition such as typhoon. The results of analysis, Maximum inside pressure 287 Pa, and consideration of outside pressure as typhoon to the maximum design pressure of 865 Pa 2756.25 Pa conditions approximately 3.1 times the difference can be seen that ensure stability.

• Journal of Welding and Joining
• /
• v.11 no.2
• /
• pp.27-41
• /
• 1993

The estimation of nugget sizes was attempted by utilizing the artificial neural networks method. Artificial neural networks is a highly simplified model of the biological nervous system. Artificial neural networks is composed of a large number of elemental processors connected like biological neurons. Although the elemental processors have only simple computation functions, because they are connected massively, they can describe any complex functional relationship between an input-output pair in an autonomous manner. The electrode head movement signal, which is a good indicator of corresponding nugget size was determined by measuring the each test specimen. The sampled electrode movement data and the corresponding nugget sizes were fed into the artificial neural networks as input-output pairs to train the networks. In the training phase for the networks, the artificial neural networks constructs a fuctional relationship between the input-output pairs autonomusly by adjusting the set of weights. In the production(estimation) phase when new inputs are sampled and presented, the artificial neural networks produces appropriate outputs(the estimates of the nugget size) based upon the transfer characteristics learned during the training mode. Experimental verification of the proposed estimation method using artificial neural networks was done by actual destructive testing of welds. The predicted result by the artifficial neural networks were found to be in a good agreement with the actual nugget size. The results are quite promising in that the real-time estimation of the invisible nugget size can be achieved by analyzing the process variable without any conventional destructive testing of welds.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.1
• /
• pp.38-49
• /
• 2017

In general, railroad operation companies sell tickets to maximize their profits by applying the ticketing release time (when selling any tickets regardless of trip distances). This study is to analyze the effect of the release time on KTX ticket reservation behavior. The reservation behavior in this study means the reservation time calculated by difference between ticketing time and departure time. The data come from KTX ticket sales data of Gyeongbu-line for a week including Saturday and Sunday. The results show that the factors to affect the reservation time are day of the week, trip distance and operation direction, in addition to the release time. Furthermore, most of tickets were reserved three hours before their departure time, and most of the up line weekend users reserved their tickets a day before the departure time. Before the release time, reservation time was affected by up line and long distance travel. On the other hand, after the release time, it was affected by long distance travel and Sunday.

• 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.

• Proceedings of the Korean Geotechical Society Conference
• /
• 2004.03b
• /
• pp.154-161
• /
• 2004

The flat dilatometer test(DMT) is a geotechnical tool to estimate in-situ properties of various types of ground materials. The undrained shear strength is known to be the most reliable and useful parameter obtained by DMT. However, the existing relationships which were established for other local deposits depend on the regional geotechnical characteristics. In addition, the flat dilatometer test results have been interpreted using three intermediate indicesmaterial index($I_p$), horizontal stres index($K_p$), and dilatometer modulus($E_p$) and the undrained shear strength is estimated only by using the horizontal stress index($K_D$). In this paper, an artificial neural network was developed to evaluate the undrained shear strength by DMT and the ANN, based on the $p_0,\;p_1,\;p_2,\;{\sigma}'_v_0$, and porewater pressure. The ANN which adopts the back-propagation algorithm was trained based on the DMT data obtained from Korean soft clay. To investigate the feasibility of ANN model, the prediction results obtained from data which were not used to train the ANN and those obtained from existing relationships were compared.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.37 no.2A
• /
• pp.95-104
• /
• 2012

Pattern recognition using ensemble classifiers is composed of strong classifier which consists of many weak classifiers. In this paper, we used feature extraction to organize strong classifier using static camera sequence. The strong classifier is made of weak classifiers which considers environmental factors. So the strong classifier overcomes environmental effect. Proposed method uses binary foreground image by frame difference method and the boosting is used to train crowdedness model and recognize crowdedness using features. Combination of weak classifiers makes strong ensemble classifier. The classifier could make use of potential features from the environment such as shadow and reflection. We tested the proposed system with road sequence and subway platform sequence which are included in "AVSS 2007" sequence. The result shows good accuracy and efficiency on complex environment.