• Journal of the Korean Academic Society of Industrial Cluster
• /
• v.4 no.1
• /
• pp.1-13
• /
• 2010

The T-DMB which was developed by the convergence of digital broadcasting technology and communication technology provides us with very good quality of music like CD, and provides TV services in a super express train like the KTX whose velocity is over 300 Km per hour. The T-DMB is diffusing toward the world as a technology which is be able to provide the various convergent services of broadcasting and communication through mobile phone, PDA, dedicated terminal, and so on. A business model needed for the diffusion of the T-DMB toward the world was established and utilized to expand the T-DMB into Vietnam in the paper. In addition, this paper describes a case for the establishment of the T-DMB system in order to provide the paid services in Vietnam. It is expected that the expansion of the T-DMB into Vietnam will make a great contribution to the diffusion of the T-DMB toward the world.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.87-91
• /
• 2005

The cascade-correlation (CC) learning algorithm of Fahlman and Lebiere is one of the most influential constructive algorithm in a neural network. Cascading the hidden neurons results in a network that can represent very strong nonlinearities. Although this power is in principle useful, it can be a disadvantage if such strong nonlinearity is not required to solve the problem. 3 models are presented and compared empirically. All of them are based on valiants of the cascade architecture and output neurons weights training of the CC algorithm. Empirical results indicate the followings： (1) In the pattern classification, the model that train only new hidden neuron to output layer connection weights shows the best predictive ability; (2) In the function approximation, the model that removed input-output connection and used sigmoid-linear activation function is better predictability than CasCor algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.8
• /
• pp.3567-3582
• /
• 2020

Human activities are often affected by weather conditions. Automatic weather recognition is meaningful to traffic alerting, driving assistance, and intelligent traffic. With the boost of deep learning and AI, deep convolutional neural networks (CNN) are utilized to identify weather situations. In this paper, a three-channel convolutional neural network (3C-CNN) model is proposed on the basis of ResNet50.The model extracts global weather features from the whole image through the ResNet50 branch, and extracts the sky and ground features from the top and bottom regions by two CNN5 branches. Then the global features and the local features are merged by the Concat function. Finally, the weather image is classified by Softmax classifier and the identification result is output. In addition, a medium-scale dataset containing 6,185 outdoor weather images named WeatherDataset-6 is established. 3C-CNN is used to train and test both on the Two-class Weather Images and WeatherDataset-6. The experimental results show that 3C-CNN achieves best on both datasets, with the average recognition accuracy up to 94.35% and 95.81% respectively, which is superior to other classic convolutional neural networks such as AlexNet, VGG16, and ResNet50. It is prospected that our method can also work well for images taken at night with further improvement.

• Smart Structures and Systems
• /
• v.26 no.1
• /
• pp.35-47
• /
• 2020

This paper proposes the use of transmissibility functions combined with a machine learning algorithm, Artificial Neural Networks (ANNs), to assess damage in a truss bridge. A new approach method, which makes use of the input parameters calculated from the transmissibility function, is proposed. The network not only can predict the existence of damage, but also can classify the damage types and identity the location of the damage. Sensors are installed in the truss joints in order to measure the bridge vibration responses under train and ambient excitations. A finite element (FE) model is constructed for the bridge and updated using FE software and experimental data. Both single damage and multiple damage cases are simulated in the bridge model with different scenarios. In each scenario, the vibration responses at the considered nodes are recorded and then used to calculate the transmissibility functions. The transmissibility damage indicators are calculated and stored as ANNs inputs. The outputs of the ANNs are the damage type, location and severity. Two machine learning algorithms are used; one for classifying the type and location of damage, whereas the other for finding the severity of damage. The measurements of the Nam O bridge, a truss railway bridge in Vietnam, is used to illustrate the method. The proposed method not only can distinguish the damage type, but also it can accurately identify damage level.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.40 no.6
• /
• pp.90-97
• /
• 2003

This paper proposes a speech recognition based on HMM(Hidden Markov Model) using FSVQ(First Section Vector Quantization) and fuzzy concept. In the proposed paper, we generate codebook of First Section, and then obtain multi-observation sequences by order of large propabilistic values based on fuzzy rule from the codebook of the first section. Thereafter, this observation sequences of first section from codebooks is trained and in case of recognition, a word that has the most highest probability of first section is selected as a recognized word by same concept. Train station names are selected as the target recognition vocabulary and LPC cepstrum coefficients are used as the feature parameters. Besides the speech recognition experiments of proposed method, we experiment the other methods under same conditions and data. Through the experiment results, it is proved that the proposed method based on HMM using FSVQ and fuzzy concept is superior to tile others in recognition rate.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.3
• /
• pp.1086-1103
• /
• 2020

The automatic identification and classification of image-based weld defects is a difficult task due to the complex texture of the X-ray images of the weld defect. Several depth learning methods for automatically identifying welds were proposed and tested. In this work, four different depth convolutional neural networks were evaluated and compared on the 1631 image set. The concavity, undercut, bar defects, circular defects, unfused defects and incomplete penetration in the weld image 6 different types of defects are classified. Another contribution of this paper is to train a CNN model "RayNet" for the dataset from scratch. In the experiment part, the parameters of convolution operation are compared and analyzed, in which the experimental part performs a comparative analysis of various parameters in the convolution operation, compares the size of the input image, gives the classification results for each defect, and finally shows the partial feature map during feature extraction with the classification accuracy reaching 96.5%, which is 6.6% higher than the classification accuracy of other existing fine-tuned models, and even improves the classification accuracy compared with the traditional image processing methods, and also proves that the model trained from scratch also has a good performance on small-scale data sets. Our proposed method can assist the evaluators in classifying pipeline welding defects.

• The KIPS Transactions:PartB
• /
• v.10B no.2
• /
• pp.229-236
• /
• 2003

Named entity recognition is the process indispensable to question answering and information extraction systems. This paper presents an HMM based named entity (m) recognition method using the construction principles of compound words. In Korean, many named entities can be decomposed into more than one word. Moreover, there are contextual relationships among nouns in an NE, and among an NE and its surrounding words. In this paper, we classify words into a word as an NE in itself, a word in an NE, and/or a word adjacent to an n, and train an HMM based on NE-related word types and parts of speech. Proposed named entity recognition (NER) system uses trigram model of HMM for considering variable length of NEs. However, the trigram model of HMM has a serious data sparseness problem. In order to solve the problem, we use multi-level back-offs. Experimental results show that our NER system can achieve an F-measure of 87.6% in the economic articles.

• KIPS Transactions on Computer and Communication Systems
• /
• v.7 no.5
• /
• pp.127-136
• /
• 2018

In this paper, we propose a PIN entry method that combines with machine learning technique on smartphone. We use not only a PIN but also touch time intervals and locations as factors to identify whether the user is correct or not. In the user registration phase, a remote server was used to train/create a machine learning model using data that collected from end-user device (i.e. smartphone). In the user authentication phase, the pre-trained model and the saved PIN was used to decide the authentication success or failure. We examined that there is no big inconvenience to use this technique (FRR: 0%) and more secure than the previous PIN entry techniques (FAR : 0%), through usability and security experiments, as a result we could confirm that this technique can be used sufficiently. In addition, we examined that a security incident is unlikely to occur (FAR: 5%) even if the PIN is leaked through the shoulder surfing attack experiments.

• Journal of Korean Society of Steel Construction
• /
• v.19 no.3
• /
• pp.281-290
• /
• 2007

In this paper, the dynamic behavior of a 12m plate girder railway bridge is analyzed using the commercial FEM program. A time history load is applied to a standard train load via the shape function ofthe beam element. In addition, lateral behavior characteristics were simulated using the Klingel sine movement. A feasibility study of the FEM program and an analysis were performed by comparing the displacement and the acceleration, from the experimental data and the results of the FEM analysis. the time history of the lateral and vertical displacements are reflected in the experimental results. Six kinds of reinforcements were studied from the effects of the displacement and the acceleration. The RF-1 model that was applied to the upper lateral bracing system, and the RF-3 model that reinforced the plate, turned out to be the most effective reinforcement methods with respect to weight limits and construction simplification.

• Journal of the Society of Naval Architects of Korea
• /
• v.52 no.1
• /
• pp.88-95
• /
• 2015

For the frequency-domain spectral fatigue analysis, the probability density function of stress range needs to be estimated based on the stress spectrum only, which is a frequency domain representation of the response. The probability distribution of the stress range of the narrow-band spectrum is known to follow the Rayleigh distribution, however the PDF of wide-band spectrum is difficult to define with clarity due to the complicated fluctuation pattern of spectrum. In this paper, efforts have been made to figure out the links between the probability density function of stress range to the structural response of wide-band Gaussian random process. An artificial neural network scheme, known as one of the most powerful system identification methods, was used to identify the multivariate functional relationship between the idealized wide-band spectrums and resulting probability density functions. To achieve this, the spectrums were idealized as a superposition of two triangles with arbitrary location, height and width, targeting to comprise wide-band spectrum, and the probability density functions were represented by the linear combination of equally spaced Gaussian basis functions. To train the network under supervision, varieties of different wide-band spectrums were assumed and the converged probability density function of the stress range was derived using the rainflow counting method and all these data sets were fed into the three layer perceptron model. This nonlinear least square problem was solved using Levenberg-Marquardt algorithm with regularization term included. It was proven that the network trained using the given data set could reproduce the probability density function of arbitrary wide-band spectrum of two triangles with great success.