• Journal of Korea Water Resources Association
• /
• v.47 no.9
• /
• pp.825-838
• /
• 2014

The stationary Markov chain model has been widely used as a daily rainfall simulation model. A main assumption of the stationary Markov model is that statistical characteristics do not change over time and do not have any trends. In other words, the stationary Markov chain model for daily rainfall simulation essentially can not incorporate any changes in mean or variance into the model. Here we develop a Non-stationary hidden Markov chain model (NHMM) based stochastic downscaling scheme for simulating the daily rainfall sequences, using general circulation models (GCMs) as inputs. It has been acknowledged that GCMs perform well with respect to annual and seasonal variation at large spatial scale and they stand as one of the primary sources for obtaining forecasts. The proposed model is applied to daily rainfall series at three stations in Nakdong watershed. The model showed a better performance in reproducing most of the statistics associated with daily and seasonal rainfall. In particular, the proposed model provided a significant improvement in reproducing the extremes. It was confirmed that the proposed model could be used as a downscaling model for the purpose of generating plausible daily rainfall scenarios if elaborate GCM forecasts can used as a predictor. Also, the proposed NHMM model can be applied to climate change studies if GCM based climate change scenarios are used as inputs.

• Journal of the Korean GEO-environmental Society
• /
• v.14 no.9
• /
• pp.31-37
• /
• 2013

In this study installation diameter, interval, area replacement ratio and ground hardness of applicable ground in C.G.S method should be mastered through surrounding ground by conducting modeling. Optimum artificial neural network was selected through the study of the parameter of artificial neural network and prediction model was developed by the relationship with numerical analysis and artificial neural network. As this result, C.G.S pile settlement and ground settlement were found to be equal in terms of diameter, interval, area replacement ratio and ground hardness, presented in a single curve, which means that the behavior pattern of applied ground in C.G.S method was presented as some form, and based on such a result, learning the artificial neural network for 3D behavior was found to be possible. As the study results of artificial neural network internal factor, when using the number of neural in hidden layer 10, momentum constant 0.2 and learning rate 0.2, relationship between input and output was expressed properly. As a result of evaluating the ground behavior of C.G.S method which was applied to using such optimum structure of artificial neural network model, is that determination coefficient in case of C.G.S pile settlement was 0.8737, in case of ground settlement was 0.7339 and in case of ground heaving was 0.7212, sufficient reliability was known.

• Journal of Radiation Protection and Research
• /
• v.40 no.1
• /
• pp.55-64
• /
• 2015

Dose calculations which are a crucial requirement for radiotherapy treatment planning systems require accuracy and rapid calculations. The conventional radiotherapy treatment planning dose algorithms are rapid but lack precision. Monte Carlo methods are time consuming but the most accurate. The new combined system that Monte Carlo methods calculate part of interesting domain and the rest is calculated by neural can calculate the dose distribution rapidly and accurately. The preliminary study showed that neural networks can map functions which contain discontinuous points and inflection points which the dose distributions in inhomogeneous media also have. Performance results between scaled conjugated gradient algorithm and Levenberg-Marquardt algorithm which are used for training the neural network with a different number of neurons were compared. Finally, the dose distributions of homogeneous phantom calculated by a commercialized treatment planning system were used as training data of the neural network. In the case of homogeneous phantom;the mean squared error of percent depth dose was 0.00214. Further works are programmed to develop the neural network model for 3-dimensinal dose calculations in homogeneous phantoms and inhomogeneous phantoms.

• Journal of the Korean Geotechnical Society
• /
• v.21 no.8
• /
• pp.73-84
• /
• 2005

A three layered neural network model was developed using back propagation algorithm to estimate the UU undrained shear strength of Korean soft soil based on the database of actual undrained shear strengths and piezocone measurements compiled from 8 sites over the Korea. The developed model was validated by comparing model predictions with measured values about new piezocone data, which were not previously employed during development of model. Performance of the neural network model was also compared with conventional empirical methods. It was found that the number of neuron in hidden layer is different for the different combination of transfer functions of neural network models. However, all piezocone neural network models are successful in inferring a complex relationship between piezocone measurements and the undrained shear strength of Korean soft soils, which give relatively high coefficients of determination ranging from 0.69 to 0.72. Since neural network model has been generalized by self-learning from database of piezocone measurements and undrained shear strength over the various sites, the developed neural network models give more precise and generally reliable undrained shear strengths than empirical approaches which still need site specific calibration.

• The Journal of the Acoustical Society of Korea
• /
• v.38 no.6
• /
• pp.703-709
• /
• 2019

This paper proposes speech recognition systems employing Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM) structures combined with Hidden Markov Moldel (HMM) to effectively recognize the speech of VeloPharyngeal Insufficiency (VPI) patients, and compares the recognition performance of the systems to the Gaussian Mixture Model (GMM-HMM) and fully-connected Deep Neural Network (DNNHMM) based speech recognition systems. In this paper, the initial model is trained using normal speakers' speech and simulated VPI speech is used for generating a prior model for speaker adaptation. For VPI speaker adaptation, selected layers are trained in the CNN-HMM based model, and dropout regulatory technique is applied in the LSTM-HMM based model, showing 3.68 % improvement in recognition accuracy. The experimental results demonstrate that the proposed LSTM-HMM-based speech recognition system is effective for VPI speech with small-sized speech data, compared to conventional GMM-HMM and fully-connected DNN-HMM system.

• Journal of the Korea Society of Computer and Information
• /
• v.20 no.5
• /
• pp.53-63
• /
• 2015

Singing voice synthesis is the generation of a song using a computer given its lyrics and musical notes. Hidden Markov models (HMM) have been proved to be the models of choice for text to speech synthesis. HMMs have also been used for singing voice synthesis research, however, a huge database is needed for the training of HMMs for singing voice synthesis. And commercially available singing voice synthesis systems which use the piano roll music notation, needs to adopt the easy to read standard music notation which make it suitable for singing learning applications. To overcome this problem, we use a speech database for training context dependent HMMs, to be used for singing voice synthesis. Pitch and duration control methods have been devised to modify the parameters of the HMMs trained on speech, to be used as the synthesis units for the singing voice. This work describes a singing voice synthesis system which uses a MusicXML based music score editor as the front-end interface for entry of the notes and lyrics to be synthesized and a hidden Markov model based text to speech synthesis system as the back-end synthesizer. A perceptual test shows the feasibility of our proposed system.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.6
• /
• pp.67-78
• /
• 2017

Traffic congestion cost is increasing annually. Specifically congestion caused by the CDB traffic contains more than a half of the total congestion cost. Recent advancement in the field of Big Data, AI paved the way to industry revolution 4.0. And, these new technologies creates tremendous changes in the traffic information dissemination. Eventually, accurate and timely traffic information will give a positive impact on decreasing traffic congestion cost. This study, therefore, focused on developing both recurrent and non-recurrent congestion prediction models on urban roads by adopting Recurrent Neural Network(RNN), a tribe in machine learning. Two hidden layers with scaled conjugate gradient backpropagation algorithm were selected, and tested. Result of the analysis driven the authors to 25 meaningful links out of 33 total links that have appropriate mean square errors. Authors concluded that RNN model is a feasible model to predict congestion.

• Journal of Korea Water Resources Association
• /
• v.36 no.2
• /
• pp.195-209
• /
• 2003

Spatial-Stochastic Neural Networks Model(SSNNM) is used to estimate long-term streamflow in the parallel reservoir groups. SSNNM employs two kinds of backpropagation algorithms, based on LMBP and BFGS-QNBP separately. SSNNM has three layers, input, hidden, and output layer, in the structure and network configuration consists of 8-8-2 nodes one by one. Nodes in input layer are composed of streamflow, precipitation, pan evaporation, and temperature with the monthly average values collected from Andong and Imha reservoir. But some temporal differences apparently exist in their time series. For the SSNNM training procedure, the training sets in input layer are generated by the PARMA(1,1) stochastic model and they covers insufficient time series. Generated data series are used to train SSNNM and the model parameters, optimal connection weights and biases, are estimated during training procedure. They are applied to evaluate model validation using observed data sets. In this study, the new approaches give outstanding results by the comparison of statistical analysis and hydrographs in the model validation. SSNNM will help to manage and control water distribution and give basic data to develop long-term coupled operation system in parallel reservoir groups of the Upper Nakdong River.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.29 no.12C
• /
• pp.1692-1706
• /
• 2004

Recently, there are rapid development of information and communication and rapid growth of e-business users. Therefore we try to solve security problem on the internet environment which charges from wire internet to wireless internet or wire/wireless internet. Since the wireless mobile environment is limited, researches such as small size, end-to-end and privacy security are performed by many people. Wireless e-business adopts credit card WPP protocol and AIP protocol proposed by ASPeCT. WAP, one of the protocol used by WPP has weakness of leaking out information from WG which conned wire and wireless communication. certification chain based AIP protocol requires a lot of computation time and user IDs are known to others. We propose a Micro-Payment protocol based on credit card. Our protocol use the encryption techniques of the public key with ID to ensure the secret of transaction in the step of session key generation. IDs are generated using ECC based Weil Paring. We also use the certification with hidden electronic sign to transmit the payment result. The proposed protocol solves the privacy protection and Non-repudiation p개blem. We solve not only the safety and efficiency problem but also independent of specific wireless platform. The protocol requires the certification organization attent the certification process of payment. Therefore, other domain provide also receive an efficient and safe service.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.30 no.3
• /
• pp.493-501
• /
• 2020

For the obfuscation of Flow Analysis on the Android operating system, the size of the Flow Graph can be large enough to make analysis difficult. To this end, a library in the form of aar was implemented so that it could be inserted into the application in the form of an external library. The library is designed to have up to five child nodes from the entry point in the dummy code, and for each depth has 2n+1 numbers of methods from 100 to 900 for each node, so it consists of a total of 2,500 entry points. In addition, entry points consist of a total of 150 views in XML, each of which is connected via asynchronous interface. Thus, the process of creating a Inter-procedural Control Flow Graph has a maximum of 14,175E+11 additional cases. As a result of applying this to application, the Inter Procedure Control Flow Analysis too generates an average of 10,931 edges and 3,015 nodes with an average graph size increase of 36.64%. In addition, in the APK analyzing process showed that up to average 76.33MB of overhead, but only 0.88MB of execution overhead in the user's ART environment.