• Journal of the Korean GEO-environmental Society
• /
• v.15 no.2
• /
• pp.45-52
• /
• 2014

The tunnel construction is increasing in order to secure a good driving performance of the car and train. A cases of tunnel collapse and the tunnel excessive displacement are increasing with the increase in tunnel construction. In terms of empirical construction methods using the strength characteristics of soil, it is important for tunnel construction to analyze causes of collapse and displacement. In the paper, it was analyzed the causes of collapse and excessive displacement of tunnel in the fractured ground condition. The results of analysis is that the increase of rainfall and lasting increase of displacement and large scale fractured ground are interconnected.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.4 no.1 s.6
• /
• pp.57-62
• /
• 2005

In this paper, we propose a channel estimation method by impulse signal train in OFDM. In order to estimate the channel response, 4 impulse signals are generated and transmitted during one OFDM (Orthogonal Frequency Division Multiplexing) symbol. The intervals between the impulse signals are all equal in time domain. At the receiver, the impulse response signals are summed and averaged. And then, the averaged impulse response signal is zero padded and fast Fourier transformed to obtain the channel estimation. The BER performance of the proposed method is compared with those of conventional estimation method using the long training sequence in fast fading environments. The simulation results show that the proposed method improves by 3 dB in terms of Eb/No, compared with the conventional method.

• Journal of Radiation Industry
• /
• v.11 no.1
• /
• pp.33-38
• /
• 2017

RI-Biomics technology is advanced convergence technologies that can be measured in real time and track in vivo behavior and metabolism of substances using characteristics of the radioactive isotope. Its application fields are increasing such as drug development, agriculture, development of new materials and their utilization, etc. In addition, according to domestic and international developments and changes in the RI-Biomics environment, RI-Biomics professionals are needed to train continuously. To develop systematic human resources basement and competency-based curriculum, we perform competency modeling of pedagogical perspective to targeted at high-performance on RI-Biomics. Furthermore, we redefine the competency model and verified by industry experts with focus group interviews. In the result, two general competencies and three professional competencies were extracted by interview. Each competencies are organized six sub-competencies and nine sub-competencies. In the finial steps, the same procedures were repeated to obtain the consensus of experts on derived competencies and behavioral objectives. The results of the study are applicable to enhance human resource management and to develop the curriculum for RI-Biomics expert training. It is expected to be used as reference material of long term-planning for RI-Biomics professional.

• International Journal of Internet, Broadcasting and Communication
• /
• v.11 no.4
• /
• pp.31-36
• /
• 2019

Unsupervised neural networks have not caught enough attention until Generative Adversarial Network (GAN) was proposed. By using both the generator and discriminator networks, GAN can extract the main characteristic of the original dataset and produce new data with similarlatent statistics. However, researchers understand fully that training GAN is not easy because of its unstable condition. The discriminator usually performs too good when helping the generator to learn statistics of the training datasets. Thus, the generated data is not compelling. Various research have focused on how to improve the stability and classification accuracy of GAN. However, few studies delve into how to improve the training efficiency and to save training time. In this paper, we propose a novel optimizer, named FAST-ADAM, which integrates the Lookahead to ADAM optimizer to train the generator of a semi-supervised generative adversarial network (SSGAN). We experiment to assess the feasibility and performance of our optimizer using Canadian Institute For Advanced Research - 10 (CIFAR-10) benchmark dataset. From the experiment results, we show that FAST-ADAM can help the generator to reach convergence faster than the original ADAM while maintaining comparable training accuracy results.

• Journal of Korea Port Economic Association
• /
• v.18 no.2
• /
• pp.109-133
• /
• 2002

The China entered World Trade Oganization(WTO) last year, thus opening its border to more - and freer - trade. With its foreign trade rapidly expanding and with economic growth continuing at a substantial -rate, China will be the largest container traffic generating country in the world. In the light of this potential trade bonanza, regional ports in North-East Asia strive to gain a competitive-edge. The Port of Busan, the world's third largest container port, wants to capture a significant share of the china's container cargoes. In this circumstance, development strategies of the Port of Busan are suggested as follows. First, to cope with increasing volumes, the New Busan Port on Gaduk island should be constructed without failure. Second, it is necessary to add modernized high-performance gantry cranes and to train crane operators' skill. Third, it needs to apply Dwell Time- Sliding Scale System for transshipment cargoes. Fourth, it needs to develop the EDI network in terminal areas or adjacent hub ports to exchange trustworthy and satisfactory informations Fifth, port authority -needs to enlarge designated Free Trade Zone to facilitate the free flow of cargoes. Sixth, the restoration of rail links between North and South Korea is abundantly clear. Thus it needs to enlarge railroad facilities in advance. Seventh, it needs to establish the Port Authority of Busan immediately. Finally, it needs to strengthen port sales and to open events like 'Marine Week 2001' regularly to attract potential canters or big shippers.

• Journal of the Korean GEO-environmental Society
• /
• v.22 no.11
• /
• pp.39-47
• /
• 2021

Tunneling is widely increased in rail-road construction due to the large portion of mountainous regions in Korea as well as the improving running performance of train. Tunneling under poor rock condition, shallow overburden, or existing fault zone has high risk for collapse. Therefore, this study presents the stability of tunnel under unfavorable geological conditions using finite element methods.

• Nuclear Engineering and Technology
• /
• v.53 no.11
• /
• pp.3563-3579
• /
• 2021

Measured decay heat data of light water reactor (LWR) spent nuclear fuel (SNF) assemblies are adopted to train machine learning (ML) models. The measured data is available for fuel assemblies irradiated in commercial reactors operated in the United States and Sweden. The data comes from calorimetric measurements of discharged pressurized water reactor (PWR) and boiling water reactor (BWR) fuel assemblies. 91 and 171 measurements of PWR and BWR assembly decay heat data are used, respectively. Due to the small size of the measurement dataset, we propose: (i) to use the method of multiple runs (ii) to generate and use synthetic data, as large dataset which has similar statistical characteristics as the original dataset. Three ML models are developed based on Gaussian process (GP), support vector machines (SVM) and neural networks (NN), with four inputs including the fuel assembly averaged enrichment, assembly averaged burnup, initial heavy metal mass, and cooling time after discharge. The outcomes of this work are (i) development of ML models which predict LWR fuel assembly decay heat from the four inputs (ii) generation and application of synthetic data which improves the performance of the ML models (iii) uncertainty analysis of the ML models and their predictions.

• Nuclear Engineering and Technology
• /
• v.52 no.12
• /
• pp.2709-2716
• /
• 2020

Compositions of large nuclear cores (e.g. boiling water reactors) are highly heterogeneous in terms of fuel composition, control rod insertions and flow regimes. For this reason, they usually lack high order of symmetry (e.g. 1/4, 1/8) making it difficult to estimate their neutronic parameters for large spaces of possible loading patterns. A detailed hyperparameter optimization technique (a combination of manual and Gaussian process search) is used to train and optimize deep neural networks for the prediction of three neutronic parameters for the Ringhals-1 BWR unit: power peaking factors (PPF), control rod bank level, and cycle length. Simulation data is generated based on half-symmetry using PARCS core simulator by shuffling a total of 196 assemblies. The results demonstrate a promising performance by the deep networks as acceptable mean absolute error values are found for the global maximum PPF (~0.2) and for the radially and axially averaged PPF (~0.05). The mean difference between targets and predictions for the control rod level is about 5% insertion depth. Lastly, cycle length labels are predicted with 82% accuracy. The results also demonstrate that 10,000 samples are adequate to capture about 80% of the high-dimensional space, with minor improvements found for larger number of samples. The promising findings of this work prove the ability of deep neural networks to resolve high dimensionality issues of large cores in the nuclear area.

• Steel and Composite Structures
• /
• v.39 no.3
• /
• pp.319-335
• /
• 2021

This study proposes a new and highly-accurate artificial intelligence model, namely ANN-IP, which combines an interior-point (IP) algorithm and artificial neural network (ANN), to improve the axial compression capacity prediction of elliptical concrete-filled steel tubular (CFST) columns. For this purpose, 145 tests of elliptical CFST columns extracted from the literature are used to develop the ANN-IP model. In this regard, axial compression capacity is considered as a function of the column length, the major axis diameter, the minor axis diameter, the thickness of the steel tube, the yield strength of the steel tube, and the compressive strength of concrete. The performance of the ANN-IP model is compared with the ANN-LM model, which uses the robust Levenberg-Marquardt (LM) algorithm to train the ANN model. The comparative results show that the ANN-IP model obtains more magnificent precision (R² = 0.983, RMSE = 59.963 kN, a20 - index = 0.979) than the ANN-LM model (R² = 0.938, RMSE = 116.634 kN, a20 - index = 0.890). Finally, a new Graphical User Interface (GUI) tool is developed to use the ANN-IP model for the practical design. In conclusion, this study reveals that the proposed ANN-IP model can properly predict the axial compression capacity of elliptical CFST columns and eliminate the need for conducting costly experiments to some extent.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.2
• /
• pp.600-616
• /
• 2021

SIMON and SPECK are two families of lightweight block ciphers that have excellent performance on hardware and software platforms. At CRYPTO 2019, Gohr first introduces the differential cryptanalysis based deep learning on round-reduced SPECK32/64, and finally reduces the remaining security of 11-round SPECK32/64 to roughly 38 bits. In this paper, we are committed to evaluating the safety of SIMON cipher under the neural differential cryptanalysis. We firstly prove theoretically that SIMON is a non-Markov cipher, which means that the results based on conventional differential cryptanalysis may be inaccurate. Then we train a residual neural network to get the 7-, 8-, 9-round neural distinguishers for SIMON32/64. To prove the effectiveness for our distinguishers, we perform the distinguishing attack and key-recovery attack against 15-round SIMON32/64. The results show that the real ciphertexts can be distinguished from random ciphertexts with a probability close to 1 only by 2^8.7 chosen-plaintext pairs. For the key-recovery attack, the correct key was recovered with a success rate of 23%, and the data complexity and computation complexity are as low as 2⁸ and 2^20.1 respectively. All the results are better than the existing literature. Furthermore, we briefly discussed the effect of different residual network structures on the training results of neural distinguishers. It is hoped that our findings will provide some reference for future research.