• 한국항공운항학회지
• /
• 제27권1호
• /
• pp.34-42
• /
• 2019

Ten AOC(Air Operation Certificate) holders certified by MOLIT of Korea are operating their own maintenance training program. Though the maintenance training program is approved by the same authority, the contents of the program are different even in the mandatory training courses among AOC holders. The survey interview showed that the maintenance training in mandatory training should have the same contents and requirements. Throughout the survey and focus group discussion, this paper suggests the list and contents of the initial mandatory training and the list, contents and interval for the recurrent mandatory training. This paper also suggests how to implement the on-line training program for recurrent mandatory training to keep the quality of the airline maintenance training program.

• 제어로봇시스템학회논문지
• /
• 제9권11호
• /
• pp.917-924
• /
• 2003

Recurrent neural networks have been successfully applied to communications channel equalization. Major disadvantages of gradient-based learning algorithms commonly employed to train recurrent neural networks are slow convergence rates and long training sequences required for satisfactory performance. In a high-speed communications system, fast convergence speed and short training symbols are essential. We propose decision feedback equalizers using a recurrent neural network trained with Kalman filtering algorithms. The main features of the proposed recurrent neural equalizers, utilizing extended Kalman filter (EKF) and unscented Kalman filter (UKF), are fast convergence rates and good performance using relatively short training symbols. Experimental results for two time-varying channels are presented to evaluate the performance of the proposed approaches over a conventional recurrent neural equalizer.

• Journal of information and communication convergence engineering
• /
• 제8권3호
• /
• pp.267-272
• /
• 2010

For the last decade, recurrent neural networks (RNNs) have been commonly applied to communications channel equalization. The major problems of gradient-based learning techniques, employed to train recurrent neural networks are slow convergence rates and long training sequences. In high-speed communications system, short training symbols and fast convergence speed are essentially required. In this paper, the derivative-free Kalman filter, so called the unscented Kalman filter (UKF), for training a fully connected RNN is presented in a state-space formulation of the system. The main features of the proposed recurrent neural equalizer are fast convergence speed and good performance using relatively short training symbols without the derivative computation. Through experiments of nonlinear channel equalization, the performance of the RNN with a derivative-free Kalman filter is evaluated.

• Journal of Korean Neurosurgical Society
• /
• 제60권1호
• /
• pp.40-46
• /
• 2017

Objective: To assess role of some inflammatory mediators in patients with primary and recurrent lumbar disc herniation. Expression of IL-6, transforming growth factor (TGF)-1, insulin-like growth factor (IGF)-1, and Bcl-2-associated X protein (BAX) have been shown to be more intense in the primary group than the recurrent goup, but this mediators may be important aspects prognostic. Methods: 19 patients underwent primary and revision operations between June 1, 2009 and June 1, 2014, and they were included in this study. The 19 patients' intervertebral disc specimens obtained from the primary procedures and reoperations were evaluated. Expression of IL-6, TGF-1, IGF-1, and BAX were examined immunohistochemically in the 38 biopsy tissues obtained from the primary and recurrent herniated intervertebral discs during the operation. Results: For IL-6 expression in the intervertebral disc specimens, there was no difference between the groups. The immunohistochemical study showed that the intervertebral disc specimens in the primary group were stained intensely by TGF-1 compared with the recurrent group. Expression of IGF-1 in the primary group was found moderate. In contrast, in the recurrent group of patients was mild expression of IGF-1. The primary group intervertebral disc specimens were stained moderately by BAX compared with the recurrent group. Conclusion: The results of our prognostic evaluation of patients in the recurrent group who were operated due to disc herniation suggest that mediators may be important parameters.

• Asian Pacific Journal of Cancer Prevention
• /
• 제16권5호
• /
• pp.1851-1855
• /
• 2015

Background: There are increasing data about microRNAs (miRNA) in the literature, providing abundant evidence that they play important roles in pathogenesis and development of colorectal cancer. In this study, we aimed to investigate the miRNA expression profiles in surgically resected specimens of patients with recurrent and non-recurrent colorectal cancer. Materials and Methods: The study population included 40 patients with stage II colorectal cancer (20 patients with recurrent tumors, and 20 sex and age matched patients without recurrence), who underwent curative colectomy between 2004 and 2011 without adjuvant therapy. Expression of 16 miRNAs (miRNA-9, 21, 30d, 31, 106a, 127, 133a, 133b, 135b, 143, 145, 155, 182, 200a, 200c, 362) was verified by quantitative real-time polymerase chain reaction (qRT-PCR) in all resected colon cancer tissue samples and in corresponding normal colonic tissues. Data analyses were carried out using SPSS 15 software. Values were statistically significantly changed in 40 cancer tissues when compared to the corresponding 40 normal colonic tissues (p<0.001). MiR-30d, miR-133a, miR-143, miR-145 and miR-362 expression was statistically significantly downregulated in 40 resected colorectal cancer tissue samples (p<0.001). When we compared subgroups, miRNA expression profiles of 20 recurrent cancer tissues were similar to all 40 cancer tissues. However in 20 non-recurrent cancer tissues, miR-133a expression was not significantly downregulated, moreover miR-133b expression was significantly upregulated (p<0.05). Conclusions: Our study revealed dysregulation of expression of ten miRNAs in Turkish colon cancer patients. These miRNAs may be used as potential biomarkers for early detection, screening and surveillance of colorectal cancer, with functional effects on tumor cell behavior.

• 한국통신학회논문지
• /
• 제34권3C호
• /
• pp.257-267
• /
• 2009

This paper presents a training method for neural networks and the employment of MSE (mean scare error) values as the basis of a decision regarding the identity claim of a speaker in a recurrent neural networks based speaker verification system. Recurrent neural networks (RNNs) are employed to capture temporally dynamic characteristics of speech signal. In the process of supervised learning for RNNs, target outputs are automatically generated and the generated target outputs are made to represent the temporal variation of input speech sounds. To increase the capability of discriminating between the true speaker and an impostor, a discriminative training method for RNNs is presented. This paper shows the use and the effectiveness of the MSE value, which is obtained from the Euclidean distance between the target outputs and the outputs of networks for test speech sounds of a speaker, as the basis of speaker verification. In terms of equal error rates, results of experiments, which have been performed using the Korean speech database, show that the proposed speaker verification system exhibits better performance than a conventional hidden Markov model based speaker verification system.

• 대한전기학회논문지:전력기술부문A
• /
• 제48권10호
• /
• pp.1231-1238
• /
• 1999

This paper presents an approach for the optimal heating load Identification using Diagonal Recurrent Neural Networks(DRNN). In this paper, the DRNN captures the dynamic nature of a system and since it is not fully connected, training is much faster than a fully connected recurrent neural network. The architecture of DRNN is a modified model of the fully connected recurrent neural network with one hidden layer. The hidden layer is comprised of self-recurrent neurons, each feeding its output only into itself. In this study, A dynamic backpropagation (DBP) with delta-bar-delta learning method is used to train an optimal heating load identifier. Delta-bar-delta learning method is an empirical method to adapt the learning rate gradually during the training period in order to improve accuracy in a short time. The simulation results based on experimental data show that the proposed model is superior to the other methods in most cases, in regard of not only learning speed but also identification accuracy.

• International Journal of Industrial Entomology and Biomaterials
• /
• 제7권1호
• /
• pp.21-27
• /
• 2003

Manifestation of heterotic genetic interaction was studied in different hybrids made between multivoltine recurrent backcross (RBL)/congenic lines (Con. L) during unfavourable season when temperature and relative humidity are > $30^{\circ}C$ and 86%, respectively. A few number of silkworm race or strain or breed like Nistari (N ＋ p or Np) can sustain the temperature above 3$0^{\circ}C$ and RH above 86%. The present heterosis study screened a hybrid i.e., CB$_{5}$Lm5RBL1M$_{6}$DPC-LmE$^1$RBL and its reciprocal provided heterobeltiotic effect on survival by number and pupation rate at a magnitude of 20% (p < 0.01) and yield by weight of 10% (p < 0.01). Beside all the hybrids expressed heterosis over check - Nistari (N ＋ p) with better quality silk. Therefore, aforesaid hybrid may be useful for utilization at commercial level during adverse seasons of West Bengal.gal.

• Journal of the Korean Society for Industrial and Applied Mathematics
• /
• 제24권4호
• /
• pp.331-350
• /
• 2020

Exploding gradient is a widely known problem in training recurrent neural networks. The explosion problem has often been coped with cutting off the gradient norm by some fixed value. However, this strategy, commonly referred to norm clipping, is an ad hoc approach to attenuate the explosion. In this research, we opt to view the problem from a different perspective, the discrete-time optimal control with infinite horizon for a better understanding of the problem. Through this perspective, we fathom the region at which gradient explosion occurs. Based on the analysis, we introduce a gradient-explosion-free algorithm that keeps the training process away from the region. Numerical tests show that this algorithm is at least three times faster than the clipping strategy.

• International Journal of Contents
• /
• 제14권4호
• /
• pp.57-64
• /
• 2018

Among many UNESCO world heritage sites in Korea, "Historic Village: Hahoe" is adjacent to Nakdong River and it is imperative to monitor the water level near the village in a bid to forecast floods and prevent disasters resulting from floods.. In this paper, we propose a recurrent neural network with multiple hidden layers to predict the water level near the village. For training purposes on the proposed model, we adopt the sixth-order error function to improve learning for rare events as well as to prevent overspecialization to abundant events. Multiple hidden layers with recurrent and crosstalk links are helpful in acquiring the time dynamics of the relationship between rainfalls and water levels. In addition, we chose hidden nodes with linear rectifier activation functions for training on multiple hidden layers. Through simulations, we verified that the proposed model precisely predicts the water level with high peaks during the rainy season and attains better performance than the conventional multi-layer perceptron.