• Proceedings of the KIEE Conference
• /
• 1996.07b
• /
• pp.939-942
• /
• 1996

This paper presents a stable learning algorithm for diagonal recurrent neural network(DRNN). DRNN is applied to a problem of controlling nonlinear dynamical systems. A architecture of DRNN is a modified model of the Recurrent Neural Network(RNN) with one hidden layer, and the hidden layer is comprised of self-recurrent neurons. DRNN has considerably fewer weights than RNN. Since there is no interlinks amongs in the hidden layer. DRNN is dynamic mapping and is better suited for dynamical systems than static forward neural network. To guarantee convergence and for faster learning, an adaptive learning rate is developed by using Lyapunov function. The ability and effectiveness of identifying and controlling a nonlinear dynamic system using the proposed algorithm is demonstrated by computer simulation.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.43.1-43
• /
• 2001

We propose two control methods of the Lyapunov exponents for Jordan-type recurrent neural networks. Both the two methods are formulated by a gradient-based learning method. The first method is derived strictly from the definition of the Lyapunov exponents that are represented by the state transition of the recurrent networks. The first method can control the complete set of the exponents, called the Lyapunov spectrum, however, it is computationally expensive because of its inherent recursive way to calculate the changes of the network parameters. Also this recursive calculation causes an unstable control when, at least, one of the exponents is positive, such as the largest Lyapunov exponent in the recurrent networks with chaotic dynamics. To improve stability in the chaotic situation, we propose a non recursive formulation by approximating ...

• Communications of the Korean Mathematical Society
• /
• v.36 no.3
• /
• pp.593-607
• /
• 2021

The aim of the present paper is to establish an intrinsic generalization of Cartan connection in Finsler geometry. This connection is called the vertical recurrent Finsler connection. An intrinsic proof of the existence and uniqueness theorem for such connection is investigated. Moreover, it is shown that for such connection, the associated semi-spray coincides with the canonical spray and the associated nonlinear connection coincides with the Barthel connection. Explicit intrinsic expression relating this connection and Cartan connection is deduced. We also investigate some applications concerning the fundamental geometric objects associated with this connection. Finally, three important results concerning the curvature tensors associated to a special vertical recurrent Finsler connection are studied.

• International Journal of Contents
• /
• v.14 no.4
• /
• 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.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.27 no.1
• /
• 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.

• Journal of Yeungnam Medical Science
• /
• v.36 no.1
• /
• pp.63-66
• /
• 2019

Malignant peripheral nerve sheath tumor (MPNST) is rare, accounting for 5-10% of all soft tissue sarcomas. MPNST is characteristically aggressive and has a poor prognosis. Fifty percent of patients with MPNST have neurofibromatosis type 1 (NF1). NF-associated MPNST occurs more often at younger ages than sporadic MPNST, but the survival difference is controversial. Superficial MPNST from a recurrent neurofibroma is extremely rare and only a limited number of cases have been reported in the literature. Herein, we report an unusual case of superficial MPNST from a recurrent neurofibroma in a patient without NF1.

• Journal of the Korean neurological association
• /
• v.36 no.4
• /
• pp.333-336
• /
• 2018

Carotid free-floating thrombus (FFT) is a rare cause of stroke. The FFT is commonly associated with an atherosclerotic plaque rupture, but other causes need to be examined in young patients. We report a case of 31-year-old male patient with recurrent ischemic stroke caused by carotid FFT. Although initial laboratory test was unremarkable, recurrent stroke events led us to perform additional study and antiphospholipid syndrome (APLS) was diagnosed. Repetitive testing for APLS seems considerable when young patients present with recurrent stroke.

• 대한상한금궤의학회지
• /
• v.12 no.1
• /
• pp.161-169
• /
• 2020

Objective: This case report describes the improvements of a patient with recurrent cystitis who was treated using an herbal medication according to the Shanghanlun disease pattern identification diagnostic system (DPIDS). Methods: 'DPIDS'and 'Interpretation based on Etymological chinese characters,'the patient was diagnosed with Shaoyin-bing, provision number 315, and administered Baektong-tang herb medication for 30 days. The changes in the symptoms of recurrent cystitis were estimated using the Interstitial Cystitis Symptom Index and Problem Index-Korean version (ICSI/ICPI-K) and Visual Analogue Scale (VAS). Results : The ICSI/ICPI-K score changed from 33 to 0 and VAS score changed from 7 to 0. Conclusions: The main causes of the disease were 微 and 利,and the symptoms of recurrent cystitis

• ETRI Journal
• /
• v.43 no.6
• /
• pp.1081-1092
• /
• 2021

Electroencephalography (EEG) recordings taken during the perception of music tempo contain information that estimates the tempo of a music piece. If information about this tempo stimulus in EEG recordings can be extracted and classified, it can be effectively used to construct a music-based brain-computer interface. This study proposes a novel convolutional recurrent attention model (CRAM) to extract and classify features corresponding to tempo stimuli from EEG recordings of listeners who listened with concentration to the tempo of musics. The proposed CRAM is composed of six modules, namely, network inputs, two-dimensional convolutional bidirectional gated recurrent unit-based sample encoder, sample-level intuitive attention, segment encoder, segment-level intuitive attention, and softmax layer, to effectively model spatiotemporal features and improve the classification accuracy of tempo stimuli. To evaluate the proposed method's performance, we conducted experiments on two benchmark datasets. The proposed method achieves promising results, outperforming recent methods.

• Clinical and Experimental Reproductive Medicine
• /
• v.49 no.3
• /
• pp.168-174
• /
• 2022

Refractory thin endometrium and recurrent implantation failure are among the most challenging infertility-related factors hindering successful pregnancy. Several adjuvant therapies have been investigated to increase endometrial thickness and the pregnancy rate, but the treatment effect is still minimal, and for many patients, these treatment methods can be quite costly and difficult to approach. Platelet-rich plasma (PRP) is an autologous concentration of platelets in plasma and has recently been elucidated as a better treatment option for these patients. PRP is rich in cytokines and growth factors, which are suggested to exert a regenerative effect at the level of the injured tissue. Another advantage of PRP is that it is easily obtained from the patient's own blood. We aimed to review the recent findings of PRP therapy used for patients with refractory thin endometrium and recurrent implantation failure.