• Journal of the Korean Society of Industry Convergence
• /
• v.27 no.1
• /
• pp.183-193
• /
• 2024

Recurrent Neural Network technology that learns past patterns and predicts future patterns using technology for recognizing and classifying objects is being applied to various industries, economies, and languages. And research for practical use is making a lot of progress. However, research on the application of Recurrent Neural Networks for evaluating and predicting the safety of mechanical structures is insufficient. Accurate detection of external load applied to the outside is required to evaluate the safety of mechanical structures. Learning of Recurrent Neural Networks for this requires a large amount of load data. This study applied the Gated Recurrent Unit technique to examine the possibility of load learning and investigated the possibility of applying a stacked Auto Encoder as a way to secure load data. In addition, the usefulness of learning mechanical loads was analyzed with the Gated Recurrent Unit technique, and the basic setting of related functions and parameters was proposed to secure accuracy in the recognition and prediction of loads.

• Journal of Astronomy and Space Sciences
• /
• v.20 no.2
• /
• pp.101-108
• /
• 2003

This study reports one approach for the classification of magnetic storms into recurrent patterns. A storm event is defined as a local minimum of Dst index. The analysis of Dst index for the period of year 1957 through year 2000 has demonstrated that a large portion of the storm events can be classified into a set of recurrent patterns. In our approach, the classification is performed by seeking a categorization that minimizes thermodynamic free energy which is defined as the sum of classification errors and entropy. The error is calculated as the squared sum of the value differences between events. The classification depends on the noise parameter T that represents the strength of the intrinsic error in the observation and classification process. The classification results would be applicable in space weather forecasting.

• Journal of Biomedical Engineering Research
• /
• v.11 no.1
• /
• pp.157-162
• /
• 1990

In this study, a peripheral auditory model is used as a frequency feature extractor and a recurrent network which has recurrent links on input nodes is constructed in order to show the reliability of the recurrent network as a recognizer by executing recognition tests for 4 Korean place names and syllables. In the case of using the general learning rule, it is found that the weights are diverged for a long sequence because of the characteristics of the node function in the hidden and output layers. So, a refined weight compensation method is proposed and, using this method, it is possible to improve the system operation and to use long data. The recognition results are considerably good, even if time worping and endpoint detection are omitted and learning patterns and test patterns are made of average length of data. The recurrent network used in this study reflects well time information of temporal speech signal.

• The KIPS Transactions:PartB
• /
• v.11B no.4
• /
• pp.449-456
• /
• 2004

This paper proposes a novel recognition model, a recurrent fuzzy associative memory(RFAM), for recognizing time-series patterns contained an ambiguity. RFAM is basically extended from FAM(Fuzzy Associative memory) by adding a recurrent layer which can be used to deal with sequential input patterns and to characterize their temporal relations. RFAM provides a Hebbian-style learning method which establishes the degree of association between input and output. The error back-propagation algorithm is also adopted to train the weights of the recurrent layer of RFAM. To evaluate the performance of the proposed model, we applied it to a word boundary detection problem of speech signal.

• Kosin Medical Journal
• /
• v.33 no.2
• /
• pp.159-170
• /
• 2018

Objectives: The purpose of this study was to compare antibiotic resistance patterns between first urinary tract infection (UTI) and recurrent UTI groups and to obtain information regarding empirical antibiotic selection for treating recurrent UTI. Methods: We retrospectively reviewed 148 children treated for UTIs from January 2009 to June 2016. The patients were divided into two groups: first UTI (N = 148) and recurrent UTI (17 patients and 20 episodes). Results: In both groups, Escherichia coli was the most frequent causative organism, accounting for 89.9% and 75.0% in the first and recurrent UTI groups, respectively. When E. coli or Klebsiella pneumoniae was the causative organism, extended-spectrum ${\beta}-lactamase$ (ESBL)-producing organisms were more frequent in the recurrent UTI group (17.6%) than in the first UTI group (14.0%); however, this difference was not statistically significant (P = 0.684). Cefotaxime was the most frequently used first-line empirical antibiotic in both groups. In the first UTI and recurrent UTI groups, 7.4% and 15.0% of patients were treated with intravenous antibiotics as definitive therapy, respectively (P = 0.250). Fifteen out of 17 patients having a second UTI had different causative organisms or antibiotic susceptibility patterns compared to their previous episode. Conclusions: Escherichia coli was the most frequent causative organism in the recurrent UTI group. There were no differences in the proportion of ESBL-producing organisms between the first UTI and recurrent UTI groups. Therefore, when a UTI recurs in children, the antibiotics effective on the most common causative organism might be administered as empirical antibiotics.

• Tuberculosis and Respiratory Diseases
• /
• v.77 no.4
• /
• pp.172-177
• /
• 2014

Background: Pseudomonas aeruginosa infection is particularly associated with progressive and ultimately chronic recurrent respiratory infections in chronic obstructive pulmonary disease, bronchiectasis, chronic destroyed lung disease, and cystic fibrosis. Its treatment is also very complex because of drug resistance and recurrence. Methods: Forty eight cultures from 18 patients with recurrent P. aeruginosa pneumonia from 1998 to 2002 were included in this study. Two or more pairs of sputum cultures were performed during 2 or more different periods of recurrences. The comparison of strains was made according to the phenotypic patterns of antibiotic resistance and chromosomal fingerprinting by pulsed field gel electrophoresis (PFGE) using the genomic DNA of P. aeruginosa from the sputum culture. Results: Phenotypic patterns of antibiotic resistance of P. aeruginosa were not correlated with their prior antibiotic exposition. Fifteen of 18 patients (83.3%) had recurrent P. aeruginosa pneumonia caused by the strains with same PFGE pattern. Conclusion: These data suggest that the most of the recurrent P. aeruginosa infections in chronic lung disease occurred due to the relapse of prior infections. Further investigations should be performed for assessing the molecular mechanisms of the persistent colonization and for determining how to eradicate clonal persistence of P. aeruginosa.

• Journal of Electrical Engineering and information Science
• /
• v.1 no.1
• /
• pp.108-117
• /
• 1996

In this paper, we propose a new type of recurrent neural network architecture in which each output unit is connected with itself and fully-connected with other output units and all hidden units. The proposed recurrent network differs from Jordan's and Elman's recurrent networks in view of functions and architectures because it was originally extended from the multilayer feedforward neural network for improving the discrimination and generalization power. We also prove the convergence property of learning algorithm of the proposed recurrent neural network and analyze the performance of the proposed recurrent neural network by performing recognition experiments with the totally unconstrained handwritten numeral database of Concordia University of Canada. Experimental results confirmed that the proposed recurrent neural network improves the discrimination and generalization power in recognizing spatial patterns.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.2
• /
• pp.401-408
• /
• 1997

Human gets almist all of his knoweledge from the recognition and the accumulation of input patterns,image or sound,the he gets theough his eyes and through his ears.Among these means,his chracter recognition,an ability that allows him to recognize characters and understand their meanings through visual information, is now applied to a pattern recognition system using neural network in computer. Recurrent neural network is one of those models that reuse the output value in neural network learning.Recently many studies try to apply this recurrent neural network to the classification of static patterns like off-line handwritten characters. But most of their efforts are not so drrdtive until now.This stusy suggests a new type of recurrent neural network for an deedctive classification of the static patterns such as off-line handwritten chracters.Using the new J-E(Jordan-Elman)neural network model that enlarges and combines Jordan Model and Elman Model,this new type is better than those of before in recobnizing the static patterms such as figures and handwritten-characters.

• Journal of the Korean Institute of Telematics and Electronics B
• /
• v.31B no.10
• /
• pp.149-157
• /
• 1994

A method of applying a recurrent backpropagation network to identifying or modelling a dynamic system is proposed. After the recurrent backpropagation network having both the characteristicsof interpolative network and associative network is applied to XOR problem, a new model of recurrent backpropagation network is proposed and compared with the original recurrent backpropagation network by applying them to XOR problem. based on the observation thata function can be approximated with polynomials to arbitrary accuracy, the new model is developed so that it may generate higher-order terms in the internal states Moreover, it is shown that the new network is succesfully applied to recognizing noisy patterns of numbers.

• Annals of Clinical Neurophysiology
• /
• v.9 no.1
• /
• pp.1-4
• /
• 2007

Vertigo is an illusion of rotation, which results from an imbalance within the vestibular system. This review focuses on two common presentations of spontaneous vertigo: acute prolonged spontaneous vertigo and recurrent spontaneous vertigo. Common causes of acute prolonged spontaneous vertigo include vestibular neuritis, labyrinthitis, and brainstem or cerebellar stroke. The history and detailed neurological/neurotological examinations usually provide the key information for distinguishing between peripheral and central causes of vertigo. Brain MRI is indicated in any patient with acute vertigo accompanied by abnormal neurological signs, profound imbalance, severe headache, and central patterns of nystagmus. Recurrent spontaneous vertigo occurs when there is a sudden, temporary, and largely reversible impairment of resting neural activity of one labyrinth or its central connections, with subsequent recovery to normal or near-normal function. Meniere's disease, migrainous vertigo, and vertebrobasilar insufficiency (VBI) are common causes. The duration of the vertigo attack is a key piece of information in recurrent spontaneous vertigo. Vertigo of vascular origin, such as VBI, typically lasts for several minutes, whereas recurrent vertigo due to peripheral inner-ear abnormalities lasts for hours. Screening neurotological evaluations, and blood tests for autoimmune and otosyphilis are useful in assessment of recurrent spontaneous vertigo that are likely to be peripheral in origin.