• The Journal of the Korea Contents Association
• /
• v.6 no.10
• /
• pp.9-16
• /
• 2006

In this paper, the acoustic model output of CSR(Continuous Speech Recognition) was used to analyze news data News database used in this experiment was consisted of 2,093 articles. Due to the low efficiency of language model, conventional Korean CSR is not appropriate to the analysis of news data. This problem could be handled successfully by introducing post-processing work of recognition result of acoustic model. The acoustic model more robust than language model in Korean environment. The result of post-processing work was made into KIF(Keyword information file). When threshold of acoustic model's output level was 100, 86.9% of whole target morpheme was included in post-processing result. At the same condition, applying length information based normalization, 81.25% of whole target morpheme was recognized. The purpose of normalization was to compensate long-length morpheme. According to experiment result, 75.13% of whole target morpheme was recognized KIF(314MB) had been produced from original news data(5,040MB). The decrease rate of absolute information met was approximately 93.8%.

• The Journal of Korean Society for Radiation Therapy
• /
• v.14 no.1
• /
• pp.79-84
• /
• 2002

The main cause factor for effective the output, especially in small & irregular shaped field of electron beam therapy, are collimation system, insert block diameter and energy. In the absorption deose of treatment fields, we should consider the lateral build-up ratio (LBR), which the ratio of dose at a point at depth for a given circular field to the dose at the same point for a 'broad-field', for the same incident fluence and profile. The LBR data for a small circular field are used to extract radial spread of the pencil beam, ${\sigma}$, as a function of depth and energy. It's based on elementary pencil beam. We consider availability of the factor, ${\sigma}$, in the small & irregular fields electron beam treatment.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.4 no.1
• /
• pp.25-44
• /
• 2010

With the increasing popularity of mobile devices, it has become necessary to protect private information and content in these devices. Face recognition has been favored over conventional passwords or security keys, because it can be easily implemented using a built-in camera, while providing user convenience. However, because mobile devices can be used both indoors and outdoors, there can be many illumination changes, which can reduce the accuracy of face recognition. Therefore, we propose a new face recognition method on a mobile device robust to illumination variations. This research makes the following four original contributions. First, we compared the performance of face recognition with illumination variations on mobile devices for several illumination normalization procedures suitable for mobile devices with low processing power. These include the Retinex filter, histogram equalization and histogram stretching. Second, we compared the performance for global and local methods of face recognition such as PCA (Principal Component Analysis), LNMF (Local Non-negative Matrix Factorization) and LBP (Local Binary Pattern) using an integer-based kernel suitable for mobile devices having low processing power. Third, the characteristics of each method according to the illumination va iations are analyzed. Fourth, we use two matching scores for several methods of illumination normalization, Retinex and histogram stretching, which show the best and $2^{nd}$ best performances, respectively. These are used as the inputs of an SVM (Support Vector Machine) classifier, which can increase the accuracy of face recognition. Experimental results with two databases (data collected by a mobile device and the AR database) showed that the accuracy of face recognition achieved by the proposed method was superior to that of other methods.

• Journal of IKEEE
• /
• v.24 no.3
• /
• pp.883-889
• /
• 2020

In this paper, we propose a method to use PV(Park's Vector) pattern for inductive motor stator fault diagnosis using CNN(Convolution Neural Network). The conventional CNN based fault diagnosis method was performed by imaging three-phase currents, but this method was troublesome to perform normalization by artificially setting the starting point and phase of current. However, when using PV pattern, the problem of normalization could be solved because the 3-phase current shows a certain circular pattern. In addition, the proposed method is proved to be superior in the accuracy of CNN by 18.18[%] compared to the previous current data image due to the autonomic normalization.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.45-54
• /
• 2021

Recently, deep learning-based denoising approaches have been actively studied. In particular, with the advances of blind denoising techniques, it become possible to train a deep learning-based denoising model only with noisy images in an image domain where it is impossible to obtain a clean image. We no longer require pairs of a clean image and a noisy image to obtain a restored clean image from the observation. However, it is difficult to recover the target using a deep learning-based denoising model trained by only noisy images if the distribution of the noisy image is far from the distribution of the clean image. To address this limitation, unpaired image denoising approaches have recently been studied that can learn the denoising model from unpaired data of the noisy image and the clean image. ISCL showed comparable performance close to that of supervised learning-based models based on pairs of clean and noisy images. In this study, we propose suitable normalization techniques for each purpose of architectures (e.g., generator, discriminator, and extractor) of ISCL. We demonstrate that the proposed method outperforms state-of-the-art unpaired image denoising approaches including ISCL.

• International Journal of Computer Science & Network Security
• /
• v.22 no.9
• /
• pp.175-182
• /
• 2022

In our daily life, we come across different types of information, for example in the format of multimedia and text. We all need different types of information for our common routines as watching/reading the news, listening to the radio, and watching different types of videos. However, sometimes we could run into problems when a certain type of information is required. For example, someone is listening to the radio and wants to listen to jazz, and unfortunately, all the radio channels play pop music mixed with advertisements. The listener gets stuck with pop music and gives up searching for jazz. So, the above example can be solved with an automatic audio classification system. Deep Learning (DL) models could make human life easy by using audio classifications, but it is expensive and difficult to deploy such models at edge devices like nano BLE sense raspberry pi, because these models require huge computational power like graphics processing unit (G.P.U), to solve the problem, we proposed DL model. In our proposed work, we had gone for a low complexity model for Audio Event Detection (AED), we extracted Mel-spectrograms of dimension 128×431×1 from audio signals and applied normalization. A total of 3 data augmentation methods were applied as follows: frequency masking, time masking, and mixup. In addition, we designed Convolutional Neural Network (CNN) with spatial dropout, batch normalization, and separable 2D inspired by VGGnet [1]. In addition, we reduced the model size by using model quantization of float16 to the trained model. Experiments were conducted on the updated dataset provided by the Detection and Classification of Acoustic Events and Scenes (DCASE) 2020 challenge. We confirm that our model achieved a val_loss of 0.33 and an accuracy of 90.34% within the 132.50KB model size.

• 한국체육학회지인문사회과학편
• /
• v.53 no.5
• /
• pp.521-531
• /
• 2014

The purposes of this study were to evaluate the effect of normalization by dimensionless number of Hof(1996) and to analysis the gait pattern for 20s Korean males and females. Subjects are selected in accordance with classification system of Korean standard body figure and age. Experimental equipment is the Motion capture system. Subjects who are walked at a self-selected normal walking speed were photographed using the Motion capture system and analyzed using 3D motion analysis method with OrthoTrak, Cortex, Matlab and SPSS for a statistical test. When used to normalize data, there are no differences of statistical significances between gender in all spatiotemporal variables. I concluded that gait research for mutual comparison requires a normalization by dimensionless number to eliminate the effects of the body size and to accurate statistical analysis.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.16 no.6
• /
• pp.1-15
• /
• 2017

Recently terrorism targets unspecified masses and causes massive destruction, which is so-called Super Terrorism. Many countries have tried hard to protect their citizens with various preparation and safety net. With inexpensive and advanced technologies of sensors, the surveillance systems have been paid attention, but few studies associated with the classification of the pedestrians' trajectories and the difference among themselves have attempted. Therefore, we collected individual trajectories at Samseoung Station using an analytical solution (system) of pedestrian trajectory by LiDAR sensor. Based on the collected trajectory data, a comprehensive framework of classifying the types of pedestrians' trajectories has been developed with data normalization and "trajectory association rule-based algorithm." As a result, trajectories with low similarity within the very same cluster is possibly detected.

• Pediatric Gastroenterology, Hepatology & Nutrition
• /
• v.25 no.2
• /
• pp.147-162
• /
• 2022

Purpose: To design a prospective study on endovascular closure of congenital portosystemic shunts. The primary endpoint was to assess the safety of endovascular closure. The secondary endpoint was to evaluate the clinical, analytical and imaging outcomes of treatment. Methods: Fifteen patients (age range: 2 days to 21 years; 10 male) were referred to our center due to congenital portosystemic shunts. The following data were collected prior to treatment: age, sex, medical history, clinical and analytical data, urine trimethylaminuria, abdominal-US, and body-CT. The following data were collected at the time of intervention: anatomical and hemodynamic characteristics of the shunts, device used, and closure success. The following data were collected at various post-intervention time points: during hospital stay (to confirm shunt closure and detect complications) and at one year after (for clinical, analytical, and imaging purposes). Results: The treatment was successful in 12 participants, migration of the device was observed in two, while acute splanchnic thrombosis was observed in one. Off-label devices were used in attempting to close the side-to-side shunts, and success was achieved using Amplatzer™ Ductus-Occluder and Amplatzer™ Muscular-Vascular-Septal-Defect-Occluder. The main changes were: increased prothrombin activity (p=0.043); decreased AST, ALT, GGT, and bilirubin (p=0.007, p=0.056, p=0.036, p=0.013); thrombocytopenia resolution (p=0.131); expansion of portal veins (p=0.005); normalization of Doppler portal flow (100%); regression of liver nodules (p=0.001); ammonia normalization (p=0.003); and disappearance of trimethylaminuria (p=0.285). Conclusion: Endovascular closure is effective. Our results support the indication of endovascular closure for side-to-side shunts and for cases of congenital absence of portal vein.

• Proceedings of the Korean Institute of Building Construction Conference
• /
• 2009.11a
• /
• pp.253-256
• /
• 2009

To the success of the megaproject including various and complex facilities, it is needed to establish a database system. Developments in data collection, storage and extracting technology have enabled iPMIS to manage various and complex information about cost and time. Especially, when we consider that both the go and no go decision in feasibility, Cost is an important and clear criteria in megaproject. Thus, Cost data modeling is the basis of the system and is necessary process. This research is focus on the structure and definition about CBS data which is collected from sites. We used four tools which are Function Analysis in VE, Casual loop Diagram in System Dynamics, Decision Tree in Data-mining, and Normalization in SQL to identify its cause and effect relationship on CBS data. Cost data modeling provide iPMIS with helpful guideline.