• Journal of Digital Contents Society
• /
• v.19 no.6
• /
• pp.1177-1183
• /
• 2018

Recent developments in machine learning have attracted a lot of attention for techniques such as machine learning and deep learning that implement artificial intelligence. In this paper, binary malicious code using deep learning based R-CNN is imaged and the feature is extracted from the image to classify the family. In this paper, two steps are used in deep learning to image malicious code using CNN. And classify the characteristics of the family of malicious codes using R-CNN. Generate malicious code as an image, extract features, classify the family, and automatically classify the evolution of malicious code. The detection rate of the proposed method is 93.4% and the accuracy is 98.6%. In addition, the CNN processing speed for image processing of malicious code is 23.3 ms, and the R-CNN processing speed is 4ms to classify one sample.

• The Journal of the Acoustical Society of Korea
• /
• v.36 no.6
• /
• pp.407-412
• /
• 2017

In this paper, we propose a speech emotion recognition method using a deep neural network based on the attention mechanism. The proposed method consists of a combination of CNN (Convolution Neural Networks), GRU (Gated Recurrent Unit), DNN (Deep Neural Networks) and attention mechanism. The spectrogram of the speech signal contains characteristic patterns according to the emotion. Therefore, we modeled characteristic patterns according to the emotion by applying the tuned Gabor filters as convolutional filter of typical CNN. In addition, we applied the attention mechanism with CNN and FC (Fully-Connected) layer to obtain the attention weight by considering context information of extracted features and used it for emotion recognition. To verify the proposed method, we conducted emotion recognition experiments on six emotions. The experimental results show that the proposed method achieves higher performance in speech emotion recognition than the conventional methods.

• Proceedings of the Microbiological Society of Korea Conference
• /
• 2007.05a
• /
• pp.80-82
• /
• 2007

We have isolated numerous cold deep-sea adapted microorganisms (piezophilic, formerly referred to as "barophilic" bacteria) using deep-sea research submersibles. Many of the isolates are novel psychrophilic bacteria, and we have identified several new piezophilic species, i.e., Photobacterium profundum, Shewanella violacea, Moritella japonica, Moritella yayanosii, Psychromonas kaikoi, and Colwellia piezophila. These piezophiles are involving to five genera in gamma-Proteobacteria subgroup and produce significant amounts of unsaturated fatty acids in their cell membrane fractions to maintain the membrane fluidity in cold and high-pressure environments. Piezophilic microorganisms have been identified in many deep-sea bottoms of many of the world oceans. Therefore, these microbes are well distributed on our planet. One of the isolated deep-sea piezophiles, Shewanella violacea strain DSS12 is a psychrophilic, moderately piezophilic bacterium from a sediment sample collected at the Ryukyu Trench (depth: 5,110 m), which grows optimally at 30 MPa and $8^{\circ}C$ but also grows at atmospheric pressure (0.1 MPa) and $8^{\circ}C$. We have examined this strain to elucidate the molecular basis for gene regulation at different pressure conditions because this strain is useful as a model bacterium for comparing the various features of bacterial physiology under pressure conditions. In addition, we completed the sequencing of the entire genome of this piezophilic bacterium and we expect that many biotechnologically useful genes will be identified from the genome information.

• Korean Journal of Bronchoesophagology
• /
• v.16 no.2
• /
• pp.115-120
• /
• 2010

Background: Pediatric deep neck infection can cause critical complications in that they are seldom able to verbalize symptoms or cooperate with physical examination. The objective of this study is to identify the clinical characteristics according to age. Material and Method: A retrospective study was performed on 26 cases with pediatric deep neck infection during 12 years. Patients were classified infancy group (1-7 yr, 19.2%), preschool age group (7-15 yr, 30.8%) and school age group (15 yr-, 50%). We analyzed the age, sex, sites of abscess, predisposing factors, symptoms and compared onset, hospital date, laboratory and outcomes at each group. Results: In pediatric patients with deep neck infection, the age distribution was 18 males (69.2%) and 8 females (30.8%), the mean age was 7.4 years. The most common infection site was the anterior cervical triangle and submandibular space (19.2%). The most commonly known associated preceding disease was upper viral infection (34.6%), but we could not find the preceding diseases in most of cases (50%). Neck swelling (69.2%) was the most frequent symptom. The mean age of patients who performed neck CT was 8.23 years and neck US was 2.75 years. The younger patients were preferred to perform the neck US than the neck CT (p=0.022). The mean time from disease onset to admission was 9 days in the infancy, 5.5 days in the preschool aged and 5 days in the school aged group. The surgical treatment was performed in 30.8% of school aged, 62.5% of preschool aged and 100% of infancy group. Surgical treatment was preferred to younger patients (p=0.026). Conclusion: Abscess sites, size, and antibiotics susceptibility and especially patient age should be carefully considered in treating pediatric deep neck infection.

• Journal of Broadcast Engineering
• /
• v.24 no.2
• /
• pp.234-242
• /
• 2019

In this paper, we propose a deep neural network which extracts SIFT feature points by determining whether the center pixel of a cropped image is a SIFT feature point. The data set of this network consists of a DIV2K dataset cut into $33{\times}33$ size and uses RGB image unlike SIFT which uses black and white image. The ground truth consists of the RobHess SIFT features extracted by setting the octave (scale) to 0, the sigma to 1.6, and the intervals to 3. Based on the VGG-16, we construct an increasingly deep network of 13 to 23 and 33 convolution layers, and experiment with changing the method of increasing the image scale. The result of using the sigmoid function as the activation function of the output layer is compared with the result using the softmax function. Experimental results show that the proposed network not only has more than 99% extraction accuracy but also has high extraction repeatability for distorted images.

• Animal Bioscience
• /
• v.36 no.6
• /
• pp.980-989
• /
• 2023

Objective: Iris pattern recognition system is well developed and practiced in human, however, there is a scarcity of information on application of iris recognition system in animals at the field conditions where the major challenge is to capture a high-quality iris image from a constantly moving non-cooperative animal even when restrained properly. The aim of the study was to validate and identify Black Bengal goat biometrically to improve animal management in its traceability system. Methods: Forty-nine healthy, disease free, 3 months±6 days old female Black Bengal goats were randomly selected at the farmer's field. Eye images were captured from the left eye of an individual goat at 3, 6, 9, and 12 months of age using a specialized camera made for human iris scanning. iGoat software was used for matching the same individual goats at 3, 6, 9, and 12 months of ages. Resnet152V2 deep learning algorithm was further applied on same image sets to predict matching percentages using only captured eye images without extracting their iris features. Results: The matching threshold computed within and between goats was 55%. The accuracies of template matching of goats at 3, 6, 9, and 12 months of ages were recorded as 81.63%, 90.24%, 44.44%, and 16.66%, respectively. As the accuracies of matching the goats at 9 and 12 months of ages were low and below the minimum threshold matching percentage, this process of iris pattern matching was not acceptable. The validation accuracies of resnet152V2 deep learning model were found 82.49%, 92.68%, 77.17%, and 87.76% for identification of goat at 3, 6, 9, and 12 months of ages, respectively after training the model. Conclusion: This study strongly supported that deep learning method using eye images could be used as a signature for biometric identification of an individual goat.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.05a
• /
• pp.169-171
• /
• 2021

Image processing through cameras such as self-driving, CCTV, mobile phone security, and parking facilities is being used to solve many real-life problems. Simple classification is solved through image processing, but it is difficult to find images or in-image features of complexly mixed objects. To solve this feature point, we utilize deep learning techniques in classification, detection, and segmentation of image data so that we can think and judge closely. Of course, the results are better than just image processing, but we confirm that the results judged by the method of image segmentation using deep learning have deviations from the real object. In this paper, we study how to perform accuracy improvement through simple image processing just before outputting the output of deep learning image segmentation to increase the precision of image segmentation.

• Journal of Korea Society of Industrial Information Systems
• /
• v.28 no.6
• /
• pp.1-10
• /
• 2023

The nuclear power plant(NPP)'s Instrumentation and Control(I&C) system periodically conducts integrity checks for the maintenance of self-diagnostic function during normal operation. Additionally, it performs functionality and performance checks during planned preventive maintenance periods. However, there is a need for technological development to diagnose failures and prevent accidents in advance. In this paper, we studied methods for estimating the reliability function by utilizing environmental data and self-diagnostic data of the I&C equipment. To obtain failure data, we assumed probability distributions for component features of the I&C equipment and generated virtual failure data. Using this failure data, we estimated the reliability function using representative artificial intelligence(AI) models used in survival analysis(DeepSurve, DeepHit). And we also estimated the reliability function through the Cox regression model of the traditional semi-parametric method. We confirmed the feasibility through the residual lifetime calculations based on environmental and diagnostic data.

• The Journal of Korea Institute of Information, Electronics, and Communication Technology
• /
• v.16 no.6
• /
• pp.369-377
• /
• 2023

In the industrial manufacturing sector, quality control is pivotal for minimizing defect rates; inadequate management can result in additional costs and production delays. This study underscores the significance of detecting texture defects in manufactured goods and proposes a more precise defect detection technique. While the DFR(Deep Feature Reconstruction) model adopted an approach based on feature map amalgamation and reconstruction, it had inherent limitations. Consequently, we incorporated a new loss function using statistical methodologies, integrated a skip connection structure, and conducted parameter tuning to overcome constraints. When this enhanced model was applied to the texture category of the MVTec-AD dataset, it recorded a 2.3% higher Defect Segmentation AUC compared to previous methods, and the overall defect detection performance was improved. These findings attest to the significant contribution of the proposed method in defect detection through the reconstruction of feature map combinations.

• Wind and Structures
• /
• v.39 no.4
• /
• pp.271-285
• /
• 2024

The multiple-fan wind tunnel is an important facility for reproducing target wind field. Existing control methods for the multiple-fan wind tunnel can generate wind speeds that satisfy the target statistical characteristics of a wind field (e.g., power spectrum). However, the frequency-domain features cannot well represent the nonstationary winds of extreme storms (e.g., downburst). Therefore, this study proposes a multiple-fan wind tunnel control scheme based on Deep Reinforcement Learning (DRL), which will completely transform into a data-driven closed-loop control problem, to reproduce the target wind field in the time domain. Specifically, the control scheme adopts the Deep Deterministic Policy Gradient (DDPG) paradigm in which the strong fitting ability of Deep Neural Networks (DNN) is utilized. It can establish the complex relationship between the target wind speed time series and the current control strategy in the DRL-agent. To address the fluid memory effect of the wind field, this study innovatively designs the system state and control reward to improve the reproduction performance based on historical data. To validate the performance of the model, we established a simplified flow field based on Navier Stokes equations to simulate a two-dimensional numerical multiple-fan wind tunnel environment. Using the strategy of DRL decision maker, we generated a wind speed time series with minor error from the target under low Reynolds number conditions. This is the first time that the AI methods have been used to generate target wind speed time series in a multiple-fan wind tunnel environment. The hyperparameters in the DDPG paradigm are analyzed to identify a set of optimal parameters. With these efforts, the trained DRL-agent can simultaneously reproduce the wind speed time series in multiple positions.