• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.449-451
• /
• 2022

암호화 프로그램에서 난수생성기는 널리 사용되며 중요한 역할을 하므로 공격의 대상이 되기 쉽고, 따라서 높은 난수성을 확보해야 한다. 최근에는 인공 신경망 기술이 발달함에 따라 난수생성기에 딥러닝 기술을 적용하는 연구들이 다수 진행되었으며, 본 논문에서는 이러한 연구 동향에 대해 알아본다. 크게 난수를 생성하는 연구와 다음에 올 수를 예측하는 예측 공격으로 나뉜다. 공통적으로는 학습해야 할 대상인 난수가 시계열 데이터이므로 대부분의 연구들이 RNN, CNN-1D 신경망을 사용한다. 난수 생성을 위해서는 분류형 신경망이 아닌, 생성형 신경망과 강화학습을 주로 사용하였다. 대부분의 연구들이 NIST SP-800 테스트를 시행하였을 때 높은 난수성을 확보할 수 있었다. 이외에도 최근 양자 컴퓨터가 개발됨에 따라 양자 하드웨어로부터의 양자 난수 생성기에 대한 예측 공격에 관한 연구도 있다. 딥러닝 기반의 난수 생성기에 대해서, 향후에는 기존의 난수생성기보다 빠른 생성 속도를 달성할 수 있는 경량 구현에 대한 연구와 그에 대한 비교 및 평가가 있어야 할 것으로 생각된다.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2023.07a
• /
• pp.7-10
• /
• 2023

최근 기후 변화가 심각해짐에 따라 수소 에너지에 대한 관심이 집중되고 있으며 이를 안전하게 운송/보관할 수 있는 용기에 대한 연구도 활발히 진행되고 있다. 특히 고압 가스를 저장하는 TypeIII 용기의 노후화 및 안전과 관련되어 결함을 인지하는 연구가 활발하다. 그러나 이 용기의 외각층을 이루는 CFRP 소재는 탄소 섬유와 에폭시가 복잡한 구조로 구성되어 결함별 탐지가 매우 어렵다. 본 논문에서는 음향방출시험과 딥러닝을 활용하여 CFRP 결함 데이터셋을 구축하고 이를 분류할 수 있는 모델을 제안한다. 특히 CFRP 시편을 직접 제작하여 AE 센서를 부착하고 파괴하여 파형 데이터를 수집하였다. 이후 표현 학습을 통해 데이터의 특징을 압축/추출하고 유사도를 비교해 결함별 데이터를 판별하는 알고리즘을 개발하였다. 구축된 데이터셋의 실루엣 계수는 0.86으로 높은 군집도를 보였다. 마지막으로 구축된 데이터셋을 실시간으로 분류할 수 있는 1D-CNN 딥러닝 모델을 개발하였으며 99.33%의 높은 분류 정확도를 보였다.

• The Korean Journal of Applied Statistics
• /
• v.36 no.2
• /
• pp.101-114
• /
• 2023

The data augmentation technique is effectively used to solve the problem of overfitting the model by allowing the training dataset to be viewed from various perspectives. In addition to image augmentation techniques such as rotation, cropping, horizontal flip, and vertical flip, occlusion-based data augmentation methods such as Cutmix and Cutout have been proposed. For models based on speech data, it is possible to use an occlusion-based data-based augmentation technique after converting a 1D speech signal into a 2D spectrogram. In particular, SpecAugment is an occlusion-based augmentation technique for speech spectrograms. In this study, we intend to compare and study data augmentation techniques that can be used in the problem of false-voice detection. Using data from the ASVspoof2017 and ASVspoof2019 competitions held to detect fake audio, a dataset applied with Cutout, Cutmix, and SpecAugment, an occlusion-based data augmentation method, was trained through an LCNN model. All three augmentation techniques, Cutout, Cutmix, and SpecAugment, generally improved the performance of the model. In ASVspoof2017, Cutmix, in ASVspoof2019 LA, Mixup, and in ASVspoof2019 PA, SpecAugment showed the best performance. In addition, increasing the number of masks for SpecAugment helps to improve performance. In conclusion, it is understood that the appropriate augmentation technique differs depending on the situation and data.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2016.06a
• /
• pp.37-39
• /
• 2016

최근 Convolutional neural networks(CNN) 기반의 초해상화 기법인 Super-Resolution Convolutional Neural Networks (SRCNN) 이 좋은 PSNR 성능을 발휘하는 것으로 보고되었다 [1]. 하지만 많은 제안 방법들이 고주파 성분을 복원하는데 한계를 드러내는 것처럼, SRCNN 도 고주파 성분 복원에 한계점을 지니고 있다. 또한 SRCNN 의 네트워크 층을 깊게 만들면 좋은 PSNR 성능을 발휘하는 것으로 널리 알려져 있지만, 네트워크의 층을 깊게 하는 것은 네트워크 파라미터 학습을 어렵게 하는 경향이 있다. 네트워크의 층을 깊게 할 경우, gradient 값이 아래(역방향) 층으로 갈수록 발산하거나 0 으로 수렴하여, 네트워크 파라미터 학습이 제대로 되지 않는 현상이 발생하기 때문이다. 따라서 본 논문에서는 네트워크 층을 깊게 하는 대신에, 입력을 다중 채널로 구성하여, 네트워크에 고주파 성분에 관한 추가적인 정보를 주는 방법을 제안하였다. 많은 초해상화 기법들이 고주파 성분의 복원 능력이 부족하다는 점에 착안하여, 우리는 네트워크가 고주파 성분에 관한 많은 정보를 필요로 한다는 것을 가정하였다. 따라서 우리는 네트워크의 입력을 고주파 성분이 여러 가지 강도로 입력되도록 저해상도 입력 영상들을 구성하였다. 또한 잔차신호 네트워크(residual networks)를 도입하여, 네트워크 파라미터를 학습할 때 고주파 성분의 복원에 집중할 수 있도록 하였다. 본 논문의 효율성을 검증하기 위하여 set5 데이터와 set14 데이터에 관하여 실험을 진행하였고, SRCNN 과 비교하여 set5 데이터에서는 2, 3, 4 배에 관하여 각각 평균 0.29, 0.35, 0.17dB 의 PSNR 성능 향상이 있었으며, set14 데이터에서는 3 배의 관하여 평균 0.20dB 의 PSNR 성능 향상이 있었다.

• International journal of advanced smart convergence
• /
• v.12 no.4
• /
• pp.434-442
• /
• 2023

The relationship between acute kidney injury (AKI) prediction and nephrotoxic drugs, or drugs that adversely affect kidney function, is one that has yet to be explored in the critical care setting. One contributing factor to this gap in research is the limited investigation of drug modalities in the intensive care unit (ICU) context, due to the challenges of processing prescription data into the corresponding drug representations and a lack in the comprehensive understanding of these drug representations. This study addresses this gap by proposing a novel approach that leverages patient prescription data as a modality to improve existing models for AKI prediction. We base our research on Electronic Health Record (EHR) data, extracting the relevant patient prescription information and converting it into the selected drug representation for our research, the extended-connectivity fingerprint (ECFP). Furthermore, we adopt a unique multimodal approach, developing machine learning models and 1D Convolutional Neural Networks (CNN) applied to clinical drug representations, establishing a procedure which has not been used by any previous studies predicting AKI. The findings showcase a notable improvement in AKI prediction through the integration of drug embeddings and other patient cohort features. By using drug features represented as ECFP molecular fingerprints along with common cohort features such as demographics and lab test values, we achieved a considerable improvement in model performance for the AKI prediction task over the baseline model which does not include the drug representations as features, indicating that our distinct approach enhances existing baseline techniques and highlights the relevance of drug data in predicting AKI in the ICU setting.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.5
• /
• pp.55-67
• /
• 2022

Sensor data can provide fault diagnosis for equipment. However, the cause analysis for fault results of equipment is not often provided. In this study, we propose an explainable convolutional neural network framework for the sensor-based time series classification model. We used sensor-based time series dataset, acquired from vehicles equipped with sensors, and the Wafer dataset, acquired from manufacturing process. Moreover, we used Cycle Signal dataset, acquired from real world mechanical equipment, and for Data augmentation methods, scaling and jittering were used to train our deep learning models. In addition, our proposed classification models are convolutional neural network based models, FCN, 1D-CNN, and ResNet, to compare evaluations for each model. Our experimental results show that the ResNet provides promising results in the context of time series classification with accuracy and F1 Score reaching 95%, improved by 3% compared to the previous study. Furthermore, we propose XAI methods, Class Activation Map and Layer Visualization, to interpret the experiment result. XAI methods can visualize the time series interval that shows important factors for sensor data classification.

• The Journal of the Acoustical Society of Korea
• /
• v.39 no.5
• /
• pp.406-413
• /
• 2020

In this paper, to improve the classification accuracy of bird and amphibian acoustic sound, we utilize GLU (Gated Linear Unit) and Self-attention that encourages the network to extract important features from data and discriminate relevant important frames from all the input sequences for further performance improvement. To utilize acoustic data, we convert 1-D acoustic data to a log-Mel spectrogram. Subsequently, undesirable component such as background noise in the log-Mel spectrogram is reduced by GLU. Then, we employ the proposed temporal self-attention to improve classification accuracy. The data consist of 6-species of birds, 8-species of amphibians including endangered species in the natural environment. As a result, our proposed method is shown to achieve an accuracy of 91 % with bird data and 93 % with amphibian data. Overall, an improvement of about 6 % ~ 7 % accuracy in performance is achieved compared to the existing algorithms.

• The Transactions of the Korea Information Processing Society
• /
• v.13 no.2
• /
• pp.41-47
• /
• 2024

When there were disparities in performance between models trained in the time and frequency domains, even after conducting an ensemble, we observed that the performance of the ensemble was compromised due to imbalances in the individual model performances. Therefore, this paper proposes a leakage detection technique to enhance the accuracy of pipeline leakage detection through a step-wise learning approach that extracts features from both the time and frequency domains and integrates them. This method involves a two-step learning process. In the Stage 1, independent model training is conducted in the time and frequency domains to effectively extract crucial features from the provided data in each domain. In Stage 2, the pre-trained models were utilized by removing their respective classifiers. Subsequently, the features from both domains were fused, and a new classifier was added for retraining. The proposed transfer learning-based feature fusion technique in this paper performs model training by integrating features extracted from the time and frequency domains. This integration exploits the complementary nature of features from both domains, allowing the model to leverage diverse information. As a result, it achieved a high accuracy of 99.88%, demonstrating outstanding performance in pipeline leakage detection.

• The Journal of the Korea Contents Association
• /
• v.21 no.8
• /
• pp.1-9
• /
• 2021

Deep learning in computer vision has made accelerated improvement over a short period but large-scale learning data and computing power are still essential that required time-consuming trial and error tasks are involved to derive an optimal network model. In this study, we propose a similar image classification performance improvement method based on CR (Confusion Rate) that considers only the characteristics of the data itself regardless of network optimization or data reinforcement. The proposed method is a technique that improves the performance of the deep learning model by calculating the CRs for images in a dataset with similar characteristics and reflecting it in the weight of the Loss Function. Also, the CR-based recognition method is advantageous for image identification with high similarity because it enables image recognition in consideration of similarity between classes. As a result of applying the proposed method to the Resnet18 model, it showed a performance improvement of 0.22% in HanDB and 3.38% in Animal-10N. The proposed method is expected to be the basis for artificial intelligence research using noisy labeled data accompanying large-scale learning data.