• 한국멀티미디어학회논문지
• /
• 제22권7호
• /
• pp.749-758
• /
• 2019

This paper proposes a data augmentation algorithm to improve the performance of DNN(Deep Neural Network) based speech enhancement. Many deep learning models are exploring algorithms to maximize the performance in limited amount of data. The most commonly used algorithm is the data augmentation which is the technique artificially increases the amount of data. For the effective data augmentation algorithm, we used a formant enhancement method that assign the different weights to the formant frequencies. The DNN model which is trained using the proposed data augmentation algorithm was evaluated in various noise environments. The speech enhancement performance of the DNN model with the proposed data augmentation algorithm was compared with the algorithms which are the DNN model with the conventional data augmentation and without the data augmentation. As a result, the proposed data augmentation algorithm showed the higher speech enhancement performance than the other algorithms.

• Communications for Statistical Applications and Methods
• /
• 제30권3호
• /
• pp.343-354
• /
• 2023

Recently, there have been many improvements in general language models using architectures such as GPT-3 proposed by Brown et al. (2020). Nevertheless, training complex models can hardly be done if the number of data is very small. Data augmentation that addressed this problem was more than normal success in image data. Image augmentation technology significantly improves model performance without any additional data or architectural changes (Perez and Wang, 2017). However, applying this technique to textual data has many challenges because the noise to be added is veiled. Thus, we have developed a novel method for performing data augmentation on text data. We divide the data into signals with positive or negative meaning and noise without them, and then perform data augmentation using k-doc augmentation to randomly combine signals and noises from all data to generate new data.

• 한국정보처리학회:학술대회논문집
• /
• 한국정보처리학회 2023년도 추계학술발표대회
• /
• pp.124-125
• /
• 2023

Defect detection during liquid crystal display (LCD) manufacturing has always been a critical challenge. This study aims to address this issue by proposing a data augmentation method based on generative adversarial networks (GAN) to improve defect identification accuracy in LCD production. By leveraging synthetically generated image data from GAN, we effectively augment the original dataset to make it more representative and diverse. This data augmentation strategy enhances the model's generalization capability and robustness on real-world data. Compared to traditional data augmentation techniques, the synthetic data from GAN are more realistic, diverse and broadly distributed. Experimental results demonstrate that training models with GAN-generated data combined with the original dataset significantly improves the detection accuracy of critical defects in LCD manufacturing, compared to using the original dataset alone. This study provides an effective data augmentation approach for intelligent quality control in LCD production.

• 전기전자학회논문지
• /
• 제26권2호
• /
• pp.176-185
• /
• 2022

데이터 증강이란 다양한 데이터 변환 및 왜곡을 통해 데이터셋의 크기와 품질을 개선하는 기법으로, 기계학습 모델의 과적합 문제를 해결하기 위한 대표적인 접근법이다. 그러나 심층학습 이미지 생성 모델인 GAN 기반 모델에서 데이터 증강을 적용하면 생성된 이미지에 데이터 변환과 왜곡이 반영되는 증강 누출 문제가 발생하여 생성 이미지의 품질이 하락한다. 이러한 문제를 해결하기 위해 본 논문에서는 데이터 증강의 종류와 수에 관계없이 증강 누출을 방지하는 기법을 제안한다. 증강 누출의 발생 조건을 분석하였으며, 보조적인 데이터 증강 작업 분류기를 GAN 모델에 적용하여 증강 누출을 방지하였다. 정성적 정량적 평가를 통해 제안된 기법을 적용하면 증강 누출이 발생하지 않음을 보이고 추가적으로 생성 이미지의 품질을 향상시키며 기존 기법과 비교하여 발전된 성능을 보임을 입증하였다.

• Journal of information and communication convergence engineering
• /
• 제21권3호
• /
• pp.208-215
• /
• 2023

Deep learning techniques provide powerful solutions to several pattern-recognition problems, including Raman spectral classification. However, these networks require large amounts of labeled data to perform well. Labeled data, which are typically obtained in a laboratory, can potentially be alleviated by data augmentation. This study investigated various data augmentation techniques and applied multiple deep learning methods to Raman spectral classification. Raman spectra yield fingerprint-like information about chemical compositions, but are prone to noise when the particles of the material are small. Five augmentation models were investigated to build robust deep learning classifiers: weighted sums of spectral signals, imitated chemical backgrounds, extended multiplicative signal augmentation, and generated Gaussian and Poisson-distributed noise. We compared the performance of nine state-of-the-art convolutional neural networks with all the augmentation techniques. The LeNet5 models with background noise augmentation yielded the highest accuracy when tested on real-world Raman spectral classification at 88.33% accuracy. A class activation map of the model was generated to provide a qualitative observation of the results.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제12권1호
• /
• pp.1-5
• /
• 2012

Data reduction has been used widely in data mining for convenient analysis. Principal component analysis (PCA) and factor analysis (FA) methods are popular techniques. The PCA and FA reduce the number of variables to avoid the curse of dimensionality. The curse of dimensionality is to increase the computing time exponentially in proportion to the number of variables. So, many methods have been published for dimension reduction. Also, data augmentation is another approach to analyze data efficiently. Support vector machine (SVM) algorithm is a representative technique for dimension augmentation. The SVM maps original data to a feature space with high dimension to get the optimal decision plane. Both data reduction and augmentation have been used to solve diverse problems in data analysis. In this paper, we compare the strengths and weaknesses of dimension reduction and augmentation for classification and propose a classification method using data reduction for classification. We will carry out experiments for comparative studies to verify the performance of this research.

• 방송공학회논문지
• /
• 제25권6호
• /
• pp.854-860
• /
• 2020

심층 신경망은 영상 분류 그리고 음성 인식 등 다양한 분야에서 뛰어난 성능을 보여주었다. 그 중에서 데이터 증대를 통해 생성된 다양한 데이터는 신경망의 성능을 향상하게 시키는 데 중요한 역할을 했다. 일반적으로 데이터의 변형을 통한 증대는 신경망이 다채로운 예시를 접하고 더 일반적으로 학습되는 것을 가능하게 했다. 기존의 영상 분야에서는 신경망 성능 향상을 위해 새로운 증대 방법을 제시할 뿐만 아니라 데이터와 신경망의 구조에 따라 변화할 수 있는 최적의 데이터 증대 방법의 탐색 방법을 제안해왔다. 본 논문은 이에 영감을 받아 음향 분야에서 최적의 데이터 증대 방법을 탐색하는 것을 목표로 한다. 잡음 추가, 음의 높낮이 변경 혹은 재생 속도를 조절하는 등의 증대 방법들을 다양하게 조합하는 실험을 통해 경험적으로 어떤 증대 방법이 가장 효과적인지 탐색했다. 결과적으로 자연 음향 데이터 세트 (ESC-50)에 최적화된 데이터 증대 방법을 적용함으로써 분류 정확도를 향상하게 시킬 수 있었다.

• ETRI Journal
• /
• 제44권2호
• /
• pp.327-338
• /
• 2022

Classification models for human action recognition require robust features and large training sets for good generalization. However, data augmentation methods are employed for imbalanced training sets to achieve higher accuracy. These samples generated using data augmentation only reflect existing samples within the training set, their feature representations are less diverse and hence, contribute to less precise classification. This paper presents new data augmentation and action representation approaches to grow training sets. The proposed approach is based on two fundamental concepts: virtual video generation for augmentation and representation of the action videos through robust features. Virtual videos are generated from the motion history templates of action videos, which are convolved using a convolutional neural network, to generate deep features. Furthermore, by observing an objective function of the genetic algorithm, the spatiotemporal features of different samples are combined, to generate the representations of the virtual videos and then classified through an extreme learning machine classifier on MuHAVi-Uncut, iXMAS, and IAVID-1 datasets.

• 응용통계연구
• /
• 제36권2호
• /
• pp.101-114
• /
• 2023

데이터 증강 기법은 학습용 데이터셋을 다양한 관점에서 볼 수 있게 해주어 모형의 과적합 문제를 해결하는데 효과적으로 사용되고 있다. 이미지 데이터 증강기법으로 회전, 잘라내기, 좌우대칭, 상하대칭등의 증강 기법 외에도 occlusion 기반 데이터 증강 방법인 Cutmix, Cutout 등이 제안되었다. 음성 데이터에 기반한 모형들에 있어서도, 1D 음성 신호를 2D 스펙트로그램으로 변환한 후, occlusion 기반 데이터 기반 증강기법의 사용이 가능하다. 특히, SpecAugment는 음성 스펙트로그램을 위해 제안된 occlusion 기반 증강 기법이다. 본 연구에서는 위조 음성 탐지 문제에 있어서 사용될 수 있는 데이터 증강기법에 대해 비교 연구해보고자 한다. Fake audio를 탐지하기 위해 개최된 ASVspoof2017과 ASVspoof2019 데이터를 사용하여 음성을 2D 스펙트로그램으로 변경시켜 occlusion 기반 데이터 증강 방식인 Cutout, Cutmix, SpecAugment를 적용한 데이터셋을 훈련 데이터로 하여 CNN 모형을 경량화시킨 LCNN 모형을 훈련시켰다. Cutout, Cutmix, SpecAugment 세 증강 기법 모두 대체적으로 모형의 성능을 향상시켰으나 방법에 따라 오히려 성능을 저하시키거나 성능에 변화가 없을 수도 있었다. ASVspoof2017 에서는 Cutmix, ASVspoof2019 LA 에서는 Mixup, ASVspoof2019 PA 에서는 SpecAugment 가 가장 좋은 성능을 보였다. 또, SpecAugment는 mask의 개수를 늘리는 것이 성능 향상에 도움이 된다. 결론적으로, 상황과 데이터에 따라 적합한 augmentation 기법이 다른 것으로 파악된다.

• 대한의용생체공학회:의공학회지
• /
• 제40권2호
• /
• pp.48-54
• /
• 2019

This paper proposed a method of validation data augmentation for improving the grading accuracy of diabetic macular edema (DME) using deep learning. The data augmentation technique is basically applied in order to secure diversity of data by transforming one image to several images through random translation, rotation, scaling and reflection in preparation of input data of the deep neural network (DNN). In this paper, we apply this technique in the validation process of the trained DNN, and improve the grading accuracy by combining the classification results of the augmented images. To verify the effectiveness, 1,200 retinal images of Messidor dataset was divided into training and validation data at the ratio 7:3. By applying random augmentation to 359 validation data, $1.61{\pm}0.55%$ accuracy improvement was achieved in the case of six times augmentation (N=6). This simple method has shown that the accuracy can be improved in the N range from 2 to 6 with the correlation coefficient of 0.5667. Therefore, it is expected to help improve the diagnostic accuracy of DME with the grading information provided by the proposed DNN.