• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2017.06a
• /
• pp.250-253
• /
• 2017

본 논문에서는 동시적 위치 추정 및 지도 작성 (simultaneous localization and mapping)에서 루프 폐쇄 검출을 딥러닝 방법의 일종인 variational autoencoder 를 이용하여 수행하는 방법에 대해 살펴본다. Autoencoder 는 비감독 학습 방법의 일종으로 입력 영상이 신경망을 통과하여 얻은 출력 영상과 동일하도록 신경망을 학습시키는 모델이다. 이 때 autoencoder 중간의 병목 지역을 통과함에도 불구하고 입력과 동일한 영상을 계산해야 하는 제약조건이 있기 때문에 이는 차원 축소나 데이터 추상화의 목적으로 많이 사용된다. 여기서 한 단계 더 발전된 variational autoencoder 는 기존의 autoencoder 가 가진 단점인 입력 변수의 분포와 잠재 변수의 분포 사이에 상관관계가 없다는 단점을 해결하기 위해 Kullback-Leibler divergence 를 활용한 손실 함수를 정의하여 사용했다. 실험결과에서는 루프 폐쇄 검출에서 많이 사용되는 City-Centre 와 New College 데이터 집합을 사용하여 평가하였으며 루프 폐쇄 검출의 결과는 정밀도와 재현율을 계산하여 나타냈다.

• Journal of the Korea Computer Graphics Society
• /
• v.27 no.5
• /
• pp.33-43
• /
• 2021

In this paper, we propose a framework that transfers the information of style motions to content motions based on a variational autoencoder network combined with a style encoding in the latent space. Because we transfer a style to a content motion that is sampled from a variational autoencoder, we can increase the diversity of existing motion data. In addition, we can improve the unnatural motions caused by decoding a new latent variable from style transfer. That improvement was achieved by additionally using the velocity information of motions when generating next frames.

• Communications for Statistical Applications and Methods
• /
• v.30 no.6
• /
• pp.589-603
• /
• 2023

Deep generative models target to infer the underlying true data distribution, and it leads to a huge success in generating fake-but-realistic data. Regarding such a perspective, the data attributes can be a crucial factor in the data generation process since non-existent counterfactual samples can be generated by altering certain factors. For example, we can generate new portrait images by flipping the gender attribute or altering the hair color attributes. This paper proposes counterfactual disentangled variational autoencoder generative adversarial networks (CDVAE-GAN), specialized for data attribute level counterfactual data generation. The structure of the proposed CDVAE-GAN consists of variational autoencoders and generative adversarial networks. Specifically, we adopt a Gaussian variational autoencoder to extract low-dimensional disentangled data features and auxiliary Bernoulli latent variables to model the data attributes separately. Also, we utilize a generative adversarial network to generate data with high fidelity. By enjoying the benefits of the variational autoencoder with the additional Bernoulli latent variables and the generative adversarial network, the proposed CDVAE-GAN can control the data attributes, and it enables producing counterfactual data. Our experimental result on the CelebA dataset qualitatively shows that the generated samples from CDVAE-GAN are realistic. Also, the quantitative results support that the proposed model can produce data that can deceive other machine learning classifiers with the altered data attributes.

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.40 no.2
• /
• pp.233-238
• /
• 2020

Most deep learning (DL) approaches for bridge damage localization based on a structural health monitoring system commonly use supervised learning-based DL models. The supervised learning-based DL model requires the response data obtained from sensors on the bridge and also the label which indicates the damaged state of the bridge. However, it is impractical to accurately obtain the label data in fields, thus, the supervised learning-based DL model has a limitation in that it is not easily applicable in practice. On the other hand, an unsupervised learning-based DL model has the merit of being able to train without label data. Considering this advantage, this study aims to propose and theoretically validate a damage localization approach for bridges using a variational autoencoder, a representative unsupervised learning-based DL network: as a result, this study indicated the feasibility of VAE for damage localization.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.28 no.6
• /
• pp.1463-1474
• /
• 2018

Fuzzing is one of the software testing techniques that find security flaws by inputting invalid values or arbitrary values into the program and various methods have been suggested to increase the efficiency of such fuzzing. In this paper, focusing on the existence of field with high relevance to coverage and software crash, we propose a new method for intensively fuzzing corresponding field part while performing field based fuzzing. In this case, we use a deep learning model called Variational Autoencoder(VAE) to learn the statistical characteristic of input values measured in high coverage and it showed that the coverage of the regenerated files are uniformly higher than that of simple variation. It also showed that new crash could be found by learning the statistical characteristic of the files in which the crash occurred and applying the dropout during the regeneration. Experimental results showed that the coverage is about 10% higher than the files in the queue of the AFL fuzzing tool and in the Hwpviewer binary, we found two new crashes using two crashes that found at the initial fuzzing phase.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2021.10a
• /
• pp.78-81
• /
• 2021

Through the smart factory construction project, sensors can be installed in manufacturing production facilities and various process data can be collected in real time. Through this, research on real-time facility anomaly detection is being actively conducted to reduce production interruption due to facility abnormality in the manufacturing process. In this paper, to detect abnormalities in production facilities, the manufacturing data was applied to deep learning models Autoencoder(AE), VAE(Variational Autoencoder), and AAE(Adversarial Autoencoder) to derive the results. Manufacturing data was used as input data through a simple moving average technique and preprocessing process, and performance analysis was conducted according to the window size of the simple movement average technique and the feature vector size of the AE model.

• Journal of Korea Society of Industrial Information Systems
• /
• v.25 no.6
• /
• pp.1-13
• /
• 2020

In this paper, the author proposed a nuclear power plant (NPP) instrumentation signal faults identification algorithm. A variational autoencoder (VAE)-based model is trained by using only normal dataset as same as existing anomaly detection method, and trained model predicts which signal within the entire signal set is anomalous. Classification of anomalous signals is performed based on the reconstruction error for each kind of signal and partial derivatives of reconstruction error with respect to the specific part of an input. Simulation was conducted to acquire the data for the experiments. Through the experiments, it was identified that the proposed signal fault identification method can specify the anomalous signals within acceptable range of error.

• Journal of Broadcast Engineering
• /
• v.28 no.3
• /
• pp.275-284
• /
• 2023

Gene expression data can be utilized in various studies, including the prediction of disease prognosis. However, there are challenges associated with collecting enough data due to cost constraints. In this paper, we propose a gene expression data generation model based on Conditional Variational Autoencoder. Our results demonstrate that the proposed model generates synthetic data with superior quality compared to two other state-of-the-art models for gene expression data generation, namely the Wasserstein Generative Adversarial Network with Gradient Penalty based model and the structured data generation models CTGAN and TVAE.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.5
• /
• pp.1590-1609
• /
• 2021

Laughter is one of the most important nonverbal sound that human generates. It is a means for expressing his emotions. The acoustic and contextual features of this specific sound are different from those of speech and many difficulties arise during their modeling process. During this work, we propose an audio laughter generation system based on unsupervised generative models: the autoencoder (AE) and its variants. This procedure is the association of three main sub-process, (1) the analysis which consist of extracting the log magnitude spectrogram from the laughter database, (2) the generative models training, (3) the synthesis stage which incorporate the involvement of an intermediate mechanism: the vocoder. To improve the synthesis quality, we suggest two hybrid models (LSTM-VAE, GRU-VAE and CNN-VAE) that combine the representation learning capacity of variational autoencoder (VAE) with the temporal modelling ability of a long short-term memory RNN (LSTM) and the CNN ability to learn invariant features. To figure out the performance of our proposed audio laughter generation process, objective evaluation (RMSE) and a perceptual audio quality test (listening test) were conducted. According to these evaluation metrics, we can show that the GRU-VAE outperforms the other VAE models.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.11-18
• /
• 2022

De novo drug design is the process of developing new drugs that can interact with biological targets such as protein receptors. Traditional process of de novo drug design consists of drug candidate discovery and drug development, but it requires a long time of more than 10 years to develop a new drug. Deep learning-based methods are being studied to shorten this period and efficiently find chemical compounds for new drug candidates. Many existing deep learning-based drug design models utilize recurrent neural networks to generate a chemical entity represented by SMILES strings, but due to the disadvantages of the recurrent networks, such as slow training speed and poor understanding of complex molecular formula rules, there is room for improvement. To overcome these shortcomings, we propose a deep learning model for SMILES string generation using variational autoencoders with self-attention mechanism. Our proposed model decreased the training time by 1/26 compared to the latest drug design model, as well as generated valid SMILES more effectively.