• Journal of Korea Multimedia Society
• /
• v.21 no.8
• /
• pp.849-857
• /
• 2018

In this paper, we propose an automatic composition method using time series embedding of RNN Auto-Encoder. RNN Auto-Encoder can learn existing songs and can compose new songs from the trained RNN decoder. If one song is fully trained in the RNN Auto-Encoder, the song is embedded into the vector values of RNN nodes in the Auto-Encoder. If we train a lot of songs and apply a specific vector to the decoder of Auto-Encoder, then we can obtain a new song that combines the features of trained multiple songs according to the given vector. From extensive experiments we could find that our method worked well and generated various songs by selecting of the composition vectors.

• Journal of Internet Computing and Services
• /
• v.22 no.2
• /
• pp.1-9
• /
• 2021

Traditionally, most malicious codes have been analyzed using feature information extracted by domain experts. However, this feature-based analysis method depends on the analyst's capabilities and has limitations in detecting variant malicious codes that have modified existing malicious codes. In this study, we propose a ResNet-Variational AutoEncder-based variant malware classification method that can classify a family of variant malware without domain expert intervention. The Variational AutoEncoder network has the characteristics of creating new data within a normal distribution and understanding the characteristics of the data well in the learning process of training data provided as input values. In this study, important features of malicious code could be extracted by extracting latent variables in the learning process of Variational AutoEncoder. In addition, transfer learning was performed to better learn the characteristics of the training data and increase the efficiency of learning. The learning parameters of the ResNet-152 model pre-trained with the ImageNet Dataset were transferred to the learning parameters of the Encoder Network. The ResNet-Variational AutoEncoder that performed transfer learning showed higher performance than the existing Variational AutoEncoder and provided learning efficiency. Meanwhile, an ensemble model, Stacking Classifier, was used as a method for classifying variant malicious codes. As a result of learning the Stacking Classifier based on the characteristic data of the variant malware extracted by the Encoder Network of the ResNet-VAE model, an accuracy of 98.66% and an F1-Score of 98.68 were obtained.

• Journal of the Korea Society of Computer and Information
• /
• v.24 no.9
• /
• pp.21-27
• /
• 2019

In this paper, we propose a deep auto-encoder-based pipe leak detection (PLD) technique from time-series acoustic data collected by microphone sensor nodes. The key idea of the proposed technique is to learn representative features of the leak-free state using leak-free time-series acoustic data and the deep auto-encoder. The proposed technique can be used to create a PLD model that detects leaks in the pipeline in an unsupervised learning manner. This means that we only use leak-free data without labeling while training the deep auto-encoder. In addition, when compared to the previous supervised learning-based PLD method that uses image features, this technique does not require complex preprocessing of time-series acoustic data owing to the unsupervised feature extraction scheme. The experimental results show that the proposed PLD method using the deep auto-encoder can provide reliable PLD accuracy even considering unsupervised learning-based feature extraction.

• The Journal of Korea Robotics Society
• /
• v.14 no.1
• /
• pp.8-13
• /
• 2019

Visual place recognition is widely researched area in robotics, as it is one of the elemental requirements for autonomous navigation, simultaneous localization and mapping for mobile robots. However, place recognition in changing environment is a challenging problem since a same place look different according to the time, weather, and seasons. This paper presents a feature extraction method using a deep convolutional auto-encoder to recognize places under severe appearance changes. Given database and query image sequences from different environments, the convolutional auto-encoder is trained to predict the images of the desired environment. The training process is performed by minimizing the loss function between the predicted image and the desired image. After finishing the training process, the encoding part of the structure transforms an input image to a low dimensional latent representation, and it can be used as a condition-invariant feature for recognizing places in changing environment. Experiments were conducted to prove the effective of the proposed method, and the results showed that our method outperformed than existing methods.

• Journal of Korea Multimedia Society
• /
• v.22 no.11
• /
• pp.1251-1258
• /
• 2019

Intelligent tutoring system enables users to effectively learn by utilizing various artificial intelligence techniques. For instance, it can recommend a proper curriculum or learning method to individual users based on their learning history. To do this effectively, user's characteristics need to be analyzed and classified based on various aspects such as interest, learning ability, and personality. Even though data labeled by the characteristics are required for more accurate classification, it is not easy to acquire enough amount of labeled data due to the labeling cost. On the other hand, unlabeled data should not need labeling process to make a large number of unlabeled data be collected and utilized. In this paper, we propose a semi-supervised learning method based on feedback variational auto-encoder(FVAE), which uses both labeled data and unlabeled data. FVAE is a variation of variational auto-encoder(VAE), where a multi-layer perceptron is added for giving feedback. Using unlabeled data, we train FVAE and fetch the encoder of FVAE. And then, we extract features from labeled data by using the encoder and train classifiers with the extracted features. In the experiments, we proved that FVAE-based semi-supervised learning was superior to VAE-based method in terms with accuracy and F1 score.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.14 no.9
• /
• pp.3823-3840
• /
• 2020

Recently, auto-encoder has emerged as the most popular method in convolutional neural network (CNN) based image compression and has achieved impressive performance. In the traditional auto-encoder based image compression model, the encoder simply sends the features of last layer to the decoder, which cannot allocate bits over different spatial regions in an efficient way. Besides, these methods do not fully exploit the contextual information under different receptive fields for better reconstruction performance. In this paper, to solve these issues, a novel auto-encoder model is designed for image compression, which can effectively transmit the hierarchical features of the encoder to the decoder. Specifically, we first propose an adaptive bit-allocation strategy, which can adaptively select an importance channel. Then, we conduct the multiply operation on the generated importance mask and the features of the last layer in our proposed encoder to achieve efficient bit allocation. Moreover, we present an additional novel perceptual loss function for more accurate image details. Extensive experiments demonstrated that the proposed model can achieve significant superiority compared with JPEG and JPEG2000 both in both subjective and objective quality. Besides, our model shows better performance than the state-of-the-art convolutional neural network (CNN)-based image compression methods in terms of PSNR.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2022.11a
• /
• pp.905-907
• /
• 2022

악성코드를 분석하는 기존 기법인 정적분석은 빠르고 효율적으로 악성코드를 탐지할 수 있지만 난독화된 파일에 취약한 반면,, 동적분석은 난독화된 파일에 적합하지만 느리고 비용이 많이 든다는 단점을 가진다. 본 연구에서는 두 분석 기법의 단점을 해결하기 위해 딥러닝 모델을 활용한 난독화에 강한 정적분석 모델을 제안하였다. 본 연구에서 제안한 방법은 원본 코드 및 난독화된 파일을 grayscale 이미지로 변환하여 데이터셋을 구축하고 AutoEncoder 를 사전학습시켜 encoder 가 원본 파일과 난독화된 파일로부터 원본 파일의 특징을 추출할 수 있도록 한 이후, encoder 의 output 을 fully connected layer 의 입력으로 넣고 전이학습시켜 악성코드를 탐지하도록 하였다. 본 연구에서는 제안한 방법론은 난독화된 파일에서 악성코드를 탐지하는 성능을 F1 score 기준 14.17% 포인트 향상시켰고, 난독화된 파일과 원본 파일을 전체를 합친 데이터셋에서도 악성코드 탐지 성능을 F1 score 기준 7.22% 포인트 향상시켰다.

• International Journal of Advanced Culture Technology
• /
• v.9 no.1
• /
• pp.218-223
• /
• 2021

Pervasive enhancement and required enforcement of the Internet of Things (IoTs) in a distributed massively multiplayer online architecture have effected in massive growth of Big-Data in terms of server over-load. There have been some previous works to overcome the overloading of server works. However, there are lack of considered methods, which is commonly applicable. Therefore, we propose a combing Sparse Auto-Encoder and Load-Balancing, which is ProGReGA for Big-Data of server loads. In the process of Sparse Auto-Encoder, when it comes to selection of the feature-pattern, the less relevant feature-pattern could be eliminated from Big-Data. In relation to Load-Balancing, the alleviated degradation of ProGReGA can take advantage of the less redundant feature-pattern. That means the most relevant of Big-Data representation can work. In the performance evaluation, we can find that the proposed method have become more approachable and stable.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2021.07a
• /
• pp.5-6
• /
• 2021

본 논문에서는 Semi-supervised Learning 방식의 이상감지 방법을 제안한다. 취득한 소음 데이터를 이미지화 시킨 후 Convolution AutoEncoder 학습 방법을 이용하여 모델을 학습한다. 고장 데이터와 정상 데이터 간의 데이터 불균형 문제가 대두되기 때문에 정상 데이터만을 활용한 이상감지는 실제 산업현장의 상황에 알맞게 사용할 수 있을 것이라 기대한다.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.27 no.7
• /
• pp.1088-1097
• /
• 2021

Vibration data of mechanical equipment inevitably have noise. This noise adversely af ects the maintenance of mechanical equipment. Accordingly, the performance of a learning model depends on how effectively the noise of the data is removed. In this study, the noise of the data was removed using the Denoising Auto Encoder (DAE) technique which does not include the characteristic extraction process in preprocessing time series data. In addition, the performance was compared with that of the Wavelet Transform, which is widely used for machine signal processing. The performance comparison was conducted by calculating the failure detection rate. For a more accurate comparison, a classification performance evaluation criterion, the F-1 Score, was calculated. Failure data were detected using the One-Class SVM technique. The performance comparison, revealed that the DAE technique performed better than the Wavelet Transform technique in terms of failure diagnosis and error rate.