• Title, Summary, Keyword: 오토인코더

Search Result 29, Processing Time 0.033 seconds

A Study on the Characteristics of a series of Autoencoder for Recognizing Numbers used in CAPTCHA (CAPTCHA에 사용되는 숫자데이터를 자동으로 판독하기 위한 Autoencoder 모델들의 특성 연구)

  • Jeon, Jae-seung;Moon, Jong-sub
    • Journal of Internet Computing and Services
    • /
    • v.18 no.6
    • /
    • pp.25-34
    • /
    • 2017
  • Autoencoder is a type of deep learning method where input layer and output layer are the same, and effectively extracts and restores characteristics of input vector using constraints of hidden layer. In this paper, we propose methods of Autoencoders to remove a natural background image which is a noise to the CAPTCHA and recover only a numerical images by applying various autoencoder models to a region where one number of CAPTCHA images and a natural background are mixed. The suitability of the reconstructed image is verified by using the softmax function with the output of the autoencoder as an input. And also, we compared the proposed methods with the other method and showed that our methods are superior than others.

Hydrodynamic scene separation from video imagery of ocean wave using autoencoder (오토인코더를 이용한 파랑 비디오 영상에서의 수리동역학적 장면 분리 연구)

  • Kim, Taekyung;Kim, Jaeil;Kim, Jinah
    • Journal of The Korea Computer Graphics Society
    • /
    • v.25 no.4
    • /
    • pp.9-16
    • /
    • 2019
  • In this paper, we propose a hydrodynamic scene separation method for wave propagation from video imagery using autoencoder. In the coastal area, image analysis methods such as particle tracking and optical flow with video imagery are usually applied to measure ocean waves owing to some difficulties of direct wave observation using sensors. However, external factors such as ambient light and weather conditions considerably hamper accurate wave analysis in coastal video imagery. The proposed method extracts hydrodynamic scenes by separating only the wave motions through minimizing the effect of ambient light during wave propagation. We have visually confirmed that the separation of hydrodynamic scenes is reasonably well extracted from the ambient light and backgrounds in the two videos datasets acquired from real beach and wave flume experiments. In addition, the latent representation of the original video imagery obtained through the latent representation learning by the variational autoencoder was dominantly determined by ambient light and backgrounds, while the hydrodynamic scenes of wave propagation independently expressed well regardless of the external factors.

Style Transfer in Korean Text using Auto-encoder and Adversarial Networks (오토인코더와 적대 네트워크를 활용한 한국어 문체 변환)

  • Yang, Kisu;Lee, Dongyub;Lee, Chanhee;Lim, Heuiseok
    • Annual Conference on Human and Language Technology
    • /
    • /
    • pp.658-660
    • /
    • 2018
  • 인공지능 산업이 발달함에 따라 사용자의 특성에 맞게 상호작용하는 기술에 대한 수요도 증가하고 있다. 하지만 텍스트 스타일 변환의 경우 사용자 경험을 크게 향상시킬 수 있는 기술임에도 불구하고, 학습에 필요한 병렬 데이터가 부족하여 모델링과 성능 개선에 어려움을 겪고 있다. 이에 따라 본 논문에서는 비 병렬 데이터만으로 텍스트 스타일 변환이 가능한 선행 모델[1]을 기반으로, 한국어에 적합한 문장 표현 방식 및 성능 개선을 위한 임의 도메인 예측 기법이 적용된 모델을 제안한다.

  • PDF

Study for Prediction System of Learning Achievements of Cyber University Students using Deep Learning based on Autoencoder (오토인코더에 기반한 딥러닝을 이용한 사이버대학교 학생의 학업 성취도 예측 분석 시스템 연구)

  • Lee, Hyun-Jin
    • Journal of Digital Contents Society
    • /
    • v.19 no.6
    • /
    • pp.1115-1121
    • /
    • 2018
  • In this paper, we have studied a data analysis method by deep learning to predict learning achievements based on accumulated data in cyber university learning management system. By predicting learner's academic achievement, it can be used as a tool to enhance learner's learning and improve the quality of education. In order to improve the accuracy of prediction of learning achievements, the autoencoder based attendance prediction method is developed to improve the prediction performance and deep learning algorithm with ongoing evaluation metrics and predicted attendance are used to predict the final score. In order to verify the prediction results of the proposed method, the final grade was predicted by using the evaluation factor attendance data of the learning process. The experimental result showed that we can predict the learning achievements in the middle of semester.

Pipe Leak Detection System using Wireless Acoustic Sensor Module and Deep Auto-Encoder

  • Yeo, Doyeob;Lee, Giyoung;Lee, Jae-Cheol
    • Journal of the Korea Society of Computer and Information
    • /
    • v.25 no.2
    • /
    • pp.59-66
    • /
    • 2020
  • In this paper, we propose a pipe leak detection system through data collection using low-power wireless acoustic sensor modules and data analysis using deep auto-encoder. Based on the Fourier transform, we propose a low-power wireless acoustic sensor module that reduces data traffic by reducing the amount of acoustic sensor data to about 1/800, and we design the system that is robust to noise generated in the audible frequency band using only 20kHz~100kHz frequency signals. In addition, the proposed system is designed using a deep auto-encoder to accurately detect pipe leaks even with a reduced amount of data. Numerical experiments show that the proposed pipe leak detection system has a high accuracy of 99.94% and Type-II error of 0% even in the environment where high frequency band noise is mixed.

Deep Learning-based Abnormal Behavior Detection System for Dementia Patients (치매 환자를 위한 딥러닝 기반 이상 행동 탐지 시스템)

  • Kim, Kookjin;Lee, Seungjin;Kim, Sungjoong;Kim, Jaegeun;Shin, Dongil;shin, Dong-kyoo
    • Journal of Internet Computing and Services
    • /
    • v.21 no.3
    • /
    • pp.133-144
    • /
    • 2020
  • The number of elderly people with dementia is increasing as fast as the proportion of older people due to aging, which creates a social and economic burden. In particular, dementia care costs, including indirect costs such as increased care costs due to lost caregiver hours and caregivers, have grown exponentially over the years. In order to reduce these costs, it is urgent to introduce a management system to care for dementia patients. Therefore, this study proposes a sensor-based abnormal behavior detection system to manage dementia patients who live alone or in an environment where they cannot always take care of dementia patients. Existing studies were merely evaluating behavior or evaluating normal behavior, and there were studies that perceived behavior by processing images, not data from sensors. In this study, we recognized the limitation of real data collection and used both the auto-encoder, the unsupervised learning model, and the LSTM, the supervised learning model. Autoencoder, an unsupervised learning model, trained normal behavioral data to learn patterns for normal behavior, and LSTM further refined classification by learning behaviors that could be perceived by sensors. The test results show that each model has about 96% and 98% accuracy and is designed to pass the LSTM model when the autoencoder outlier has more than 3%. The system is expected to effectively manage the elderly and dementia patients who live alone and reduce the cost of caring.

Clustering Performance Analysis for Time Series Data: Wavelet vs. Autoencoder (시계열 데이터에 대한 클러스터링 성능 분석: Wavelet과 Autoencoder 비교)

  • Hwang, Woosung;Lim, Hyo-Sang
    • Proceedings of the Korea Information Processing Society Conference
    • /
    • /
    • pp.585-588
    • /
    • 2018
  • 시계열 데이터의 특징을 추출하여 분석하는 과정에서 시게열 데이터가 가지는 고차원성은 차원의 저주(Course of Dimensionality)로 인해 데이터내의 유효한 정보를 찾는데 어려움을 만든다. 이러한 문제를 해결하기 위해 차원 축소 기법(dimensionality reduction)이 널리 사용되고 있지만, 축소 과정에서 발생하는 정보의 희석으로 인하여 시계열 데이터에 대한 군집화(clustering)등을 수행하는데 있어서 성능의 변화를 가져온다. 본 논문은 이러한 현상을 관찰하기 위해 이산 웨이블릿 변환(Discrete Wavelet Transform:DWT)과 오토 인코더(AutoEncoder)를 차원 축소 기법으로 활용하여 시계열 데이터의 차원을 압축 한 뒤, 압축된 데이터를 K-평균(K-means) 알고리즘에 적용하여 군집화의 효율성을 비교하였다. 성능 비교 결과, DWT는 압축된 차원수 그리고 오토인코더는 시계열 데이터에 대한 충분한 학습이 각각 보장된다면 좋은 군집화 성능을 보이는 것을 확인하였다.

인공신경망 알고리즘을 통한 사물인터넷 위협 탐지 기술 연구

  • Oh, Sungtaek;Go, Woong;Kim, Mijoo;Lee, Jaehyuk;Kim, Hong-Geun;Park, SoonTai
    • Review of KIISC
    • /
    • v.29 no.6
    • /
    • pp.59-66
    • /
    • 2019
  • 사물인터넷 환경은 무수히 많은 이기종의 기기가 연결되는 초연결 네트워크 구성을 갖는 특성이 있다. 본 논문에서는 이러한 특성을 갖는 사물인터넷 환경에 적합한 보안 기술로 네트워크를 통해 침입하는 위협의 효율적인 탐지 기술을 제안한다. 사물인터넷 환경에서의 대표적인 위협 행위를 분석하고 관련하여 공격 데이터를 수집하고 이를 토대로 특성 연구를 진행하였다. 이를 기반으로 인공신경망 기반의 오토인코더 알고리즘을 활용하여 심층학습 탐지 모델을 구축하였다. 본 논문에서 제안하는 탐지 모델은 비지도 학습 방식의 오토인코더를 지도학습 기반의 분류기로 확장하여 사물인터넷 환경에서의 대표적인 위협 유형을 식별할 수 있었다. 본 논문은 1. 서론을 통해 현재 사물인터넷 환경과 보안 기술 연구 동향을 소개하고 2. 관련연구를 통하여 머신러닝 기술과 위협 탐지 기술에 대해 소개한다. 3. 제안기술에서는 본 논문에서 제안하는 인공신경망 알고리즘 기반의 사물인터넷 위협 탐지 기술에 대해 설명하고, 4. 향후연구계획을 통해 추후 활용 방안 및 고도화에 대한 내용을 작성하였다. 마지막으로 5. 결론을 통하여 제안기술의 평가와 소회에 대해 설명하였다.

  • PDF

Audio High-Band Coding based on Autoencoder with Side Information (부가 정보를 이용하는 오토 인코더 기반의 오디오 고대역 부호화 기술)

  • Cho, Hyo-Jin;Shin, Seong-Hyeon;Beack, Seung Kwon;Lee, Taejin;Park, Hochong
    • Journal of Broadcast Engineering
    • /
    • v.24 no.3
    • /
    • pp.387-394
    • /
    • 2019
  • In this study, a new method of audio high-band coding based on autoencoder with side information is proposed. The proposed method operates in the MDCT domain, and improves the performance by using additional side information consisting of the previous and current low bands, which is different from the conventional autoencoder that only inputs information to be encoded. Moreover, the side information in a time-frequency domain enables the high-band coder to utilize temporal characteristics of the signal. In the proposed method, the encoder transmits a 4-dimensional latent vector computed by the autoencoder and a gain variable using 12 bits for each frame. The decoder reconstructs the high band by applying the decoded low bands in the previous and current frames and the transmitted information to the autoencoder. Subjective evaluation confirms that the proposed method provides equivalent performance to the SBR at approximately half the bit rate of the SBR.

Improving Non-Profiled Side-Channel Analysis Using Auto-Encoder Based Noise Reduction Preprocessing (비프로파일링 기반 전력 분석의 성능 향상을 위한 오토인코더 기반 잡음 제거 기술)

  • Kwon, Donggeun;Jin, Sunghyun;Kim, HeeSeok;Hong, Seokhie
    • Journal of the Korea Institute of Information Security & Cryptology
    • /
    • v.29 no.3
    • /
    • pp.491-501
    • /
    • 2019
  • In side-channel analysis, which exploit physical leakage from a cryptographic device, deep learning based attack has been significantly interested in recent years. However, most of the state-of-the-art methods have been focused on classifying side-channel information in a profiled scenario where attackers can obtain label of training data. In this paper, we propose a new method based on deep learning to improve non-profiling side-channel attack such as Differential Power Analysis and Correlation Power Analysis. The proposed method is a signal preprocessing technique that reduces the noise in a trace by modifying Auto-Encoder framework to the context of side-channel analysis. Previous work on Denoising Auto-Encoder was trained through randomly added noise by an attacker. In this paper, the proposed model trains Auto-Encoder through the noise from real data using the noise-reduced-label. Also, the proposed method permits to perform non-profiled attack by training only a single neural network. We validate the performance of the noise reduction of the proposed method on real traces collected from ChipWhisperer board. We demonstrate that the proposed method outperforms classic preprocessing methods such as Principal Component Analysis and Linear Discriminant Analysis.