• Nuclear Engineering and Technology
• /
• 제55권2호
• /
• pp.506-515
• /
• 2023

This study is to find a method to learn engine sound after the start-up of a diesel generator installed in nuclear power plant with an unsupervised deep learning algorithm (CNN autoencoder) and a new method to predict the failure of a diesel generator using it. In order to learn the sound of a diesel generator with a deep learning algorithm, sound data recorded before and after the start-up of two diesel generators was used. The sound data of 20 min and 2 h were cut into 7 s, and the split sound was converted into a spectrogram image. 1200 and 7200 spectrogram images were created from sound data of 20 min and 2 h, respectively. Using two different deep learning algorithms (CNN autoencoder and binary classification), it was investigated whether the diesel generator post-start sounds were learned as normal. It was possible to accurately determine the post-start sounds as normal and the pre-start sounds as abnormal. It was also confirmed that the deep learning algorithm could detect the virtual abnormal sounds created by mixing the unusual sounds with the post-start sounds. This study showed that the unsupervised anomaly detection algorithm has a good accuracy increased about 3% with comparing to the binary classification algorithm.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제12권6호
• /
• pp.2806-2825
• /
• 2018

Unsupervised learning has shown good performance on image, video and audio classification tasks, and much progress has been made so far. It studies how systems can learn to represent particular input patterns in a way that reflects the statistical structure of the overall collection of input patterns. Many promising deep learning systems are commonly trained by the greedy layerwise unsupervised learning manner. The performance of these deep learning architectures benefits from the unsupervised learning ability to disentangling the abstractions and picking out the useful features. However, the existing unsupervised learning algorithms are often difficult to train partly because of the requirement of extensive hyperparameters. The tuning of these hyperparameters is a laborious task that requires expert knowledge, rules of thumb or extensive search. In this paper, we propose a simple and effective unsupervised feature learning algorithm for image classification, which exploits an explicit optimizing way for population and lifetime sparsity. Firstly, a sparse target matrix is built by the competitive rules. Then, the sparse features are optimized by means of minimizing the Euclidean norm ($L_2$) error between the sparse target and the competitive layer outputs. Finally, a classifier is trained using the obtained sparse features. Experimental results show that the proposed method achieves good performance for image classification, and provides discriminative features that generalize well.

• 품질경영학회지
• /
• 제50권3호
• /
• pp.459-471
• /
• 2022

Purpose: The purpose of this study was to increase prediction accuracy for an anomaly interval identified using an artificial intelligence-based time series anomaly detection technique by establishing a pre-processing process. Methods: Significant variables were extracted by applying feature selection techniques, and anomalies were derived using the TadGAN time series anomaly detection algorithm. After applying machine learning and deep learning methodologies using normal section data (excluding anomaly sections), the explanatory power of the anomaly sections was demonstrated through performance comparison. Results: The results of the machine learning methodology, the performance was the best when SHAP and TadGAN were applied, and the results in the deep learning, the performance was excellent when Chi-square Test and TadGAN were applied. Comparing each performance with the papers applied with a Conventional methodology using the same data, it can be seen that the performance of the MLR was significantly improved to 15%, Random Forest to 24%, XGBoost to 30%, Lasso Regression to 73%, LSTM to 17% and GRU to 19%. Conclusion: Based on the proposed process, when detecting unsupervised learning anomalies of data that are not actually labeled in various fields such as cyber security, financial sector, behavior pattern field, SNS. It is expected to prove the accuracy and explanation of the anomaly detection section and improve the performance of the model.

• 한국멀티미디어학회논문지
• /
• 제25권8호
• /
• pp.991-998
• /
• 2022

Recently, object recognition using image/video signals is rapidly spreading on autonomous driving and mobile phones. However, the actual input image/video signals are easily exposed to a poor illuminance environment. A recent researches for improving illumination enable to estimate and compensate the illumination parameters. In this study, we propose VE-DCE (video enhancement zero-reference deep curve estimation) to improve the illumination of low-light images. The proposed VE-DCE uses unsupervised learning-based zero-reference deep curve, which is one of the latest among learning based estimation techniques. Experimental results show that the proposed method can achieve the quality of low-light video as well as images compared to the previous method. In addition, it can reduce the computational complexity with respect to the existing method.

• 한국전자거래학회지
• /
• 제27권1호
• /
• pp.1-13
• /
• 2022

인터넷, 모바일 등 네트워크 기술이 발전함에 따라 내외부 침입 및 위협으로부터 조직의 자원을 보호하기 위한 보안의 중요성이 커지고 있다. 따라서 최근에는 다양한 보안 로그 이벤트에 대하여 보안 위협 여부를 사전에 파악하고, 예방하는 이상징후 식별 알고리즘의 개발이 강조되고 있다. 과거 규칙 기반 또는 통계 학습에 기반하여 개발되어 온 보안 이상징후 식별 알고리즘은 점차 기계 학습과 딥러닝에 기반한 모델링으로 진화하고 있다. 본 연구에서는 다양한 기계 학습 분석 방법론을 활용하여 악의적 내부자 위협을 사전에 식별하는 최적 알고리즘으로 LSTM-autoencoder를 변형한 Deep-autoencoder 모형을 제안한다. 본 연구는 비지도 학습에 기반한 이상탐지 알고리즘 개발을 통해 적응형 보안의 가능성을 향상시키고, 지도 학습에 기반한 정탐 레이블링을 통해 기존 알고리즘 대비 오탐율을 감소시켰다는 점에서 학문적 의의를 갖는다.

• Asia pacific journal of information systems
• /
• 제32권2호
• /
• pp.226-248
• /
• 2022

The existing model for sentiment analysis of product reviews learned from past data and new data was labeled based on training. But new data was never used by the existing system for making a decision. The proposed Aspect-based multi-agent Deep Reinforcement learning Sentiment Analysis (ADRSA) model learned from its very first data without the help of any training dataset and labeled a sentence with aspect category and sentiment polarity. It keeps on learning from the new data and updates its knowledge for improving its intelligence. The decision of the proposed system changed over time based on the new data. So, the accuracy of the sentiment analysis using deep reinforcement learning was improved over supervised learning and unsupervised learning methods. Hence, the sentiments of premium customers on a particular site can be explored to other customers effectively. A dynamic environment with a strong knowledge base can help the system to remember the sentences and usage State Action Reward State Action (SARSA) algorithm with Bidirectional Encoder Representations from Transformers (BERT) model improved the performance of the proposed system in terms of accuracy when compared to the state of art methods.

• 정보처리학회논문지:소프트웨어 및 데이터공학
• /
• 제8권12호
• /
• pp.483-490
• /
• 2019

네트워크 침입 탐지 시스템(NIDS)에서 분류의 기능은 상당히 중요하며 탐지 성능은 다양한 특징에 따라 달라진다. 최근 딥러닝에 대한 연구가 많이 이루어지고 있으나 네트워크 침입탐지 시스템에서는 많은 수의 트래픽과 고차원의 특징으로 인하여 속도가 느려지는 문제점이 있다. 따라서 딥러닝을 분류에 사용하는 것이 아니라 특징 추출을 위한 전처리 과정으로 사용하며 추출한 특징을 기반으로 분류하는 연구 방법을 제안한다. 딥러닝의 대표적인 비지도 학습인 Stacked AutoEncoder를 사용하여 특징을 추출하고 Random Forest 분류 알고리즘을 사용하여 분류한 결과 분류 성능과 탐지 속도의 향상을 확인하였다. IOT 환경에서 수집한 데이터를 이용하여 정상 및 공격트래픽을 멀티클래스로 분류하였을 때 99% 이상의 성능을 보였으며, AE-RF, Single-RF와 같은 다른 모델과 비교하였을 때도 성능 및 탐지속도가 우수한 것으로 나타났다.

• 융합정보논문지
• /
• 제12권4호
• /
• pp.260-269
• /
• 2022

본 논문에서는 기존에 전문가에 의해서 이루어지던 국가 대기오염 측정망 데이터들의 이상 탐지 작업을 인공지능을 통해 자동화하고자 심층 신경망을 이용한 이상 탐지 모델을 제안하였다. 환경과학원에서 제공받은 기상자료 데이터의 결측치 및 이상치를 분석하여 학습데이터를 생성하였으며 비지도 학습 방식의 BeatGAN 모델에 기반하여 커널 구조 변경과 합성곱 필터층 및 전치 합성곱 필터층의 추가를 통해 새로운 모델을 제안하여 이상 탐지 성능을 높이고자 하였다. 또한 제안하는 모델의 생성적 특징을 활용하여 새로운 데이터를 생성하고 이를 학습에 사용하는 재학습 알고리즘을 구현 및 적용하여 기존 BeatGAN 모델뿐 아니라 다른 비지도 학습 모델인 Iforest, One Class SVM과 비교하였을 때 제안모델의 성능이 가장 높았음을 확인할 수 있었다. 본 연구를 통해 실제 산업현장에서 센서의 이상, 점검 등의 여러 요인으로 인해 학습 데이터가 부족한 상황에서 추가적인 비용없이 과적합을 피하며 제안하는 모델의 이상탐지 성능을 올릴 수 있는 방법을 제시할 수 있었다.

• 한국컴퓨터정보학회논문지
• /
• 제27권9호
• /
• pp.41-47
• /
• 2022

본 논문에서는 자동표정인식을 위하여 얼굴 이미지 배열의 가운데 이미지를 예측하는 새롭고 간단한 자기주도학습 방법을 제안한다. 자동표정인식은 딥러닝 모델을 통해 높은 성능을 달성할 수 있으나 일반적으로 큰 비용과 시간이 투자된 대용량의 데이터 세트가 필요하고, 데이터 세트의 크기와 알고리즘의 성능이 비례한다. 제안하는 방법은 추가적인 데이터 세트 구축 없이 기존의 데이터 세트를 활용하여 자기주도학습을 통해 얼굴의 잠재적인 심층표현방법을 학습하고 학습된 파라미터를 전이시켜 자동표정인식의 성능을 향상한다. 제안한 방법은 CK+와 AFEW 8.0 두가지 데이터 세트에 대하여 높은 성능 향상을 보여주었고, 간단한 방법으로 큰 효과를 얻을 수 있음을 보여주었다.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제14권10호
• /
• pp.3955-3971
• /
• 2020

Due to the significant increase in the use of autonomous car technology, it is essential to integrate this technology with high-precision digital map data containing more precise and accurate roadway information, as compared to existing conventional map resources, to ensure the safety of self-driving operations. While existing map technologies may assist vehicles in identifying their locations via Global Positioning System, it is however difficult to update the environmental changes of roadways in these maps. Roadway vision algorithms can be useful for building autonomous vehicles that can avoid accidents and detect real-time location changes. We incorporate a hybrid architectural design that combines unsupervised classification of vision data with supervised joint fusion classification to achieve a better noise-resistant algorithm. We identify, via a deep learning approach, an intelligent hybrid fusion algorithm for fusing multimodal vision feature data for roadway classifications and characterize its improvement in accuracy over unsupervised identifications using image processing and supervised vision classifiers. We analyzed over 93,000 vision frame data collected from a test vehicle in real roadways. The performance indicators of the proposed hybrid fusion algorithm are successfully evaluated for the generation of roadway digital maps for autonomous vehicles, with a recall of 0.94, precision of 0.96, and accuracy of 0.92.