21HS1600, 불확실한 지도 기반 실내ㆍ외 환경에서 최종 목적지까지 이동로봇을 가이드할 수 있는 AI 기술 개발,
이재영
초록
With the increase in the learning capability of deep convolution-based architectures, various applications of such models have been proposed over time. In the field of anomaly detection, improvements in deep learning opened new prospects of exploration for the researchers whom tried to automate the labor-intensive features of data collection. First, in terms of data collection, it is impossible to anticipate all the anomalies that might exist in a given environment. Second, assuming we limit the possibilities of anomalies, it will still be hard to record all these scenarios for the sake of training a model Third, even if we manage to record a significant amount of abnormal data, it's laborious to annotate this data on pixel or even frame level. Various approaches address the problem by proposing one-class classification using generative models trained on only normal data. In such methods, only the normal data is used, which is abundantly available and doesn?셳 require significant human input. However, such approaches have two drawbacks. First, these are trained with only normal data and at the test time, given abnormal data as input, still generate normal-looking output. This happens due to the hallucination characteristic of generative models, which is not desirable in anomaly detection systems because of their need to be accurate and reliable. Next, these systems are not capable of utilizing abnormal examples, however small in number, during the training. In this paper, we propose anomaly detection with negative learning (ADNL), which employs the negative learning concept for the enhancement of anomaly detection by utilizing a very small number of labeled anomaly data as compared with the normal data during training. The idea, which is fairly simple yet effective, is to limit the reconstruction capability of a generative model using the given anomaly examples. During the training, normal data is learned as would have been in a conventional method, but the abnormal data is utilized to maximize loss of the network on abnormality distribution. With this simple tweaking, the network not only learns to reconstruct normal data but also encloses the normal distribution far from the possible distribution of anomalies. In order to evaluate the efficiency of our proposed method, we defined the baseline using Adversarial Auto-Encoder (AAE). Our experiments show significant improvement in area under the curve (AUC) over conventional AAE. An extensive evaluation, which has been carried out on the MNIST dataset as well as a locally recorded pedestrian dataset, is reported in this paper.
KSP 제안 키워드
Auto-Encoder(AE), Conventional methods, Data Collection, Extensive evaluation, Intrusion detection system(IDS), Learning Capability, MNIST Dataset, Normal distribution, One-class classification(OCC), Over time, Test Time
저작권정책 안내문
한국전자동신연구원 지식공유플랫폼 저작권정책
한국전자통신연구원 지식공유플랫폼에서 제공하는 모든 저작물(각종 연구과제, 성과물 등)은 저작권법에 의하여 보호받는 저작물로 무단복제 및 배포를 원칙적으로 금하고 있습니다. 저작물을 이용 또는 변경하고자 할 때는 다음 사항을 참고하시기 바랍니다.
저작권법 제24조의2에 따라 한국전자통신연구원에서 저작재산권의 전부를 보유한 저작물의 경우에는 별도의 이용허락 없이 자유이용이 가능합니다. 단, 자유이용이 가능한 자료는 "공공저작물 자유이용허락 표시 기준(공공누리, KOGL) 제4유형"을 부착하여 개방하고 있으므로 공공누리 표시가 부착된 저작물인지를 확인한 이후에 자유이용하시기 바랍니다. 자유이용의 경우에는 반드시 저작물의 출처를 구체적으로 표시하여야 하고 비영리 목적으로만 이용이 가능하며 저작물을 변형하거나 2차 저작물로 사용할 수 없습니다.
<출처표시방법 안내> 작성자, 저작물명, 출처, 권호, 출판년도, 이용조건 [예시1] 김진미 외, "매니코어 기반 고성능 컴퓨팅을 지원하는 경량커널 동향", 전자통신동향분석, 32권 4호, 2017, 공공누리 제4유형 [예시2] 심진보 외, "제4차 산업 혁명과 ICT - 제4차 산업 혁명 선도를 위한 IDX 추진 전략", ETRI Insight, 2017, 공공누리 제 4유형
공공누리가 부착되지 않은 자료들을 사용하고자 할 경우에는 담당자와 사전협의한 이후에 이용하여 주시기 바랍니다.