Research Monographs

Anomaly Detection Based on Machine Learning

Anomaly Detection Based on Machine Learning

  • Author

    Oh, Miae

  • Publication Date

    0000

  • Pages

  • Series No.

  • Language

Artificial intelligence (AI) and big data analysis are the core technologies underlying the Fourth Industrial Revolution, and the self-sustained evolution of algorithms, based upon machine learning and big data, is key to all related progress. Machine learning, which is a part of AI, refers to the technology with which computers learn and adapt on the basis of large quantities of accumulated data. Machine learning holds the key to analytical and anomaly detection tasks required in a variety of fields, including image processing, video and voice recognition, and Internet search. In data mining, anomaly detection is the identification of rare items, events or observations which raise suspicions by differing significantly from the majority of the data. Typically the anomalous items will translate to some kind of problem such as bank fraud, a structural defect, medical problems or errors in a text. In this paper, we define the concept of anomaly detection and discuss various applications of anomaly detection techniques using machine learning techniques. We introduce the anomaly detection technique and compare the disadvantages of each methodology. We also study the anomaly detection study using Deep Learning machine learning method which is the latest machine learning method. We conduct exploratory analysis by applying the methodology of anomaly detection technique using data of health field and welfare field respectively. Finally, we deal with issues related to the application of anomaly detection techniques and conclude with policy. By using anomaly detection techniques based on machine learning techniques in combination with fraud detection social security and improving budget efficiency, we can get closer to predictable customized welfare.  

Attachments

공공누리 공공저작물 자유 이용허락