kumoh national institute of technology
Networked Systems Lab.


NSL > Education> Thesis> Dissertation
Time-Series Data Anomaly Detection using Online Learning Approach
By : Nita Hidayati
Date : 2020-06-05
Views : 111

In processing time-series data classifications, the actual updated data is the key component in anomaly detection. Using constant parameters in offline learning are prone to create error condition in dynamic environments. Moreover, inaccurate anomaly detection delivers a dangerous effect that spread throughout the whole system. In this thesis, data anomaly detection model for time-series data is proposed using online machine learning scheme. The system uses sampled data from raspberry pi 3 that are updated regularly. In order to improve the accuracy of detection, the multi-phase learning process is conducted. Through learning phase, logistic regression and neural network are utilized to evaluate the system. The experimental result proves that the proposed system produces better accuracy compared to using offline learning.
(Total:88 articles / page:1/9 )
No. Subject By Date Views
88  Trajectory Modeling for Combat UAV Communication-hands.. Williams P 2020-08-29 59
87  Full duplex Cognitive Networks; Enhanced Spectrum Mana.. Gaspard 2020-06-08 127
86  Accurate Movement Prediction Model for UAV Mobility in.. Muhammad Taufiq Rama 2020-06-05 119
85  CSI Reconstruction Enhancement Method in MIMO Systems .. heidy 2020-06-05 1803
84  Time-Series Data Anomaly Detection using Online Learni.. Nita Hidayati 2020-06-05 111
83  Cooperative Computation of Hierarchical Edge Framework.. Riesa Krisna Astuti 2020-06-05 116
82  Blockchain over MMS (BoM) for Secure IIoT Kevin 2020-06-05 2611
81  Resource Allocation for Industrial Wireless Networks sanjay 2020-06-05 2009
80  Gyeong Seon Kim "Answer Sheet" 2020-01-31 208
79  Gyeong Seon Kim "Design and Implementation DDS Mid.. 2020-01-31 174