The advantages of supervised learning techniques are efficient and fast, as they get the ’correct’ answers during training, that is, the clear feedbacks help them learn quickly. Besides, it is more powerful to detect the known problem since the patterns have been taught. But the disadvantages are obvious that it is hard to get enough reliable labeled data. First, it is hard to provide absolutely normal data (i.e. containing no problems), and if some erroneous data are labeled as normal data, it increases the false positive error.Secondly, as even the human expert cannot detect every kind of problem, supervised learning will fail to detect a totally unknown problem. Finally, the supervised learning system can never be superior to human experts, since the goal is to imitate the experts [8].In this project, it is nearly impossible to get enough labeled data to do supervised learning and the stakeholders are interested in those unknown problems as well. Therefore, this project did not use classification techniques.