Nt1310 Unit 3 Data Collection

Satisfactory Essays
In this paper, we present the first data collection and profiling process result in our research framework. At this time, the second and the third data collection process are still on going. If it is completed, we will conduct the second part of our proposed experiment. The challenges is, we have to obtain an appropriate and enough RAW data that need more prolonged time for trial and error. We have to design scalable devices and computation architecture, since the system proposed will handle high volume of traffic at national level network. A comment and suggestion are welcome. There are some potential for future works and further study. Especially from the RAW data being obtained and recorded: - Developing new classified Data Set especially for DNS traffic to be used in machine learning study. Availability of qualified and updated Data Set especially for DNS, in a purpose to provide new data set for Machine Learning trainings, are very rare. Contributing a new specific DNS Data Set will be very beneficial for incoming research…show more content…
Since the volume of infected host and IP’s are growing rapidly, faster process are needed. It can be easily done by increasing computing power, but it will need more investment. Another workaround: employ automated sanitation – eliminating known bad element, to save computation
Get Access