The CM4105 Honours Project is a Bundle of Machine Learning Experiments written in Python and Java Samples with the ultimate goal of allowing the creation of a JavaFX Desktop Application that uses the machine learning experiments to provide accurate predictions related to computer systems failure. The Application supports Algorithms such as the Support Vector Machines, Random Forest Model, Logistic Regression Model and the Multi-Layer Perceptron Model.
As computer systems are used more and more for problem-solving, the complexity of the systems grows just as much; they are also becoming more dynamic due to the devices mobility, modifications in the environment of execution, software updates, hardware upgrades, maintenance events and hardware components replacements. The classical reliability theory that concerns the computer systems or the conventional approaches put in place for problem-solving present a significant lack of consideration of the actual state of the computer systems as they are not capable to offer a reflection for the dynamic and the unforeseen runtime of a computer system or the failure of processes.
The focus of this research is to try to forecast possible events that could lead to computer systems failure by reviewing and then selecting the right computer systems failure predictions methods associated with the right hardware sensors. The ultimate goal of the work presented in this paper is to implement computer systems failure forecasting features into a desktop application in order to reduce the impact caused by such failure events.
- Python (2.7 required)
- Java (1.8 required)
- sklearn (required)
- pandas (required)
- matplotlib (required)
- CX_Freeze (optional)
- LaTeX (optional)
- Git (optional)
The [CM4105 Honours Project installation guides] includes instructions for installing the project as part of a local application.
python <path/to/main.py>- Path to entry point file. If unspecified, the current working directory is used.
Due to the nature of the Command & Control type of application, only the machine learning part of the project is included in this repository.