Identifying PCB contaminated transformers through active learning

Exposure to polychlorinated biphenyals (PCBs) is hazardous to human health. The United Nations Environment Programme has decreed that nations, including Canada and the US, must eliminate PCB contaminated utility equipment such as transformers by 2025. Sampling, which imposes a non-trivial expenditure, is required to confirm the PCB content of a transformer. For the first time, we apply an iterative machine learning technique known as active learning to construct a PCB transformer identification model that aims to minimize the number of transformers sampled and thus reduce the total cost. In this thesis, we propose a dynamic sampling size algorithm to address two key issues in active learning: the sampling size per iteration and the stopping criterion. The proposed algorithm is evaluated using the real world datasets from BC Hydro in Canada.