Approximating Optimisation Solutions for Travelling Officer Problem with Customised Deep Learning Network
This work addresses a domain-specific problem in orienteering for applications like parking enforcement, but it is incremental as it applies deep learning to an under-explored variant of a known problem.
The paper tackled the Travelling Officer Problem by converting it into a classification task and designing a customised deep learning network to approximate optimisation solutions, achieving performance tested on a real-world parking violation dataset with empirical analysis of architectural components.
Deep learning has been extended to a number of new domains with critical success, though some traditional orienteering problems such as the Travelling Salesman Problem (TSP) and its variants are not commonly solved using such techniques. Deep neural networks (DNNs) are a potentially promising and under-explored solution to solve these problems due to their powerful function approximation abilities, and their fast feed-forward computation. In this paper, we outline a method for converting an orienteering problem into a classification problem, and design a customised multi-layer deep learning network to approximate traditional optimisation solutions to this problem. We test the performance of the network on a real-world parking violation dataset, and conduct a generic study that empirically shows the critical architectural components that affect network performance for this problem.