Impact of COVID-19 lockdown: Domestic and child abuse in Bridgend.

INTRODUCTION: Financial stress, social stress and lack of support at home can precipitate domestic and child abuse (World Health Organization, 2020). These factors have been exacerbated by the COVID-19 pandemic (NSPCC, 2020b) (NSPCC, 2020a). We hypothesise an increase in Bridgend's domestic and child abuse during lockdown. METHOD: Data was collected retrospectively from 23rd March to 30th September 2020 and compared to the same time period in 2019. Wales-wide data on domestic abuse was shared by the Welsh Government's Live Fear free helpline. Local data was shared by domestic abuse charity CALAN, the Emergency Department (ED) and Paediatric Department of Princess of Wales Hospital (POWH). RESULTS: During lockdown, Live Fear Free reported increasing average monthly contact across Wales in 2020 (511 April; 631 December). Locally, CALAN reported a 190% increase in self-referrals and a 198% increase in third party referrals, but there was a 36% decrease in referrals from Police for domestic abuse. The Paediatric Department observed a 67% decrease in child protection medical examinations (CPMEs) undertaken (52 vs. 17). 23 examinations in 2019 were referred from schools compared to 1 in 2020. There was a greater proportion of self-referrals for CPMEs in 2020. ED child protection referrals increased from 189 (2019) to 204 (2020). CONCLUSION: There was an increase in self-referrals to local support services for domestic and child abuse concerns and an increase in referrals from families/friends for child protection concerns. This was not the case with police, ED and schools/nurseries referrals. This suggests reduced engagement with public sector organisations during lockdown which services should consider.

Hyper-heuristic Evolution of Dispatching Rules: A Comparison of Rule Representations.

Dispatching rules are frequently used for real-time, online scheduling in complex manufacturing systems. Design of such rules is usually done by experts in a time consuming trial-and-error process. Recently, evolutionary algorithms have been proposed to automate the design process. There are several possibilities to represent rules for this hyper-heuristic search. Because the representation determines the search neighborhood and the complexity of the rules that can be evolved, a suitable choice of representation is key for a successful evolutionary algorithm. In this paper we empirically compare three different representations, both numeric and symbolic, for automated rule design: A linear combination of attributes, a representation based on artificial neural networks, and a tree representation. Using appropriate evolutionary algorithms (CMA-ES for the neural network and linear representations, genetic programming for the tree representation), we empirically investigate the suitability of each representation in a dynamic stochastic job shop scenario. We also examine the robustness of the evolved dispatching rules against variations in the underlying job shop scenario, and visualize what the rules do, in order to get an intuitive understanding of their inner workings. Results indicate that the tree representation using an improved version of genetic programming gives the best results if many candidate rules can be evaluated, closely followed by the neural network representation that already leads to good results for small to moderate computational budgets. The linear representation is found to be competitive only for extremely small computational budgets.

On Using Surrogates with Genetic Programming.

One way to accelerate evolutionary algorithms with expensive fitness evaluations is to combine them with surrogate models. Surrogate models are efficiently computable approximations of the fitness function, derived by means of statistical or machine learning techniques from samples of fully evaluated solutions. But these models usually require a numerical representation, and therefore cannot be used with the tree representation of genetic programming (GP). In this paper, we present a new way to use surrogate models with GP. Rather than using the genotype directly as input to the surrogate model, we propose using a phenotypic characterization. This phenotypic characterization can be computed efficiently and allows us to define approximate measures of equivalence and similarity. Using a stochastic, dynamic job shop scenario as an example of simulation-based GP with an expensive fitness evaluation, we show how these ideas can be used to construct surrogate models and improve the convergence speed and solution quality of GP.