'The application of Bayesian Optimization and Classifier Systems in Nurse Scheduling'

Abstract. Two ideas taken from Bayesian optimization and classifier systems are presented for personnel scheduling based on choosing a suitable scheduling rule from a set for each person's assignment. Unlike our previous work of using genetic algorithms whose learning is implicit, the learning in both approaches is explicit, i.e. we are able to identify building blocks directly. To achieve this target, the Bayesian optimization algorithm builds a Bayesian network of the joint probability distribution of the rules used to construct solutions, while the adapted classifier system assigns each rule a strength value that is constantly updated according to its usefulness in the current situation. Computational results from 52 real data instances of nurse scheduling demonstrate the success of both approaches. It is also suggested that the learning mechanism in the proposed approaches might be suitable for other scheduling problems.

'The application of Bayesian Optimization and Classifier Systems in Nurse Scheduling'

Abstract. Two ideas taken from Bayesian optimization and classifier systems are presented for personnel scheduling based on choosing a suitable scheduling rule from a set for each person's assignment. Unlike our previous work of using genetic algorithms whose learning is implicit, the learning in both approaches is explicit, i.e. we are able to identify building blocks directly. To achieve this target, the Bayesian optimization algorithm builds a Bayesian network of the joint probability distribution of the rules used to construct solutions, while the adapted classifier system assigns each rule a strength value that is constantly updated according to its usefulness in the current situation. Computational results from 52 real data instances of nurse scheduling demonstrate the success of both approaches. It is also suggested that the learning mechanism in the proposed approaches might be suitable for other scheduling problems.

The organization, form and function of intermediate care services and systems in England: results from a national survey

This paper reports the results of a postal survey of intermediate care co-ordinators (ICCs) on the organization and delivery of intermediate care services for older people in England, conducted between November 2003 and May 2004. Questionnaires, which covered a range of issues with a variety of quantitative, ‘tick-box’ and open-ended questions, were returned by 106 respondents, representing just over 35% of primary care trusts (PCTs). We discuss the role of ICCs, the integration of local systems of intermediate care provision, and the form, function and model of delivery of services described by respondents. Using descriptive and statistical analysis of the responses, we highlight in particular the relationship between provision of admission avoidance and supported discharge, the availability of 24-hour care, and the locations in which care is provided, and relate our findings to the emerging evidence base for intermediate care, guidance on implementation from central government, and debate in the literature. Whilst the expansion and integration of intermediate care appear to be continuing apace, much provision seems concentrated in supported discharge services rather than acute admission avoidance, and particularly in residential forms of post-acute intermediate care. Supported discharge services tend to be found in residential settings, while admission avoidance provision tends to be non-residential in nature. Twenty-four hour care in non-residential settings is not available in several responding PCTs. These findings raise questions about the relationship between the implementation of intermediate care and the evidence for and aims of the policy as part of NHS modernization, and the extent to which intermediate care represents a genuinely novel approach to the care and rehabilitation of older people.