'A Bayesian Optimisation Algorithm for the Nurse Scheduling Problem'

Abstract- A Bayesian optimization algorithm for the nurse scheduling problem is presented, which involves choosing a suitable scheduling rule from a set for each nurse's assignment. Unlike our previous work that used GAs to implement implicit learning, the learning in the proposed algorithm is explicit, i.e. eventually, we will be able to identify and mix building blocks directly. The Bayesian optimization algorithm is applied to implement such explicit learning by building a Bayesian network of the joint distribution of solutions. The conditional probability of each variable in the network is computed according to an initial set of promising solutions. Subsequently, each new instance for each variable is generated by using the corresponding conditional probabilities, until all variables have been generated, i.e. in our case, a new rule string has been obtained. Another set of rule strings will be generated in this way, some of which will replace previous strings based on fitness selection. If stopping conditions are not met, the conditional probabilities for all nodes in the Bayesian network are updated again using the current set of promising rule strings. Computational results from 52 real data instances demonstrate the success of this approach. It is also suggested that the learning mechanism in the proposed approach might be suitable for other scheduling problems.

'Bayesian Optimisation for Nurse Scheduling'

A Bayesian optimisation algorithm for a nurse scheduling problem is presented, which involves choosing a suitable scheduling rule from a set for each nurse's assignment. When a human scheduler works, he normally builds a schedule systematically following a set of rules. After much practice, the scheduler gradually masters the knowledge of which solution parts go well with others. He can identify good parts and is aware of the solution quality even if the scheduling process is not yet completed, thus having the ability to finish a schedule by using flexible, rather than fixed, rules. In this paper, we design a more human-like scheduling algorithm, by using a Bayesian optimisation algorithm to implement explicit learning from past solutions. A nurse scheduling problem from a UK hospital is used for testing. Unlike our previous work that used Genetic Algorithms to implement implicit learning [1], the learning in the proposed algorithm is explicit, i.e. we identify and mix building blocks directly. The Bayesian optimisation algorithm is applied to implement such explicit learning by building a Bayesian network of the joint distribution of solutions. The conditional probability of each variable in the network is computed according to an initial set of promising solutions. Subsequently, each new instance for each variable is generated by using the corresponding conditional probabilities, until all variables have been generated, i.e. in our case, new rule strings have been obtained. Sets of rule strings are generated in this way, some of which will replace previous strings based on fitness. If stopping conditions are not met, the conditional probabilities for all nodes in the Bayesian network are updated again using the current set of promising rule strings. For clarity, consider the following toy example of scheduling five nurses with two rules (1: random allocation, 2: allocate nurse to low-cost shifts). In the beginning of the search, the probabilities of choosing rule 1 or 2 for each nurse is equal, i.e. 50%. After a few iterations, due to the selection pressure and reinforcement learning, we experience two solution pathways: Because pure low-cost or random allocation produces low quality solutions, either rule 1 is used for the first 2-3 nurses and rule 2 on remainder or vice versa. In essence, Bayesian network learns 'use rule 2 after 2-3x using rule 1' or vice versa. It should be noted that for our and most other scheduling problems, the structure of the network model is known and all variables are fully observed. In this case, the goal of learning is to find the rule values that maximize the likelihood of the training data. Thus, learning can amount to 'counting' in the case of multinomial distributions. For our problem, we use our rules: Random, Cheapest Cost, Best Cover and Balance of Cost and Cover. In more detail, the steps of our Bayesian optimisation algorithm for nurse scheduling are: 1. Set t = 0, and generate an initial population P(0) at random; 2. Use roulette-wheel selection to choose a set of promising rule strings S(t) from P(t); 3. Compute conditional probabilities of each node according to this set of promising solutions; 4. Assign each nurse using roulette-wheel selection based on the rules' conditional probabilities. A set of new rule strings O(t) will be generated in this way; 5. Create a new population P(t+1) by replacing some rule strings from P(t) with O(t), and set t = t+1; 6. If the termination conditions are not met (we use 2000 generations), go to step 2. Computational results from 52 real data instances demonstrate the success of this approach. They also suggest that the learning mechanism in the proposed approach might be suitable for other scheduling problems. Another direction for further research is to see if there is a good constructing sequence for individual data instances, given a fixed nurse scheduling order. If so, the good patterns could be recognized and then extracted as new domain knowledge. Thus, by using this extracted knowledge, we can assign specific rules to the corresponding nurses beforehand, and only schedule the remaining nurses with all available rules, making it possible to reduce the solution space. Acknowledgements The work was funded by the UK Government's major funding agency, Engineering and Physical Sciences Research Council (EPSRC), under grand GR/R92899/01. References [1] Aickelin U, "An Indirect Genetic Algorithm for Set Covering Problems", Journal of the Operational Research Society, 53(10): 1118-1126,

'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.

Bayesian Optimisation Algorithm for Nurse Scheduling, Scalable Optimization via Probabilistic Modeling

Our research has shown that schedules can be built mimicking a human scheduler by using a set of rules that involve domain knowledge. This chapter presents a Bayesian Optimization Algorithm (BOA) for the nurse scheduling problem that chooses such suitable scheduling rules from a set for each nurse’s assignment. Based on the idea of using probabilistic models, the BOA builds a Bayesian network for the set of promising solutions and samples these networks to generate new candidate solutions. Computational results from 52 real data instances demonstrate the success of this approach. It is also suggested that the learning mechanism in the proposed algorithm may 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.

'Bayesian Optimisation for Nurse Scheduling'

A Bayesian optimisation algorithm for a nurse scheduling problem is presented, which involves choosing a suitable scheduling rule from a set for each nurse's assignment. When a human scheduler works, he normally builds a schedule systematically following a set of rules. After much practice, the scheduler gradually masters the knowledge of which solution parts go well with others. He can identify good parts and is aware of the solution quality even if the scheduling process is not yet completed, thus having the ability to finish a schedule by using flexible, rather than fixed, rules. In this paper, we design a more human-like scheduling algorithm, by using a Bayesian optimisation algorithm to implement explicit learning from past solutions. A nurse scheduling problem from a UK hospital is used for testing. Unlike our previous work that used Genetic Algorithms to implement implicit learning [1], the learning in the proposed algorithm is explicit, i.e. we identify and mix building blocks directly. The Bayesian optimisation algorithm is applied to implement such explicit learning by building a Bayesian network of the joint distribution of solutions. The conditional probability of each variable in the network is computed according to an initial set of promising solutions. Subsequently, each new instance for each variable is generated by using the corresponding conditional probabilities, until all variables have been generated, i.e. in our case, new rule strings have been obtained. Sets of rule strings are generated in this way, some of which will replace previous strings based on fitness. If stopping conditions are not met, the conditional probabilities for all nodes in the Bayesian network are updated again using the current set of promising rule strings. For clarity, consider the following toy example of scheduling five nurses with two rules (1: random allocation, 2: allocate nurse to low-cost shifts). In the beginning of the search, the probabilities of choosing rule 1 or 2 for each nurse is equal, i.e. 50%. After a few iterations, due to the selection pressure and reinforcement learning, we experience two solution pathways: Because pure low-cost or random allocation produces low quality solutions, either rule 1 is used for the first 2-3 nurses and rule 2 on remainder or vice versa. In essence, Bayesian network learns 'use rule 2 after 2-3x using rule 1' or vice versa. It should be noted that for our and most other scheduling problems, the structure of the network model is known and all variables are fully observed. In this case, the goal of learning is to find the rule values that maximize the likelihood of the training data. Thus, learning can amount to 'counting' in the case of multinomial distributions. For our problem, we use our rules: Random, Cheapest Cost, Best Cover and Balance of Cost and Cover. In more detail, the steps of our Bayesian optimisation algorithm for nurse scheduling are: 1. Set t = 0, and generate an initial population P(0) at random; 2. Use roulette-wheel selection to choose a set of promising rule strings S(t) from P(t); 3. Compute conditional probabilities of each node according to this set of promising solutions; 4. Assign each nurse using roulette-wheel selection based on the rules' conditional probabilities. A set of new rule strings O(t) will be generated in this way; 5. Create a new population P(t+1) by replacing some rule strings from P(t) with O(t), and set t = t+1; 6. If the termination conditions are not met (we use 2000 generations), go to step 2. Computational results from 52 real data instances demonstrate the success of this approach. They also suggest that the learning mechanism in the proposed approach might be suitable for other scheduling problems. Another direction for further research is to see if there is a good constructing sequence for individual data instances, given a fixed nurse scheduling order. If so, the good patterns could be recognized and then extracted as new domain knowledge. Thus, by using this extracted knowledge, we can assign specific rules to the corresponding nurses beforehand, and only schedule the remaining nurses with all available rules, making it possible to reduce the solution space. Acknowledgements The work was funded by the UK Government's major funding agency, Engineering and Physical Sciences Research Council (EPSRC), under grand GR/R92899/01. References [1] Aickelin U, "An Indirect Genetic Algorithm for Set Covering Problems", Journal of the Operational Research Society, 53(10): 1118-1126,

'A Bayesian Optimisation Algorithm for the Nurse Scheduling Problem'

Abstract- A Bayesian optimization algorithm for the nurse scheduling problem is presented, which involves choosing a suitable scheduling rule from a set for each nurse's assignment. Unlike our previous work that used GAs to implement implicit learning, the learning in the proposed algorithm is explicit, i.e. eventually, we will be able to identify and mix building blocks directly. The Bayesian optimization algorithm is applied to implement such explicit learning by building a Bayesian network of the joint distribution of solutions. The conditional probability of each variable in the network is computed according to an initial set of promising solutions. Subsequently, each new instance for each variable is generated by using the corresponding conditional probabilities, until all variables have been generated, i.e. in our case, a new rule string has been obtained. Another set of rule strings will be generated in this way, some of which will replace previous strings based on fitness selection. If stopping conditions are not met, the conditional probabilities for all nodes in the Bayesian network are updated again using the current set of promising rule strings. Computational results from 52 real data instances demonstrate the success of this approach. It is also suggested that the learning mechanism in the proposed approach might be suitable for other scheduling problems.

A Bayesian optimization algorithm for the nurse scheduling problem

A Bayesian optimization algorithm for the nurse scheduling problem is presented, which involves choosing a suitable scheduling rule from a set for each nurse’s assignment. Unlike our previous work that used GAs to implement implicit learning, the learning in the proposed algorithm is explicit, i.e. eventually, we will be able to identify and mix building blocks directly. The Bayesian optimization algorithm is applied to implement such explicit learning by building a Bayesian network of the joint distribution of solutions. The conditional probability of each variable in the network is computed according to an initial set of promising solutions. Subsequently, each new instance for each variable is generated by using the corresponding conditional probabilities, until all variables have been generated, i.e. in our case, a new rule string has been obtained. Another set of rule strings will be generated in this way, some of which will replace previous strings based on fitness selection. If stopping conditions are not met, the conditional probabilities for all nodes in the Bayesian network are updated again using the current set of promising rule strings. Computational results from 52 real data instances demonstrate the success of this approach. It is also suggested that the learning mechanism in the proposed approach might be suitable for other scheduling problems.

Classifying an opponent’s behaviour in robot soccer

This paper illustrates the prediction of opponent behaviour in a competitive, highly dynamic, multi-agent and partially observable environment, namely RoboCup small size league robot soccer. The performance is illustrated in the context of the highly successful robot soccer team, the RoboRoos. The project is broken into three tasks; classification of behaviours, modelling and prediction of behaviours and integration of the predictions into the existing planning system. A probabilistic approach is taken to dealing with the uncertainty in the observations and with representing the uncertainty in the prediction of the behaviours. Results are shown for a classification system using a Naïve Bayesian Network that determines the opponent’s current behaviour. These results are compared to an expert designed fuzzy behaviour classification system. The paper illustrates how the modelling system will use the information from behaviour classification to produce probability distributions that model the manner with which the opponents perform their behaviours. These probability distributions are show to match well with the existing multi-agent planning system (MAPS) that forms the core of the RoboRoos system.

Privacy and trust management for electronic health records

Establishing a nationwide Electronic Health Record system has become a primary objective for many countries around the world, including Australia, in order to improve the quality of healthcare while at the same time decreasing its cost. Doing so will require federating the large number of patient data repositories currently in use throughout the country. However, implementation of EHR systems is being hindered by several obstacles, among them concerns about data privacy and trustworthiness. Current IT solutions fail to satisfy patients’ privacy desires and do not provide a trustworthiness measure for medical data. This thesis starts with the observation that existing EHR system proposals suer from six serious shortcomings that aect patients’ privacy and safety, and medical practitioners’ trust in EHR data: accuracy and privacy concerns over linking patients’ existing medical records; the inability of patients to have control over who accesses their private data; the inability to protect against inferences about patients’ sensitive data; the lack of a mechanism for evaluating the trustworthiness of medical data; and the failure of current healthcare workflow processes to capture and enforce patient’s privacy desires. Following an action research method, this thesis addresses the above shortcomings by firstly proposing an architecture for linking electronic medical records in an accurate and private way where patients are given control over what information can be revealed about them. This is accomplished by extending the structure and protocols introduced in federated identity management to link a patient’s EHR to his existing medical records by using pseudonym identifiers. Secondly, a privacy-aware access control model is developed to satisfy patients’ privacy requirements. The model is developed by integrating three standard access control models in a way that gives patients access control over their private data and ensures that legitimate uses of EHRs are not hindered. Thirdly, a probabilistic approach for detecting and restricting inference channels resulting from publicly-available medical data is developed to guard against indirect accesses to a patient’s private data. This approach is based upon a Bayesian network and the causal probabilistic relations that exist between medical data fields. The resulting definitions and algorithms show how an inference channel can be detected and restricted to satisfy patients’ expressed privacy goals. Fourthly, a medical data trustworthiness assessment model is developed to evaluate the quality of medical data by assessing the trustworthiness of its sources (e.g. a healthcare provider or medical practitioner). In this model, Beta and Dirichlet reputation systems are used to collect reputation scores about medical data sources and these are used to compute the trustworthiness of medical data via subjective logic. Finally, an extension is made to healthcare workflow management processes to capture and enforce patients’ privacy policies. This is accomplished by developing a conceptual model that introduces new workflow notions to make the workflow management system aware of a patient’s privacy requirements. These extensions are then implemented in the YAWL workflow management system.

Fault diagnostics and supervised testing : How fault diagnostic tools can be proactive?

The topic of fault detection and diagnostics (FDD) is studied from the perspective of proactive testing. Unlike most research focus in the diagnosis area in which system outputs are analyzed for diagnosis purposes, in this paper the focus is on the other side of the problem: manipulating system inputs for better diagnosis reasoning. In other words, the question of how diagnostic mechanisms can direct system inputs for better diagnosis analysis is addressed here. It is shown how the problem can be formulated as decision making problem coupled with a Bayesian Network based diagnostic mechanism. The developed mechanism is applied to the problem of supervised testing in HVAC systems.

Modelling passenger flow at airport terminals : individual agent decision model for stochastic passenger behaviour

Airport system is complex. Passenger dynamics within it appear to be complicate as well. Passenger behaviours outside standard processes are regarded more significant in terms of public hazard and service rate issues. In this paper, we devised an individual agent decision model to simulate stochastic passenger behaviour in airport departure terminal. Bayesian networks are implemented into the decision making model to infer the probabilities that passengers choose to use any in-airport facilities. We aim to understand dynamics of the discretionary activities of passengers.

Higher degree research at Australian Universities : Responding to diversity in engineering and information technology

BACKGROUND There is increasing enrolment of international students in the Engineering and Information Technology disciplines and anecdotal evidence of a need for additional understanding and support for these students and their supervisors due to differences both in academic and social cultures. While there is a growing literature on supervisory styles and guidelines on effective supervision, there is little on discipline-specific, cross-cultural supervision responding to the growing diversity. In this paper, we report findings from a study of Engineering and Information technology Higher Degree Research (HDR)students and supervision in three Australian universities. PURPOSE The aim was to assess perceptions of students and supervisors of factors influencing success that are particular to international or culturally and linguistically diverse (CaLD) HDR students in Engineering and Information technology. DESIGN/METHOD Online survey and qualitative data was collected from international and CaLD HDR students and supervisors at the three universities. Bayesian network analysis, inferential statistics, and qualitative analysis provided the main findings. RESULTS Survey results indicate that both students and supervisors are positive about their experiences, and do not see language or culture as particularly problematic. The survey results also reveal strong consistency between the perceptions of students and supervisors on most factors influencing success. Qualitative analysis of critical supervision incidents has provided rich data that could help improve support services. CONCLUSIONS In contrast with anecdotal evidence, HDR completion data from the three universities reveal that international students, on average, complete in shorter time periods than domestic students. The analysis suggests that success is linked to a complex set of factors involving the student, supervision, the institution and broader community.

Factors affecting timely completion of a PhD : a complex systems approach

Completing a PhD on time is a complex process, influenced by many interacting factors. In this paper we take a Bayesian Network approach to analyzing the factors perceived to be important in achieving this aim. Focusing on a single research group in Mathematical Sciences, we develop a conceptual model to describe the factors considered to be important to students and then quantify the network based on five individual perspectives: the students, a supervisor and a university research students centre manager. The resultant network comprised 37 factors and 40 connections, with an overall probability of timely completion of between 0.6 and 0.8. Across all participants, the four factors that were considered to most directly influence timely completion were personal aspects, the research environment, the research project, and incoming skills.

Agent-based model of passenger flows in airport terminals

Passenger flow studies in airport terminals have shown consistent statistical relationships between airport spatial layout and pedestrian movement, facilitating prediction of movement from terminal designs. However, these studies are done at an aggregate level and do not incorporate how individual passengers make decisions at a microscopic level. Therefore, they do not explain the formation of complex movement flows. In addition, existing models mostly focus on standard airport processing procedures such as immigration and security, but seldom consider discretionary activities of passengers, and thus are not able to truly describe the full range of passenger flows within airport terminals. As the route-choice decision-making of passengers involves many uncertain factors within the airport terminals, the mechanisms to fulfill the capacity of managing the route-choice have proven difficult to acquire and quantify. Could the study of cognitive factors of passengers (i.e. human mental preferences of deciding which on-airport facility to use) be useful to tackle these issues? Assuming the movement in virtual simulated environments can be analogous to movement in real environments, passenger behaviour dynamics can be similar to those generated in virtual experiments. Three levels of dynamics have been devised for motion control: the localised field, tactical level, and strategic level. A localised field refers to basic motion capabilities, such as walking speed, direction and avoidance of obstacles. The other two fields represent cognitive route-choice decision-making. This research views passenger flow problems via a "bottom-up approach", regarding individual passengers as independent intelligent agents who can behave autonomously and are able to interact with others and the ambient environment. In this regard, passenger flow formation becomes an emergent phenomenon of large numbers of passengers interacting with others. In the thesis, first, the passenger flow in airport terminals was investigated. Discretionary activities of passengers were integrated with standard processing procedures in the research. The localised field for passenger motion dynamics was constructed by a devised force-based model. Next, advanced traits of passengers (such as their desire to shop, their comfort with technology and their willingness to ask for assistance) were formulated to facilitate tactical route-choice decision-making. The traits consist of quantified measures of mental preferences of passengers when they travel through airport terminals. Each category of the traits indicates a decision which passengers may take. They were inferred through a Bayesian network model by analysing the probabilities based on currently available data. Route-choice decision-making was finalised by calculating corresponding utility results based on those probabilities observed. Three sorts of simulation outcomes were generated: namely, queuing length before checkpoints, average dwell time of passengers at service facilities, and instantaneous space utilisation. Queuing length reflects the number of passengers who are in a queue. Long queues no doubt cause significant delay in processing procedures. The dwell time of each passenger agent at the service facilities were recorded. The overall dwell time of passenger agents at typical facility areas were analysed so as to demonstrate portions of utilisation in the temporal aspect. For the spatial aspect, the number of passenger agents who were dwelling within specific terminal areas can be used to estimate service rates. All outcomes demonstrated specific results by typical simulated passenger flows. They directly reflect terminal capacity. The simulation results strongly suggest that integrating discretionary activities of passengers makes the passenger flows more intuitive, observing probabilities of mental preferences by inferring advanced traits make up an approach capable of carrying out tactical route-choice decision-making. On the whole, the research studied passenger flows in airport terminals by an agent-based model, which investigated individual characteristics of passengers and their impact on psychological route-choice decisions of passengers. Finally, intuitive passenger flows in airport terminals were able to be realised in simulation.