'Explicit Learning: an Effort towards Human Scheduling Algorithms'

Abstract Scheduling problems are generally NP-hard combinatorial problems, and a lot of research has been done to solve these problems heuristically. However, most of the previous approaches are problem-specific and research into the development of a general scheduling algorithm is still in its infancy. Mimicking the natural evolutionary process of the survival of the fittest, Genetic Algorithms (GAs) have attracted much attention in solving difficult scheduling problems in recent years. Some obstacles exist when using GAs: there is no canonical mechanism to deal with constraints, which are commonly met in most real-world scheduling problems, and small changes to a solution are difficult. To overcome both difficulties, indirect approaches have been presented (in [1] and [2]) for nurse scheduling and driver scheduling, where GAs are used by mapping the solution space, and separate decoding routines then build solutions to the original problem. In our previous indirect GAs, learning is implicit and is restricted to the efficient adjustment of weights for a set of rules that are used to construct schedules. The major limitation of those approaches is that they learn in a non-human way: like most existing construction algorithms, once the best weight combination is found, the rules used in the construction process are fixed at each iteration. However, normally a long sequence of moves is needed to construct a schedule and using fixed rules at each move is thus unreasonable and not coherent with human learning processes. When a human scheduler is working, he normally builds a schedule step by step 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 completed yet, thus having the ability to finish a schedule by using flexible, rather than fixed, rules. In this research we intend to design more human-like scheduling algorithms, by using ideas derived from Bayesian Optimization Algorithms (BOA) and Learning Classifier Systems (LCS) to implement explicit learning from past solutions. BOA can be applied to learn to identify good partial solutions and to complete them by building a Bayesian network of the joint distribution of solutions [3]. A Bayesian network is a directed acyclic graph with each node corresponding to one variable, and each variable corresponding to individual rule by which a schedule will be constructed step by step. The conditional probabilities are computed according to an initial set of promising solutions. Subsequently, each new instance for each node is generated by using the corresponding conditional probabilities, until values for all nodes have been generated. 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 Bayesian network is updated again using the current set of good rule strings. The algorithm thereby tries to explicitly identify and mix promising building blocks. It should be noted that for most scheduling problems the structure of the network model is known and all the 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. In the LCS approach, each rule has its strength showing its current usefulness in the system, and this strength is constantly assessed [4]. To implement sophisticated learning based on previous solutions, an improved LCS-based algorithm is designed, which consists of the following three steps. The initialization step is to assign each rule at each stage a constant initial strength. Then rules are selected by using the Roulette Wheel strategy. The next step is to reinforce the strengths of the rules used in the previous solution, keeping the strength of unused rules unchanged. The selection step is to select fitter rules for the next generation. It is envisaged that the LCS part of the algorithm will be used as a hill climber to the BOA algorithm. This is exciting and ambitious research, which might provide the stepping-stone for a new class of scheduling algorithms. Data sets from nurse scheduling and mall problems will be used as test-beds. It is envisaged that once the concept has been proven successful, it will be implemented into general scheduling algorithms. It is also hoped that this research will give some preliminary answers about how to include human-like learning into scheduling algorithms and may therefore be of interest to researchers and practitioners in areas of scheduling and evolutionary computation. References 1. Aickelin, U. and Dowsland, K. (2003) 'Indirect Genetic Algorithm for a Nurse Scheduling Problem', Computer & Operational Research (in print). 2. Li, J. and Kwan, R.S.K. (2003), 'Fuzzy Genetic Algorithm for Driver Scheduling', European Journal of Operational Research 147(2): 334-344. 3. Pelikan, M., Goldberg, D. and Cantu-Paz, E. (1999) 'BOA: The Bayesian Optimization Algorithm', IlliGAL Report No 99003, University of Illinois. 4. Wilson, S. (1994) 'ZCS: A Zeroth-level Classifier System', Evolutionary Computation 2(1), pp 1-18.

An Estimation of Distribution Algorithm for Nurse Scheduling

Schedules can be built in a similar way to a human scheduler by using a set of rules that involve domain knowledge. This paper presents an Estimation of Distribution Algorithm (EDA) for the nurse scheduling problem, which involves choosing a suitable scheduling rule from a set for the assignment of each nurse. Unlike previous work that used Genetic Algorithms (GAs) to implement implicit learning, the learning in the proposed algorithm is explicit, i.e. we identify and mix building blocks directly. The EDA 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.

BOA for nurse scheduling

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.

How to cope with air transport disruptions: airport airside resilience and vulnerability

The efficiency of airport airside operations is often compromised by unplanned disruptive events of different kinds, such as bad weather, strikes or technical failures, which negatively influence the punctuality and regularity of operations, causing serious delays and unexpected congestion. They may provoke important impacts and economic losses on passengers, airlines and airport operators, and consequences may propagate in the air network throughout different airports. In order to identify strategies to cope with such events and minimize their impacts, it is crucial to understand how disruptive events affect airports’ performance. The research field related with the risk of severe air transport network disruptions and their impact on society is related to the concepts of vulnerability and resilience. The main objective of this project is to provide a framework that allows to evaluate performance losses and consequences due to unexpected disruptions affecting airport airside operations, supporting the development of a methodology for estimating vulnerability and resilience indicators for airport airside operations. The methodology proposed comprises three phases. In the first phase, airside operations are modelled in both the baseline and disrupted scenarios. The model includes all main airside processes and takes into consideration the uncertainties and dynamics of the system. In the second phase, the model is implemented by using a generic simulation software, AnyLogic. Vulnerability is evaluated by taking into consideration the costs related to flight delays, cancellations and diversions; resilience is determined as a function of the loss of capacity during the entire period of disruption. In the third phase, a Bayesian Network is built in which uncertain variables refer to airport characteristics and disruption type. The Bayesian Network expresses the conditional dependence among these variables and allows to predict the impacts of disruptions on an airside system, determining the elements which influence the system resilience the most.

Synergies among safety and security in the prevention of major accidents related to dangerous substances

Historical evidence shows that chemical, process, and Oil&Gas facilities where dangerous substances are stored or handled are target of deliberate malicious attacks (security attacks) aiming at interfering with normal operations. Physical attacks and cyber-attacks may generate events with consequences on people, property, and the surrounding environment that are comparable to those of major accidents caused by safety-related causes. The security aspects of these facilities are commonly addressed using Security Vulnerability/Risk Assessment (SVA/SRA) methodologies. Most of these methodologies are semi-quantitative and non-systematic approaches that strongly rely on expert judgment, leading to security assessments that are not reproducible. Moreover, they do not consider the synergies with the safety domain. The present 3-year research is aimed at filling the gap outlined by providing knowledge on security attacks, as well as rigorous and systematic methods supporting existing SVA/SRA studies suitable for the chemical, process, and Oil&Gas industry. The different nature of cyber and physical attacks resulted in the development of different methods for the two domains. The first part of the research was devoted to the development and statistical analysis of security databases that allowed to develop new knowledge and lessons learnt on security threats. Based on the obtained background, a Bow-Tie based procedure and two reverse-HazOp based methodologies were developed as hazard identification approaches for physical and cyber threats respectively. To support the quantitative estimation of the security risk, a quantitative procedure based on the Bayesian Network was developed allowing to calculate the probability of success of physical security attacks. All the developed methods have been applied to case studies addressing chemical, process and Oil&Gas facilities (offshore and onshore) proving the quality of the results that can be achieved in improving site security. Furthermore, the outcomes achieved allow to step forward in developing synergies and promoting integration among safety and security management.

Haplotype distribution of five nuclear genes based on network genealogies and Bayesian inference indicates that Trypanosoma cruzi hybrid strains are polyphyletic

Chagas disease is still a major public health problem in Latin America. Its causative agent, Trypanosoma cruzi, can be typed into three major groups, T. cruzi I, T. cruzi II and hybrids. These groups each have specific genetic characteristics and epidemiological distributions. Several highly virulent strains are found in the hybrid group; their origin is still a matter of debate. The null hypothesis is that the hybrids are of polyphyletic origin, evolving independently from various hybridization events. The alternative hypothesis is that all extant hybrid strains originated from a single hybridization event. We sequenced both alleles of genes encoding EF-1 alpha, actin and SSU rDNA of 26 T. cruzi strains and DHFR-TS and TR of 12 strains. This information was used for network genealogy analysis and Bayesian phylogenies. We found T. cruzi I and T. cruzi II to be monophyletic and that all hybrids had different combinations of T. cruzi I and T. cruzi II haplotypes plus hybrid-specific haplotypes. Bootstrap values (networks) and posterior probabilities (Bayesian phylogenies) of clades supporting the monophyly of hybrids were far below the 95% confidence interval, indicating that the hybrid group is polyphyletic. We hypothesize that T. cruzi I and T. cruzi II are two different species and that the hybrids are extant representatives of independent events of genome hybridization, which sporadically have sufficient fitness to impact on the epidemiology of Chagas disease.

A multi-agent system with distributed bayesian reasoning for network fault diagnosis

In this paper, an innovative approach to perform distributed Bayesian inference using a multi-agent architecture is presented. The final goal is dealing with uncertainty in network diagnosis, but the solution can be of applied in other fields. The validation testbed has been a P2P streaming video service. An assessment of the work is presented, in order to show its advantages when it is compared with traditional manual processes and other previous systems.

Learning Bayesian networks from data by the incremental compilation of new network polynomials

Probabilistic graphical models are a huge research field in artificial intelligence nowadays. The scope of this work is the study of directed graphical models for the representation of discrete distributions. Two of the main research topics related to this area focus on performing inference over graphical models and on learning graphical models from data. Traditionally, the inference process and the learning process have been treated separately, but given that the learned models structure marks the inference complexity, this kind of strategies will sometimes produce very inefficient models. With the purpose of learning thinner models, in this master thesis we propose a new model for the representation of network polynomials, which we call polynomial trees. Polynomial trees are a complementary representation for Bayesian networks that allows an efficient evaluation of the inference complexity and provides a framework for exact inference. We also propose a set of methods for the incremental compilation of polynomial trees and an algorithm for learning polynomial trees from data using a greedy score+search method that includes the inference complexity as a penalization in the scoring function.

A bayesian artificial neural network method to characterise laminar defects using dynamic measurements

This paper reports on the development of an artificial neural network (ANN) method to detect laminar defects following the pattern matching approach utilizing dynamic measurement. Although structural health monitoring (SHM) using ANN has attracted much attention in the last decade, the problem of how to select the optimal class of ANN models has not been investigated in great depth. It turns out that the lack of a rigorous ANN design methodology is one of the main reasons for the delay in the successful application of the promising technique in SHM. In this paper, a Bayesian method is applied in the selection of the optimal class of ANN models for a given set of input/target training data. The ANN design method is demonstrated for the case of the detection and characterisation of laminar defects in carbon fibre-reinforced beams using flexural vibration data for beams with and without non-symmetric delamination damage.

A Bayesian neural network algorithm identifies patients in whom post-EVAR surveillance may be unnecessary

Lifelong surveillance is not cost-effective after endovascular aneurysm repair (EVAR), but is required to detect aortic complications which are fatal if untreated (type 1/3 endoleak, sac expansion, device migration). Aneurysm morphology determines the probability of aortic complications and therefore the need for surveillance, but existing analyses have proven incapable of identifying patients at sufficiently low risk to justify abandoning surveillance. This study aimed to improve the prediction of aortic complications, through the application of machine-learning techniques. Patients undergoing EVAR at 2 centres were studied from 2004–2010. Aneurysm morphology had previously been studied to derive the SGVI Score for predicting aortic complications. Bayesian Neural Networks were designed using the same data, to dichotomise patients into groups at low- or high-risk of aortic complications. Network training was performed only on patients treated at centre 1. External validation was performed by assessing network performance independently of network training, on patients treated at centre 2. Discrimination was assessed by Kaplan-Meier analysis to compare aortic complications in predicted low-risk versus predicted high-risk patients. 761 patients aged 75 +/− 7 years underwent EVAR in 2 centres. Mean follow-up was 36+/− 20 months. Neural networks were created incorporating neck angu- lation/length/diameter/volume; AAA diameter/area/volume/length/tortuosity; and common iliac tortuosity/diameter. A 19-feature network predicted aor- tic complications with excellent discrimination and external validation (5-year freedom from aortic complications in predicted low-risk vs predicted high-risk patients: 97.9% vs. 63%; p < 0.0001). A Bayesian Neural-Network algorithm can identify patients in whom it may be safe to abandon surveillance after EVAR. This proposal requires prospective study.

An empirical hierarchical Bayesian unification of occupational exposure assessment methods.

In occupational exposure assessment of airborne contaminants, exposure levels can either be estimated through repeated measurements of the pollutant concentration in air, expert judgment or through exposure models that use information on the conditions of exposure as input. In this report, we propose an empirical hierarchical Bayesian model to unify these approaches. Prior to any measurement, the hygienist conducts an assessment to generate prior distributions of exposure determinants. Monte-Carlo samples from these distributions feed two level-2 models: a physical, two-compartment model, and a non-parametric, neural network model trained with existing exposure data. The outputs of these two models are weighted according to the expert's assessment of their relevance to yield predictive distributions of the long-term geometric mean and geometric standard deviation of the worker's exposure profile (level-1 model). Bayesian inferences are then drawn iteratively from subsequent measurements of worker exposure. Any traditional decision strategy based on a comparison with occupational exposure limits (e.g. mean exposure, exceedance strategies) can then be applied. Data on 82 workers exposed to 18 contaminants in 14 companies were used to validate the model with cross-validation techniques. A user-friendly program running the model is available upon request.

Bayesian image reconstruction with space-variant noise suppression

In this paper we present a Bayesian image reconstruction algorithm with entropy prior (FMAPE) that uses a space-variant hyperparameter. The spatial variation of the hyperparameter allows different degrees of resolution in areas of different statistical characteristics, thus avoiding the large residuals resulting from algorithms that use a constant hyperparameter. In the first implementation of the algorithm, we begin by segmenting a Maximum Likelihood Estimator (MLE) reconstruction. The segmentation method is based on using a wavelet decomposition and a self-organizing neural network. The result is a predetermined number of extended regions plus a small region for each star or bright object. To assign a different value of the hyperparameter to each extended region and star, we use either feasibility tests or cross-validation methods. Once the set of hyperparameters is obtained, we carried out the final Bayesian reconstruction, leading to a reconstruction with decreased bias and excellent visual characteristics. The method has been applied to data from the non-refurbished Hubble Space Telescope. The method can be also applied to ground-based images.

Implementing statistical learning methods through Bayesian networks. Part 1: a guide to Bayesian parameter estimation using forensic science data

As a thorough aggregation of probability and graph theory, Bayesian networks currently enjoy widespread interest as a means for studying factors that affect the coherent evaluation of scientific evidence in forensic science. Paper I of this series of papers intends to contribute to the discussion of Bayesian networks as a framework that is helpful for both illustrating and implementing statistical procedures that are commonly employed for the study of uncertainties (e.g. the estimation of unknown quantities). While the respective statistical procedures are widely described in literature, the primary aim of this paper is to offer an essentially non-technical introduction on how interested readers may use these analytical approaches - with the help of Bayesian networks - for processing their own forensic science data. Attention is mainly drawn to the structure and underlying rationale of a series of basic and context-independent network fragments that users may incorporate as building blocs while constructing larger inference models. As an example of how this may be done, the proposed concepts will be used in a second paper (Part II) for specifying graphical probability networks whose purpose is to assist forensic scientists in the evaluation of scientific evidence encountered in the context of forensic document examination (i.e. results of the analysis of black toners present on printed or copied documents).

An integrative computational analysis provides evidence for FBN1-associated network deregulation in trisomy 21

Although approximately 50% of Down Syndrome (DS) patients have heart abnormalities, they exhibit an overprotection against cardiac abnormalities related with the connective tissue, for example a lower risk of coronary artery disease. A recent study reported a case of a person affected by DS who carried mutations in FBN1, the gene causative for a connective tissue disorder called Marfan Syndrome (MFS). The fact that the person did not have any cardiac alterations suggested compensation effects due to DS. This observation is supported by a previous DS meta-analysis at the molecular level where we have found an overall upregulation of FBN1 (which is usually downregulated in MFS). Additionally, that result was cross-validated with independent expression data from DS heart tissue. The aim of this work is to elucidate the role of FBN1 in DS and to establish a molecular link to MFS and MFS-related syndromes using a computational approach. To reach that, we conducted different analytical approaches over two DS studies (our previous meta-analysis and independent expression data from DS heart tissue) and revealed expression alterations in the FBN1 interaction network, in FBN1 co-expressed genes and FBN1-related pathways. After merging the significant results from different datasets with a Bayesian approach, we prioritized 85 genes that were able to distinguish control from DS cases. We further found evidence for several of these genes (47%), such as FBN1, DCN, and COL1A2, being dysregulated in MFS and MFS-related diseases. Consequently, we further encourage the scientific community to take into account FBN1 and its related network for the study of DS cardiovascular characteristics.

The transcriptional network activated by Cln3 cyclin at the G1-to-S transition of the yeast cell cycle

Background: The G1-to-S transition of the cell cycle in the yeast Saccharomyces cerevisiae involves an extensive transcriptional program driven by transcription factors SBF (Swi4-Swi6) and MBF (Mbp1-Swi6). Activation of these factors ultimately depends on the G1 cyclin Cln3. Results: To determine the transcriptional targets of Cln3 and their dependence on SBF or MBF, we first have used DNA microarrays to interrogate gene expression upon Cln3 overexpression in synchronized cultures of strains lacking components of SBF and/or MBF. Secondly, we have integrated this expression dataset together with other heterogeneous data sources into a single probabilistic model based on Bayesian statistics. Our analysis has produced more than 200 transcription factor-target assignments, validated by ChIP assays and by functional enrichment. Our predictions show higher internal coherence and predictive power than previous classifications. Our results support a model whereby SBF and MBF may be differentially activated by Cln3. Conclusions: Integration of heterogeneous genome-wide datasets is key to building accurate transcriptional networks. By such integration, we provide here a reliable transcriptional network at the G1-to-S transition in the budding yeast cell cycle. Our results suggest that to improve the reliability of predictions we need to feed our models with more informative experimental data.