Siddhartha Shakya

Optimising cancer chemotherapy using an estimation of distribution algorithm and genetic algorithms

This paper presents a methodology for using heuristic search methods to optimise cancer chemotherapy. Specifically, two evolutionary algorithms - Population Based Incremental Learning (PBIL), which is an Estimation of Distribution Algorithm (EDA), and Genetic Algorithms (GAs) have been applied to the problem of finding effective chemotherapeutic treatments. To our knowledge, EDAs have been applied to fewer real world problems compared to GAs, and the aim of the present paper is to expand the application domain of this technique.We compare and analyse the performance of both algorithms and draw a conclusion as to which approach to cancer chemotherapy optimisation is more efficient and helpful in the decision-making activity led by the oncologists.

Using a Markov network model in a univariate EDA: an empirical cost-benefit analysis

This paper presents an empirical cost-benefit analysis of an algorithm called Distribution Estimation Using MRF with direct sampling (DEUMd). DEUMd belongs to the family of Estimation of Distribution Algorithm (EDA). Particularly it is a univariate EDA. DEUMd uses a computationally more expensive model to estimate the probability distribution than other univariate EDAs. We investigate the performance of DEUMd in a range of optimization problem. Our experiments shows a better performance (in terms of the number of fitness evaluation needed by the algorithm to find a solution and the quality of the solution) of DEUMd on most of the problems analysed in this paper in comparison to that of other univariate EDAs. We conclude that use of a Markov Network in a univariate EDA can be of net benefit in defined set of circumstances.

Solving the Ising Spin Glass Problem using a Bivariate EDA based on Markov Random Fields

Markov random field (MRF) modelling techniques have been recently proposed as a novel approach to probabilistic modelling for estimation of distribution algorithms (EDAs). An EDA using this technique was called distribution estimation using Markov random fields (DEUM). DEUM was later extended to DEUMd. DEUM and DEUMd use a univariate model of probability distribution, and have been shown to perform better than other univariate EDAs for a range of optimization problems. This paper extends DEUM to use a bivariate model and applies it to the Ising spin glass problems. We propose two variants of DEUM that use different sampling techniques. Our experimental result show a noticeable gain in performance.

An EDA based on local markov property and gibbs sampling

The key ideas behind most of the recently proposed Markov networks based EDAs were to factorise the joint probability distribution in terms of the cliques in the undirected graph. As such, they made use of the global Markov property of the Markov network. Here we presents a Markov Network based EDA that exploits Gibbs sampling to sample from the Local Markov property, the Markovianity, and does not directly model the joint distribution. We call it Markovianity based Optimisation Algorithm. Some initial results on the performance of the proposed algorithm shows that it compares well with other Bayesian network based EDAs.

A Markovianity based optimisation algorithm

Several Estimation of Distribution Algorithms (EDAs) based on Markov networks have been recently proposed. The key idea behind these EDAs was to factorise the joint probability distribution of solution variables in terms of cliques in the undirected graph. As such, they made use of the global Markov property of the Markov network in one form or another. This paper presents a Markov Network based EDA that is based on the use of the local Markov property, the Markovianity, and does not directly model the joint distribution. We call it Markovianity based Optimisation Algorithm. The algorithm combines a novel method for extracting the neighbourhood structure from the mutual information between the variables, with a Gibbs sampler method to generate new points. We present an extensive empirical validation of the algorithm on problems with complex interactions, comparing its performance with other EDAs that use higher order interactions. We extend the analysis to other functions with discrete representation, where EDA results are scarce, comparing the algorithm with state of the art EDAs that use marginal product factorisations.

A fully multivariate DEUM algorithm

Distribution Estimation Using Markov network (DEUM) algorithm is a class of estimation of distribution algorithms that uses Markov networks to model and sample the distribution. Several different versions of this algorithm have been proposed and are shown to work well in a number of different optimisation problems. One of the key similarities between all of the DEUMalgorithms proposed so far is that they all assume the interaction between variables in the problem to be pre given. In other words, they do not learn the structure of the problem and assume that it is known in advance. Therefore, they may not be classified as full estimation of distribution algorithms. This work presents a fully multivariate DEUM algorithm that can automatically learn the undirected structure of the problem, automatically find the cliques from the structure and automatically estimate a joint probability model of the Markov network. This model is then sampled using Monte Carlo samplers. The proposed DEUM algorithm can be applied to any general optimisation problem even when the structure is not known.

Markov Networks in Evolutionary Computation

Markov networks and other probabilistic graphical modes have recently received an upsurge in attention from Evolutionary computation community, particularly in the area of Estimation of distribution algorithms (EDAs). EDAs have arisen as one of the most successful experiences in the application of machine learning methods in optimization, mainly due to their efficiency to solve complex real-world optimization problems and their suitability for theoretical analysis. This book focuses on the different steps involved in the conception, implementation and application of EDAs that use Markov networks, and undirected models in general. It can serve as a general introduction to EDAs but covers also an important current void in the study of these algorithms by explaining the specificities and benefits of modeling optimization problems by means of undirected probabilistic models. All major developments to date in the progressive introduction of Markov networks based EDAs are reviewed in the book. Hot current research trends and future perspectives in the enhancement and applicability of EDAs are also covered. The contributions included in the book address topics as relevant as the application of probabilistic-based fitness models, the use of belief propagation algorithms in EDAs and the application of Markov network based EDAs to real-world optimization problems. The book should be of interest to researchers and practitioners from areas such as optimization, evolutionary computation, and machine learning.

Structure learning and optimisation in a Markov-network based estimation of distribution algorithm

Structure learning is a crucial component of a multivariate Estimation of Distribution algorithm. It is the part which determines the interactions between variables in the probabilistic model, based on analysis of the fitness function or a population. In this paper we take three different approaches to structure learning in an EDA based on Markov networks and use measures from the information retrieval community (precision, recall and the F-measure) to assess the quality of the structures learned. We then observe the impact that structure has on the fitness modelling and optimisation capabilities of the resulting model, concluding that these results should be relevant to research in both structure learning and fitness modelling.

A multi-objective genetic type-2 fuzzy logic based system for mobile field workforce area optimization

In industries which employ large numbers of mobile field engineers (resources), there is a need to optimize the task allocation process. This particularly applies to utility companies such as electricity, gas and water suppliers as well as telecommunications. The process of allocating tasks to engineers involves finding the optimum area for each engineer to operate within where the locations available to the engineers depends on the work area she/he is assigned to. This particular process is termed as work area optimization and it is a sub-domain of workforce optimization. The optimization of resource scheduling, specifically the work area in this instance, in large businesses can have a noticeable impact on business costs, revenues and customer satisfaction.In previous attempts to tackle workforce optimization in real world scenarios, single objective optimization algorithms employing crisp logic were employed. The problem is that there are usually many objectives that need to be satisfied and hence multi-objective based optimization methods will be more suitable. Type-2 fuzzy logic systems could also be employed as they are able to handle the high level of uncertainties associated with the dynamic and changing real world workforce optimization and scheduling problems.This paper presents a novel multi-objective genetic type-2 fuzzy logic based system for mobile field workforce area optimization, which was employed in real world scheduling problems. This system had to overcome challenges, like how working areas were constructed, how teams were generated for each new area and how to realistically evaluate the newly suggested working areas. These problems were overcome by a novel neighborhood based clustering algorithm, sorting team members by skill, location and effect, and by creating an evaluation simulation that could accurately assess working areas by simulating one days worth of work, for each engineer in the working area, while taking into account uncertainties.The results show strong improvements when the proposed system was applied to the work area optimization problem, compared to the heuristic or type-1 single objective optimization of the work area. Such optimization improvements of the working areas will result in better utilization of the mobile field workforce in utilities and telecommunications companies.

Estimating the distribution in an EDA

This paper presents an extension to our work on estimating the probability distribution by using a Markov Random Field (MRF) model in an Estimation of Distribution Algorithm (EDA) [1]. We propose a method that directly samples a MRF model to generate new population. We also present a new EDA, called the Distribution Estimation Using MRF with direct sampling (DEUMd), that uses this method, and iteratively refines the probability distribution to generate better solutions. Our experiments show that the direct sampling of a MRF model as estimation of distribution provides a significant advantage over other techniques on problems where a univariate EDA is typically used.