Adam Prügel-Bennett

Automatic gait recognition using area-based metrics

A novel technique for analysing moving shapes is presented in an example application to automatic gait recognition. The technique uses masking functions to measure area as a time varying signal from a sequence of silhouettes of a walking subject. Essentially, this combines the simplicity of a baseline area measure with the specificity of the selected (masked) area. The dynamic temporal signal is used as a signature for automatic gait recognition. The approach is tested on the largest extant gait database, consisting of 114 subjects (filmed under laboratory conditions). Though individual masks have limited discriminatory ability, a correct classification rate of over 75% was achieved by combining information from different area masks. Knowledge of the leg with which the subject starts a gait cycle is shown to improve the recognition rate from individual masks, but has little influence on the recognition rate achieved from combining masks. Finally, this technique is used to attempt to discriminate between male and female subjects. The technique is presented in basic form: future work can improve implementation factors such as using better data fusion and classifiers with potential to increase discriminatory capability.

An analysis of the feasibility of short read sequencing

Several methods for ultra high-throughput DNA sequencing are currently under investigation. Many of these methods yield very short blocks of sequence information (reads). Here we report on an analysis showing the level of genome sequencing possible as a function of read length. It is shown that re-sequencing and de novo sequencing of the majority of a bacterial genome is possible with read lengths of 20–30 nt, and that reads of 50 nt can provide reconstructed contigs (a contiguous fragment of sequence data) of 1000 nt and greater that cover 80% of human chromosome 1.

Genetic drift in genetic algorithm selection schemes

A method for calculating genetic drift in terms of changing population fitness variance is presented. The method allows for an easy comparison of different selection schemes and exact analytical results are derived for traditional generational selection, steady-state selection with varying generation gap, a simple model of Eshelmans CHC algorithm (1991), and (/spl mu/+/spl lambda/) evolution strategies. The effects of changing genetic drift on the convergence of a GA are demonstrated empirically.

The dynamics of a genetic algorithm for simple random Ising systems

Abstract A formalism is presented for analysing Genetic Algorithms. It is used to study a simple Genetic Algorithm consisting of selection, mutation and crossover which is searching for the ground states of simple random Ising-spin systems: a random-field ideal paramagnet and a spin-glass chain. The formalism can also be applied to other population based search techniques and to biological models of micro-evolution. To make the problem tractable, it is assumed that the population dynamics can be described by a few macroscopic order parameters and that the remaining microscopic degrees of freedom can be averaged out. The macroscopic quantities that are used are the cumulants of the distribution of fitnesses (or energies) in the population. A statistical mechanics model is presented which describes the population configuration in terms of the cumulants, this is used to derive equations of motion for the cumulants. Predictions of the theory are compared with experiments and are shown to predict the average time to convergence and the average fitness of the final population accurately. A simplified version of the equations is produced by keeping only leading nonlinear terms, and truncating the cumulant expansion. This is shown to give a novel description of the role of genetic operators in search, e.g. it is argued that an important role of crossover is to reduce the skewness of the population.

Leveraging clustering approaches to solve the gray-sheep users problem in recommender systems

We provide detailed analysis of gray-sheep users problem in recommender systems.We show how conventional collaborative filtering fail for gray-sheep users problem.We use K-means clustering to separate these users from rest of the users.We propose switching hybrid recommender system to overcome this problem. Recommender systems apply data mining and machine learning techniques for filtering unseen information and can predict whether a user would like a given item. This paper focuses on gray-sheep users problem responsible for the increased error rate in collaborative filtering based recommender systems. This paper makes the following contributions: we show that (1) the presence of gray-sheep users can affect the performance - accuracy and coverage - of the collaborative filtering based algorithms, depending on the data sparsity and distribution; (2) gray-sheep users can be identified using clustering algorithms in offline fashion, where the similarity threshold to isolate these users from the rest of community can be found empirically. We propose various improved centroid selection approaches and distance measures for the K-means clustering algorithm; (3) content-based profile of gray-sheep users can be used for making accurate recommendations. We offer a hybrid recommendation algorithm to make reliable recommendations for gray-sheep users. To the best of our knowledge, this is the first attempt to propose a formal solution for gray-sheep users problem. By extensive experimental results on two different datasets (MovieLens and community of movie fans in the FilmTrust website), we showed that the proposed approach reduces the recommendation error rate for the gray-sheep users while maintaining reasonable computational performance.

Training HMM structure with genetic algorithm for biological sequence analysis

SUMMARY Hidden Markov models (HMMs) are widely used for biological sequence analysis because of their ability to incorporate biological information in their structure. An automatic means of optimizing the structure of HMMs would be highly desirable. However, this raises two important issues; first, the new HMMs should be biologically interpretable, and second, we need to control the complexity of the HMM so that it has good generalization performance on unseen sequences. In this paper, we explore the possibility of using a genetic algorithm (GA) for optimizing the HMM structure. GAs are sufficiently flexible to allow incorporation of other techniques such as Baum-Welch training within their evolutionary cycle. Furthermore, operators that alter the structure of HMMs can be designed to favour interpretable and simple structures. In this paper, a training strategy using GAs is proposed, and it is tested on finding HMM structures for the promoter and coding region of the bacterium Campylobacter jejuni. The proposed GA for hidden Markov models (GA-HMM) allows, HMMs with different numbers of states to evolve. To prevent over-fitting, a separate dataset is used for comparing the performance of the HMMs to that used for the Baum-Welch training. The GA-HMM was capable of finding an HMM comparable to a hand-coded HMM designed for the same task, which has been published previously.

A Statistical Mechanical Formulation of the Dynamics of Genetic Algorithms

A new mathematical description of the dynamics of a simple genetic algorithm is presented. This formulation is based on ideas from statistical physics. Rather than trying to predict what happens to each individual member of the population, methods of statistical mechanics are used to describe the evolution of statistical properties of the population. We present equations which predict these properties at one generation in terms of those at the previous generation. The effect of the selection operator is shown to depend only on the distribution of fitnesses within the population, and is otherwise problem independent. We predict an optimal form of selection scaling and compare it with linear scaling. Crossover and mutation are problem-dependent, and are discussed in terms of a test problem — the search for the low energy states of a random spin chain. The theory is shown to be in good agreement with simulations.

An evolutionary method for learning HMM structure: prediction of protein secondary structure

BackgroundThe prediction of the secondary structure of proteins is one of the most studied problems in bioinformatics. Despite their success in many problems of biological sequence analysis, Hidden Markov Models (HMMs) have not been used much for this problem, as the complexity of the task makes manual design of HMMs difficult. Therefore, we have developed a method for evolving the structure of HMMs automatically, using Genetic Algorithms (GAs).ResultsIn the GA procedure, populations of HMMs are assembled from biologically meaningful building blocks. Mutation and crossover operators were designed to explore the space of such Block-HMMs. After each step of the GA, the standard HMM estimation algorithm (the Baum-Welch algorithm) was used to update model parameters. The final HMM captures several features of protein sequence and structure, with its own HMM grammar. In contrast to neural network based predictors, the evolved HMM also calculates the probabilities associated with the predictions. We carefully examined the performance of the HMM based predictor, both under the multiple- and single-sequence condition.ConclusionWe have shown that the proposed evolutionary method can automatically design the topology of HMMs. The method reads the grammar of protein sequences and converts it into the grammar of an HMM. It improved previously suggested evolutionary methods and increased the prediction quality. Especially, it shows good performance under the single-sequence condition and provides probabilistic information on the prediction result. The protein secondary structure predictor using HMMs (P.S.HMM) is on-line available http://www.binf.ku.dk/~won/pshmm.htm. It runs under the single-sequence condition.

Novel centroid selection approaches for KMeans-clustering based recommender systems

Recommender systems have the ability to filter unseen information for predicting whether a particular user would prefer a given item when making a choice. Over the years, this process has been dependent on robust applications of data mining and machine learning techniques, which are known to have scalability issues when being applied for recommender systems. In this paper, we propose a k-means clustering-based recommendation algorithm, which addresses the scalability issues associated with traditional recommender systems. An issue with traditional k-means clustering algorithms is that they choose the initial k centroid randomly, which leads to inaccurate recommendations and increased cost for offline training of clusters. The work in this paper highlights how centroid selection in k-means based recommender systems can improve performance as well as being cost saving. The proposed centroid selection method has the ability to exploit underlying data correlation structures, which has been proven to exhibit superior accuracy and performance in comparison to the traditional centroid selection strategies, which choose centroids randomly. The proposed approach has been validated with an extensive set of experiments based on five different datasets (from movies, books, and music domain). These experiments prove that the proposed approach provides a better quality cluster and converges quicker than existing approaches, which in turn improves accuracy of the recommendation provided.

When a genetic algorithm outperforms hill-climbing

A toy optimisation problem is introduced which consists of a fitness gradient broken up by a series of hurdles. The performance of a hill-climber and a stochastic hill-climber are computed. These are compared with the empirically observed performance of a genetic algorithm (GA) with and without. The hill-climber with a sufficiently large neighbourhood outperforms the stochastic hill-climber, but is outperformed by a GA both with and without crossover. The GA with crossover substantially outperforms all the other heuristics considered here. The relevance of this result to real world problems is discussed.