Andrew Cumming

Timetabling the Classes of an Entire University with an Evolutionary Algorithm

This paper describes extensions to an evolutionary algorithm that timetables classes for an entire University. A new method of dealing with multi-objectives is described along with a user interface designed for it. New results are given concerning repair of poor recombination choices during local search. New methods are described and evaluated that allow timetables to be produced which have minimal changes compared to a full or partial reference timetable. The paper concludes with a discussion of scale-up issues, and gives some initial results that are very encouraging.

Extensions to a Memetic Timetabling System

This paper describes work in progress to increase the performance of a memetic timetabling system. The features looked at are two directed mutation operators, targeted mutation and a structured population that facilitates parallel implementation. Experimental results are given that show good performance improvements with directed and targeted mutation, and acceptable first results with the structure population.

The Use of Local Search Suggestion Lists for Improving the Solution of Timetable Problems with Evolutionary Algorithms

This paper presents a new genetic representation for timetabling with evolutionary algorithms. The representation involves the use of suggestion lists for the placement of events into timeslots. A set of recombination operators is defined for the new representation, and experimental results are given to compare the performance of the operators with each other and with a system not using suggestion lists.

Animated interval scatter-plot views for the exploratory analysis of large-scale microarray time-course data

Microarray technologies are a relatively new development that allow biologists to monitor the activity of thousands of genes (normally around 8,000) in parallel across multiple stages of a biological process. While this new perspective on biological functioning is recognised as having the potential to have a significant impact on the diagnosis, treatment, and prevention of diseases, it is only through effective analysis of the data produced that biologists can begin to unlock this potential. A significant obstacle to achieving effective analysis of microarray time-course is the combined scale and complexity of the data. This inevitably makes it difficult to reveal certain significant patterns in the data. In particular, it is less dominant patterns and, specifically, patterns that occur over smaller intervals of an experiments overall time-frame that are more difficult to find. While existing techniques are capable of finding either unexpected patterns of activity over the majority of an experiments time-frame or expected patterns of activity over smaller intervals of the time-frame, there are no techniques, or combination of techniques, that are suitable for finding unsuspected patterns of activity over smaller intervals. In order to overcome this limitation we have developed the Time-series Explorer, which specifically supports biologists in their attempts to reveal these types of pattern by allowing them to control an animated interval scatter-plot view of their data. This paper discusses aspects of the technique that make such an animated overview viable and describes the results of a user evaluation assessing the practical utility of the technique within the wider context of microarray time-series analysis as a whole.

Towards visualising temporal features in large scale microarray time-series data

Current techniques for visualising large-scale microarray data are unable to present temporal features without reducing the number of elements being displayed. This paper introduces a technique that overcomes this problem by combining a novel display technique, which operates over a continuous temporal subset of the time series, with direct manipulation of the parameters defining the subset.

Multiple Traffic Signal Control Using A Genetic Algorithm

Optimising traffic signal timings for a multiple-junction road network is a difficult but important problem. The essential difficulty of this problem is that the traffic signals need to coordinate their behaviours to achieve the common goal of optimising overall network delay. This paper discusses a novel approach towards the generation of optimal signalling strategies, based on the use of a genetic algorithm (GA). This GA optimises the set of signal timings for all junctions in network. The different efficient red and green times for all the signals are determined by genetic algorithm as well as the offset time for each junction. Previous attempts to do this rely on a fixed cycle time, whereas the algorithm described here attempts to optimise cycle time for each junction as well as proportion of green times. The fitness function is a measure of the overall delay of the network. The resulting optimised signalling strategies were compared against a well-known civil engineering technique, and conclusions drawn.

Evaluating environments for functional programming

Functional programming presents new challenges in the design of programming environments. In a strongly typed functional language, such as ML, much conventional debugging of runtime errors is replaced by dealing with compile-time error reports. On the other hand, the cleanness of functional programming opens up new possibilities for incorporating sophisticated correctness-checking techniques into such environments. CYNTHIA is a novel editor for ML that both addresses the challenges and explores the possibilities. It uses an underlying proof system as a framework for automatically checking for semantic errors such as non-termination. In addition, CYNTHIA embodies the idea of programming by analogy?whereby users write programs by applying abstract transformations to existing programs. This paper investigatesCYNTHIA s potential as a novice ML programming environment. We report on two studies in which it was found that students using CYNTHIA commit fewer errors and correct errors more quickly than when using a compiler/text editor approach.

Time-series Explorer: An Animated Information Visualisation for Microarray Time-course Data

Microarray technologies are a relatively new development that allow biologists to monitor the activity of thousands of genes (normally around 8,000) in parallel across multiple stages of a biological process. While this new perspective on biological functioning is recognised as having the potential to have a significant impact on the diagnosis, treatment, and prevention of diseases, it is only through effective analysis of the data produced that biologists can begin to unlock this potential. A significant obstacle to achieving effective analysis of microarray time-course is the combined scale and complexity of the data. This inevitably makes it difficult to reveal certain significant patterns in the data. In particular it is less dominant patterns and, specifically, patterns that occur over smaller intervals of an experiments overall time-frame that are more difficult to find. While existing techniques are capable of finding either unexpected patterns of activity over the majority of an experiments time frame or expected patterns of activity over smaller intervals of the time frame, there are no techniques, or combination of techniques, that are suitable for finding unsuspected patterns of activity over smaller intervals. In order to overcome this limitation we have developed the Time-series Explorer, which specifically supports biologists in their attempts to reveal these types of pattern by allowing them to visualise their data controlling an animated interval scatter-plot linked to two complementary graph views. An evaluation, involving biologists working with real data, tested the extent of the tools desired functionality and assessed the techniques practical utility within the wider context of microarray time-course analysis. This proved the technique not only capable of revealing previously unsuspected temporal patterns but also, in certain cases, more appropriate for finding previously suspected patterns and patterns that occurred over the majority of the time-frame.

Poxels: polygonal voxel environment rendering

We present efficient rendering of opaque, sparse, voxel environments with data amplified in local graphics memory with stream-out from a geomery shader to a cached vertex buffer pool. We show that our Poxel rendering primitive aligns with optimized rasterization hardware and so results in high visual quality over ray casting methods. Lossless run length encoding of occlusion culled voxels and coordinate quantization further reduces host data transfers.