Browsing Faculty of Science and Engineering by Publisher "The Society for the Study of Artificial Intelligence and Simulation for Behaviour (AISB)"
Now showing items 1-3 of 3
Associating Colours with Emotions Detected in Social Media TweetsThis project involves two major areas of work, the detection of emotions in text from Twitter posts (tweets), and the association of that emotion with colour. Emotion mining is the field of natural language processing which is concerned with the detection and classification. It is a subfield of semantic analysis which contains both emotion and opinion mining. Both tasks depend on an emotion model to classify detected emotions and to associate a colour depending on the location of the emotion in the model. This research paper demonstrates preliminary results from classification of tweets to assign emotion labels. Also designs are presented for a prototype web interface for displaying the assigned colour and emotion associated with tweets.
How effective is Ant Colony Optimisation at Robot Path PlanningThis project involves investigation of the problem robot path planning using ant colony optimisation heuristics to construct the quickest path from the starting point to the end. The project has developed a simulation that successfully simulates as well as demonstrates visually through a graphical user interface, robot path planning using ant colony optimisation. The simulation shows an ability to traverse an unknown environment from a start point to an end and successfully construct a route for others to follow both when the terrain is dynamic and static
Morphogenetic Engineering For Evolving Ant Colony Pheromone CommunicationThis research investigates methods for evolving swarm communication in a simulated colony of ants using pheromone when foriaging for food. This research implemented neuroevolution and obtained the capability to learn pheromone communication autonomously. Building on previous literature on pheromone communication, this research applies evolution to adjust the topology and weights of an artificial neural network which controls the ant behaviour. Comparison of performance is made between a hard-coded benchmark algorithm, a fixed topology ANN and neuroevolution of the ANN topology and weights. The resulting neuroevolution produced a neural network which was successfully evolved to achieve the task objective, to collect food and return it to the nest.