Automatically Evolving Rotation-invariant Texture Image Descriptors by Genetic Programming

In computer vision, training a model that performs classification effectively is highly dependent on the extracted features, and the number of training instances. Conventionally, feature detection and extraction are performed by a domain-expert who, in many cases, is expensive to employ and hard to find. Therefore, image descriptors have emerged to automate these tasks. However, designing an image descriptor still requires domain-expert intervention. Moreover, the majority of machine learning algorithms require a large number of training examples to perform well. However, labelled data is not always available or easy to acquire, and dealing with a large dataset can dramatically slow down the training process. In this paper, we propose a novel Genetic Programming based method that automatically synthesises a descriptor using only two training instances per class. The proposed method combines arithmetic operators to evolve a model that takes an image and generates a feature vector. The performance of the proposed method is assessed using six datasets for texture classification with different degrees of rotation, and is compared with seven domain-expert designed descriptors. The results show that the proposed method is robust to rotation, and has significantly outperformed, or achieved a comparable performance to, the baseline methods.

Categorising Asynchronous Discussion Threads: Improving the Quality of Student Learning

My paper will focus on the generative potential of categorising asynchronous discussion threads as one strategy for improving the quality of students’ learning in a blended learning module. The approach to categorisation is based on social network analysis using intuitively simple descriptors of message posting patterns e.g. passive facilitator, dominant facilitator, unresponsive star and formulaic discussion. The intention is to produce descriptively vivid illustrative examples of the categories and to begin to suggest affordances of the different participation patterns. Looking forward to the beginning of the next module, it is anticipated that discussion during the module of approaches to participating in asynchronous discussion will contribute to effective engagement patterns and deeper learning.