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.

Common Environment for Undergraduate Computer Programming

We present an Integrated Environment suitable for learning and teaching computer programming which is designed for both students of specialised Computer Science courses, and also non-specialist students such as those following Liberal Arts. The environment is rich enough to allow exploration of concepts from robotics, artificial intelligence, social science, and philosophy as well as the specialist areas of operating systems and the various computer programming paradigms.

An Action Research Study Engaging in the Use of Storyboarding as Research-based Approach to Teaching to Identify Issues Faced when Working with People with Dementia from Minority Ethnic Communities

The common view that research informs teaching assumes a linear approach whereby teaching is considered an output of research. This paper reports the findings of an action research project that identified the issues and challenges faced by those working across health and social care when working with people with dementia from minority ethnic communities. It explored the research-teaching nexus by using an approach to teaching that was research-based as opposed to research-led. A storyboarding technique was used which involved identifying and dissecting real life experiences for discussion. The realisation that each story was unique to the individual demonstrated the benefits and importance of education and training for applying a person-centred approach to dementia care. This project also revealed the benefits of actively engaging course participants with research moving them from being recipients of research, to research- active. Such a process not only encouraged their intrinsic motivations but, also, critical thinking and reflective practice to support deep learning. Such findings demonstrate the benefits of linking teaching with research.