Enhanced Learning Techniques Research Articles

Evaluation of Enhanced Learning Techniques for Segmenting Ischaemic Stroke Lesions in Brain Magnetic Resonance Perfusion Images Using a Convolutional Neural Network Scheme.

Magnetic resonance (MR) perfusion imaging non-invasively measures cerebral perfusion, which describes the blood's passage through the brain's vascular network. Therefore, it is widely used to assess cerebral ischaemia. Convolutional Neural Networks (CNN) constitute the state-of-the-art method in automatic pattern recognition and hence, in segmentation tasks. But none of the CNN architectures developed to date have achieved high accuracy when segmenting ischaemic stroke lesions, being the main reasons their heterogeneity in location, shape, size, image intensity and texture, especially in this imaging modality. We use a freely available CNN framework, developed for MR imaging lesion segmentation, as core algorithm to evaluate the impact of enhanced machine learning techniques, namely data augmentation, transfer learning and post-processing, in the segmentation of stroke lesions using the ISLES 2017 dataset, which contains expert annotated diffusion-weighted perfusion and diffusion brain MRI of 43 stroke patients. Of all the techniques evaluated, data augmentation with binary closing achieved the best results, improving the mean Dice score in 17% over the baseline model. Consistent with previous works, better performance was obtained in the presence of large lesions.

Usability evaluation of an augmented reality system for teaching Euclidean vectors

Augmented reality (AR) is one of the emerging technologies that has demonstrated to be an efficient technological tool to enhance learning techniques. In this paper, we describe the development and evaluation of an AR system for teaching Euclidean vectors in physics and mathematics. The goal of this pedagogical tool is to facilitate user’s understanding of physical concepts, such as magnitude, direction and orientation, together with basic vector-related operations like addition, subtraction and cross product. The result of the system usability scale showed our system’s usability and learnability. The system merges a real-world scenario with virtual elements controlled with a practical body-interactive interface.

Neural network prediction analysis: The bankruptcy case

In this paper we evaluate the prediction capability of various neural network models. The models examined in this study differ on the following parameters: data span, learning technique and number of iterations. The neural net prediction capabilities are also compared to results obtained by classical discriminant analysis models. The specific case evaluated is bankruptcy prediction. The common assumption of all bankruptcy prediction models is that fundamental economic factors and the characteristics of a firm are reflected in its financial statements. Therefore, using analytic tools and data from the firm's financial reports, one can evaluate and predict its future financial status. Since the number of bankrupt firms is limited, we used examples (financial statements) from various periods preceding the bankruptcy event. Although the financial statements from the bankruptcy period convey more information, financial statements form distinct periods always improved the models. The prediction capability of the models is improved by using enhanced learning techniques. However, if the enhancement learning technique is too ‘strong’, the model becomes too specific for the training data set and thus loses its prediction capabilities.