Ruttenberg, D; Porayska-Pomsta, K; White, SJ; Holmes, J; (2020) In Defence of ML/CNN for the SensorAble Research Project. OSF Preprints: Charlottesville, VA, USA.

Preview

Text Ruttenberg_Research Paper #3--Study #3 -- In Defence of CNN_ML for SensorAble Research.pdf Download (655kB) | Preview

Abstract

Animals and humans use a midbrain structure to coordinate and process relevant visual and auditory stimuli while suppressing distracting information. In modelling this assembly and managing both environmental and physiological stimuli using engineering principles, my research aspires to deep learning models that sense, categorize and alert autistic individuals of ecological distractions, biophysical cues and other multimodal input that—left unchecked—could decrease individual focus and increase distractibility and anxiety. The designs that follow are based upon valid and reliable constructs presented in recent, peripherally related research, including: (i) a framework for developing adaptive intelligent user interfaces that enhances user experience (Johnston et al., 2019); and, (ii) convolution neural networks (CNNs) that improve expression recognition through emotion- modulated attention (Barros et al., 2017). My intention is to weave a compelling and explicit rationale as to how and why deep learning models make the most sense when learning tasks derived from image, time-series and text- data and applying these to the SensorAble Research Project.

Download activity - last month

Export as JSONXMLCSV

Download activity - last 12 months

Export as JSONXMLCSV

Downloads by country - last 12 months

Export as JSONXMLCSV

Archive Staff Only

View Item