The research paper "Refining the ML/DL Argument for the SensorAble Project" by Dr David Ruttenberg and others who investigate the application of Machine Learning (ML) and Deep Learning (DL) within the SensorAble project to better understand and support autistic individuals.

The authors propose using Multimodal Learning Analytics (MMLA) to capture diverse sensory data related to distractibility and anxiety in autistic individuals. The study explores whether ML/DL is essential for processing this complex, multi-sourced data to model neurocognitive processes or if more traditional Artificial Intelligence (AI) methods would suffice.

Ultimately, the paper aims to frame research questions that align MMLA, ML/DL, and SensorAble to develop practical tools, while also considering ethical implications and the balance between heuristic and analytic decision-making processes.

This academic paper introduces SensorAble, a research project aiming to develop deep learning models, specifically Convolutional Neural Networks (CNNs), to assist autistic individuals in managing environmental and physiological stimuli.

Dr David Ruttenberg's research proposes re-engineering existing neurocomputational models that enhance attention and emotional recognition by incorporating multimodal sensory inputs like visual, auditory, inertial, and physiological data. SensorAble seeks to identify and localize distracting stimuli, predict their occurrence, and ultimately alert users through various response triggers to reduce distractibility and anxiety.

The paper outlines the engineering components of an adaptive system and details how the proposed model differs from traditional CNNs by focusing on probability distributions for attention rather than strict classification, allowing for more nuanced and personalized user experiences.