Autism Spectrum Condition (ASC) is a life-long diagnosis, which has a subset of individualized characteristics consisting of hyper-, seeking- and/or hypo-reactivity to sensory inputs or unusual interests (APA, 2013). These sensitivities are evident in both environmental (e.g. apparent response to specific sounds, visual fascination with lights or movements) and physiological domains (e.g. anxiety, respiration or euthermia). As part of a larger PhD Research Project (SensorAble), this pilot study proposes that autistic individuals who exhibit greater distractibility and reduced focus/attention resulting stimuli may benefit from interventions that alter, redirect and/or attenuate stimuli. In particular, Irrelevant-Sound Effect (ISE) consisting of un-targeted and/or modulated sonics cause greater disruption of performance of simultaneous and visual simple tasks compared to baseline ISE that are merely directed. Using gold-standard Stroop experiments, data collected among neurotypical (NT) and ASC individuals at baseline and at various ISE modes result in greater reaction time (RT) improvements among ASC than NT participants. In this study, which focuses on aural distractibility only, data supports that signal processing may provide a gateway to enhancing focus and attention while reduce distractibility and anxiety in other domains.
Autism Spectrum Condition (ASC) is a life-long diagnosis, which has a subset of features including hyper-, seeking- and/or hypo-reactivity to sensory inputs or unusual interests (APA, 2013). These qualities are evident across environmental (e.g. response to specific sounds, visual fascination with lights or movements) and physiological domains (e.g. anxiety, respiration or euthermia). Scholars report that ninety (90%) of autistic adults experience sensory issues causing significant barriers at school/work (Leekam et al., 2007). As part of a larger PhD Research Project, this pilot study establishes designs, processes and measures that may establish if autistic individuals find value utilising adaptive/wearable interventions that possibly alter, redirect and/or attenuate disruptive stimuli. This study incorporates benign information not yet containing practical data, other than to provision and trial space where real data is nominally present. This pilot loads systems functionality for future use (e.g. consent, demographic collection, measures, post-mortem/survey feedback, storage, sorting, query, statistical analyses and reporting). Finally, this pilot provisions a follow-on and full-fledge Participant Public Involvement (PPI) designed to exploit data from focus group and co-produced surveys/designs. In turn, these may be used to inform an as-yet-to-be developed interventional prototype. Hence, the forthcoming PPI—by leveraging this pilot—aims to describe what degree sensory distractions occur among adolescent and adult ASC participants. Both pilot and PPI aspire to whether focus, anxiety and attentional concerns are perceived as negative issues and if individuals prefer assistance (vis à vis assistive wearables) to reduce anxiety, distractions and increase focus at school and at work (Bagley et al., 2016). This study results yield promise; in that, a subsequent PPI can be leveraged to obtain co-designed autistic data leading to a randomised clinical trial.
Is Machine Learning/Deep Learning (ML/DL) a technological necessity when implementing SensorAble or is it something to be investigated because of its potential? Should ML/DL be implemented because it permits processing large quantities of multimodal data enabling modelling of autistic neurocognitive processes that well relate to distractibility and anxiety? Or would interventional prototyping using old-fashioned Artificial Intelligence (AI), Bayesian theory or a hand-crafted rule be preferable?Following Participant Public Information (PPI), can ML/DL techniques permit greater understanding of how disruptions occur and properly align/prepare the groundwork for an interventional prototype? Would heuristics, data mining, or perhaps some other statistical approach adequately provide evidence proceeding a design? With the constellation of supervisors who have invested in this project, can fundamental science properly situate SensorAble in a broader vision that creates practical tools? It is one thing to understand and model a problem. It’s another to simply design/build. Doing the latter may inform the user, but how does it guarantee that other stress factors, ethical issues and newly created anomalies aren’t inadvertently introduced?
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.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.