Author:
Kauper Julia,Franke Susanne,Franke Felix,Grieshammer Steven
Abstract
AbstractWith the increasing prevalence of mobile applications across various domains, there is a growing demand for individualised and self-adaptive learning pathways. This is particularly important in the mobile health sector, where there is a critical need to investigate how expert and experiential knowledge can be acquired, digitalised and formalised into data which is subsequently processed and further used. To address this demand, our research explores how Artificial Intelligence (AI) can power this process. We developed a prototype mobile application with a standardised learning pathway that features speech-language therapy exercises of varying levels of difficulty. In a 12-week field experiment involving 21 individuals with aphasia, we analysed the results using supervised and unsupervised algorithms. Our findings suggest that AI has the potential to generate new knowledge, such as identifying features that can determine which learning words are perceived as easier or more difficult on an inter-individual basis. This knowledge enables algorithmisation and the design of standardised (database-supported) artefacts, which in turn can be used to formulate self-adaptive and individualised learning pathways. This significantly enhances the development of effective mobile applications to assist speech-language therapy.
Publisher
Springer Fachmedien Wiesbaden
Reference33 articles.
1. European Commission, Directorate-General for Research and Innovation, Breque, M., De Nul, L., Petridis, A.: Industry 5.0: towards a sustainable, human-centric and resilient European industry, Publications Office (2021). https://data.europa.eu/doi/10.2777/308407.
2. Rannertshauser, P., Kessler, M., & Arlinghaus, J. C. (2022). Human-centricity in the design of production planning and control systems: A first approach towards Industry 5.0, IFAC-PapersOnLine 55(10), 2641–2646. https://doi.org/10.1016/j.ifacol.2022.10.108.
3. Bishop, C. M. (2006). Pattern Recognition and Machine Learning (1st edn., pp. 67–227). New York: Springer.
4. Shalev-Shwartz, S., & Ben-David, S. (2014). Understanding Machine Learning. From Theory to Algorithms (1st edn., pp. 115–284). Cambridge University Press.
5. Goodfellow, 1., Bengio, Y., & Courville, A. (2016). Deep Learning (pp. 162–481). The MIT Press.