In very old and/or frail older people living in long-term care facilities, physical inactivity negatively affects activities of daily living. The main reason to assess older adults' perceived fitness is to establish the relation with their beliefs about their ability to perform physical activity adjusted to daily tasks. The Self-Assessment of Physical Fitness scale was developed to address these needs. The aim of this study was to estimate the test-retest reliability and construct validity of the scale. 76 elderly people (M age = 86.0 yr., SD = 6.3) completed the test. Cronbach's a was .71. One-week test-retest reliability ICC's ranged from .66 (SAPF aerobic endurance and SAPF balance) to .70 (SAPF sum score). Concurrent validity with the Groningen Fitness Test for the Elderly was fair to moderate. Despite the limited number of participants (N = 76), results suggest that the scale may be useful as an assessment of perceived fitness in older adults.
LINK
We present a novel architecture for an AI system that allows a priori knowledge to combine with deep learning. In traditional neural networks, all available data is pooled at the input layer. Our alternative neural network is constructed so that partial representations (invariants) are learned in the intermediate layers, which can then be combined with a priori knowledge or with other predictive analyses of the same data. This leads to smaller training datasets due to more efficient learning. In addition, because this architecture allows inclusion of a priori knowledge and interpretable predictive models, the interpretability of the entire system increases while the data can still be used in a black box neural network. Our system makes use of networks of neurons rather than single neurons to enable the representation of approximations (invariants) of the output.
LINK
Rond 2022 koopt een vijfde van de wereldbevolking producten online over de grens. Consumenten krijgen steeds meer vertrouwen in buitenlandse aanbieders en Nederlandse webshops breiden uit naar grote buitenlandse e-commerce markten zoals in Duitsland.Samen met het Center for Market Insights, het onderzoekscentrum van Hogeschool van Amsterdam, onder leiding van Sjoukje Goldman en Alexander Lamprecht hebben Annabel Bak en Kristy Bruijn onderzoek gedaan naar de volgende onderzoeksvraag: Wat zijn de succes- en faalfactoren van Nederlandse webwinkeliers op de Duitse e-commerce markt?
LINK