6974 research outputs found
Sort by
Changes in biopsychosocial factors based on transportation independence among older adults:A one-year study post-COVID-19 movement restrictions
No full textIntroduction: The global COVID-19 pandemic prompted widespread lockdown measures, impacting transportation systems and specifically affecting the mobility of older adults, which could result in changes to their biophysical, psychological and social health, or better known as biopsychosocial health. However, limited information exists regarding the alterations in the biopsychosocial aspects of older adults during and after the COVID-19 movement restrictions, as well as their association. The objective of this study is to investigate the biopsychosocial dynamics associated with navigating transportation during and after the recovery phase of COVID-19 pandemic. Additionally, it aims to determine the association between transportation independence status and various biopsychosocial factors. Methods: A sub-sample of 100 individuals aged 60 years and above (mean age ± SD: 68.4 ± 5.3), from earlier cross-sectional study were recruited in a one year follow up study. Face-to-face interviews were conducted by the same researcher from baseline to obtain older adults’ sociodemographic health status, anthropometric measurements, functional status, depressive symptoms, nutritional status, cognitive status, visual assessment, physical activity and physical performance and transportation independence. Bivariate logistic regression was performed to examine the association. Results: While there were no significant changes in transportation independence among older adults during and after the COVID-19 movement restriction, there were noticeable increases in outdoor mobility and certain changes in biopsychosocial factors. Results revealed higher fat mass (Adj OR = 1.20, 95% CI: 1.03–1.41, p < 0.05), poorer performance in Timed up and Go (TUG) (Adj OR = 1.40, 95% CI: 1.03–1.88, p < 0.05) test, poorer Hand Grip Strength (HGS) (Adj OR = .85, 95% CI: .74–.98, p < 0.05) and changes in Instrumental Activities of Daily Living (IADL) (p < 0.05) are associated with restricted transportation in older adults. Conclusion: The findings of this study highlight the importance of biopsychosocial health factors, such as body composition, physical performance, and function, which may be influenced by transportation independence among older adults.</p
Long-tailed recognition via key attribute learning
No full textDeep learning models often struggle with datasets exhibiting long-tailed distributions, where the majority of data is concentrated in a few categories, leaving many with very few samples. This imbalance results in models favouring well-represented categories, leading to poorer performance for those with fewer instances. Existing methodologies focus on addressing class-wise imbalance but disregard the attribute-wise disparities. By assigning equal weight to each instance within a class, these approaches overlook the long-tailed distribution of attributes, thus underrepresenting information from infrequent attributes. The reduction in feature diversity consequently diminishes model performance. To address this challenge, we introduce an innovative methodology, namely Key Attribute Learning (KAL). It emphasises the importance of less common attributes by utilising the Instance Diversity Index (IDI) to assess and prioritise attribute diversity for each instance. KAL effectively expands feature margins among categories and addresses the overfitting problem. Our results demonstrate that KAL is non-invasive in both single-model and Mixture of Experts (MoE) settings. Implementing our method on BalPoE, we attained state-of-the-art (SOTA) performance on CIFAR-100-im100, ImageNet-LT, and iNaturalist datasets, showcasing its broad applicability and significant improvements across both balanced and diverse test distributions.</p
