Predictive self-organizing neural networks for in-home detection of Mild Cognitive Impairment
作者：
Highlights：
• In-home sensing data for mild cognitive impairment detection is typically small.
• Predictive adaptive resonance theory is applied for the first time on such dataset.
• Listwise deletion was found to be useful for handling missing values.
• Antecedent pruning was uncovered to improve generalizability.
• Compared to support vector machines, our model showed higher predictive performance.
摘要
•In-home sensing data for mild cognitive impairment detection is typically small.•Predictive adaptive resonance theory is applied for the first time on such dataset.•Listwise deletion was found to be useful for handling missing values.•Antecedent pruning was uncovered to improve generalizability.•Compared to support vector machines, our model showed higher predictive performance.
论文关键词：Predictive self-organizing neural networks,Adaptive Resonance Associative Map,Fuzzy ARAM,In-home monitoring,Mild Cognitive Impairment
论文评审过程：Received 22 December 2021, Revised 30 March 2022, Accepted 6 May 2022, Available online 19 May 2022, Version of Record 1 June 2022.
论文官网地址：https://doi.org/10.1016/j.eswa.2022.117538
