Discovering the Typing Behaviour of Parkinson’s Patients Using Topic Models

Milne, Antony; Nicolaou, Mihalis A.; Farrahi, Katayoun

doi:10.1007/978-3-319-67256-4_9

Cited by 1 publication

(1 citation statement)

References 12 publications

(12 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Interest in this topic has grown significantly in recent years with increasing availability of cheap wearable sensors integrated into everyday devices such as smart phones. Remote monitoring of elderly in homes [16] and early diagnosis of complex diseases [21] are examples of the use of activity recognition.…”

Section: Introductionmentioning

confidence: 99%

Transfer learning across human activities using a cascade neural network architecture

Farrahi

Niranjan

2019

Proceedings of the 23rd International Symposium on Wearable Computers

Self Cite

View full text Add to dashboard Cite

Cascade Learning (CL) [20] is a new adaptive approach to train deep neural networks. It is particularly suited to transfer learning, as learning is achieved in a layerwise fashion, enabling the transfer of selected layers to optimize the quality of transferred features. In the domain of Human Activity Recognition (HAR), where the consideration of resource consumption is critical, CL is of particular interest as it has demonstrated the ability to achieve significant reductions in computational and memory costs with negligible performance loss. In this paper, we evaluate the use of CL and compare it to end to end (E2E) learning in various transfer learning experiments, all applied to HAR. We consider transfer learning across objectives, for example opening the door features transferred to opening the dishwasher. We additionally consider transfer across sensor locations on the body, as well as across datasets. Over all of our experiments, we find that CL achieves state of the art performance for transfer learning in comparison to previously published work, improving F 1 scores by over 15%. In comparison to E2E learning, CL performs similarly considering F 1 scores, with the additional advantage of requiring fewer parameters. Finally, the overall results considering HAR classification performance and memory requirements demonstrate that CL is a good approach for transfer learning.

show abstract

Section: Introductionmentioning

confidence: 99%