Wyniki wyszukiwania - BazTech

Ograniczanie wyników

Znaleziono wyników: 2

Liczba wyników na stronie

Wyniki wyszukiwania

Sortuj według:

Ogranicz wyniki do:

3D Body Scan as Anthropometric Tool for Individualized Prosthetic Socks

Lindell Eva, Tingsvik Hanna, Guo Li, Peterson Joel

Autex Research Journal

2022

Vol. 22, no. 3

350--357

Every year, approximately 3,000 people in Sweden undergo amputation of a body part. The use of a prosthesis can greatly improve the quality of life for these people. To improve the fit and comfort of a prosthesis, a sock is used as an interface between the prosthesis socket and the stump. A three-dimensional (3D) body scanner can be used to take measurements that are used to produce individualized socks that improve fit and comfort. The standardized method for taking measurements with a 3D body scanner often requires a standing position and hence a new scanning method is needed to improve the accessibility for 3D body scanning. This study aimed to create a scanning scenario and an algorithm for scanning amputation stumps for individualizing prosthesis socks for upper-body amputations. Vitronic VITUSSMART LC 3D Body Scanner was used in this study. The results show a seated position with arms slightly away from the body, scanned at 45° as the best. To measure the right upper arm and the left armpit, the best was to scan at a 315° angle. Paired t-tests showed no significant differences compared with the 3D body scanner of traditional manual measurements. The proposed method exhibited good relative reliability and potential to facilitate the customization of prosthetic socks for amputees.

Inter-patient ECG classification with convolutional and recurrent neural networks

Guo Li, Sim Gavin, Matuszewski Bogdan

Biocybernetics and Biomedical Engineering

2019

Vol. 39, no. 3

868--879

The recent advances in ECG sensor devices provide opportunities for user self-managed auto-diagnosis and monitoring services over the internet. This imposes the requirements for generic ECG classification methods that are inter-patient and device independent. In this paper, we present our work on using the densely connected convolutional neural network (DenseNet) and gated recurrent unit network (GRU) for addressing the inter-patient ECG classification problem. A deep learning model architecture is proposed and is evaluated using the MIT-BIH Arrhythmia and Supraventricular Databases. The results obtained show that without applying any complicated data pre-processing or feature engineering methods, both of our models have considerably outperformed the state-of-the-art performance for supraventricular (SVEB) and ventricular (VEB) arrhythmia classifications on the unseen testing dataset (with the F1 score improved from 51.08 to 61.25 for SVEB detection and from 88.59 to 89.75 for VEB detection respectively). As no patient-specific or device-specific information is used at the training stage in this work, it can be considered as a more generic approach for dealing with scenarios in which varieties of ECG signals are collected from different patients using different types of sensor devices.