No abstract

Sensor-based human activity recognition is a fundamental research problem in ubiquitous computing, which uses the rich sensing data from multimodal embedded sensors such as accelerometer and gyroscope to infer human activities. The existing activity recognition approaches either rely on domain knowledge or fail to address the spatial-temporal dependencies of the sensing signals. In this paper, we propose a novel attention-based multimodal neural network model called AttnSense for multimodal human activity recognition. AttnSense introduce the framework of combining attention mechanism with a convolutional neural network (CNN) and a Gated Recurrent Units (GRU) network to capture the dependencies of sensing signals in both spatial and temporal domains, which shows advantages in prioritized sensor selection and improves the comprehensibility. Extensive experiments based on three public datasets show that AttnSense achieves a competitive performance in activity recognition compared with several state-of-the-art methods.

Eighty-three cases of secondary postpartum haemorrhage managed in this teaching unit over a 3-year period are described. Bleeding occurred most frequently between the 8th and 14th day of the puerperium; 73% of the patients had already been discharged from hospital and required readmission. Suction evacuation was performed in 72 patients and was successful in arresting haemorrhage whether retained placental tissue could be demonstrated on histology or not. There was histological confirmation of retained gestational products in only 30 (42%) of the patients treated surgically. No predictive factors for secondary postpartum haemorrhage could be identified in the obstetric profiles or antenatal course of most of these patients. Patients with retained gestational products could not be distinguished from those without on the basis of history or examination alone apart from 4 patients noted to have incomplete membranes at delivery.