A smart home equipped with a diversity of multimodal sensors is a meaningful setting for acquiring the health status of its residents and improving their well-being. In recent years, sensor-based activity recognition has received growing research attention. However, the multi-modal nature of these sensor platforms raises great challenges with respect to the data fusion of the different sensor sources. To solve this problem, we present an activity recognition approach incorporating attention mechanism in this paper. A Convolutional Neural Network-based training framework is developed to extract representative features for activities. Specifically, we design two attention modules-channel-wise and temporal-wise modules to capture the interdependencies between channel and temporal dimensions of its convolutional features. We evaluate the attention-based approach on a real activity recognition challenge dataset. Experiments justify that the attention network-based feature fusion can effectively improve the activity recognition performance.
A microwave imaging system has been developed as a clinical diagnostic tool operating in the 3- to 8-GHz region using multistatic data collection. A total of 86 patients recruited from a symptomatic breast care clinic were scanned with a prototype design. The resultant three-dimensional images have been compared “blind” with available ultrasound and mammogram images to determine the detection rate. Images show the location of the strongest signal, and this corresponded in both older and younger women, with sensitivity of >74%, which was found to be maintained in dense breasts. The pathway from clinical prototype to clinical evaluation is outlined.
In this proceedings the Finite Difference Time Domain (FDTD) and frequency domain Finite Element (FE) methods are used to model both linear chirped pulse and arbitrary chirped pulse propagation in 2D Photonic Crystal (PhC) waveguides. An in-house FDTD code has been implemented which allows the study of pulse propagation in a very direct way. The carrier wavelength of the pulse is swept across the bandwidth of a mini-stopband feature and pulse compression behaviour is observed. In the case of linear chirped pulse, both round hole and square hole PhC waveguides are studied with the latter giving increased pulse compression. An input pulse is then derived from a SOA model which has arbitrary chirp. This is passed through a mini-stop band in a narrowed W3 PhC waveguide and pulse compression is observed.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.