Evaluation of Deep Neural Network Compression Methods for Edge Devices Using Weighted Score-Based Ranking Scheme.

The demand for object detection capability in edge computing systems has surged. As such, the need for lightweight Convolutional Neural Network (CNN)-based object detection models has become a focal point. Current models are large in memory and deployment in edge devices is demanding.

Pulse wave registration from radial artery using photoplethysmographic method.

This pilot study was aimed to investigate the possibilities to use the photoplethysmographic (PPG) method for the pulse wave registration from radial artery. The PPG sensor with different separation distances between light emitting diodes (LED) and photodiode was built. The PPG signal registration was carried out at the locations with two different depths of artery and at the locations without large blood vessels under the sensor.

Smart photoplethysmographic sensor for pulse wave registration at different vascular depths.

The aim of this paper is to propose a smart optical sensor for cardiovascular activity monitoring at different tissue layers. Photoplethysmography (PPG) is a noninvasive optical technique for monitoring mainly blood volume changes in the examined tissue. However, different important physiological parameters, such as oxygen saturation, heart and breathing rate, dynamics of skin micro-circulation, vasomotion activity etc.