Download presentation
Presentation is loading. Please wait.
Published byRosaline Dixon Modified over 9 years ago
1
Mobile Sensor Application Group 4
2
Introduction Modern smartphones are often equipped with quite a large number of sensors. The sensors data can be used to extract information with regards to the users environmental condition or the users activity. Here we present two such applications – Fall Detection – Earthquake alert system
3
Fall Detection Falls can be detected using Accelerometer Accelerometer sensor provides acceleration reading(ms -2 ) in all 3 dimensions. Basic approach to find out the fall is to calculate the resultant of acceleration. This resultant is compared to a threshold value, above which it is classified as fall.
4
Further improvements to fall detection We can improve the accuracy by expanding the algorithm to include the readings from gyroscope and barometric sensors. Characterizing different kinds of fall.
5
Earthquake Detection The principle is similar to fall detection but here the decision of the ‘event’ is not taken by the phone. The vibration data is sent to the server. The server, based on crowdsourced data, will issue an alert if an earthquake occurred.
6
Crowdsourcing? Crowdsourcing is the practice of obtaining needed services or content from a large group of people. In case of an event, phones will report the event, sending the sensor data to the server. If the server receives lots of event from a specific region, we classify such an event as earthquake.
7
MQTT- Message queue Telemetry transport This is a lightweight messaging protocol designed for low power applications. It was primarily designed for systems with limited CPU cycles and memory, and also for networks with minimal bandwidth or high latency. So MQTT can be used to run very efficiently on small devices or in areas where network coverage is patchy.
8
Thank You
Similar presentations
© 2024 SlidePlayer.com. Inc.
All rights reserved.