Context Inference for Mobile Applications in the UPCASE Project
read more
Citations
Preprocessing techniques for context recognition from accelerometer data
A survey on smartphone-based systems for opportunistic user context recognition
Security, Privacy, and Incentive Provision for Mobile Crowd Sensing Systems
Providing user context for mobile and social networking applications
SPPEAR: security & privacy-preserving architecture for participatory-sensing applications
References
C4.5: Programs for Machine Learning
Induction of Decision Trees
Programs for Machine Learning
Programs for machine learning Part I
Related Papers (5)
Frequently Asked Questions (14)
Q2. What are the techniques used to process raw data from sensors?
Processing raw data from sensors may require a wide variety of techniques such as noise reduction, mean and variance calculation, time- and frequency-domain transformations, estimation of time series or sensor fusion.
Q3. What is the key enabling factor for a new generation of context-aware services and?
Being able to gather information about user context is a key enabling factor for a new generation of context-aware services and applications.
Q4. What are the main features of the SenSay prototype?
The SenSay prototype uses a smartphone and a sensor unit consisting of a 3-axis accelerometer, two microphones (one to capture sound from the environment and the other to capture voice from the user), and a light sensor.
Q5. What is the context that is stored in the decision tree?
The context identified via the decision tree is stored in a buffer which gathers a finite number of contexts and returns the context that has been recorded more often within a certain time window.
Q6. What are the main approaches used to identify user activities?
Regarding the inference of user activities such as ”walking” or ”running”, they use a plethora of approaches, ranging from simple processing steps and threshold operations [8, 22, 27] to the use of neural networks as the clustering algorithm [20]; or even using non-supervised time-series segmentation [9].
Q7. What is the purpose of the application of the UPCASE system?
The applications exploit not only the ability of the system to identify user contexts, but also of making context information available to other users via a context server.
Q8. What is the purpose of the JSR-256 API?
The JSR-256 API allows developers to retrieve data not only from embedded sensors but also from sensors connected via infrared, bluetooth and GPRS.
Q9. How can a mobile device determine whether an elderly has fallen at home?
Using sensors it might be possible to determine whether an elderly has fallen at home and has been immobile for some time thus triggering an emergency call.
Q10. What is the definition of emergency management?
Emergency management is the discipline that deals with preparing for, preventing, responding to, and recovering from emergency situations [6].
Q11. What is the purpose of the paper?
In this paper the authors addressed the problem of distinguishing between a number of daily activity contexts by means of a prototype proof-of-concept system developed in the context of the UPCASE project.
Q12. What are the types of user activities that are used to identify a context?
These include simple user activities (e.g., ”walking”, ”running”, ”standing”), environment characteristics (e.g., ”cold”, ”warm”), or even emotional condition of the user (e.g., ”happy”, ”sad”, ”nervous”).
Q13. What is the sensor node used to communicate with the smartphone?
The BlueSentry sensor node communicates with the smartphone via Bluetooth to provide sensor readings, thus avoiding the need for physical connection between the two.
Q14. What are the basic techniques used to identify the user activities?
The prototype makes use of simple techniques such as performing an average of sensor readings over a given window and applying a numeric threshold to identify each activity.