In this paper we investigate how to measure real world performance of Android devices using app start durations. To this end we collect ground truth app start times using an automated mechanical setup. The ground truth start times are highly correlated with the outputs from Android's ActivityManager, which we then use to obtain app start times during normal use on a range of rooted devices. We then predict app start times with supervised learning to detect if device performance has changed over time. We show that training data can be gathered on a small set of rooted devices and then applied to other, non rooted devices. We also present an unsupervised method that can track the evolution of the system performance without requiring root access at all.

In this paper we present Disca, a tool to analyze discussions in terms of which person is speaking at what time. We rely on a set of smartphones collaborating in detecting the most likely speaker at every given moment in real time. Each pair of smartphones observes a time difference of arrival pattern that is caused by the location of the different participants. The set of observations between all pairs of smartphones is then used to identify speakers on-line. To achieve this, clock differences and clock drifts between devices are estimated and compensated. Ultimately, participants are found by clustering time difference of arrival measurements which are unique for distinct speakers. We implement the system as an Android application and show that for more than 90% of time windows the correct speaker can be identified. To cope with heterogeneous hardware of Android smartphones, the computational burden is dynamically distributed among all participating smartphones according to their performance.

GPS is used for outdoor localization in a large variety of applications. Current receivers consume too much power for energy-constrained situations like continuous location tracking on small wearable devices. Mainly, this is due to the large amount of GPS signal that has to be decoded to compute the first position fix. While Coarse-Time Navigation (CTN) can reduce the necessary signal to a few milliseconds, it is not robust to noise. Collective Detection (CD) of satellites can mitigate noise to some degree, but the basic method is computationally expensive. We show how CD can be solved optimally and efficiently. Furthermore, we improve the accuracy of CD by exploiting the shape of the likelihood function. All our results are based on real-world signal observations and we achieve localization accuracies of less than 25 meters using a single millisecond of signal. When using 10 consecutive millisecond samples the accuracy improves to less than 10 meters.

We present RTDS, an Android application to analyze discussions while they are taking place. Using two microphones of a smart phone and Time Difference of Arrival measurements, conversations of participants are evaluated regarding, e.g., speaking time, contributions, or complex interaction patterns. The application can also assume the role of an active referee to ensure that all speakers get a fair share of the on-going conversation. By using an off the shelf smart phone with two microphones, our system can immediately be applied to track spoken interactions between people. Experimental results show that our implementation causes only 2% user classification errors whilst being able to run in real-time on a standard smart phone without hardware modifications.