Matthias Budde

ActiServ: Activity Recognition Service for mobile phones

Smart phones have become a powerful platform for wearable context recognition. We present a service-based recognition architecture which creates an evolving classification system using feedback from the user community. The approach utilizes classifiers based on fuzzy inference systems which use live annotation to personalize the classifier instance on the device. Our recognition system is designed for everyday use: it allows flexible placement of the device (no assumed or fixed position), requires only minimal personalization effort from the user (1–3 minutes per activity) and is capable of detecting a high number of activities. The components of the service are shown in an evaluation scenario, in which recognition rates up to 97% can be achieved for ten activity classes.

Using a 2DST waveguide for usable, physically constrained out-of-band Wi-Fi authentication

This paper proposes using a 2D waveguide for a novel means of authentication in public Wi-Fi infrastructures. The design of the system is presented, and its practicability and usability is comparatively discussed with that of five other tag and context based authentication schemes, two of which have not been previously realized. In accordance with the presented application scenarios, all of the schemes were implemented in a platform-independent fashion built on web technology.

Investigating the use of commodity dust sensors for the embedded measurement of particulate matter

A variety of studies in the past decades have shown that fine particulate matter can be a serious health hazard, contributing to respiratory and cardiovascular disease. Due to this, more and more regulations defining certain permissible concentration limits have been set by governments around the world. However, current standard measurement equipment is large, expensive and sparsely deployed. Additionally, both the exposure to hazardous conditions and the susceptibility to negative health effects vary from person to person. As a result, we see the need for fine-grained, mobile and distributed measurements, e.g. to identify hot spots or monitor people at risk. Our research investigates the feasibility of particulate matter measurements using cheap, commodity dust sensors which are small enough to be incorporated into mobile devices. This paper first discusses application scenarios which would benefit from inexpensive methods to assess the particulate matter load. Subsequently, commercial-off-the-shelf (COTS) sensors are compared and their general suitability for the application scenarios is examined. Finally, an experimental setup for the evaluation of one of the sensors is presented along with preliminary results.

Enabling low-cost particulate matter measurement for participatory sensing scenarios

This paper presents a mobile, low-cost particulate matter sensing approach for the use in Participatory Sensing scenarios. It shows that cheap commercial off-the-shelf (COTS) dust sensors can be used in distributed or mobile personal measurement devices at a cost one to two orders of magnitude lower than that of current hand-held solutions, while reaching meaningful accuracy. We conducted a series of experiments to juxtapose the performance of a gauged high-accuracy measurement device and a cheap COTS sensor that we fitted on a Bluetooth-enabled sensor module that can be interconnected with a mobile phone. Calibration and processing procedures using multi-sensor data fusion are presented, that perform very well in lab situations and show practically relevant results in a realistic setting. An on-the-fly calibration correction step is proposed to address remaining issues by taking advantage of co-located measurements in Participatory Sensing scenarios. By sharing few measurement across devices, a high measurement accuracy can be achieved in mobile urban sensing applications, where devices join in an ad-hoc fashion. A performance evaluation was conducted by co-locating measurement devices with a municipal measurement station that monitors particulate matter in a European city, and simulations to evaluate the on-the-fly cross-device data processing have been done.

The TECO Envboard: A mobile sensor platform for accurate urban sensing — And more

Participatory Urban Sensing scenarios have increasingly been studied in the past years. At the same time, societys concern about the effects of pollutants on peoples personal health as well as on the environment grew. This, in conjunction with studies that helped to give a better understanding of those effects, lead to new and stricter regulations and standards set up by governments. Such standards define limits for concentrations which should or may not be exceeded. There are usually several of such maximum permissible values for different pollutants, and they may differ from country to country. As a result, we see the need for ways to take accurate, fine-grained and mobile measurements, e.g in order to identify hot spots or monitor people at risk. Standard fixed measuring methods are not suitable for such scenarios. This demo presents a generic platform for such measurements - the TECO Envboard.

An extensible modular recognition concept that makes activity recognition practical

In mobile and ubiquitous computing, there is a strong need for supporting different users with different interests, needs, and demands. Activity recognition systems for context aware computing applications usually employ highly optimized off-line learning methods. In such systems, a new classifier can only be added if the whole recognition system is redesigned. For many applications that is not a practical approach. To be open for new users and applications, we propose an extensible recognition system with a modular structure. We will show that such an approach can produce almost the same accuracy compared to a system that has been generally trained (only 2 percentage points lower). Our modular classifier system allows the addition of new classifier modules. These modules use Recurrent Fuzzy Inference Systems (RFIS) as mapping functions, that not only deliver a classification, but also an uncertainty value describing the reliability of the classification. Based on the uncertainty value we are able to boost recognition rates. A genetic algorithm search enables the modular combination.

Retrofitting smartphones to be used as particulate matter dosimeters

This work discusses ways of measuring particulate matter with mobile devices. Solutions using a dedicated sensor device are presented along with a novel method of retrofitting a sensor to a camera phone without need for electrical modifications. Instead, the flash and camera of the phone are used as light source and receptor of an optical dust sensor respectively. Experiments to evaluate the accuracy are presented.

Point & control -- interaction in smart environments: you only click twice

This work presents a system that makes use of the Microsoft Kinect to enable Point&Click interaction for the control of appliances in smart environments. A backend server determines through collision detection which device the user is pointing at and sends the respective control interface to the users smartphone. Any commands the user issues are then sent back to the server which in turn controls the appliance. New devices can either be registered manually or using markers such as QR codes to identify them and get their position at the same time. The video demonstrates the interaction concept and our technical implementation.

How to use smartphones for less obtrusive ambulatory mood assessment and mood recognition

We present MoA2, a context-aware smartphone app for the ambulatory assessment of mood, tiredness and stress level. In principle, it has two features: (1) mood assessment and (2) mood recognition. The mood assessment system combines benefits of state of the art approaches. The mood recognition is concluded by smartphone-based wearable sensing. In a formative study, we evaluated the usability and unobtrusiveness of our mood assessment. A median SUS score of 90 shows a high usability. Subjects reported an easy, fast and intuitive use. The mood recognition was evaluated in terms of classification accuracy. First, we analyzed which features are best for the recognition. Spatio-temporal attributes, i.e. daytime, day of week and location, correlate most with the monitored mood. Based on the identified attributes, we trained personalized classifiers using Naïve Bayes and applied ten-fold-cross validation. The average recognition accuracy was 0.76 which is comparable to related work.

Device-Free Radio-based Low Overhead Identification of Subject Classes

An increasing corpus of research focuses on inferring contexts solely through analysis of changes in surrounding wireless signals without the subject carrying a device (device-free). This paper takes device-free recognition a step further: We present WiDisc, a novel device-free RF system for distinguishing three subject classes (e.g. tall, medium, small). WiDisc models the problem as fingerprinting-based classification. To alleviate the significant location-based training overhead per subject class which is usually required, WiDisc employs 3D subject class model construction and electromagnetic simulations to generate the fingerprints with no manual training overhead. WiDisc further estimates the most relevant RF links to maximize recognition performance. Our lab evaluation with only four transceivers and three subject classes shows that the link selection module can accurately predict the two most important links, falling short only 5% of the achievable accuracy. In addition, WiDisc achieves a classification accuracy of 67% with zero training overhead vs 76% with traditional fingerprinting. Discrimination works esp. well for the medium and tall subjects but confusions for the small subject are frequent, indicating potential for further research. Still, the results highlight WiDiscs ability to trade off accuracy and training overhead and opens the door for new applications including finer-grained intrusion detection forensics, device-free parental control, personalized device-free gesture recognition, to name a few.