The emerging class of wide-area streaming analytics faces the challenge of scarce and variable WAN bandwidth. Non-adaptive applications built with TCP or UDP suffer from increased latency or degraded accuracy. State-of-the-art approaches that adapt to network changes require developer writing sub-optimal manual policies or are limited to application-specific optimizations.

Although many software libraries and hardware modules support reading data from sensors, makers of interactive systems often struggle to extract higher-level information from raw sensor data. Available general-purpose machine learning (ML) libraries remain difficult to use for non-experts. Prior research has sought to bridge this gap through domain-specific user interfaces for particular types of sensors or algorithms. Our ESP (Example-based Sensor Prediction) system introduces a more general approach in which interactive visualizations and control interfaces are dynamically generated from augmented code examples written by experts. ESP's augmented examples allow experts to write logic that guides makers through important steps such as sensor calibration, parameter tuning, and assessing signal quality and classification performance. Writing augmented examples requires additional effort. ESP leverages a fundamental dynamic of online communities: experts are often willing to invest such effort to teach and train novices. Thus support for particular sensing domains does not have to be hard-wired a priori by system authors, but can be provided later by its community of users. We illustrate ESP's flexibility by detailing pipelines for four distinct sensors and classification algorithms. We validated the usability and flexibility of our example-based approach through a one-day workshop with 11 participants.

A mobile phone, as a pervasive device, has great potential in human wellness monitoring. In this demo, we first present the design and implementation of our hardware - SEPTIMU. SEPTIMU consists of a small baseboard and a pair of tiny sensor boards embedded inside conventional earphones. The baseboard provides power conversion and data communication through the normal audio jack interface. The embedded sensor board is 1×1cm2 and integrates 3-axis accelerometer, gyroscope, thermometer, photodiode and microphone. Secondly, we evaluate SEPTIMU using a mobile application that continuously monitors body posture and provides feedback to the user.

Many indoor sensing applications leverage knowledge of relative proximity among physical objects and humans, such as the notion of "within arm's reach". In this paper, we quantify this notion using "proximity zone", and propose a methodology that empirically and systematically compare the proximity zones created by various wireless technologies. We find that existing technologies such as 802.15.4, Bluetooth Low Energy (BLE), and RFID fall short on metrics such as boundary sharpness, robustness against interference, and obstacle penetration. We then present the design and evaluation of a wireless proximity detection platform based on magnetic induction - LiveSynergy. LiveSynergy provides sweet spot for indoor applications that require reliable and precise proximity detection. Finally, we present the design and evaluation of an end-to-end system, deployed inside a large food court to offer context-aware and personalized advertisements and diet suggestions at a per-counter granularity.

MusicalHeart is a biofeedback-based, context-aware, automated music recommendation system for smartphones. We introduce a new wearable sensing platform, Septimu, which consists of a pair of sensor-equipped earphones that communicate to the smartphone via the audio jack. The Septimu platform enables the MusicalHeart application to continuously monitor the heart rate and activity level of the user while listening to music. The physiological information and contextual information are then sent to a remote server, which provides dynamic music suggestions to help the user maintain a target heart rate. We provide empirical evidence that the measured heart rate is 75% -- 85% correlated to the ground truth with an average error of 7.5 BPM. The accuracy of the person-specific, 3-class activity level detector is on average 96.8%, where these activity levels are separated based on their differing impacts on heart rate. We demonstrate the practicality of MusicalHeart by deploying it in two real world scenarios and show that MusicalHeart helps the user achieve a desired heart rate intensity with an average error of less than 12.2%, and its quality of recommendation improves over time.

In this demonstration, we present the architecture, implementation, and applications of LiveSynergy --- a system that provides reliable proximity sensing and open interactive abstractions for physical spaces and objects, to enable rich interactions between humans and their environment.