My research with Prof. Zhou and the LENS Lab focuses on wireless sensor networks and mobile devices. To date, my research projects have focused on three areas: 1) practical activity classification in body sensor networks, 2) meeting event detection accuracy requirements in wireless sensor networks, and 3) routing in mobile wireless sensor networks. My dissertation aims to provide accurate sensing by using a machine learning-based approach which exploits the nuances of each specific sensor deployment. Details of these research projects are as follows:
The vast array of small wireless sensors is a boon to body sensor network applications, especially in the context awareness and activity recognition arena. However, most activity recognition deployments and applications are challenged to provide personal control and practical functionality for everyday use. We argue that activity recognition for mobile devices must meet several goals in order to provide a practical solution: user friendly hardware and software, accurate and efficient classification, and reduced reliance on ground truth.
To meet the challenges of a practical solution, we present PBN: Practical Body Networking. Through the unification of TinyOS motes and Android smartphones, we combine the sensing power of on-body wireless sensors with the additional sensing power, computational resources, and user-friendly interface of an Android smartphone. We provide an accurate and efficient classification approach through the use of ensemble learning. We explore the properties of different sensors and sensor data to further improve classification efficiency and reduce reliance on user annotated ground truth. We evaluate our PBN system with multiple subjects over a two week period and demonstrate that the system is easy to use, accurate, and appropriate for mobile devices.
Wireless sensor networks for human health monitoring, military surveillance, and disaster warning all have stringent accuracy requirements for detecting or classifying events while maximizing system lifetime. Failure to meet accuracy requirements for such performance critical applications may result in distastrous consequences. Therefore, we define confident sensing as meeting user accuracy requirements for sensing, classification, or event detection. To perform confident sensing and reduce energy, we must address sensing diversity: the sensing capability differences among heterogeneous and homogeneous sensors in a specific deployment. Existing approaches do not fully address sensing diversity: they do not explore the detection capability of a deployed system and choose the right sensors, homogeneous or heterogeneous, to meet user specified detection accuracy.
We first propose Watchdog, a confident sensing framework for event detection at critical locations, such as a vehicle detection application for traffic flow monitoring. Watchdog is a modality-agnostic framework that clusters the right sensors to meet user specified detection accuracy during runtime while significantly reducing energy consumption. Through evaluation with vehicle detection trace data and a building traffic monitoring testbed of IRIS motes, we demonstrate the superior performance of Watchdog over existing solutions in terms of meeting user specified detection accuracy and energy savings.
Furthermore, we are among the first to explore the impact of sensing diversity on sensor collaboration, exploit diversity for sensing confidence, and apply diversity exploitation for confident sensing coverage. We show that our diversity-exploiting confident coverage problem is NP-hard for any specific deployment and present a practical solution, Wolfpack. Through a distributed and iterative sensor collaboration approach, Wolfpack maximizes a specific deployment's capability to meet user detection requirements and save energy by powering off unneeded nodes. Using real vehicle detection trace data, we demonstrate that Wolfpack provides confident event detection coverage for 30% more detection locations, using 20% less energy than a state of the art approach.
While most existing wireless sensor network deployments are terrestrial networks with static sensor nodes, mobile wireless sensor networks are receiving increasing attention in the research community. We envision a buoyant sensor network for in-situ flood inundation monitoring to motivate the need for a holistic forwarding protocol for mobile wireless sensor networks. Since inundation prediction is largely based on modeling and simulation, it is imperative to collect runtime flooding information as in-situ feedback to simulation models. With our application scenario, we demonstrate that existing approaches to routing in mobile environments do not work well due to volatile topology changes.
Consequently, due to the dynamic topology changes present in mobile wireless sensor networks, we propose Sidewinder, a predictive data forwarding protocol. Like a heat-seeking missile, data packets are guided towards a sink node with increasing accuracy as packets approach the sink. Different from conventional sensor network routing protocols, Sidewinder continuously predicts the current sink location based on distributed knowledge of sink mobility among nodes in a multi-hop routing process. Moreover, the continuous sink estimation is scaled and adjusted to perform with resource-constrained wireless sensors. Our design is implemented with nesC and evaluated in TOSSIM. The performance evaluation demonstrates that Sidewinder significantly outperforms state-of-the-art solutions in packet delivery ratio, time delay, and energy efficiency.