Hallstrom, Jason O.

Mobility monitoring in urban environments can provide valuable insights into pedestrian and vehicle movement – where people want to go, how they get there, and the challenges they face along the way. Today, local governments can automate the acquisition of such data using video surveillance to understand the potential impact of investment and policy decisions. However, public disapproval of computer vision due to privacy concerns opens opportunities for research into alternative tools built with privacy constraints at the core of the design. WiFi sensing emerges as a promising solution. Modern mobile devices ubiquitously support the 802.11 standard and regularly emit WiFi probe requests for network discovery. We can passively monitor this traffic to estimate the levels of congestion in public spaces.
In this dissertation, we address three fundamental research problems pertaining to developing streetscape-scale mobility intelligence: scalable infrastructure for WiFi signal capture, passive device localization, and device re-identification.

Capturing pedestrian mobility patterns with high fidelity provides a foundation for data-driven decision-making in support of city planning, emergency response, and more. Due to scalability requirements and the sensitive nature of studying pedestrian movements in public spaces, the methods involved must be passive, low-cost, and privacy-centric. Pedestrian localization based on Received Signal Strength Indicator (RSSI) measurements from Wi-Fi probe requests is a promising approach. Probe requests are spontaneously emitted by Wi-Fi-enabled devices, are readily captured by of-the-shelf components, and offer the potential for anonymous RSSI measurement. Given the ubiquity of Wi-Fi-enabled devices carried by pedestrians (e.g., smartphones), RSSI-based passive localization in outdoor environments holds promise for mobility monitoring at scale. To this end, we developed the Mobility Intelligence System (MobIntel), comprising inexpensive sensor hardware to collect RSSI data, a cloud backend for data collection and storage, and web-based visualization tools. The system is deployed along Clematis Street in the heart of downtown West Palm Beach, FL, and over the past three years, over 50 sensors have been installed.
Our research first confirms that RSSI-based passive localization is feasible in a controlled outdoor environment (i.e., no obstructions and little signal interference), achieving ≤ 4 m localization error in more than 90% of the cases. When significant time-varying signal fluctuations are introduced as a result of long-term deployment, performance can be maintained with an overhaul of the problem formulation and an updated localization model. However, when the outdoor environment is fully uncontrolled (e.g., along Clematis Street), the performance decreases to ≤ 4 m error in fewer than 70% of the cases. However, the drop in performance may be addressed through improved sensor maintenance, additional data collection, and appropriate domain knowledge.

Artificial neural networks are increasing in power, with attendant increases in demand for efficient processing. Performance is limited by clock speed and degree of parallelization available through multi-core processors and GPUs. With a design tailored to a specific network, a field-programmable gate array (FPGA) can be used to minimize latency without the need for geographically distributed computing. However, the task of programming an FPGA is outside the realm of most data scientists. There are tools to program FPGAs from a high level description of a network, but there is no unified interface for programmers across these tools.
In this thesis, I present the design and implementation of NeuralSynth, a prototype Python framework which aims to bridge the gap between data scientists and FPGA programming for neural networks. My method relies on creating an extensible Python framework that is used to automate programming and interaction with an FPGA. The implementation includes a digital design for the FPGA that is completed by a Python framework. Programming and interacting with the FPGA does not require leaving the Python environment. The extensible approach allows multiple implementations, resulting in a similar workflow for each implementation. For evaluation, I compare the results of my implementation with a known neural network framework.

Embedded systems and Internet of Things (IoT) devices have been limited in application by constraints posed by batteries. Batteries add size, weight, and upkeep costs, while also limiting the lifetime of devices that are preferred to be small, lightweight, and long-lasting. We present Apis, a software and hardware toolkit for federated power management in energy harvesting applications. By replacing batteries with rapid charging storage capacitors, circuitry to control federated energy storage, and software support to make this architecture useful to developers, embedded devices can potentially run inde nitely with limited maintenance. We present the Apis hardware design for controlling federated energy storage, supporting software for controlling this hardware, and the results of experiments performed to validate the Apis model. The system is named after the taxonomy genus for the honey bee, a creature dedicated to the harvesting and federated storage of energy resources.

Food availability and food waste are signi cant global problems which can be
mitigated through the use of sensor networks. Current methods of monitoring food
waste require manual data collection and are implemented infrequently, providing
imprecise information. The use of sensors to automate food waste measurement
allows constant monitoring, provides a better dataset for analysis, and enables real-
time feedback, which can be used to affect behavioral change in consumers. The
data from such networks can be used to drive ambient displays designed to educate
a target audience, and ultimately reduce the amount of waste generated. We present
WASTE REDUCE, a system for automating the measurement of food waste and
affecting behavioral change. The challenges and results of deploying such a system
are presented. To assess the bene ts of using WASTE REDUCE, two case studies
are conducted. The rst study evaluates three different displays, and the second
reevaluates one of these displays in a separate location. These studies con rm that
the combination of automated monitoring and ambient feedback can reduce food
waste for targeted groups.