ABSTRACT
The number of Internet-of-Things (IoT) and edge devices has exploded in the last decade, providing new opportunities to sense and enable many applications to transform everyday people's lives. Wide-scale time series data collected through such devices, coupled with advances in learning technologies, can transform how people interact with their environment. However, as we enter the era of ubiquitous computing, there is a growing need for methods that are easy to use, computationally feasible, and require minimal human supervision to sense human activities by analyzing large-scale data. The goal of this research work is to propose data-driven techniques that focus on human activity sensing at different scales.The first part of the thesis focuses on human activity sensing at building scale for smart indoor environments. Towards that end, this work emphasizes general-purpose human activity sensing using ambient sensors for context-aware computing in smart environments. A deep neural network-based technique for sensing human-environment interaction is proposed and experiments explored interpretability for different ambient sensors and their contribution to model performance to avoid data redundancy. Identifying the challenge of distribution shift in long-term activity sensing, the thesis next focuses on time series partitioning for unlabeled IoT sensor streams, which is an important step toward continuous human activity sensing. This work proposes Cadence, a generalized change point detection technique that detects change points through hypothesis testing by learning a data representation specifically with the segmentation objective. Experiments show that it is sample-efficient, unsupervised, and can robustly detect time-series events across different applications while needing only 9-93 seconds for training.The second part of the thesis focuses on human activity sensing at city scale using large-scale spatio-temporal data. A framework is introduced for sensing urban activity and policy compliance during the COVID-19 crisis using vision and language-based sensing from street view images. Understanding the challenges of street view image usage in urban sensing due to its large scale and distribution variance, a data-driven framework is proposed to evaluate the quality of information in urban scale street view images based on quality attributes capturing spatial, temporal, and content information present in the data. Our experiments show that such framework can be useful for ranking, querying, and improving spatio-temporal data quality and usage in urban computing and activity sensing. We believe such techniques can be useful to model our living patterns by analyzing large-scale data and improve the quality of our life through applications such as home automation, energy optimization, and personalized healthcare. (PsycInfo Database Record (c) 2023 APA, all rights reserved)