A large plethora of models to predict human mobility exists in the literature. The problem of how to select the most appropriate model to solve a specific mobility prediction task has however received only little attention. Yet, a wrong model choice may lead to severe performance losses. In this paper, we address the model selection problem in human mobility prediction and make the following contributions. We present SELECTOR, a generic framework to explore human mobility data and compute both population models and individual models to predict human mobility. The former are models that are adapted to the characteristics of an entire population of users and can be used to overcome the cold-start problem. The latter are prediction models optimized for individual users. We present and analyze the results obtainable using SELECTOR on the Nokia data set, which is one of the largest and richest, publicly available data sets of human mobility data. We show that for many users, generic population models can be used in place of individual models with negligible performance losses. Yet for about 25 percent of the users, individual models perform at least three percentage points better than population models. Thereby, we show that the use of phone context data does not lead to significantly better performance of human mobility predictors with respect to the case in which only temporal and spatial features are used. We further observe that the population models we derive are robust against the demographics of the users and that building different population models for different periods of the day leads to performance improvements. We make SELECTOR publicly available to allow other researchers and practitioners to explore further mobility data sets and to embed the code base of SELECTOR in their applications.

Occupancy count in rooms is valuable for applications such as room utilization, opportunistic meeting support, and efficient heating-cooling operations. Few buildings, however, have the means of knowing occupancy beyond simple binary presence-absence. In this paper we present the PerCCS algorithm that explores the possibility of estimating person count from CO2 sensors already integrated in everyday room air-conditioning infrastructure. PerCSS uses task-driven Sparse Non-negative Matrix Factorization (SNMF) to learn a nonnegative low-dimensional representation of the CO2 data in the preprocessing stage. This denoised CO2 acts as the predictor variable for estimating occupancy count using Ensemble Least Square Regression. We tested the algorithm to estimate 15 minutes average occupancy count from a classroom of capacity 42 and compared its performance against existing methods from the literature. PerCSS estimates occupancy with a normalized mean squared error (NMSE) of 0.075 and outperformed our comparative methods in predicting occupancy count with 91 % and 15 % for exact occupancy estimation, when the room was unoccupied and occupied respectively, whereas the competing methods failed mostly.

Smart devices are becoming increasingly commercially available. However, uptake of these devices has been slow and abandonment swift, which indicates that smart devices may not currently meet the needs of users. To advance an understanding of the ways users benefit from, are challenged by, and abandon smart devices, we asked a group of users to purchase smart sensing devices to advance themselves towards a personal, self-defined goal. We found that participants abandoned devices because they did not fit with the their conceptions of themselves, the data collected by devices were perceived to not be useful, and device maintenance became unmanageable. Participants used devices because they had developed routines and because devices were useful, satisfied curiosity, and held hope for potential benefit to them. We propose ways to reduce barriers, motivate use, and argue for envisioning an additional function of these devices for short-term interventions, in addition to standard long-term use.

Location prediction enables us to use a person's mobility history to realize various applications such as efficient temperature control, opportunistic meeting support, and automated receptionists. Indoor location prediction is a challenging problem, particularly due to a high density of possible locations and short transition distances between these locations. In this paper we present Indoor-ALPS, an Adaptive Indoor Location Prediction System that uses temporal-spatial features to create individual daily models for the prediction of when a user will leave their current location (transition time) and the next location she will transition to. We tested Indoor-ALPS on the Augsburg Indoor Location Tracking Benchmark and compared our approach to the best performing temporal-spatial mobility prediction algorithm, Prediction by Partial Match (PPM). Our results show that Indoor-ALPS improves the temporal-spatial prediction accuracy over PPM for look-aheads up to 90 minutes by 6.2%, and for up to 30 minute look-aheads by 10.7%. These results demonstrate that Indoor-ALPS can be used to support a wide variety of indoor mobility prediction-based applications.

Reducing the large energy consumption of temperature regulation systems is a challenge for researchers and practitioners alike. In this paper, we explore and compare two common types of solutions: A manual systems that encourages reduced energy use, and an intelligent automatic control system. We deployed an eco-feedback system with the ability to remotely control one's thermostat to ten participants for three months. Participants appreciated the ability to remotely control the thermostat, and controlled their heating system with 78.8% accuracy, a 6.3% improvement over not having this system. However, despite having feedback and remote control, they still wasted a lot of energy heating when away from home for the day. Using data from our deployment, we developed TherML, an occupancy prediction algorithm that uses GPS data from a user's smartphone to automatically control the indoor temperature of a home with 92.1% accuracy. We compare TherML to other state-of-the-art techniques, and show that the higher accuracy of our approach optimizes both energy usage and user comfort. We end with recommendations for a mixed initiative system that leverages aspects of both the manual and automated approaches that can better match heating control to users' routines and preferences.