Measuring mental well-being with mobile sensing has been an increasingly active research topic. Pervasiveness of smartphones combined with the convenience of mobile app distribution platforms (e.g., Google Play) provide a tremendous opportunity to reach out to millions of users. However, the studies at the confluence of mental health and mobile sensing have been longitudinally limited, controlled, or confined to a small number of participants. In this paper we report on what we believe is the largest longitudinal in-the-wild study of mood through smartphones. We describe an Android app to collect participants' self-reported moods and system triggered experience sampling data while passively measuring their physical activity, sociability, and mobility via their device's sensors. We report the results of a large-scale analysis of the data collected for about three years from 18,000 users.

Mobile apps that use sensors to monitor user behavior often employ resource heavy inference algorithms that make computational offloading a common practice. However, existing schedulers/offloaders typically emphasize one primary offloading aspect without fully exploring complementary goals (e.g., heterogeneous resource management with only partial visibility into underlying algorithms, or concurrent sensor app execution on a single resource) and as a result, may overlook performance benefits pertinent to sensor processing.

Smartphone sensing research has been advancing at a brisk pace. Yet, current social networking services often only take advantage of location sensing: applications like Foursquare use the phone's GPS and Wi-Fi radios to infer the user's location to simplify checking-in to a place. However, smartphone sensing could be exploited to considerably expand the spectrum of information a user can share with a few clicks with friends: not only the location of an event but activities such as “cooking dinner” or “waiting for a bus” can be predicted and suggested to the user to ease the check-in process. In this paper we show how mobile phone sensing can be used in this sense. For this prediction process to be accurate however, sensors need to be sampled often, with a considerable impact on the phone battery. To alleviate this issue, we explore streams of phone usage data (soft sensors), such as application usage, messages, and phone calls for predicting the user's activity in a more efficient fashion for augmenting mobile social check-in apps. We have deployed our application and collected a dataset of over 2700 check-ins to 48 activities from 20 users. Our analysis shows a prediction accuracy of 75% when offering 5 check-in suggestions to users. Furthermore, we show that when using only soft sensors we can achieve very similar performance to that obtained with real sensors, thereby significantly reducing the impact on the phone battery. This finding might have a potentially high impact on smartphone based activity check-in apps.

Smartphones can collect considerable context data about the user, ranging from apps used to places visited. Frequent user patterns discovered from longitudinal, multi-modal context data could help personalize and improve overall user experience. Our long term goal is to develop novel middleware and algorithms to efficiently mine user behavior patterns entirely on the phone by utilizing idle processor cycles. Mining patterns on the mobile device provides better privacy guarantees to users, and reduces dependency on cloud connectivity. As an important step in this direction, we develop a novel general-purpose service called MobileMiner that runs on the phone and discovers frequent co-occurrence patterns indicating which context events frequently occur together. Using longitudinal context data collected from 106 users over 1--3 months, we show that MobileMiner efficiently generates patterns using limited phone resources. Further, we find interesting behavior patterns for individual users and across users, ranging from calling patterns to place visitation patterns. Finally, we show how our co-occurrence patterns can be used by developers to improve the phone UI for launching apps or calling contacts.

The rapidly growing adoption of sensor-enabled smartphones has greatly fueled the proliferation of applications that use phone sensors to monitor user behavior. A central sensor among these is the microphone which enables, for instance, the detection of valence in speech, or the identification of speakers. Deploying multiple of these applications on a mobile device to continuously monitor the audio environment allows for the acquisition of a diverse range of sound-related contextual inferences. However, the cumulative processing burden critically impacts the phone battery.

The Experience Sampling Method (ESM) has been widely used to collect longitudinal survey data from participants; in this domain, smartphone sensors are now used to augment the context-awareness of sampling strategies. In this paper, we study the effect of ESM design choices on the inferences that can be made from participants' sensor data, and on the variance in survey responses that can be collected. In particular, we answer the question: are the behavioural inferences that a researcher makes with a trigger-defined subsample of sensor data biased by the sampling strategy's design? We demonstrate that different single-sensor sampling strategies will result in what we refer to as contextual dissonance: a disagreement in how much different behaviours are represented in the aggregated sensor data. These results are not only relevant to researchers who use the ESM, but call for future work into strategies that may alleviate the biases that we measure.

Mobile phones play a pivotal role in supporting ubiquitous and unobtrusive sensing of human activities. However, maintaining a highly accurate record of a user's behavior throughout the day imposes significant energy demands on the phone's battery. In this paper, we present the design, implementation, and evaluation of METIS: an adaptive mobile sensing platform that efficiently supports social sensing applications. The platform implements a novel sensor task distribution scheme that dynamically decides whether to perform sensing on the phone or in the infrastructure, considering the energy consumption, accuracy, and mobility patterns of the user. By comparing the sensing distribution scheme with sensing performed solely on the phone or exclusively on the fixed remote sensors, we show, through benchmarks using real traces, that the opportunistic sensing distribution achieves over 60% and 40% energy savings, respectively. This is confirmed through a real world deployment in an office environment for over a month: we developed a social application over our frameworks, that is able to infer the collaborations and meetings of the users. In this setting the system preserves over 35% more battery life over pure phone sensing.

The interactions and social relations among users in workplaces have been studied by many generations of social psychologists. There is evidence that groups of users that interact more in workplaces are more productive. However, it is still hard for social scientists to capture fine-grained data about phenomena of this kind and to find the right means to facilitate interaction. It is also difficult for users to keep track of their level of sociability with colleagues. While mobile phones offer a fantastic platform for harvesting long term and fine grained data, they also pose challenges: battery power is limited and needs to be traded-off for sensor reading accuracy and data transmission, while energy costs in processing computationally intensive tasks are high.

Today's mobile phones represent a rich and powerful computing platform, given their sensing, processing and communication capabilities. Phones are also part of the everyday life of billions of people, and therefore represent an exceptionally suitable tool for conducting social and psychological experiments in an unobtrusive way.

In this paper, we focus on maximizing network lifetime of a Wireless Sensor Network (WSN) using mobile Data-Collectors (DCs) without compromising on the reliability requirements. We consider a heterogeneous WSN which consists of a large number of sensor nodes, a few DCs, and a static Base Station (BS). The sensor nodes are static and are deployed uniformly in the terrain. The DCs have locomotion capabilities and their movement can be controlled. Each sensor node periodically sends sensed event packets to its nearest DC. The DCs aggregate the event packets received from the sensor nodes and send these aggregate event packets to the static BS. We address the following problem: the DCs should send the aggregate event packets to the BS with a given reliability while avoiding the hot-spot regions such that the network lifetime is improved. Reliability is achieved by sending each aggregate event packet via multiple paths to the BS. The network lifetime is maximized by moving the DCs in such a way that the forwarding load is distributed among the sensor nodes. We propose both centralized and distributed approaches for finding a movement strategy of the DCs. We show via simulations that the proposed approaches achieve the required reliability and also maximize the network lifetime compared to the existing approaches.

In this paper, we consider the problem of information discovery in wireless sensor networks (WSNs), where the search initiator is unaware of any of the gamma locations of target information. One of the fundamental techniques which is used for this purpose is random walk since it has several advantages like low cost (number of bytes transmitted) compared to flooding, load balancing among nodes, and minimal state maintenance. Even though random walk reduces cost, it is still high enough for energy constrained networks like WSNs. Furthermore, random walk incurs high latencies making it infeasible for delay sensitive applications. To alleviate the above mentioned problems in random walk, we propose a variant of random walk called level biased random walk (LBRW). In LBRW, the search packet traverses from the sink node (search initiator) to the circumference nodes (nodes without children) of the network and vice versa via random paths. The idea is to improve the node coverage of LBRW compared to that of random walk by forcing it to move in some particular directions. We show by extensive simulations that the cost and latency of LBRW are only 56-69% of that by random walk, when gamma=3 and at reasonable densities.

In this paper, we consider the problem of information discovery in a densely deployed wireless sensor network (WSN), where the initiator of search is unaware of the location of target information. We propose two protocols: increasing ray search (IRS), an energy efficient and scalable search protocol, and k-IRS, an enhanced variant of IRS. The priority of IRS is energy efficiency and sacrifices latency whereas k-IRS is configurable in terms of energy-latency trade-off and this flexibility makes it applicable to varied application scenarios. The basic principle of these protocols is to route the search packet along a set of trajectories called rays that maximizes the likelihood of discovering the target information by consuming least amount of energy. The rays are organized such that if the search packet travels along all these rays, then the entire terrain area will be covered by its transmissions while minimizing the overlap of these transmissions. In this way, only a subset of total sensor nodes transmits the search packet to cover the entire terrain area while others listen. We believe that query resolution based on the principles of area coverage provides a new dimension for conquering the scale of WSN. We compare IRS and k-IRS with existing query resolution techniques for unknown target location such as expanding ring search (ERS), Random walk search, and variants of Gossip search. We show by analysis, simulation, and implementation in testbed that IRS and k-IRS are highly scalable, the cost of search (total number of transmitted bytes) is independent of node density, and it is much lower than that of existing proposals under high node density.