In today's always-connected world, we receive a large number of notifications on our mobile devices. These notifications cause interruptions, stress, and even impact users' lifestyle. To understand how users respond to notifications, we develop an application that monitors various features (e.g., importance) of the notifications, users' actions, and the level of users' engagement with the notifications. We recruit 30 users to use the application and monitor over 30 days, and subsequently find that 20% to 50% of the notifications generally get ignored by the users. In addition, we also solicit explicit feedback about the importance of notifications from 12 users over 14 days and identify the relation between perceived importance and users' engagement level. Based on this study, we identify the key characteristics of notifications and users' engagement, which is further substantiated by an onfine survey of 400+ users. In addition, we develop a notification manager that includes a machine learning based prediction model and that shows only the important notifications and delays the unimportant notifications. Our experimental results show that our notification manager automatically assesses the importance of notifications with more than 87% accuracy. We believe this work is a promising step toward intelligent personal assistant that manages notifications.

The field of mobile health (mHealth) has the potential to yield new insights into health and behavior through the analysis of continuously recorded data from wearable health and activity sensors. In this paper, we present a hierarchical span-based conditional random field model for the key problem of jointly detecting discrete events in such sensor data streams and segmenting these events into high-level activity sessions. Our model includes higher-order cardinality factors and inter-event duration factors to capture domain-specific structure in the label space. We show that our model supports exact MAP inference in quadratic time via dynamic programming, which we leverage to perform learning in the structured support vector machine framework. We apply the model to the problems of smoking and eating detection using four real data sets. Our results show statistically significant improvements in segmentation performance relative to a hierarchical pairwise CRF.

With the great success of LTE(-A) outdoor, LTE-based small cell technology has become popular and is penetrating indoor enterprise environment, co-existing with WiFi networks, to provide better user experience or Quality-of-Experience (QoE). However, accurate estimation of LTE links is challenging and critical to continue providing QoE for many enterprise applications (e.g., video/audio) and services (network selection). While prior work on LTE link throughput estimation depends mostly on a single factor (e.g., link rate), we argue that it needs to consider more factors to improve the estimation to meet increasing demands on QoE. In this paper, we propose a new metric, called Pulsar (Per-user LTE ShAre of Resources), that estimates per flow throughput in LTE networks by leveraging both underlying channel information and application traffic characteristics. Our extensive evaluation study through ns-3 shows that Pulsar reduces the estimation error more than 92%, compared to prior work, in various scenarios, while keeping estimation overhead low.

, a mobile solution that leverages a wristband containing a 9-axis inertial measurement unit to capture changes in the orientation of a person's arm, and a machine learning pipeline that processes this data to accurately detect smoking gestures and sessions in real-time. Our key innovations are fourfold: a) an arm trajectory-based method that extracts candidate hand-to-mouth gestures, b) a set of trajectory-based features to distinguish smoking gestures from confounding gestures including eating and drinking, c) a probabilistic model that analyzes sequences of hand-to-mouth gestures and infers which gestures are part of individual smoking sessions, and d) a method that leverages multiple IMUs placed on a person's body together with 3D animation of a person's arm to reduce burden of self-reports for labeled data collection. Our experiments show that our gesture recognition algorithm can detect smoking gestures with high accuracy (95.7%), precision (91%) and recall (81%). We also report a user study that demonstrates that we can accurately detect the number of smoking sessions with very few false positives over the period of a day, and that we can reliably extract the beginning and end of smoking session periods.

Ubiquitous physiological sensing has the potential to profoundly improve our understanding of human behavior, leading to more targeted treatments for a variety of disorders. The long term goal of this work is development of novel computational tools to support the study of addiction in the context of cocaine use. The current paper takes the first step in this important direction by posing a simple, but crucial question: Can cocaine use be reliably detected using wearable electrocardiogram (ECG) sensors? The main contributions in this paper include the presentation of a novel clinical study of cocaine use, the development of a computational pipeline for inferring morphological features from noisy ECG waveforms, and the evaluation of feature sets for cocaine use detection. Our results show that 32mg/70kg doses of cocaine can be detected with the area under the receiver operating characteristic curve levels above 0.9 both within and between-subjects.

Mobile phones have evolved from communication devices to indispensable accessories with access to real-time content. The increasing reliance on dynamic content comes at the cost of increased latency to pull the content from the Internet before the user can start using it. While prior work has explored parts of this problem, they ignore the bandwidth costs of prefetching, incur significant training overhead, need several sensors to be turned on, and do not consider practical systems issues that arise from the limited background processing capability supported by mobile operating systems. In this paper, we make app prefetch practical on mobile phones. Our contributions are two-fold. First, we design an app prediction algorithm, APPM, that requires no prior training, adapts to usage dynamics, predicts not only which app will be used next but also when it will be used, and provides high accuracy without requiring additional sensor context. Second, we perform parallel prefetch on screen unlock, a mechanism that leverages the benefits of prediction while operating within the constraints of mobile operating systems. Our experiments are conducted on long-term traces, live deployments on the Android Play Market, and user studies, and show that we outperform prior approaches to predicting app usage, while also providing practical ways to prefetch application content on mobile phones.

The proliferation of sensors on mobile phones and wearables has led to a plethora of context classifiers designed to sense the individual's context. We argue that a key missing piece in mobile inference is a layer that fuses the outputs of several classifiers to learn deeper insights into an individual's habitual patterns and associated correlations between contexts, thereby enabling new systems optimizations and opportunities. In this paper, we design CQue, a dynamic bayesian network that operates over classifiers for individual contexts, observes relations across these outputs across time, and identifies opportunities for improving energy-efficiency and accuracy by taking advantage of relations. In addition, such a layer provides insights into privacy leakage that might occur when seemingly innocuous user context revealed to different applications on a phone may be combined to reveal more information than originally intended. In terms of system architecture, our key contribution is a clean separation between the detection layer and the fusion layer, enabling classifiers to solely focus on detecting the context, and leverage temporal smoothing and fusion mechanisms to further boost performance by just connecting to our higher-level inference engine. To applications and users, CQue provides a query interface, allowing a) applications to obtain more accurate context results while remaining agnostic of what classifiers/sensors are used and when, and b) users to specify what contexts they wish to keep private, and only allow information that has low leakage with the private context to be revealed. We implemented CQue in Android, and our results show that CQue can i) improve activity classification accuracy up to 42%, ii) reduce energy consumption in classifying social, location and activity contexts with high accuracy(>90%) by reducing the number of required classifiers by at least 33%, and iii) effectively detect and suppress contexts that reveal private information.

A communication trace is a detailed record of the communication between two entities. Communication traces are vital for research in computer networks and protocols in many domains, but their release is severely constrained by privacy and security concerns. In this paper, we propose a framework in which a trace owner can match an anonymizing transformation with the requirements of analysts. The trace owner can release multiple transformed traces, each customized to an analyst’s needs, or a single transformation satisfying all requirements. The framework enables formal reasoning about anonymization policies, for example to verify that a given trace has utility for the analyst, or to obtain the most secure anonymization for the desired level of utility. Because communication traces are typically very large, we also provide techniques that allow efficient application of transformations using relational database systems. 1.

In this paper, we present a system, called Sensei, for assessment of spoken English skills of call center agents. Sensei evaluates multiple parameters of spoken English skills, i.e., articulation of sounds, correctness of lexical stress in words and spoken grammar proficiency. Sensei provides an assessment test to be taken by a call center agent (or candidate) and generates score on each of the spoken English parameters as well as a combined score. It is implemented in the form of a web application so that it can be accessed through a web browser and doesn’t require any software to be installed at the client side. We describe how the individual parameters are assessed in Sensei using various speech processing techniques and the experiments conducted to evaluate these techniques. The performance is compared with assessment performed by human assessors. A correlation of 0.8 is obtained between overall score generated by Sensei and human assessors on a real life test dataset of 243 candidates which compares well with the corresponding human-to-human correlation of 0.91.