We have developed a near-real-time computer system that can locate and track a subject's head, and then recognize the person by comparing characteristics of the face to those of known individuals. The computational approach taken in this system is motivated by both physiology and information theory, as well as by the practical requirements of near-real-time performance and accuracy. Our approach treats the face recognition problem as an intrinsically two-dimensional (2-D) recognition problem rather than requiring recovery of three-dimensional geometry, taking advantage of the fact that faces are normally upright and thus may be described by a small set of 2-D characteristic views. The system functions by projecting face images onto a feature space that spans the significant variations among known face images. The significant features are known as "eigenfaces," because they are the eigenvectors (principal components) of the set of faces; they do not necessarily correspond to features such as eyes, ears, and noses. The projection operation characterizes an individual face by a weighted sum of the eigenface features, and so to recognize a particular face it is necessary only to compare these weights to those of known individuals. Some particular advantages of our approach are that it provides for the ability to learn and later recognize new faces in an unsupervised manner, and that it is easy to implement using a neural network architecture.

Smart-phones are becoming our constant companions , they are with us all of the time, being used for calling, web surfing, apps, music listening, TV viewing, social networking, buying, gaming, and a myriad of other uses. Smart-phones are a technology that knows us much better than most of us could imagine. Based on our usage and the fact that we are never far away from our smart phones, they know where we go, who we interact with, what information we consume, and with a little clever software, they can know what we are doing and even why we are doing it. They are beginning to know us better than we know ourselves. In this work we present SenseSeer a generic mobile-cloud-based mobile Lifelogging framework. This framework supports customisable analytic services for sensing the person, understanding the semantics of life activities and the easy deployment of analytic tools and novel interfaces. At present, SenseSeer supports services in many domains, such as personal health monitoring, location tracking, lifestyle analysis and tourism focused applications. This work demonstrate the design principles of SenseSeer and three of its services: My Health, My Location and My Social Activity.

Data collected from mobile phones have the potential to provide insight into the relational dynamics of individuals. This paper compares observational data from mobile phones with standard self-report survey data. We find that the information from these two data sources is overlapping but distinct. For example, selfreports of physical proximity deviate from mobile phone records depending on the recency and salience of the interactions. We also demonstrate that it is possible to accurately infer 95% of friendships based on the observational data alone, where friend dyads demonstrate distinctive temporal and spatial patterns in their physical proximity and calling patterns. These behavioral patterns, in turn, allow the prediction of individual-level outcomes such as job satisfaction.engineering-social systems ͉ relational inference ͉ social network analysis ͉ reality mining ͉ relational scripts T he field devoted to the study of the system of human interactions-social network analysis-has been constrained in accuracy, breadth, and depth because of its reliance on self-report data. Social network studies relying on self-report relational data typically involve both limited numbers of people and a limited number of time points (usually one). As a result, social network analysis has generally been limited to examining small, well-bounded populations, involving a small number of snapshots of interaction patterns (1). Although important work has been done over the last 30 years to analyze the relationship between self-reported and observed behavior, much of the social network literature is written as if self-report data are behavioral data.There is, however, a small but emerging thread of research examining social communication patterns based on directly observable data such as e-mail (2, 3) and call logs (4,5). Here, we demonstrate the power of collecting not only communication information but also location and proximity data from mobile phones over an extended period, and compare the resulting behavioral social network to self-reported relationships from the same group. We show that pairs of individuals that report themselves as friends demonstrate distinctive behavioral signatures as measured only by the mobile phone data. Further, these purely objective measures of behavior show powerful relationships with key outcomes of interest at the individual levelnotably, satisfaction.The Reality Mining study followed 94 subjects using mobile phones preinstalled with several pieces of software that recorded and sent the researcher data about call logs, Bluetooth devices in proximity of approximately five meters, cell tower IDs, application usage, and phone status (6, 7). Subjects were observed using these measurements over the course of nine months and included students and faculty from two programs within a major research institution. We also collected self-report relational data from each individual, where subjects were asked about their proximity to, and friendship with, others. Subjects were also asked about their satisf...

No abstract

No abstract