Bo Begole

Activity-based serendipitous recommendations with the Magitti mobile leisure guide

This paper presents a context-aware mobile recommender system, codenamed Magitti. Magitti is unique in that it infers user activity from context and patterns of user behavior and, without its user having to issue a query, automatically generates recommendations for content matching. Extensive field studies of leisure time practices in an urban setting (Tokyo) motivated the idea, shaped the details of its design and provided data describing typical behavior patterns. The paper describes the fieldwork, user interface, system components and functionality, and an evaluation of the Magitti prototype.

Which Way Am I Facing: Inferring Horizontal Device Orientation from an Accelerometer Signal

We present a method to infer the orientation of mobile device carried in a pocket from the acceleration signal acquired when the user is walking. Whereas previous work has shown how to determine the the orientation in the vertical plane (angle towards earth gravity), we demonstrate how to compute the orientation within the horizontal plane. To validate our method we compare the output of our method with GPS heading information when walking in a straight line. On a total of 16 different orientations and traces we have a mean difference of 5 degrees with 2.5 degrees standard deviation.

Collaborative Filtering Is Not Enough? Experiments with a Mixed-Model Recommender for Leisure Activities

Collaborative filtering (CF) is at the heart of most successful recommender systems nowadays. While this technique often provides useful recommendations, conventional systems also ignore data that could potentially be used to refine and adjust recommendations based on a users context and preferences. The problem is particularly acute with mobile systems where information delivery often needs to be contextualized. Past research has also shown that combining CF with other techniques often improves the quality of recommendations. In this paper, we present results from an experiment assessing user satisfaction with recommendations for leisure activities that are obtained from different combinations of these techniques. We show that the most effective mix is highly dependent on a users familiarity with a geographical area and discuss the implications of our findings for future research.

Real-time clothes comparison based on multi-view vision

In this paper, we present a clothing recognition system that augments clothes recommendation and fashion exploration using the intelligent multi-view vision technology of the responsive mirror, an implicitly controlled human-computer interaction system for clothes fitting rooms. The responsive mirror provides shoppers with real-time ldquoselfrdquo and ldquosocialrdquo clothes comparisons. The system recommends clothing that is ldquosimilarrdquo and ldquodifferentrdquo than the clothing that the person is trying on in the mirror. The goal of the research in this paper is to create a recommendation system that uses a definition of ldquosimilarrdquo and ldquodifferentrdquo that matches human perception. We address the social nature of the recognition problem by conducting a user study to identify the salient clothes factors that people use to determine clothes similarity. We describe the computer vision and machine learning techniques employed to recognize the factors that human eyes perceive in term of clothing similarity from frontal-view outfit images. We describe the key components of the motion-tracking and clothes-recognition systems and evaluate their performance by user study and experiments on a simulated clothes fitting image dataset. The approach and results presented here will benefit designers and developers of similar applications in the future.

Scalable architecture for context-aware activity-detecting mobile recommendation systems

One of the main challenges in building multi-user mobile information systems for real-world deployment lies in the development of scalable systems. Recent work on scaling infrastructure for conventional web services using distributed approaches can be applied to the mobile space, but limitations inherent to mobile devices (computational power, battery life) and their communication infrastructure (availability and quality of network connectivity) challenge system designers to carefully design and optimize their software architectures. Additionally, notions of mobility and position in space, unique to mobile systems, provide interesting directions for the segmentation and scalability of mobile information systems. In this paper we describe the implementation of a mobile recommender system for leisure activities, codenamed Magitti, which was built for commercial deployment under stringent scalability requirements. We present concrete solutions addressing these scalability challenges, with the goal of informing the design of future mobile multi-user systems.

Activity-Based Advertising

This chapter discusses Activity-based Advertising, an approach to more accurately target advertisements by inferring a consumer’s activities. This chapter begins with some of the important characteristics of advertising, and explains the incentives held by consumers and marketers. We explain why consumer and advertiser interests are not necessarily at odds, and briefly survey some existing targeting technologies that benefit both. We then describe the vision and benefits of activity-based advertising, and describe how it can advance targeting technologies even further. We finish with a methodology for evaluating activity-based advertising technologies, and present some initial results of activity-based advertising’s potential.

Using temporal patterns (t-patterns) to derive stress factors of routine tasks

We describe the use of a statistical technique called T-pattern analysis to derive and characterize the routineness of tasks. T-patterns provide significant advantages over traditional sequence analyses by incorporating time. A T-pattern is characterized by a significant time window (critical interval) that describes the duration of this pattern. Our analysis is based on data collected from shadowing 10 knowledge workers over a total of 29 entire work days. We report on the statistics of detected T-patterns and derived correlations with participant perceptions of workload, autonomy, and productivity.

Inferring personality of online gamers by fusing multiple-view predictions

Reliable personality prediction can have direct impact on many adaptive systems, such as targeted advertising, interface personalization and content customization. We propose an algorithm to infer a users personality profile more reliably by fusing analytical predictions from multiple sources including behavioral traces, textual data, and social networking information. We applied and validated our approach using a real data set obtained from 1,040 World of Warcraft players. Besides behavioral and social networking information, we found that text analysis of character names yields the strongest personality cues.

Asynchronous reflections: theory and practice in the design of multimedia mirror systems

In this paper, we present a theoretical framing of the functions of a mirror by breaking the synchrony between the state of a reference object and its reflection. This framing provides a new conceptualization of the uses of reflections for various applications. We describe the fundamental technical components of such systems and illustrate the technical challenges in two different forms of electronic mirror systems for apparel shopping. The first example, the Responsive Mirror, is an intelligent video capture and access system for clothes shopping in physical stores that provides personalized asynchronous reflections of clothing items through an implicitly controlled human–computer interface. The Responsive Mirror employs computer vision and machine learning techniques to interpret the visual cues of the shopper’s behavior from cameras to then display two different reflections of the shopper on digital displays: (1) the shopper in previously worn clothing with matching pose and orientation and (2) other people in similar and dissimilar shirts with matching pose and orientation. The second example system is a Countertop Responsive Mirror that differs from the first in that the images do not respond to the real-time movement of the shopper but to frames in a recorded video so that the motion of the shopper in the different recordings are matched non-sequentially. These instantiations of the mirror systems in fitting room and jewelry shopping scenarios are described, focusing on the system architecture and the intelligent computer vision components. The effectiveness of Responsive Mirror is demonstrated by the user study. The paper contributes a conceptualization of reflection and examples of systems illustrating new applications in multimedia systems that break traditional reflective synchronies.

Ubiquitous meeting facilitator with playful real-time user interface

Effective group meetings are important for the productivity of corporations. But many meetings do not achieve their goals because some people are too shy to speak while others are too dominant. To avoid the cost and intrusiveness of human meeting facilitation and to increase self-awareness of conversation behaviors, various types of meeting facilitators have been developed over the past couple of years. We present a prototype that is unique because it captures both individual and group behaviors and provides real time playful feedback. The portable prototype includes a set of table-top microphones with an audio interface to a laptop PC, where audio data are processed and an avatar-based UI displays the shared state of individual and group behaviors during a meeting. The interface reveals not only level of participation, but also several other meaningful but harder to detect behaviors such as turn taking, interruptions, and group laughter. The presentations design is deliberately playful to keep participants monitor, self-estimate and improve their meeting behavior.