Welcome to the 3rd International Workshop on Physical Analytics (WPA) being held in Singapore on June 26, 2016. We are honored to serve as the chairs for this latest WPA edition that continues in the tradition of previous workshops in the series that were also co-located with MobiSys.
Broadly speaking, WPA is motivated by the observations that people spend a significant part of their daily lives performing a variety of activities in the physical world---travelling to places (including commuting to/from work using public or private transport), dwelling and engaging in various activities at various locations (e.g., exercising in the gym, eating at restaurants and food courts), interacting with various physical objects and artefacts (e.g., touching or picking up products at a retail store, or browsing through books and magazines at a library), being subject to various audiovisual stimuli (e.g., listening to announcements at transit hubs, watching advertisements on public displays or movies on TV) and interacting with other people (in groups, as part of crowds or one-on-one). These activities and interactions contain a wealth of information about user behavior, preferences, attitudes and interests, that, if harnessed, can benefit both users and consumer-facing businesses. While research has been underway in utilizing various sensing and analytics tools to capture and annotate such behavior (e.g., profile smoking episodes using wearable devices or monitor consumer reactions to advertising content via video analysis), the vast majority of such research focuses on exploring individual sensing techniques targeted at specific activities, and is scattered across various academic forums. The goal of this workshop series is to offer a unified forum to explore both (a) the technologies (current and emerging) that can enable unobtrusive capture of such individual and collective physical world behavior, and (b) the realworld commercial applications and services that leverage upon such understanding of physical world behavior. By bringing together researchers and practitioners from industry to have a continuing conversation on Physical Analytics, our goal is to help coalesce a research agenda for our community.
This year we are particularly honored to have Kyle Jamieson (Princeton University) giving the workshop keynote. We look forward to hearing Kyle's perspective on what new innovations in high-precision localization, and breakthroughs in wireless networking more generally, will mean for the physical analytics area.
Proceeding Downloads
MobiCamp: a Campus-wide Testbed for Studying Mobile Physical Activities
Ubiquitous WiFi infrastructure and smart phones offer a great opportunity to study physical activities. In this paper, we present MobiCamp, a large-scale testbed for studying mobility-related activities of residents on a campus. MobiCamp consists of ~2,...
MyDrive: Drive Behavior Analytics Method And Platform
In recent times, research on intelligent transportation and drive quality characterization has emerged to be an important area in the domain of intelligent vehicular telematics. The estimation of driving behavior quality and relative assessment of risky ...
AnnoTainted: Automating Physical Activity Ground Truth Collection Using Smartphones
In this work, we provide motivation for a zero-effort crowdsensing task: auto-annotated ground truth collection for physical activity recognition. Data obtained through Smartphones for classification of human activities is prone to discrepancies, which ...
Next Generation Physical Analytics for Digital Signage
Traditional digital signage analytics are based on a display-centric view of the world, reporting data on the content shown augmented with frequency of views and possibly classification of the audience demographics. What these systems are unable to ...
Small Scale Deployment of Seat Occupancy Detectors
In this paper, we present the results of a small-scale field deployment of our capacitance-based seat occupancy detector [1]. We deployed our sensors to 36 seats in our university library and measured the performance of our system over a period of 8 ...
Margdarshak: A Mobile Data Analytics based Commute Time Estimator cum Route Recommender
Waiting at traffic signals and getting stuck in traffic congestion eats a lot of time for a commuter in most of the metro cities of the world. Although there exists a large pool of navigation applications, but all of them turn out to be ineffective for ...
A Trained-once Crowd Counting Method Using Differential WiFi Channel State Information
This paper focuses on the problem of providing a rough count of the number of people in a room using passive WiFi Channel State Information (CSI) measurements taken by a single commodity receiver. The feature which mainly distinguishes our work from ...
Capturing Personal and Crowd Behavior with Wi-Fi Analytics
- Utku Gunay Acer,
- Geert Vanderhulst,
- Afra Masshadi,
- Aidan Boran,
- Claudio Forlivesi,
- Philipp M. Scholl,
- Fahim Kawsar
We present a solution for analysing crowds at events such as conferences where people have networking opportunities. Often, potential social relations go unexploited because no business cards were exchanged or we forget about interesting people we met ...
Fusing WiFi and Video Sensing for Accurate Group Detection in Indoor Spaces
Understanding one's group context in indoor spaces is useful for many reasons -- e.g., at a shopping mall, knowing a customer's group context can help in offering context-specific incentives, or estimating taxi demand for customers exiting the mall. ...
Index Terms
- Proceedings of the 3rd International on Workshop on Physical Analytics