Anticipatory Mobile Computing

@article{Pejovi2015AnticipatoryMC,
  title={Anticipatory Mobile Computing},
  author={Veljko Pejovi{\'c} and Mirco Musolesi},
  journal={ACM Computing Surveys (CSUR)},
  year={2015},
  volume={47},
  pages={1 - 29}
}
Today’s mobile phones are far from the mere communication devices they were 10 years ago. Equipped with sophisticated sensors and advanced computing hardware, phones can be used to infer users’ location, activity, social setting, and more. As devices become increasingly intelligent, their capabilities evolve beyond inferring context to predicting it, and then reasoning and acting upon the predicted context. This article provides an overview of the current state of the art in mobile sensing and… 

Figures and Tables from this paper

FutureWare: Designing a Middleware for Anticipatory Mobile Computing
TLDR
This paper implements FutureWare as an Android library, and through a scenario-based testing and a demo app it is shown that it represents an efficient way of supporting anticipatory applications, reducing the necessary coding effort by two orders of magnitude.
Lightweight Modeling of User Context Combining Physical and Virtual Sensor Data
TLDR
This work presents a framework developed to collect datasets containing heterogeneous sensing data derived from personal mobile devices and proposes a lightweight approach to model the user context able to efficiently perform the entire reasoning process on the user mobile device.
Recurrent Neural Networks for Predicting Mobile Device State
TLDR
Smartphones have become a key part of everyday life as an essential tool for their users and, at the same time, helping to ease the use of smartphones’ services, and several domains leverage on the prediction of mobile devices’ states to improve the outcome.
An Extensible Pervasive Platform for Large-Scale Anticipatory Mobile Computing
TLDR
This paper presents architectural concepts and a reference implementation of a distributed platform acting as base frame for various anticipatory mobile applications to provide cooperative personal assistants and demonstrates that the proof of concept prototype enables fast and time-saving development of various cooperating intelligent assistants through a hierarchical modular approach.
Interruptibility prediction for ubiquitous systems: conventions and new directions from a growing field
TLDR
A meta-analysis of this area is presented, decomposing and comparing historical and recent works that seek to understand and predict how users will perceive and respond to interruptions to identify research gaps, questions and opportunities that characterise this important emerging field for pervasive technology.
HCFContext: Smartphone Context Inference via Sequential History-based Collaborative Filtering
TLDR
Two stochastic models based on the theory of Hidden Markov Models to obtain mobile context are proposed—personalized model (HPContext) and collaborative filtering model (HCFContext), which predicts the current context using sequential history of the user’s past context observations.
Big Mobile Data Mining: Good or Evil?
TLDR
This article aims to add elements to this ongoing debate about big mobile data mining technologies good or evil.
Urban Mobility Sensing Analysis through a Layered Sensing Approach
TLDR
This study investigated the challenge of analysis of heterogeneous data from ubiquitous and pervasive applications using an approach based on layers of sensing and showed a phenomenon of behavior transition within a specific temperature range for a group of cities studied in this paper.
Opportunistic sensing platforms to interpret human behaviour
TLDR
This work showed that mobile devices are able to accurately detect social interactions and further social and trust relationships among people, despite the noise induced in real-world situations.
...
...

References

SHOWING 1-10 OF 189 REFERENCES
A survey of mobile phone sensing
TLDR
This article surveys existing mobile phone sensing algorithms, applications, and systems, and discusses the emerging sensing paradigms, and formulates an architectural framework for discussing a number of the open issues and challenges emerging in the new area ofMobile phone sensing research.
Darwin phones: the evolution of sensing and inference on mobile phones
TLDR
Darwin is the first system that applies distributed machine learning techniques and collaborative inference concepts to mobile phones and it is demonstrated that Darwin improves the reliability and scalability of the proof-of-concept speaker recognition application without additional burden to users.
Using context-aware computing to reduce the perceived burden of interruptions from mobile devices
TLDR
A context-aware mobile computing device was developed that automatically detects postural and ambulatory activity transitions in real time using wireless accelerometers and was used to experimentally measure the receptivity to interruptions delivered at activity transitions relative to those delivered at random times, suggesting a viable strategy forcontext-aware message delivery in sensor-enabled mobile computing devices.
Pogo, a Middleware for Mobile Phone Sensing
TLDR
It is argued that a research infrastructure in the form of a large-scale mobile phone testbed is required to unlock the potential of this new technology and a pragmatic middleware framework is provided that is easy to use and features fine-grained user-level control to guard the privacy of the volunteer smart-phone users.
SenSay: a context-aware mobile phone
TLDR
Results from the threshold analyses show a clear delineation can be made among several user states by examining sensor data trends.
A Predictive Protocol for Mobile Context Updates with Hard Energy Constraints
TLDR
This work proposes a novel protocol that maximizes the context accuracy perceived by a remote consumer while guaranteeing that the consumed energy stays under a given limit, and applies it to a real-world trace of user context.
SoundSense: scalable sound sensing for people-centric applications on mobile phones
TLDR
This paper proposes SoundSense, a scalable framework for modeling sound events on mobile phones that represents the first general purpose sound sensing system specifically designed to work on resource limited phones and demonstrates that SoundSense is capable of recognizing meaningful sound events that occur in users' everyday lives.
The Rise of People-Centric Sensing
TLDR
In the MetroSense Project's vision of people-centric sensing, users are the key architectural system component, enabling a host of new application areas such as personal, public, and social sensing.
Context-aware mobile computing: learning context- dependent personal preferences from a wearable sensor array
TLDR
A wearable system which can learn context-dependent personal preferences by identifying individual user states and observing how the user interacts with the system in these states is designed, implemented, and evaluated.
MyExperience: a system for in situ tracing and capturing of user feedback on mobile phones
TLDR
This paper presents MyExperience, a system for capturing both objective and subjective in situ data on mobile computing activities, and presents several case studies of field deployments on people's personal phones to demonstrate how MyExperience can be used effectively to understand how people use and experience mobile technology.
...
...