A Dynamic Bayesian Network Approach to Location Prediction in Ubiquitous Computing Environments

@inproceedings{Lee2010ADB,
  title={A Dynamic Bayesian Network Approach to Location Prediction in Ubiquitous Computing Environments},
  author={Sunyoung Lee and Kun Chang Lee and Heeryon Cho},
  booktitle={International Conference on Advances in Information Technology},
  year={2010}
}
The ability to predict the future contexts of users significantly improves service quality and user satisfaction in ubiquitous computing environments. [] Key Result The evaluation result suggests that a dynamic Bayesian network model offers significant predictive power.

Contextual location prediction using spatio-temporal clustering

This study/paper aims to propose a methodology that predicts a user’s location on the basis of a user's mobility history, which uses contextual information that can be acquired easily and accurately with the help of common sensors such as GPS.

Next place prediction by understanding mobility patterns

Three combined models using least entropy, highest probability and ensemble are developed using dynamic Bayesian network (DBN) to solve next place prediction problem for mobility data.

Indoor-ALPS: an adaptive indoor location prediction system

Indoor-ALPS is presented, an Adaptive Indoor Location Prediction System that uses temporal-spatial features to create individual daily models for the prediction of when a user will leave their current location (transition time) and the next location she will transition to.

A novel multilayered context awareness technology for internetware evolution

This paper builds a three-layered architecture for Internetware to avoid disorderly context information transmission and utilizes the ontology model language OWL to formalize Internetware context, to form a unified understanding of context information in the whole Internetware system.

A Person-search System for an Assistive Robot

Experiments show that the HMM-based person-search system is effective at locating a target person considerably faster than an uninformed baseline approach.

Sentient destination prediction

This work evaluates an adapted ontological construct, which it calls context-specific cognitive frame (CSCF), in order to capture the entire experience of a user at a given moment, and shows that this method can be used to provide a flexible, more accurate and therefore more personalized user experience using the example of location prediction.

References

SHOWING 1-10 OF 19 REFERENCES

Predicting the location of mobile users: a machine learning approach

A spatial context model is proposed, which deals with the location prediction of mobile users and is used for the classification of the users' trajectories through Machine Learning (ML) algorithms.

Prediction of Indoor Movements Using Bayesian Networks

This paper investigates the efficiency of in-door next location prediction by comparing several prediction methods and shows that the Bayesian network predictor performs in the same accuracy range as the neural network and the state predictor.

Adaptive On-Device Location Recognition

This work constructs a conceptual framework for the tasks of learning important locations and predicting the next location, and gives algorithms for efficient approximation of the ideal concepts, and evaluates them experimentally with real data.

Location- and Context-Awareness, Third International Symposium, LoCA 2007, Oberpfaffenhofen, Germany, September 20-21, 2007, Proceedings

These proceedings contain the papers presented at the 2nd International Workshop on Location- and Context-Awareness in May of 2006, intended to present research aimed at sensing, inferring, and using location and context data in ways that help the user.

Discovery of activity patterns using topic models

Experimental results show the ability of the approach to model and recognize daily routines without user annotation to be able to be used in this work.

Discovering Activities to Recognize and Track in a Smart Environment

This paper introduces an automated approach to activity tracking that identifies frequent activities that naturally occur in an individual's routine and can then track the occurrence of regular activities to monitor functional health and to detect changes in anindividual's patterns and lifestyle.

Modelling situation awareness for Context-aware Decision Support

Detecting Individual Activities from Video in a Smart Home

The evaluation results of the Hybrid classifier for the recorded data sets show that the combination of generative and discriminative classification methods outperforms the individual methods when identifying unseen activities.

Predicting Sequences of User Actions

Characteristics of an idealized algorithm that, when applied to sequences of user actions, would allow a user interface to adapt over time to an individual’s pattern of use are proposed.

Recognizing independent and joint activities among multiple residents in smart environments

This paper looks at approaches to perform real-time recognition of Activities of Daily Living, and enhances other related research efforts to develop approaches that are effective when activities are interrupted and interleaved.