Sensor Integration and Context Detection in Intelligent Systems

Abstract

Sensor data integration into a more information-rich structure that reflects both the system state of and the state of its environment i.e. context information is a subject of the intensive study in military applications. Endowing an object with the ability of grasping context information is one of the prior prerequisite of its autonomous operability. An autonomously operating system, be it a terrestrial mobile machine or UAV, is required to respond to instantaneous incentives coming form the surrounding environment. To this end the system needs to handle wide range of unexpected contexts. In particular the system should be able to distinguish between common (normal) and unusual (abnormal) contexts. The distinguished contexts should be then classified with respect to their criticality. To perform these tasks, the system functionality must be organized into an appropriate architecture, i.e. a set of organizing principles and core components that are used to build the basis for the system. The first part of the paper summarizes both features of intelligent systems and current approaches to the sensor integration. The aim is to imbue the intelligent system with the ability to acquire the context. Within the second part the topic is narrowed and focused on the results obtained by the originally developed fusing and classification algorithm of detection and classification of abnormal behavioural contexts. The results obtained were verified by simulation as well as by experimenting with a walking machine.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
May 01, 2005
Accession Number
ADA472239

Entities

People

  • Anton Vitko
  • Dusan Kameniar
  • Jurisica Ladislav
  • Michal Savel

Organizations

  • Slovak University of Technology in Bratislava

Tags

Communities of Interest

  • Energy and Power Technologies
  • Materials and Manufacturing Processes
  • Sensors

DTIC Thesaurus Topics

  • Abstracts
  • Algorithms
  • Classification
  • Collision Avoidance
  • Computer Programs
  • Detection
  • Detectors
  • Environment
  • Fuzzy Logic
  • Fuzzy Sets
  • Information Science
  • Information Systems
  • Intelligent Systems
  • Machine Learning
  • Mechanical Engineering
  • Neural Networks
  • Simulations

Fields of Study

  • Computer science

Readers

  • Distributed Systems and Data Platform Development
  • Robotics and Automation.
  • Theoretical Analysis.