Earticle

초록

영어

Breathing is a crucial human process that requires easy and accurate monitoring. There are several available breathing monitoring methods which are based on strapping subjects with special sensors for monitoring their breathing rate. The results of these methods have been acceptable but connecting people with such equipment is awkward, especially in the case of monitoring the breathing of infants who have tiny and sensitive bodies. Therefore, providing a noncontact method is a good alternative. Thermal imaging is one of the latest non-contact passive techniques that are used for monitoring and controlling different human processes, including breathing. In this paper, a thermal image feature extraction method with neural network based classification system is developed to be used as part of a breathing monitoring system. The classification is based on matching the entries of mixed breathing images, either breath-in or breath-out images, with their desired values. The extracted breathing image features are used as entries for the neural network classifier. The neural network based model has produced promising classification results. Additionally, it has been possible to calculate the breathing rate of each subject from the classification results.

목차

Abstract
 1. Introduction
 2. Background
  2.1. Thermal Imaging
  2.2. Multi-Layer Perceptron (MLP) Neural Network
 3. Proposed Breath Monitoring System
 4. Experiments and Results
  4.1. Experiments Setup and Features Extraction
  4.2. MLP Classification Results
  4.3. Calculating Breathing Rate
 5. Conclusion and Future Work
 Acknowledgements
 References

키워드

저자

• Fida’ Al-Obaisi [ The Department of Engineering and Mathematics, Sheffield Hallam University, UK ]
• Ja’far Alqatawna [ King Abdulla II School for Information Technology, The University of Jordan, Amman, Jordan ]
• Hossam Faris [ King Abdulla II School for Information Technology, The University of Jordan, Amman, Jordan ]
• Ali Rodan [ King Abdulla II School for Information Technology, The University of Jordan, Amman, Jordan ]
• Omar Al-Kadi [ King Abdulla II School for Information Technology, The University of Jordan, Amman, Jordan ]

참고문헌

발행기관

간행물

표지보기 관심저널 등록

• 간행물명

  International Journal of Control and Automation

• 간기

  월간

• pISSN

  2005-4297

• 수록기간

  2008~2016

• 십진분류

  KDC 505 DDC 605