Journal of Information Processing Systems

Korea Information Processing Society (한국정보처리학회)
권호 표지
DOI QR코드

DOI QR Code

Stream-based Biomedical Classification Algorithms for Analyzing Biosignals

  • Fong, Simon (Department of Computer and Information Science, University of Macau) ;
  • Hang, Yang (Department of Computer and Information Science, University of Macau) ;
  • Mohammed, Sabah (Department of Computer Science, Lakehead University) ;
  • Fiaidhi, Jinan (Department of Computer Science, Lakehead University)
  • Received : 2011.11.17
  • Accepted : 2011.11.22
  • Published : 2011.12.31
Download PDF
⟨ Previous Next ⟩

Abstract

Classification in biomedical applications is an important task that predicts or classifies an outcome based on a given set of input variables such as diagnostic tests or the symptoms of a patient. Traditionally the classification algorithms would have to digest a stationary set of historical data in order to train up a decision-tree model and the learned model could then be used for testing new samples. However, a new breed of classification called stream-based classification can handle continuous data streams, which are ever evolving, unbound, and unstructured, for instance--biosignal live feeds. These emerging algorithms can potentially be used for real-time classification over biosignal data streams like EEG and ECG, etc. This paper presents a pioneer effort that studies the feasibility of classification algorithms for analyzing biosignals in the forms of infinite data streams. First, a performance comparison is made between traditional and stream-based classification. The results show that accuracy declines intermittently for traditional classification due to the requirement of model re-learning as new data arrives. Second, we show by a simulation that biosignal data streams can be processed with a satisfactory level of performance in terms of accuracy, memory requirement, and speed, by using a collection of stream-mining algorithms called Optimized Very Fast Decision Trees. The algorithms can effectively serve as a corner-stone technology for real-time classification in future biomedical applications.

Keywords

References

  1. S. Fong, H. Yang, "The Six Technical Gaps Between Intelligent Applications and Real-Time Data Mining: A Critical Review," Journal of Emerging Technologies in Web Intelligence (JETWI), Academy Publisher, ISSN 1798-0461, Vol.30, No.2, 2011, pp.63-73.
  2. Q. Fang, F. Sufi, I. Cosic, A Mobile Device Based ECG Analysis System, Data Mining in Medical and Biological Research, In-Tech, Vienna, Austria, 2008, pp.320-338.
  3. H. Hermens, V. Jones, "Extending Remote Patient Monitoring with Mobile Real Time Clinical Decision Support," Proc. of IEEE-EMBS Benelux Chapter Symposium, 2009, Enschede, The Netherlands, pp.50-53.
  4. M. Zwaag van der, E.L. Broek van den, J.H. Janssen, "Guidelines for biosignal driven HCI," Proc. of ACM CHI 2010 Workshop - Brain, Body, and Bytes: Physiological user interaction, 2010, Atlanta, GA, USA, pp.77-80.
  5. H.G. Lee, K.Y. Noh, K.H Ryu, "Mining Biosignal Data: Coronary Artery Disease Diagnosis Using Linear and Nonlinear Features of HRV," PAKDD 2007 Workshops, LNAI 4819, 2007, pp.218-228.
  6. J.C.Y. Chen, V.S.M. Tseng, An Integrated Bio-Signal Data Mining Mechanism with Applications on Asthma Monitoring and Prevention, [dissertation], MSc Thesis, National Cheng Kung University, Taiwan, 2007.
  7. P. Domingos, G. Hulten, "Mining high-speed data streams," Proc. of KDD 2000, New York, USA, 2000, pp.71-80.
  8. H. Yang, S. Fong, "An Experimental Comparison of Decision Trees in Traditional Data Mining and Data Stream Mining," The 6th International Conference on Advanced Information Management and Service (IMS 2010), 30 November-2 December, 2010, Seoul, Korea, pp.442-447.
  9. H. Yang, S. Fong, A. Ip, S. Mohammed, "Case-based and Stream-based Classification in Biomedical Application," The Eighth IASTED International Conference on Biomedical Engineering (Biomed 2011), 16-18 February 2011, Innsbruck, Austria, pp.207-214.
  10. H. Yang, S. Fong, "Optimized Very Fast Decision Tree with Balanced Classification Accuracy and Compact Tree Size", Proc. of the 3rd International Conference on Data Mining and Intelligent Information Technology Applications (ICMIA2011), IEEE Press, 24-26 October, 2011.

Cited by

  1. Incremental Optimization Mechanism for Constructing a Decision Tree in Data Stream Mining vol.2013, 2013, https://doi.org/10.1155/2013/580397
  2. Hierarchical Aggregation of Uncertain Sensor Data for M2M Wireless Sensor Network Using Reinforcement Learning vol.10, pp.5, 2014, https://doi.org/10.1155/2014/535707
  3. Evaluation of Stream Mining Classifiers for Real-Time Clinical Decision Support System: A Case Study of Blood Glucose Prediction in Diabetes Therapy vol.2013, 2013, https://doi.org/10.1155/2013/274193
  4. Feature Selection in Life Science Classification: Metaheuristic Swarm Search vol.16, pp.4, 2014, https://doi.org/10.1109/MITP.2014.50
  5. A time series pre-processing methodology with statistical and spectral analysis for classifying non-stationary stochastic biosignals vol.72, pp.10, 2016, https://doi.org/10.1007/s11227-016-1635-9
  6. Underwater Sonar Signals Recognition by Incremental Data Stream Mining with Conflict Analysis vol.10, pp.5, 2014, https://doi.org/10.1155/2014/635834
  7. Strategies for data stream mining method applied in anomaly detection pp.1573-7543, 2018, https://doi.org/10.1007/s10586-018-2835-2