A systematic approach to embedded biomedical decision making

An embedded decision making is a key feature for many biomedical systems. In most cases human life directly depends on correct decisions made by these systems, therefore they have to work reliably. This paper describes how we applied systems engineering principles to design a high performance embedded classification system in a systematic and well structured way. We introduce the structured design approach by discussing requirements capturing, specifications refinement, implementation and testing. Thereby, we follow systems engineering principles and execute each of these processes as formal as possible. The requirements, which motivate the system design, describe an automated decision making system for diagnostic support. These requirements are refined into the implementation of a support vector machine (SVM) algorithm which enables us to integrate automated decision making in embedded systems. With a formal model we establish functionality, stability and reliability of the system. Furthermore, we investigated different parallel processing configurations of this computationally complex algorithm. We found that, by adding SVM processes, an almost linear speedup is possible. Once we established these system properties, we translated the formal model into an implementation. The resulting implementation was tested using XMOS processors with both normal and failure cases, to build up trust in the implementation. Finally, we demonstrated that our parallel implementation achieves the speedup, predicted by the formal model.

[1]  Yiqiang Chen,et al.  Building Sparse Multiple-Kernel SVM Classifiers , 2009, IEEE Transactions on Neural Networks.

[2]  A. W. Roscoe,et al.  Using CSP to Detect Errors in the TMN Protocol , 1997, IEEE Trans. Software Eng..

[3]  Brian W. Kernighan,et al.  The C Programming Language , 1978 .

[4]  Steve A. Schneider,et al.  Verifying Controlled Components , 2004, IFM.

[5]  U. Rajendra Acharya,et al.  Automatic Detection of Epileptic EEG Signals Using Higher Order cumulant Features , 2011, Int. J. Neural Syst..

[6]  U. Rajendra Acharya,et al.  Application of Recurrence Quantification Analysis for the Automated Identification of Epileptic EEG Signals , 2011, Int. J. Neural Syst..

[7]  Stanislaw Osowski,et al.  Support vector machine-based expert system for reliable heartbeat recognition , 2004, IEEE Transactions on Biomedical Engineering.

[8]  Patrick M. Lenders.  A Generalized Message-Passing Mechanism for Communicating Sequential Processes , 1988, IEEE Trans. Computers.

[9]  U. Rajendra Acharya,et al.  Algorithms for the Automated Detection of Diabetic Retinopathy Using Digital Fundus Images: A Review , 2012, Journal of Medical Systems.

[10]  U. Rajendra Acharya,et al.  Automatic Identification of Epileptic and Background EEG Signals Using Frequency Domain Parameters , 2010, Int. J. Neural Syst..

[11]  C. A. R. Hoare,et al.  Communicating sequential processes , 1978, CACM.

[12]  Sol M. Shatz,et al.  Post-Failure Reconfiguration of CSP Programs , 1985, IEEE Transactions on Software Engineering.

[13]  Elif Derya Übeyli,et al.  Multiclass Support Vector Machines for EEG-Signals Classification , 2007, IEEE Transactions on Information Technology in Biomedicine.

[14]  Giles M. Foody,et al.  Feature Selection for Classification of Hyperspectral Data by SVM , 2010, IEEE Transactions on Geoscience and Remote Sensing.

[15]  Andrew William Roscoe,et al.  The Theory and Practice of Concurrency , 1997 .

[16]  Pedro Larrañaga,et al.  Detecting reliable gene interactions by a hierarchy of Bayesian network classifiers , 2008, Comput. Methods Programs Biomed..

[17]  U. Rajendra Acharya,et al.  Systems engineering principles for the design of biomedical signal processing systems , 2011, Comput. Methods Programs Biomed..

[18]  U. Acharya,et al.  Automated Diagnosis of Oral Cancer Using Higher Order Spectra Features and Local Binary Pattern: A Comparative Study , 2011, Technology in cancer research & treatment.

[19]  C.Y.R. Cheng,et al.  Vector and multithread computation of silencer performance prediction on a dual-processor PC workstation , 2002 .

[20]  Tharam S. Dillon,et al.  Software Complexity and Its Impact on Software Reliability , 1988, IEEE Trans. Software Eng..

[21]  Vladimir N. Vapnik,et al.  The Nature of Statistical Learning Theory , 2000, Statistics for Engineering and Information Science.

[22]  Davide Anguita,et al.  Improved neural network for SVM learning , 2002, IEEE Trans. Neural Networks.

[23]  Bjarne Stroustrup,et al.  C++ Programming Language , 1986, IEEE Softw..

[24]  U. Rajendra Acharya,et al.  Automated Diagnosis of Glaucoma Using Texture and Higher Order Spectra Features , 2011, IEEE Transactions on Information Technology in Biomedicine.

[25]  U. Rajendra Acharya,et al.  Author's Personal Copy Biomedical Signal Processing and Control Automated Diagnosis of Epileptic Eeg Using Entropies , 2022 .

[26]  David Taniar,et al.  Performance evaluation of the object-relational transformation methodology , 2001, Data Knowl. Eng..

[27]  Manoj Franklin,et al.  A general compiler framework for speculative multithreaded processors , 2004, IEEE Transactions on Parallel and Distributed Systems.

[28]  Nello Cristianini,et al.  An Introduction to Support Vector Machines and Other Kernel-based Learning Methods , 2000 .

[29]  Adnan M. Alattar,et al.  > REPLACE THIS LINE WITH YOUR PAPER IDENTIFICATION NUMBER (DOUBLE-CLICK HERE TO EDIT) < Reversible Watermark Using the Difference Expansion of A Generalized Integer Transform , 2022 .

[30]  U. Rajendra Acharya,et al.  Application of Higher Order Spectra for the Identification of Diabetes Retinopathy Stages , 2008, Journal of Medical Systems.

[31]  Farid Melgani,et al.  Toward an Optimal SVM Classification System for Hyperspectral Remote Sensing Images , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[32]  T. Tamura,et al.  An integrated diabetic index using heart rate variability signal features for diagnosis of diabetes , 2013, Computer methods in biomechanics and biomedical engineering.

[33]  Nello Cristianini,et al.  An introduction to Support Vector Machines , 2000 .

[34]  Dianhui Wang,et al.  Data mining for building neural protein sequence classification systems with improved performance , 2003, Proceedings of the International Joint Conference on Neural Networks, 2003..

[35]  A. Seidl,et al.  Mathematical implementation of segregation model for two-dimensional process simulation , 1983, IEEE Transactions on Electron Devices.