Conference Paper

Hardware-software analysis of pole model features.

DOI: 10.1109/CCECE.2011.6030671 Conference: Proceedings of the 24th Canadian Conference on Electrical and Computer Engineering, CCECE 2011, Niagara Falls, Ontario, Canada, 8-11 May, 2011
Source: DBLP

ABSTRACT In real time applications or portable devices, software implementation is not enough by itself to evaluate a signal feature analysis technique and a hardware implementation needs to be considered. The selection of the right signal feature analysis technique for an application depends on the algorithmic (software) performance, and also on the hardware efficiency of that technique. However, there are not enough studies exist in the evaluation of the pole modeling feature analysis technique from the hardware/software implementation aspects. The objective of this paper is to investigate both the hardware and software perspectives of pole modeling as a promising signal feature analysis method. The computational complexity is analyzed in detail and an estimation for the FPGA area usage is proposed for pole modeling. This paper also investigates the software performance of pole modeling by performing an audio classification in MATLAB.

0 Bookmarks
 · 
41 Views
  • [Show abstract] [Hide abstract]
    ABSTRACT: The paper reports some results with phonocardiogram pattern classification. Linear prediction analysis was applied to extract the spectral pattern from phonocardiogram signals, a relatively new technique. In this examination, 29 design samples are classified correctly, except for three samples; and 19 test samples correctly, except for five samples. The characteristics for each class are well extracted and the results of the classifications are good. The efficiency of the spectral features for phonocardiogram classification has been confirmed experimentally. Der Aufsatz beschreibt einige durch Phonokardiogrammbildklassifizierung erzielte Resultate. Die Linearvoraussageanalyse wurde dazu verwendet, Spektralbilder aus Phonokardiogrammsignalen zu entwickeln, — ein verhältnismäßig neues Verfahren. Bei dieser Unersuchung wurden 29 Konstruktionsmuster mit Ausnahme von drei Mustern und 19 Testmuster mit Ausnahme von fünf Mustern korrekt klassifiziert. Die Merkmale jeder Klasse werden gut herausgebracht, und die Resultate der Klassifizierungen sind gut. Die Zweckmäßigkeit der Spektralmerkmale für die Phonokardiogrammklassifizierung ist experimentell bestätigt worden. Cet article fait état des résultats du classement des types de phonocardiogammes. Des techniques d'analyse et de prédiction linéaires ont été appliquées pour établir les courbes spectrales des signaux de phonocardiogrammes; il s'agit d'une technique relativement nouvelle. Au cours de cette expérience, 29 malades ont été classés correctement, à l'exception de 3; et 19 autres ont été calssés correctement, à l'exception de 5. Les caractéristiques de chaque classe ont bien été isolées et les résultats du classement sont bons. L'efficacité d'un classement spectral des phonocardiogrammes a été confirmée expérimentalement.
    Medical & Biological Engineering & Computing 08/1977; 15(4):407-12. · 1.79 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: We have been investigating analysis of knee joint vibration or vibroarthrographic (VAG) signals as a potential tool for noninvasive diagnosis and monitoring of cartilage pathology. In this paper, we present a comprehensive comparative study of different parametric representations of VAG signals. Dominant poles and cepstral coefficients were derived from autoregressive models of adaptively segmented VAG signals. Signal features and a few clinical features were used as feature vectors in pattern classification experiments based on logistic regression analysis and the leave-one-out method. The results using 51 normal and 39 abnormal signals indicated the superior performance of cepstral coefficients in VAG signal classification with an accuracy rate of 75.6%. With 51 normal and 20 abnormal signals limited to chondromalacia patella, cepstral coefficients again gave the highest accuracy rate of 85.9%.
    IEEE Transactions on Biomedical Engineering 12/1997; 44(11):1068-74. · 2.35 Impact Factor
  • [Show abstract] [Hide abstract]
    ABSTRACT: This paper presents a novel approach for classification of audio signals for a noise free hearing aid system. Due to the large number of people who suffer from hearing problems, the impact of developing such a system is significant. Using the proposed classification tool, we are able to discriminate the environmental noise from speech, and then prevent the noise signals from being magnified by the hearing aid. A set of features is extracted in the time-frequency domain due to the non-stationary nature of the signals. Then a novel classification method is applied, which is based on the self organizing tree maps clustering algorithm followed by a fuzzy labeling of the clusters. The result show an accuracy of 96% for separating the human voice from the environmental noise.
    Science and Technology for Humanity (TIC-STH), 2009 IEEE Toronto International Conference; 10/2009