The detection of murmurs from phonocardiographic recordings is an interesting problem that has be... more The detection of murmurs from phonocardiographic recordings is an interesting problem that has been addressed before using a wide variety of techniques. In this context, this article explores the capabilities of an enhanced time–frequency representation (TFR) based on a time-varying autoregressive model. The parametric technique is used to compute the TFR of the signal, which serves as a complete characterization of the process. Parametric TFRs contain a large quantity of data, including redundant and irrelevant information. In order to extract the most relevant features from TFRs, two specific approaches for dimensionality reduction are presented: feature extraction by linear decomposition, and tiling partition of the t–f plane. In the first approach, the feature extraction was carried out by means of eigenplane-based PCA and PLS techniques. Likewise, a regular partition and a refined Quadtree partition of the t–f plane were tested for the tiled-TFR approach. As a result, the feature extraction methodology presented, which searches for the most relevant information immersed on the TFR, has demonstrated to be very effective. The features extracted were used to feed a simple k-nn classifier. The experiments were carried out using 45 phonocardiographic recordings (26 normal and 19 records with murmurs), segmented to extract 548 representative individual beats. The results using these methods point out that better accuracy and flexibility can be accomplished to represent non-stationary PCG signals, showing evidences of improvement with respect to other approaches found in the literature. The best accuracy obtained was 99.06 ± 0.06%, evidencing high performance and stability. Because of its effectiveness and simplicity of implementation, the proposed methodology can be used as a simple diagnostic tool for primary health-care purposes.
This work presents a comparison of different approaches for the detection of murmurs from phonoca... more This work presents a comparison of different approaches for the detection of murmurs from phonocardiographic signals. Taking into account the variability of the phonocardiographic signals induced by valve disorders, three families of features were analyzed: (a) time-varying & time-frequency features; (b) perceptual; and (c) fractal features. With the aim of improving the performance of the system, the accuracy of the system was tested using several combinations of the aforementioned families of parameters. In the second stage, the main components extracted from each family were combined together with the goal of improving the accuracy of the system. The contribution of each family of features extracted was evaluated by means of a simple k-nearest neighbors classifier, showing that fractal features provide the best accuracy (97.17%), followed by time-varying & time-frequency (95.28%), and perceptual features (88.7%). However, an accuracy around 94% can be reached just by using the two main features of the fractal family; therefore, considering the difficulties related to the automatic intrabeat segmentation needed for spectral and perceptual features, this scheme becomes an interesting alternative. The conclusion is that fractal type features were the most robust family of parameters (in the sense of accuracy vs. computational load) for the automatic detection of murmurs. This work was carried out using a database that contains 164 phonocardiographic recordings (81 normal and 83 records with murmurs). The database was segmented to extract 360 representative individual beats (180 per class).
The detection of murmurs from phonocardio-graphic recordings is an interesting problem that has b... more The detection of murmurs from phonocardio-graphic recordings is an interesting problem that has been addressed before using a wide variety of techniques. In this context, this article explores the capabilities of an enhanced time–frequency representation (TFR) based on a time-varying autoregressive model. The parametric technique is used to compute the TFR of the signal, which serves as a complete characterization of the process. Parametric TFRs contain a large quantity of data, including redundant and irrelevant information. In order to extract the most relevant features from TFRs, two specific approaches for dimensionality reduction are presented: feature extraction by linear decomposition , and tiling partition of the t–f plane. In the first approach, the feature extraction was carried out by means of eigenplane-based PCA and PLS techniques. Likewise, a regular partition and a refined Quadtree partition of the t–f plane were tested for the tiled-TFR approach. As a result, the feature extraction methodology presented, which searches for the most relevant information immersed on the TFR, has demonstrated to be very effective. The features extracted were used to feed a simple k-nn classifier. The experiments were carried out using 45 phonocardiographic recordings (26 normal and 19 records with murmurs), segmented to extract 548 representative individual beats. The results using these methods point out that better accuracy and flexibility can be accomplished to represent non-stationary PCG signals, showing evidences of improvement with respect to other approaches found in the literature. The best accuracy obtained was 99.06 ± 0.06%, evidencing high performance and stability. Because of its effectiveness and simplicity of implementation , the proposed methodology can be used as a simple diagnostic tool for primary health-care purposes.
2011 IEEE International Symposium of Circuits and Systems (ISCAS), 2011
Nearly perfect reconstruction (N-PR) modified discrete Fourier Transform (MDFT) filter banks (FBs... more Nearly perfect reconstruction (N-PR) modified discrete Fourier Transform (MDFT) filter banks (FBs) have been widely applied to signal coding and their use for data transmission in multicarrier communications has also been addressed in the literature. However, comparison and assessment of the performance of alternative designs for uniform N-PR MDFT-based systems is hampered by the lack of explicit formulas for easily
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2008
Atrial fibrillation (AF) is a common cardiac arrythmia that is usually developed for elder people... more Atrial fibrillation (AF) is a common cardiac arrythmia that is usually developed for elder people with aging. AF may result in complications such as chest pain or even heart failure in later stage. Based on the characteristics of surface ECG, AF can be detected by several methods. A particular investigation on the fibrillatory waveform reveals the inherent structure of AF signals. As opposed to traditional frequency domain methods, we utilize the stationary wavelet transform to extract the information from ECG signal which differentiates AF and non-AF cases based on some feature extraction and selection processes. A linear classifier is then designed for computational efficiency. The proposed method eliminates the need for QRST cancellation step which is required for frequency domain methods and provides a more systematic approach for AF detection. Extensive experiments are tested on signals from the MIT-BIH Atrial Fibrillation Database to show the superior performance of the propos...
2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2011
The aim of electrocardiogram (ECG) compression is to achieve as much compression as possible whil... more The aim of electrocardiogram (ECG) compression is to achieve as much compression as possible while the significant information is preserved in the reconstructed signal. Lossy thresholding-based compressors have shown good performance needing low computational resources. In this work, two compression schemes that include nearly perfect reconstruction cosine modulated filter banks for the signal decomposition are proposed. They are evaluated for highly reliable applications, where the reconstructed signal must be very similar to the original. The whole MIT-BIH Arrhythmia Database and suitable metrics are used in the assessment, to obtain representative results. Results show that the proposed compressors yield better performance than discrete wavelet transform-based techniques, when high quality requirements are imposed.
2011 IEEE International Symposium of Circuits and Systems (ISCAS), 2011
ABSTRACT In this work, the design of filter bank multicarrier (FBMC) sytems using several kinds o... more ABSTRACT In this work, the design of filter bank multicarrier (FBMC) sytems using several kinds of Modified Discrete Fourier Transform (MDFT) filter banks is considered. Our attention is focused on Nearly Perfect Reconstruction (NPR) systems since an increase of selectivity and discrimination in each subchannel filter can provide better performance than the equivalent perfect reconstruction system. A new scheme is proposed with the main novelty of embedding an MDFT FBMC system into the standardized DFT-based multicarrier modulator (MCM). The new system also inserts a cyclic prefix into each transmitted symbol to facilitate the equalization task at the receiver. Finally, in order to illustrate the properties and capabilities of the proposed system, several simulation results are presented. They show that the proposed system can improve the standard DFT-based MCM. a zero-forcing or a minimum mean-squared error (MMSE) equalizer. Then, the design of the prototype filter from which all the transmitting and the receiving filter are obtained, is also addressed. Finally, we illustrate by means of computer simulations that the proposed system compares favorably to the standard DFT-based MCM in the presence of an AR narrow-band interference and over a frequency-selective fading channel. The rest of this work is organized as follows. In section II, we give a brief description of three kinds of modulation and two different block diagrams to implement MDFT FBMC sys- tems. In section III, the new proposed system is shown. Section IV deals with design techniques for obtaining prototype filters. We illustrate in section V, by means of several examples, the performance of the proposed system compared to conventional OFDM. Finally, we summarize our conclusions.
A procedure for obtaining tighter bounds on zero-input limit cycles is presented. The determined ... more A procedure for obtaining tighter bounds on zero-input limit cycles is presented. The determined new bounds are appli- cable to digital filters of arbitrary order described in state- space formulation and implemented with fixed-point arith- metic. In most filters, we obtain smaller bounds through this new algorithm easy to implement and to execute in a very short computer time. The
The detection of murmurs from phonocardiographic recordings is an interesting problem that has be... more The detection of murmurs from phonocardiographic recordings is an interesting problem that has been addressed before using a wide variety of techniques. In this context, this article explores the capabilities of an enhanced time–frequency representation (TFR) based on a time-varying autoregressive model. The parametric technique is used to compute the TFR of the signal, which serves as a complete characterization of the process. Parametric TFRs contain a large quantity of data, including redundant and irrelevant information. In order to extract the most relevant features from TFRs, two specific approaches for dimensionality reduction are presented: feature extraction by linear decomposition, and tiling partition of the t–f plane. In the first approach, the feature extraction was carried out by means of eigenplane-based PCA and PLS techniques. Likewise, a regular partition and a refined Quadtree partition of the t–f plane were tested for the tiled-TFR approach. As a result, the feature extraction methodology presented, which searches for the most relevant information immersed on the TFR, has demonstrated to be very effective. The features extracted were used to feed a simple k-nn classifier. The experiments were carried out using 45 phonocardiographic recordings (26 normal and 19 records with murmurs), segmented to extract 548 representative individual beats. The results using these methods point out that better accuracy and flexibility can be accomplished to represent non-stationary PCG signals, showing evidences of improvement with respect to other approaches found in the literature. The best accuracy obtained was 99.06 ± 0.06%, evidencing high performance and stability. Because of its effectiveness and simplicity of implementation, the proposed methodology can be used as a simple diagnostic tool for primary health-care purposes.
This work presents a comparison of different approaches for the detection of murmurs from phonoca... more This work presents a comparison of different approaches for the detection of murmurs from phonocardiographic signals. Taking into account the variability of the phonocardiographic signals induced by valve disorders, three families of features were analyzed: (a) time-varying & time-frequency features; (b) perceptual; and (c) fractal features. With the aim of improving the performance of the system, the accuracy of the system was tested using several combinations of the aforementioned families of parameters. In the second stage, the main components extracted from each family were combined together with the goal of improving the accuracy of the system. The contribution of each family of features extracted was evaluated by means of a simple k-nearest neighbors classifier, showing that fractal features provide the best accuracy (97.17%), followed by time-varying & time-frequency (95.28%), and perceptual features (88.7%). However, an accuracy around 94% can be reached just by using the two main features of the fractal family; therefore, considering the difficulties related to the automatic intrabeat segmentation needed for spectral and perceptual features, this scheme becomes an interesting alternative. The conclusion is that fractal type features were the most robust family of parameters (in the sense of accuracy vs. computational load) for the automatic detection of murmurs. This work was carried out using a database that contains 164 phonocardiographic recordings (81 normal and 83 records with murmurs). The database was segmented to extract 360 representative individual beats (180 per class).
The detection of murmurs from phonocardio-graphic recordings is an interesting problem that has b... more The detection of murmurs from phonocardio-graphic recordings is an interesting problem that has been addressed before using a wide variety of techniques. In this context, this article explores the capabilities of an enhanced time–frequency representation (TFR) based on a time-varying autoregressive model. The parametric technique is used to compute the TFR of the signal, which serves as a complete characterization of the process. Parametric TFRs contain a large quantity of data, including redundant and irrelevant information. In order to extract the most relevant features from TFRs, two specific approaches for dimensionality reduction are presented: feature extraction by linear decomposition , and tiling partition of the t–f plane. In the first approach, the feature extraction was carried out by means of eigenplane-based PCA and PLS techniques. Likewise, a regular partition and a refined Quadtree partition of the t–f plane were tested for the tiled-TFR approach. As a result, the feature extraction methodology presented, which searches for the most relevant information immersed on the TFR, has demonstrated to be very effective. The features extracted were used to feed a simple k-nn classifier. The experiments were carried out using 45 phonocardiographic recordings (26 normal and 19 records with murmurs), segmented to extract 548 representative individual beats. The results using these methods point out that better accuracy and flexibility can be accomplished to represent non-stationary PCG signals, showing evidences of improvement with respect to other approaches found in the literature. The best accuracy obtained was 99.06 ± 0.06%, evidencing high performance and stability. Because of its effectiveness and simplicity of implementation , the proposed methodology can be used as a simple diagnostic tool for primary health-care purposes.
2011 IEEE International Symposium of Circuits and Systems (ISCAS), 2011
Nearly perfect reconstruction (N-PR) modified discrete Fourier Transform (MDFT) filter banks (FBs... more Nearly perfect reconstruction (N-PR) modified discrete Fourier Transform (MDFT) filter banks (FBs) have been widely applied to signal coding and their use for data transmission in multicarrier communications has also been addressed in the literature. However, comparison and assessment of the performance of alternative designs for uniform N-PR MDFT-based systems is hampered by the lack of explicit formulas for easily
Conference proceedings : ... Annual International Conference of the IEEE Engineering in Medicine and Biology Society. IEEE Engineering in Medicine and Biology Society. Annual Conference, 2008
Atrial fibrillation (AF) is a common cardiac arrythmia that is usually developed for elder people... more Atrial fibrillation (AF) is a common cardiac arrythmia that is usually developed for elder people with aging. AF may result in complications such as chest pain or even heart failure in later stage. Based on the characteristics of surface ECG, AF can be detected by several methods. A particular investigation on the fibrillatory waveform reveals the inherent structure of AF signals. As opposed to traditional frequency domain methods, we utilize the stationary wavelet transform to extract the information from ECG signal which differentiates AF and non-AF cases based on some feature extraction and selection processes. A linear classifier is then designed for computational efficiency. The proposed method eliminates the need for QRST cancellation step which is required for frequency domain methods and provides a more systematic approach for AF detection. Extensive experiments are tested on signals from the MIT-BIH Atrial Fibrillation Database to show the superior performance of the propos...
2011 Annual International Conference of the IEEE Engineering in Medicine and Biology Society, 2011
The aim of electrocardiogram (ECG) compression is to achieve as much compression as possible whil... more The aim of electrocardiogram (ECG) compression is to achieve as much compression as possible while the significant information is preserved in the reconstructed signal. Lossy thresholding-based compressors have shown good performance needing low computational resources. In this work, two compression schemes that include nearly perfect reconstruction cosine modulated filter banks for the signal decomposition are proposed. They are evaluated for highly reliable applications, where the reconstructed signal must be very similar to the original. The whole MIT-BIH Arrhythmia Database and suitable metrics are used in the assessment, to obtain representative results. Results show that the proposed compressors yield better performance than discrete wavelet transform-based techniques, when high quality requirements are imposed.
2011 IEEE International Symposium of Circuits and Systems (ISCAS), 2011
ABSTRACT In this work, the design of filter bank multicarrier (FBMC) sytems using several kinds o... more ABSTRACT In this work, the design of filter bank multicarrier (FBMC) sytems using several kinds of Modified Discrete Fourier Transform (MDFT) filter banks is considered. Our attention is focused on Nearly Perfect Reconstruction (NPR) systems since an increase of selectivity and discrimination in each subchannel filter can provide better performance than the equivalent perfect reconstruction system. A new scheme is proposed with the main novelty of embedding an MDFT FBMC system into the standardized DFT-based multicarrier modulator (MCM). The new system also inserts a cyclic prefix into each transmitted symbol to facilitate the equalization task at the receiver. Finally, in order to illustrate the properties and capabilities of the proposed system, several simulation results are presented. They show that the proposed system can improve the standard DFT-based MCM. a zero-forcing or a minimum mean-squared error (MMSE) equalizer. Then, the design of the prototype filter from which all the transmitting and the receiving filter are obtained, is also addressed. Finally, we illustrate by means of computer simulations that the proposed system compares favorably to the standard DFT-based MCM in the presence of an AR narrow-band interference and over a frequency-selective fading channel. The rest of this work is organized as follows. In section II, we give a brief description of three kinds of modulation and two different block diagrams to implement MDFT FBMC sys- tems. In section III, the new proposed system is shown. Section IV deals with design techniques for obtaining prototype filters. We illustrate in section V, by means of several examples, the performance of the proposed system compared to conventional OFDM. Finally, we summarize our conclusions.
A procedure for obtaining tighter bounds on zero-input limit cycles is presented. The determined ... more A procedure for obtaining tighter bounds on zero-input limit cycles is presented. The determined new bounds are appli- cable to digital filters of arbitrary order described in state- space formulation and implemented with fixed-point arith- metic. In most filters, we obtain smaller bounds through this new algorithm easy to implement and to execute in a very short computer time. The
Uploads