Sridhar Sri Krishnan

Real-Time Classification of Forearm Electromyographic Signals Corresponding to User-Selected Intentional Movements for Multifunction Prosthesis Control

Pattern recognition-based multifunction prosthesis control strategies have largely been demonstrated with subsets of typical able-bodied hand movements. These movements are often unnatural to the amputee, necessitating significant user training and do not maximally exploit the potential of residual muscle activity. This paper presents a real-time electromyography (EMG) classifier of user-selected intentional movements rather than an imposed subset of standard movements. EMG signals were recorded from the forearm extensor and flexor muscles of seven able-bodied participants and one congenital amputee. Participants freely selected and labeled their own muscle contractions through a unique training protocol. Signals were parameterized by the natural logarithm of root mean square values, calculated within 0.2 s sliding and non overlapping windows. The feature space was segmented using fuzzy C-means clustering. With only 2 min of training data from each user, the classifier discriminated four different movements with an average accuracy of 92.7% plusmn 3.2%. This accuracy could be further increased with additional training data and improved user proficiency that comes with practice. The proposed method may facilitate the development of dynamic upper extremity prosthesis control strategies using arbitrary, user-preferred muscle contractions.

Phase Mapping of Cardiac Fibrillation

Received January 25, 2009; accepted October 6, 2009. Phase is a descriptor that tracks the progression of a defined region of myocardium through the action potential and has been demonstrated to be an effective parameter in analyzing spatiotemporal changes during fibrillation. In this review, the basic principles behind phase mapping are presented mainly in the context of ventricular fibrillation (VF), atrial fibrillation (AF), and fibrillation from experimental monolayer data. During fibrillation, the phase distribution changes over time, depending on activation patterns. Analyzing these phase patterns provides us insight into the fibrillatory dynamics and helps clarify the mechanisms of cardiac fibrillation and modulation by interventions. Winfree1 introduced the phase analysis to study cardiac fibrillation in the late eighties. This time-encoding technique deals with a scenario where the activation periods are the same over the surface being mapped. To deal with the scenario of varying activation period over the mapped surface (common in animal and human fibrillation models), Gray et al2,3⇓ introduced the state-space encoding concept from nonlinear dynamics. In analyzing spatiotemporal phase maps constructed from electric or optical mapping of the surface of heart during VF, points around which the phase progresses through a complete cycle from −π to +π are of great interest. At these points, the phase becomes indeterminate and the activation wave fronts hinge to these points and rotate around them in an organized fashion. These points in the phase map are called phase singularity (PS) points. Bray et al4 developed a procedure to locate PS points in a phase map. Nash et al5 used phase mapping to study the entire ventricular epicardium of human hearts with a sock containing 256 unipolar contact electrodes. The development of this phase mapping tool has led to better understanding of fibrillation dynamics as evidenced by the …

Time–Frequency Matrix Feature Extraction and Classification of Environmental Audio Signals

Audio feature extraction and classification are important tools for audio signal analysis in many applications, such as multimedia indexing and retrieval, and auditory scene analysis. However, due to the nonstationarities and discontinuities exist in these signals, their quantification and classification remains a formidable challenge. In this paper, we develop a new approach for audio feature extraction to effectively quantify these nonstationarities in an attempt to achieve high classification accuracy for environmental audio signals. Our approach consists of three stages: first we propose to construct the time-frequency matrix (TFM) of audio signals using matching-pursuit time-frequency distribution (MP-TFD) technique, and then apply the non-negative matrix decomposition (NMF) technique to decompose the TFM into its significant components. Finally, we propose seven novel features from the spectral and temporal structures of the decomposed vectors in a way that they successfully represent joint TF structure of the audio signal, and combine them with the Mel-frequency cepstral coefficients (MFCCs) features. These features are examined using a database of 192 environmental audio signals which includes 20 aircraft, 17 helicopter, 20 drum, 15 flute, 20 piano, 20 animal, 20 bird, and 20 insect sounds, and the speech of 20 males and 20 females. The results of the numerical simulation support the effectiveness of the proposed approach for environmental audio classification with over 10% accuracy-rate improvement compared to the MFCC features.

Audio Signal Feature Extraction and Classification Using Local Discriminant Bases

Audio feature extraction plays an important role in analyzing and characterizing audio content. Auditory scene analysis, content-based retrieval, indexing, and fingerprinting of audio are few of the applications that require efficient feature extraction. The key to extract strong features that characterize the complex nature of audio signals is to identify their discriminatory subspaces. In this paper, we propose an audio feature extraction and a multigroup classification scheme that focuses on identifying discriminatory time-frequency subspaces using the local discriminant bases (LDB) technique. Two dissimilarity measures were used in the process of selecting the LDB nodes and extracting features from them. The extracted features were then fed to a linear discriminant analysis-based classifier for a three-level hierarchical classification of audio signals into ten classes. In the first level, the audio signals were grouped into artificial and natural sounds. Each of the first level groups were subdivided to form the second level groups viz. instrumental, automobile, human, and nonhuman sounds. The third level was formed by subdividing the four groups of the second level into the final ten groups (drums, flute, piano, aircraft, helicopter, male, female, animals, birds and insects). A database of 213 audio signals were used in this study and an average classification accuracy of 83% for the first level (113 artificial and 100 natural sounds), 92% for the second level (73 instrumental and 40 automobile sounds; 40 human and 60 nonhuman sounds), and 89% for the third level (27 drums, 15 flute, and 31 piano sounds; 23 aircraft and 17 helicopter sounds; 20 male and 20 female speech; 20 animals, 20 birds and 20 insects sounds) were achieved. In addition to the above, a separate classification was also performed combining the LDB features with the mel-frequency cepstral coefficients. The average classification accuracies achieved using the combined features were 91% for the first level, 99% for the second level, and 95% for the third level

Statistical Analysis of Gait Rhythm in Patients With Parkinson's Disease

To assess the gait variability in patients with Parkinsons disease (PD), we first used the nonparametric Parzen-window method to estimate the probability density functions (PDFs) of stride interval and its two subphases (i.e., swing interval and stance interval). The gait rhythm standard deviation (¿) parameters computed with the PDFs indicated that the gait variability is significantly increased in PD. Signal turns count (STC) was also derived from each outlier-processed gait rhythm time series to serve as a dominant feature, which could be used to characterize the gait variability in PD. Since it was observed that the statistical parameters of swing interval or stance interval were highly correlated with those of stride interval, this article only used the stride interval parameters, i.e., ¿r and STCr , to form the feature vector in the pattern classification experiments. The results evaluated with the leave-one-out cross-validation method demonstrated that the least squares support vector machine with polynomial kernels was able to provide a classification accurate rate of 90.32% and an area (Az) of 0.952 under the receiver operating characteristic curve, both of which were better than the results obtained with the linear discriminant analysis (accuracy: 67.74%, Az: 0.917). The features and the classifiers used in the present study could be useful for monitoring of the gait in PD.

Gaussian Mixture Modeling of Keystroke Patterns for Biometric Applications

The keystroke patterns produced during typing have been shown to be unique biometric signatures. Therefore, these patterns can be used as digital signatures to verify the identity of computer users remotely over the Internet or locally at a specific workstation. In particular, keystroke recognition can enhance the username and password security model by monitoring the way that these strings are typed. To this end, this paper proposes a novel up--up keystroke latency (UUKL) feature and compares its performance with existing features using a Gaussian mixture model (GMM)-based verification system that utilizes an adaptive and user-specific threshold based on the leave-one-out method (LOOM). The results show that the UUKL feature significantly outperforms the commonly used key hold-down time (KD) and down--down keystroke latency (DDKL) features. Overall, the inclusion of the UUKL feature led to an equal error rate (EER) of 4.4% based on a database of 41 users, which is a 2.1% improvement as compared to the existing features. Comprehensive results are also presented for a two-stage authentication system that has shown significant benefits. Lastly, due to many inconsistencies in previous works, a formal keystroke protocol is recommended that consolidates a number of parameters concerning how to improve performance, reliability, and accuracy of keystroke-recognition systems.

Multigroup classification of audio signals using time-frequency parameters

The ongoing advancements in the multimedia technologies drive the need for efficient classification of the audio signals to make the content-based retrieval process more accurate and much easier from huge databases. The challenge of this task lies in an accurate extraction of signal characteristics so as to derive a strong discriminatory feature suitable for classification. In this paper, a time-frequency (TF) approach for audio classification is proposed. Audio signals are nonstationary in nature and TF approach is the best way to analyze them. The audio signals were decomposed using an adaptive TF decomposition algorithm, and the signal decomposition parameter based on octave (scaling) was used to generate a set of 42 features over three frequency bands within the auditory range. These features were analyzed using linear discriminant functions and classified into six music groups (rock, classical, country, jazz, folk and pop). Overall classification accuracies as high as 97.6 % was achieved by linear discriminant analysis of 170 audio signals.

Modified local discriminant bases algorithm and its application in analysis of human knee joint vibration signals

Knee joint disorders are common in the elderly population, athletes, and outdoor sports enthusiasts. These disorders are often painful and incapacitating. Vibration signals [vibroarthrographic (VAG)] are emitted at the knee joint during the swinging movement of the knee. These VAG signals contain information that can be used to characterize certain pathological aspects of the knee joint. In this paper, we present a noninvasive method for screening knee joint disorders using the VAG signals. The proposed approach uses wavelet packet decompositions and a modified local discriminant bases algorithm to analyze the VAG signals and to identify the highly discriminatory basis functions. We demonstrate the effectiveness of using a combination of multiple dissimilarity measures to arrive at the optimal set of discriminatory basis functions, thereby maximizing the classification accuracy. A database of 89 VAG signals containing 51 normal and 38 abnormal samples were used in this study. The features extracted from the coefficients of the selected basis functions were analyzed and classified using a linear-discriminant-analysis-based classifier. A classification accuracy as high as 80% was achieved using this true nonstationary signal analysis approach.

Localized rotational activation in the left atrium during human atrial fibrillation: Relationship to complex fractionated atrial electrograms and low-voltage zones

BACKGROUND In humans, the existence of rotors or reentrant sources maintaining atrial fibrillation (AF) and the underlying electroanatomic substrate has not been well defined. OBJECTIVE Our aim was to determine the prevalence of localized rotational activation (RotA) in the left atrium (LA) during human AF and whether complex fractionated atrial electrograms (CFAEs) or low-voltage areas colocalize with RotA sites. METHODS We prospectively studied 32 patients (mean age 57 ± 8 years; 88% with persistent AF) undergoing AF catheter ablation. Bipolar electrograms were recorded for 2.5 seconds during AF using a roving 20-pole circular catheter in the LA. RotA was defined as sequential temporal activation of bipoles around the circular catheter. Bipolar electrogram fractionation index and bipolar voltage were used to define CFAEs and low-voltage areas, respectively. RESULTS In 21 (66%) patients, 47 RotA sites were identified. Few (9%) lasted 2.5 seconds (cycle length 183 ± 6 ms), while the majority (91%) were nonsustained (duration 610 ± 288 ms; cycle length 149 ± 11 ms). RotA was most common in the pulmonary vein antrum (71%) and posterior LA (25%). CFAEs were recorded from 18% ± 12% of LA area, and most (92% ± 7%) were not associated with RotA sites. However, 85% of RotA sites contained CFAEs. Very low voltage (<0.1 mV) areas comprised 12% ± 10% of LA area and were present in 23% of RotA sites. CONCLUSIONS In patients with predominantly persistent AF, localized RotA is commonly present but tends to be transient (<1 second). Although most CFAEs do not colocalize with RotA sites, the high prevalence of CFAEs and very low voltages within RotA sites may indicate slow conduction in diseased myocardium necessary for their maintenance.

Combining least-squares support vector machines for classification of biomedical signals: a case study with knee-joint vibroarthrographic signals

The knee-joint vibroarthrographic (VAG) signal could be used as an indicator with regard to the degenerative articular cartilage surfaces of the knee. Computer-aided analysis of VAG signals could provide quantitative indices for the noninvasive diagnosis of knee-joint pathologies at different stages. In this article, we propose a novel multiple classifier system (MCS) based on a recurrent neural network (RNN), to classify a dataset of 89 knee-joint VAG signals. The MCS consists of a group of component classifiers in the form of the least-squares support vector machine. The knowledge generated by the component classifiers is combined with the linear and normalised fusion model, the weights of which are optimised during the energy convergence process of the RNN. The experimental results showed that the proposed MCS was able to provide the classification accuracy of 80.9% and the area of 0.9484 under the receiver operating characteristics curve. The diagnostic performance of the MCS was superior to that obtained with the prevailing fusion approaches, such as the majority vote, the simple average and the median average.