Time Domain Feature Extraction Methods Research Articles

Spatio-spectral filters for low-density surface electromyographic signal classification

In this paper, we proposed to utilize a novel spatio-spectral filter, common spatio-spectral pattern (CSSP), to improve the classification accuracy in identifying intended motions based on low-density surface electromyography (EMG). Five able-bodied subjects and a transradial amputee participated in an experiment of eight-task wrist and hand motion recognition. Low-density (six channels) surface EMG signals were collected on forearms. Since surface EMG signals are contaminated by large amount of noises from various sources, the performance of the conventional time-domain feature extraction method is limited. The CSSP method is a classification-oriented optimal spatio-spectral filter, which is capable of separating discriminative information from noise and, thus, leads to better classification accuracy. The substantially improved classification accuracy of the CSSP method over the time-domain and other methods is observed in all five able-bodied subjects and verified via the cross-validation. The CSSP method can also achieve better classification accuracy in the amputee, which shows its potential use for functional prosthetic control.

Evaluation of bagging ensemble method with time-domain feature extraction for diagnosing of arrhythmia beats

We explore the effect of using bagged decision tree (BDT) as an ensemble learning method with proposed time-domain feature extraction methods on electrocardiogram (ECG) arrhythmia beat classification comparing with single decision tree (DT) classifier. RR interval is the main property which defines irregular heart rhythm, and its ratio to the previous value and difference from mean value are used as morphological feature extraction methods. Form factor, its ratio to the previous value and difference from mean value are used to express ECG waveform complexity. In addition, skewness and second-order linear predictive coding coefficients are added to the feature vector of 56,569 ECG heart beats obtained from MIT–BIH arrhythmia database as time-domain feature extraction methods. The quarter of ECG heart beat samples are used as test data for DT and BDT. The performance measures of these classifiers are evaluated using the metrics such as accuracy, sensitivity, specificity and Kappa coefficient for both classifiers, and the performance of BDT classifier is examined for number of base learners up to 75. The BDT results in more predictive performance than DT according to the performance measures. BDT with 69 base learners has 99.51 % of accuracy, 97.50 % of sensitivity, 99.80 % of specificity and 0.989 of Kappa coefficient while DT gives 98.78, 96.05, 99.57 and 0.975 %, respectively. These metrics show that the suggested BDT increases the numbers of successfully identified arrhythmia beats. Moreover, BDT with at least three base learners has higher distinguishing capability than DT.

Vehicle classification in Sensor Networks using time-domain signal processing and Neural Networks

Vehicle classification is a demanding application of Wireless Sensor Networks. In many cases, sensor nodes detect and classify vehicles from their acoustic and/or seismic signature using spectral or wavelet based feature extraction methods. Such methods, while providing good results are quite demanding in computational power and energy and are difficult to implement on low-cost sensor nodes with limited resources. In this work, we investigate the use of a time-domain encoding and feature extraction method, to produce simple, fixed-size matrices from complex acoustic and seismic signatures of vehicles for classification purposes. Classification is accomplished using an Artificial Neural Network and a basic, L1 distance, archetype classifier. Hardware implementation issues on a prototype sensor node, based on an 8-bit microcontroller, are also discussed. For evaluation purposes we use real data from DARPA’s SensIt project, which contains various acoustic and seismic signatures from two different vehicle types, a tracked vehicle and a heavy truck.

Classification of a known sequence of motions and postures from accelerometry data using adapted Gaussian mixture models

Accelerometry shows promise in providing an inexpensive but effective means of long-term ambulatory monitoring of elderly patients. The accurate classification of everyday movements should allow such a monitoring system to exhibit greater ‘intelligence’, improving its ability to detect and predict falls by forming a more specific picture of the activities of a person and thereby allowing more accurate tracking of the health parameters associated with those activities. With this in mind, this study aims to develop more robust and effective methods for the classification of postures and motions from data obtained using a single, waist-mounted, triaxial accelerometer; in particular, aiming to improve the flexibility and generality of the monitoring system, making it better able to detect and identify short-duration movements and more adaptable to a specific person or device. Two movement classification methods were investigated: a rule-based Heuristic system and a Gaussian mixture model (GMM)-based system. A novel time-domain feature extraction method is proposed for the GMM system to allow better detection of short-duration movements. A method for adapting the GMMs to compensate for the problem of limited user-specific training data is also proposed and investigated. Classification performance was considered in relation to data gathered in an unsupervised, directed routine conducted in a three-month field trial involving six elderly subjects. The GMM system was found to achieve a mean accuracy of 91.3%, distinguishing between three postures (sitting, standing and lying) and five movements (sit-to-stand, stand-to-sit, lie-to-stand, stand-to-lie and walking), compared to 71.1% achieved by the Heuristic system. The adaptation method was found to offer a mean accuracy of 92.2%; a relative improvement of 20.2% over tests without subject-specific data and 4.5% over tests using only a limited amount of subject-specific data. While limited to a restricted subset of possible motions and postures, these results provide a significant step in the search for a more robust and accurate ambulatory classification system.