Yaniv Zigel

The weighted diagnostic distortion (WDD) measure for ECG signal compression

In this paper, a new distortion measure for electrocardiogram (ECG) signal compression, called weighted diagnostic distortion (WDD) is introduced. The WDD measure is designed for comparing the distortion between original ECG signal and reconstructed ECG signal (after compression). The WDD is based on PQRST complex diagnostic features (such as P wave duration, QT interval, T shape, ST elevation) of the original ECG signal and the reconstructed one. Unlike other conventional distortion measures [e.g. percentage root mean square (rms) difference, or PRD], the WDD contains direct diagnostic information and thus is more meaningful and useful. Four compression algorithms were implemented (AZTEC, SAPA2, LTP, ASEC) in order to evaluate the WDD. A mean opinion score (MOS) test was applied to test the quality of the reconstructed signals and to compare the quality measure (MOS/sub error/) with the proposed WDD measure and the popular PRD measure. The evaluators in the WIGS test were three independent expert cardiologists, who studied the reconstructed ECG signals in a blind and a semiblind tests. The correlation between the proposed WDD measure and the MOS test measure (MOS/sub error/) was found superior to the correlation between the popular PRD measure and the MOS/sub error/.

A Method for Automatic Fall Detection of Elderly People Using Floor Vibrations and Sound—Proof of Concept on Human Mimicking Doll Falls

Falls are a major risk for the elderly people living independently. Rapid detection of fall events can reduce the rate of mortality and raise the chances to survive the event and return to independent living. In the last two decades, several technological solutions for detection of falls were published, but most of them suffer from critical limitations. In this paper, we present a proof of concept to an automatic fall detection system for elderly people. The system is based on floor vibration and sound sensing, and uses signal processing and pattern recognition algorithm to discriminate between fall events and other events. The classification is based on special features like shock response spectrum and mel frequency ceptral coefficients. For the simulation of human falls, we have used a human mimicking doll: ldquoRescue Randy.rdquo The proposed solution is unique, reliable, and does not require the person to wear anything. It is designed to detect fall events in critical cases in which the person is unconscious or in a stress condition. From the preliminary research, the proposed system can detect human mimicking dolls falls with a sensitivity of 97.5% and specificity of 98.6%.

ECG signal compression using analysis by synthesis coding

An electrocardiogram (ECG) compression algorithm, called analysis by synthesis ECG compressor (ASEC), is introduced. The ASEC algorithm is based on analysis by synthesis coding, and consists of a beat codebook, long and short-term predictors, and an adaptive residual quantizer. The compression algorithm uses a defined distortion measure in order to efficiently encode every heartbeat, with minimum bit rate, while maintaining a predetermined distortion level. The compression algorithm was implemented and tested with both the percentage rms difference (PRD) measure and the recently introduced weighted diagnostic distortion (WDD) measure. The compression algorithm has been evaluated with the MIT-BIH Arrhythmia Database. A mean compression rate of approximately 100 bits/s (compression ratio of about 30:1) has been achieved with a good reconstructed signal quality (WDD below 4% and PRD below 8%). The ASEC was compared with several well-known ECG compression algorithms and was found to be superior at all tested bit rates. A mean opinion score (MOS) test was also applied. The testers were three independent expert cardiologists. As In the quantitative test, the proposed compression algorithm was found to be superior to the other tested compression algorithms.

Fall detection of elderly through floor vibrations and sound

Falls are very prevalent among the elderly especially in their home. The statistics show that approximately one in every three adults 65 years old or older falls each year. Almost 30% of those falls result in serious injuries. Studies have shown that the medical outcome of a fall is largely dependent upon the response and rescue time. Therefore, reliable and immediate fall detection system is important so that adequate medical support could be delivered. We have developed a unique and inexpensive solution that does not require subjects to wear anything. The solution is based on floor vibration and acoustic sensing, and uses a pattern recognition algorithm to discriminate between human or inanimate object fall events. Using the proposed system we can detect human falls with a sensitivity of 95% and specificity of 95%.

Obstructive Apnea Hypopnea Index Estimation by Analysis of Nocturnal Snoring Signals in Adults

STUDY OBJECTIVE To develop a whole-night snore sounds analysis algorithm enabling estimation of obstructive apnea hypopnea index (AHI(EST)) among adult subjects. DESIGN Snore sounds were recorded using a directional condenser microphone placed 1 m above the bed. Acoustic features exploring intra-(mel- cepstability, pitch density) and inter-(running variance, apnea phase ratio, inter-event silence) snore properties were extracted and integrated to assess AHI(EST). SETTING University-affiliated sleep-wake disorder center and biomedical signal processing laboratory. PATIENTS Ninety subjects (age 53 ± 13 years, BMI 31 ± 5 kg/m(2)) referred for polysomnography (PSG) diagnosis of OSA were prospectively and consecutively recruited. The system was trained and tested on 60 subjects. Validation was blindly performed on the additional 30 consecutive subjects. MEASUREMENTS AND RESULTS AHI(EST) correlated with AHI (AHI(PSG); r(2) = 0.81, P < 0.001). Area under the receiver operating characteristic curve of 85% and 92% for thresholds of 10 and 20 events/h, respectively, were obtained for OSA detection. Both Altman-Bland analysis and diagnostic agreement criteria revealed 80% and 83% agreements of AHI(EST) with AHI(PSG), respectively. CONCLUSIONS Acoustic analysis based on intra- and inter-snore properties can differentiate subjects according to AHI. An acoustic-based screening system may address the growing needs for reliable OSA screening tool. Further studies are needed to support these findings.

Automatic detection of whole night snoring events using non-contact microphone.

Objective Although awareness of sleep disorders is increasing, limited information is available on whole night detection of snoring. Our study aimed to develop and validate a robust, high performance, and sensitive whole-night snore detector based on non-contact technology. Design Sounds during polysomnography (PSG) were recorded using a directional condenser microphone placed 1 m above the bed. An AdaBoost classifier was trained and validated on manually labeled snoring and non-snoring acoustic events. Patients Sixty-seven subjects (age 52.5±13.5 years, BMI 30.8±4.7 kg/m2, m/f 40/27) referred for PSG for obstructive sleep apnea diagnoses were prospectively and consecutively recruited. Twenty-five subjects were used for the design study; the validation study was blindly performed on the remaining forty-two subjects. Measurements and Results To train the proposed sound detector, >76,600 acoustic episodes collected in the design study were manually classified by three scorers into snore and non-snore episodes (e.g., bedding noise, coughing, environmental). A feature selection process was applied to select the most discriminative features extracted from time and spectral domains. The average snore/non-snore detection rate (accuracy) for the design group was 98.4% based on a ten-fold cross-validation technique. When tested on the validation group, the average detection rate was 98.2% with sensitivity of 98.0% (snore as a snore) and specificity of 98.3% (noise as noise). Conclusions Audio-based features extracted from time and spectral domains can accurately discriminate between snore and non-snore acoustic events. This audio analysis approach enables detection and analysis of snoring sounds from a full night in order to produce quantified measures for objective follow-up of patients.

Analysis by synthesis ECG signal compression

The authors introduce a new ECG compression algorithm, and a new distortion measure. The distortion measure, called the Weighted Diagnostic Distortion (WDD), is based on comparing PQRST complex features (such as: RR interval, QT interval, ST elevation, etc.) of the original ECG signal and the reconstructed one. The compression algorithm is based on analysis by synthesis coding. It consists of a beat codebook, long and short term predictors, and an adaptive residual quantizer. The compression algorithm uses the WDD measure in order to encode, by means of analysis by synthesis, every beat of the original ECG signal. The compression algorithm has been applied to the MIT-BIH Arrhythmia Database. A rate of approximately 100 bits per second has been achieved with a very good quality (WDD below 4%, and PRD below 8%).

Automatic Detection of Obstructive Sleep Apnea Using Speech Signals

Obstructive sleep apnea (OSA) is a common disorder associated with anatomical abnormalities of the upper airways that affects 5% of the population. Acoustic parameters may be influenced by the vocal tract structure and soft tissue properties. We hypothesize that speech signal properties of OSA patients will be different than those of control subjects not having OSA. Using speech signal processing techniques, we explored acoustic speech features of 93 subjects who were recorded using a text-dependent speech protocol and a digital audio recorder immediately prior to polysomnography study. Following analysis of the study, subjects were divided into OSA ( n = 67) and non-OSA (n = 26) groups. A Gaussian mixture model-based system was developed to model and classify between the groups; discriminative features such as vocal tract length and linear prediction coefficients were selected using feature selection technique. Specificity and sensitivity of 83% and 79% were achieved for the male OSA and 86% and 84% for the female OSA patients, respectively. We conclude that acoustic features from speech signals during wakefulness can detect OSA patients with good specificity and sensitivity. Such a system can be used as a basis for future development of a tool for OSA screening.

Supervector Dimension Reduction for Efficient Speaker Age Estimation Based on the Acoustic Speech Signal

This paper presents a novel dimension reduction method which aims to improve the accuracy and the efficiency of speakers age estimation systems based on speech signal. Two different age estimation approaches were studied and implemented; the first, age-group classification, and the second, precise age estimation using regression. These two approaches use the Gaussian mixture model (GMM) supervectors as features for a support vector machine (SVM) model. When a radial basis function (RBF) kernel is used, the accuracy is improved compared to using a linear kernel; however, the computation complexity is more sensitive to the feature dimension. Classic dimension reduction methods like principal component analysis (PCA) and linear discriminant analysis (LDA) tend to eliminate the relevant feature information and cannot always be applied without damaging the models accuracy. In our study, a novel dimension reduction method was developed, the weighted-pairwise principal components analysis (WPPCA) based on the nuisance attribute projection (NAP) technique. This method projects the supervectors to a reduced space where the redundant within-class pairwise variability is eliminated. This method was applied and compared to the baseline system where no dimensionality reduction is done on the supervectors. The conducted experiments showed a dramatic speed-up in the SVM training testing time using reduced feature vectors. The system accuracy was improved by 5% for the classification system and by 10% for the regression system using the proposed dimension reduction method.

Nocturnal sound analysis for the diagnosis of obstructive sleep apnea

A novel method for screening obstructive sleep apnea syndrome (OSAs) based on nocturnal acoustic signal is proposed. Full-night audio signals from sixty subjects were segmented into snore, noise and silence events using semi-automatic algorithm based on Gaussian mixture models which achieves more than 90% (92%) sensitivity (specificity) and produces an average of 2,000 snores per subject. A classification into 3 groups is proposed for the diagnosis: comparison group - non-OSA subjects (apnea hypopnea index, AHI<10), mild to moderate OSA (10<AHI<30) and severe OSA (AHI>30). A Bayes classifier was implemented, fed with five acoustic features, all correlated with the severity of the syndrome: (1) Inter Event Silence, which quantifies segments suspicious as apnea; (2) Mel Cepstability, measures the entire night stability of the spectrum, expressed using mel-frequency cepstrum; (3) Energy Running Variance, a criterion for the variation of the nocturnal acoustic pattern; (4) Apneic Phase Ratio, exploiting the finding that snores around apnea events expressing larger acoustic variation; and (5) Pitch Density. Correct classification of 92% for resubstitution method and 80% for 5-fold cross validation method was achieved. Moreover, in a case of two groups with a threshold of AHI=10, a sensitivity (specificity) of 96.5% (90.6%) and 87.5% (82.1%) for resubstitution and cross-validation respectively were obtained.