Domain adaptation for EEG-based, cross-subject epileptic seizure prediction.

The ability to predict the occurrence of an epileptic seizure is a safeguard against patient injury and health complications. However, a major challenge in seizure prediction arises from the significant variability observed in patient data. Common patient-specific approaches, which apply to each patient independently, often perform poorly for other patients due to the data variability. The aim of this study is to propose deep learning models which can handle this variability and generalize across various patients. This study addresses this challenge by introducing a novel cross-subject and multi-subject prediction models. Multiple-subject modeling broadens the scope of patient-specific modeling to account for the data from a dedicated ensemble of patients, thereby providing some useful, though relatively modest, level of generalization. The basic neural network architecture of this model is then adapted to cross-subject prediction, thereby providing a broader, more realistic, context of application. For accrued performance, and generalization ability, cross-subject modeling is enhanced by domain adaptation. Experimental evaluation using the publicly available CHB-MIT and SIENA data datasets shows that our multiple-subject model achieved better performance compared to existing works. However, the cross-subject faces challenges when applied to different patients. Finally, through investigating three domain adaptation methods, the model accuracy has been notably improved by 10.30% and 7.4% for the CHB-MIT and SIENA datasets, respectively.

Use of Empirical Mode Decomposition in ERP Analysis to Classify Familial Risk and Diagnostic Outcomes for Autism Spectrum Disorder.

Event-related potentials (ERPs) activated by faces and gaze processing are found in individuals with autism spectrum disorder (ASD) in the early stages of their development and may serve as a putative biomarker to supplement behavioral diagnosis. We present a novel approach to the classification of visual ERPs collected from 6-month-old infants using intrinsic mode functions (IMFs) derived from empirical mode decomposition (EMD). Selected features were used as inputs to two machine learning methods (support vector machines and k-nearest neighbors (k-NN)) using nested cross validation. Different runs were executed for the modelling and classification of the participants in the control and high-risk (HR) groups and the classification of diagnosis outcome within the high-risk group: HR-ASD and HR-noASD. The highest accuracy in the classification of familial risk was 88.44%, achieved using a support vector machine (SVM). A maximum accuracy of 74.00% for classifying infants at risk who go on to develop ASD vs. those who do not was achieved through k-NN. IMF-based extracted features were highly effective in classifying infants by risk status, but less effective by diagnostic outcome. Advanced signal analysis of ERPs integrated with machine learning may be considered a first step toward the development of an early biomarker for ASD.

EEG-IP: an international infant EEG data integration platform for the study of risk and resilience in autism and related conditions.

BACKGROUND: Establishing reliable predictive and diganostic biomarkers of autism would enhance early identification and facilitate targeted intervention during periods of greatest plasticity in early brain development. High impact research on biomarkers is currently limited by relatively small sample sizes and the complexity of the autism phenotype. METHODS: EEG-IP is an International Infant EEG Data Integration Platform developed to advance biomarker discovery by enhancing the large scale integration of multi-site data. Currently, this is the largest multi-site standardized dataset of infant EEG data. RESULTS: First, multi-site data from longitudinal cohort studies of infants at risk for autism was pooled in a common repository with 1382 EEG longitudinal recordings, linked behavioral data, from 432 infants between 3- to 36-months of age. Second, to address challenges of limited comparability across independent recordings, EEG-IP applied the Brain Imaging Data Structure (BIDS)-EEG standard, resulting in a harmonized, extendable, and integrated data state. Finally, the pooled and harmonized raw data was preprocessed using a common signal processing pipeline that maximizes signal isolation and minimizes data reduction. With EEG-IP, we produced a fully standardized data set, of the pooled, harmonized, and pre-processed EEG data from multiple sites. CONCLUSIONS: Implementing these integrated solutions for the first time with infant data has demonstrated success and challenges in generating a standardized multi-site data state. The challenges relate to annotation of signal sources, time, and ICA analysis during pre-processing. A number of future opportunities also emerge, including validation of analytic pipelines that can replicate existing findings and/or test novel hypotheses.

A fully automated approach for baby cry signal segmentation and boundary detection of expiratory and inspiratory episodes.

The detection of cry sounds is generally an important pre-processing step for various applications involving cry analysis such as diagnostic systems, electronic monitoring systems, emotion detection, and robotics for baby caregivers. Given its complexity, an automatic cry segmentation system is a rather challenging topic. In this paper, a framework for automatic cry sound segmentation for application in a cry-based diagnostic system has been proposed. The contribution of various additional time- and frequency-domain features to increase the robustness of a Gaussian mixture model/hidden Markov model (GMM/HMM)-based cry segmentation system in noisy environments is studied. A fully automated segmentation algorithm to extract cry sound components, namely, audible expiration and inspiration, is introduced and is grounded on two approaches: statistical analysis based on GMMs or HMMs classifiers and a post-processing method based on intensity, zero crossing rate, and fundamental frequency feature extraction. The main focus of this paper is to extend the systems developed in previous works to include a post-processing stage with a set of corrective and enhancing tools to improve the classification performance. This full approach allows to precisely determine the start and end points of the expiratory and inspiratory components of a cry signal, EXP and INSV, respectively, in any given sound signal. Experimental results have indicated the effectiveness of the proposed solution. EXP and INSV detection rates of approximately 94.29% and 92.16%, respectively, were achieved by applying a tenfold cross-validation technique to avoid over-fitting.

Expiratory and Inspiratory Cries Detection Using Different Signals' Decomposition Techniques.

This paper addresses the problem of automatic cry signal segmentation for the purposes of infant cry analysis. The main goal is to automatically detect expiratory and inspiratory phases from recorded cry signals. The approach used in this paper is made up of three stages: signal decomposition, features extraction, and classification. In the first stage, short-time Fourier transform, empirical mode decomposition (EMD), and wavelet packet transform have been considered. In the second stage, various set of features have been extracted, and in the third stage, two supervised learning methods, Gaussian mixture models and hidden Markov models, with four and five states, have been discussed as well. The main goal of this work is to investigate the EMD performance and to compare it with the other standard decomposition techniques. A combination of two and three intrinsic mode functions (IMFs) that resulted from EMD has been used to represent cry signal. The performance of nine different segmentation systems has been evaluated. The experiments for each system have been repeated several times with different training and testing datasets, randomly chosen using a 10-fold cross-validation procedure. The lowest global classification error rates of around 8.9% and 11.06% have been achieved using a Gaussian mixture models classifier and a hidden Markov models classifier, respectively. Among all IMF combinations, the winner combination is IMF3+IMF4+IMF5.

Cry-based infant pathology classification using GMMs.

Traditional studies of infant cry signals focus more on non-pathology-based classification of infants. In this paper, we introduce a noninvasive health care system that performs acoustic analysis of unclean noisy infant cry signals to extract and measure certain cry characteristics quantitatively and classify healthy and sick newborn infants according to only their cries. In the conduct of this newborn cry-based diagnostic system, the dynamic MFCC features along with static Mel-Frequency Cepstral Coefficients (MFCCs) are selected and extracted for both expiratory and inspiratory cry vocalizations to produce a discriminative and informative feature vector. Next, we create a unique cry pattern for each cry vocalization type and pathological condition by introducing a novel idea using the Boosting Mixture Learning (BML) method to derive either healthy or pathology subclass models separately from the Gaussian Mixture Model-Universal Background Model (GMM-UBM). Our newborn cry-based diagnostic system (NCDS) has a hierarchical scheme that is a treelike combination of individual classifiers. Moreover, a score-level fusion of the proposed expiratory and inspiratory cry-based subsystems is performed to make a more reliable decision. The experimental results indicate that the adapted BML method has lower error rates than the Bayesian approach or the maximum a posteriori probability (MAP) adaptation approach when considered as a reference method.