A Shallow Autoencoder Framework for Epileptic Seizure Detection in EEG Signals.

This paper presents a trainable hybrid approach involving a shallow autoencoder (AE) and a conventional classifier for epileptic seizure detection. The signal segments of a channel of electroencephalogram (EEG) (EEG epochs) are classified as epileptic and non-epileptic by employing its encoded AE representation as a feature vector. Analysis on a single channel-basis and the low computational complexity of the algorithm allow its use in body sensor networks and wearable devices using one or few EEG channels for wearing comfort. This enables the extended diagnosis and monitoring of epileptic patients at home. The encoded representation of EEG signal segments is obtained based on training the shallow AE to minimize the signal reconstruction error. Extensive experimentation with classifiers has led us to propose two versions of our hybrid method: (a) one yielding the best classification performance compared to the reported methods using the k-nearest neighbor (kNN) classifier and (b) the second with a hardware-friendly architecture and yet with the best classification performance compared to other reported methods in this category using a support-vector machine (SVM) classifier. The algorithm is evaluated on the Children's Hospital Boston, Massachusetts Institute of Technology (CHB-MIT), and University of Bonn EEG datasets. The proposed method achieves 98.85% accuracy, 99.29% sensitivity, and 98.86% specificity on the CHB-MIT dataset using the kNN classifier. The best figures using the SVM classifier for accuracy, sensitivity, and specificity are 99.19%, 96.10%, and 99.19%, respectively. Our experiments establish the superiority of using an AE approach with a shallow architecture to generate a low-dimensionality yet effective EEG signal representation capable of high-performance abnormal seizure activity detection at a single-channel EEG level and with a fine granularity of 1 s EEG epochs.

Channels and Features Identification: A Review and a Machine-Learning Based Model With Large Scale Feature Extraction for Emotions and ASD Classification.

Autism Spectrum Disorder (ASD) is characterized by impairments in social and cognitive skills, emotional disorders, anxiety, and depression. The prolonged conventional ASD diagnosis raises the sheer need for early meaningful intervention. Recently different works have proposed potential for ASD diagnosis and intervention through emotions prediction using deep neural networks (DNN) and machine learning algorithms. However, these systems lack an extensive large-scale feature extraction (LSFE) analysis through multiple benchmark data sets. LSFE analysis is required to identify and utilize the most relevant features and channels for emotion recognition and ASD prediction. Considering these challenges, for the first time, we have analyzed and evaluated an extensive feature set to select the optimal features using LSFE and feature selection algorithms (FSA). A set of up to eight most suitable channels was identified using different best-case FSA. The subject-wise importance of channels and features is also identified. The proposed method provides the best-case accuracies, precision, and recall of 95, 92, and 90%, respectively, for emotions prediction using a linear support vector machine (LSVM) classifier. It also provides the best-case accuracy, precision, and recall of 100% for ASD classification. This work utilized the largest number of benchmark data sets (5) and subjects (99) for validation reported till now in the literature. The LSVM classification algorithm proposed and utilized in this work has significantly lower complexity than the DNN, convolutional neural network (CNN), Naïve Bayes, and dynamic graph CNN used in recent ASD and emotion prediction systems.

A 10.13µJ/Classification 2-Channel Deep Neural Network Based SoC for Negative Emotion Outburst Detection of Autistic Children.

An electroencephalogram (EEG)-based non-invasive 2-channel neuro-feedback SoC is presented to predict and report negative emotion outbursts (NEOB) of Autistic patients. The SoC incorporates area-and-power efficient dual-channel Analog Front-End (AFE), and a deep neural network (DNN) emotion classification processor. The classification processor utilizes only the two-feature vector per channel to minimize the area and overfitting problems. The 4-layers customized DNN classification processor is integrated on-sensor to predict the NEOB. The AFE comprises two entirely shared EEG channels using sampling capacitors to reduce the area by 30%. Moreover, it achieves an overall integrated input-referred noise, NEF, and crosstalk of 0.55 µVRMS, 2.71, and -79 dB, respectively. The 16 mm2 SoC is implemented in 0.18 um 1P6M, CMOS process and consumes 10.13 µJ/classification for 2 channel operation while achieving an average accuracy of >85% on multiple emotion databases and real-time testing.

An On-Chip Processor for Chronic Neurological Disorders Assistance Using Negative Affectivity Classification.

Chronic neurological disorders (CND's) are lifelong diseases and cannot be eradicated, but their severe effects can be alleviated by early preemptive measures. CND's, such as Alzheimer's, Autism Spectrum Disorder (ASD), and Amyotrophic Lateral Sclerosis (ALS), are the chronic ailment of the central nervous system that causes the degradation of emotional and cognitive abilities. Long term continuous monitoring with neuro-feedback of human emotions for patients with CND's is crucial in mitigating its harmful effect. This paper presents hardware efficient and dedicated human emotion classification processor for CND's. Scalp EEG is used for the emotion's classification using the valence and arousal scales. A linear support vector machine classifier is used with power spectral density, logarithmic interhemispheric power spectral ratio, and the interhemispheric power spectral difference of eight EEG channel locations suitable for a wearable non-invasive classification system. A look-up-table based logarithmic division unit (LDU) is to represent the division features in machine learning (ML) applications. The implemented LDU minimizes the cost of integer division by 34% for ML applications. The implemented emotion's classification processor achieved an accuracy of 72.96% and 73.14%, respectively, for the valence and arousal classification on multiple publicly available datasets. The 2 x 3mm2 processor is fabricated using a 0.18 µm 1P6M CMOS process with power and energy utilization of 2.04 mW and 16 µJ/classification, respectively, for 8-channel operation.

Design and Implementation of a Machine Learning Based EEG Processor for Accurate Estimation of Depth of Anesthesia.

Accurate monitoring of the depth of anesthesia (DoA) is essential for intraoperative and postoperative patient's health. Commercially available electroencephalograph (EEG)-based DoA monitors are recommended only for certain anesthetic drugs and specific age-group patients. This paper presents a machine learning classification processor for accurate DoA estimation irrespective of the patient's age and anesthetic drug. The classification is solely based on six features extracted from EEG signal, i.e., spectral edge frequency (SEF), beta ratio, and four bands of spectral energy (FBSE). A machine learning fine decision tree classifier is adopted to achieve a four-class DoA classification (deep, moderate, and light DoA versus awake state). The feature selection and the classification processor are optimized to achieve the highest classification accuracy for the state of moderate anesthesia required for the surgical operations. The proposed 256-point fast Fourier transform accelerator is implemented to realize SEF, beta ratio, and FBSE that enables minimal latency and high accuracy feature extraction. The proposed DoA processor is implemented using a 65 nm CMOS technology and experimentally verified using field programming gate array (FPGA) based on the EEG recordings of 75 patients undergoing elective surgery with different types of anesthetic agents. The processor achieves an average accuracy of 92.2% for all DoA states, with a latency of 1s The 0.09 mm2 DoA processor consumes 140nJ/classification.

A Patient-Specific Single Sensor IoT-Based Wearable Fall Prediction and Detection System.

Falls in older adults are a major cause of morbidity and mortality and are a key class of preventable injuries. This paper presents a patient-specific (PS) fall prediction and detection prototype system that utilizes a single tri-axial accelerometer attached to the patient's thigh to distinguish between activities of daily living (ADL) and fall events. The proposed system consists of two modes of operation: 1) fast mode for fall predication (FMFP) predicting a fall event (300-700 msec) before occurring and 2) slow mode for fall detection (SMFD) with a 1-sec latency for detecting a fall event. The nonlinear support vector machine classifier (NLSVM)-based FMFP algorithm extracts seven discriminating features for the pre-fall case to identify a fall risk event and alarm the patient. The proposed SMFD algorithm utilizes a Three-cascaded 1-sec sliding frames classification architecture with a linear regression-based offline training to identify a single and optimal threshold for each patient. Fall incidence will trigger an alarming notice to the concern healthcare providers via the Internet. Experiments are performed with 20 different subjects (age above 65 years) and a total number of 100 associated falls and ADL recordings indoors and outdoors. The accuracy of the proposed algorithms is furthermore validated via MobiFall Dataset. FMFP achieves sensitivity and specificity of 97.8% and 99.1%, respectively, while SMFD achieves sensitivity and specificity of 98.6% and 99.3%, respectively, for a total number of 600 measured falls and ADL cases from 77 subjects.