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

Identification of autism spectrum disorder using electroencephalography and machine learning: a review

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by communication barriers, societal disengagement, and monotonous actions. Traditional diagnostic methods for ASD rely on clinical observations and behavioural assessments, which are time-consuming. In recent years, researchers have focused mainly on the early diagnosis of ASD due to the unavailability of recognised causes and the lack of permanent curative solutions. Electroencephalography (EEG) research in ASD offers insight into the neural dynamics of affected individuals. This comprehensive review examines the unique integration of EEG, machine learning, and statistical analysis for ASD identification, highlighting the promise of an interdisciplinary approach for enhancing diagnostic precision. The comparative analysis of publicly available EEG datasets for ASD, along with local data acquisition methods and their technicalities, is presented in this paper. This study also compares preprocessing techniques, and feature extraction methods, followed by classification models and statistical analysis which are discussed in detail. In addition, it briefly touches upon comparisons with other modalities to contextualize the extensiveness of ASD research. Moreover, by outlining research gaps and future directions, this work aims to catalyse further exploration in the field, with the main goal of facilitating more efficient and effective early identification methods that may be helpful to the lives of ASD individuals.

A Closed-Loop Ear-Worn Wearable EEG System with Real-Time Passive Electrode Skin Impedance Measurement for Early Autism Detection

Autism spectrum disorder (ASD) is a chronic neurological disorder with the severity directly linked to the diagnosis age. The severity can be reduced if diagnosis and intervention are early (age < 2 years). This work presents a novel ear-worn wearable EEG system designed to aid in the early detection of ASD. Conventional EEG systems often suffer from bulky, wired electrodes, high power consumption, and a lack of real-time electrode-skin interface (ESI) impedance monitoring. To address these limitations, our system incorporates continuous, long-term EEG recording, on-chip machine learning for real-time ASD prediction, and a passive ESI evaluation system. The passive ESI methodology evaluates impedance using the root mean square voltage of the output signal, considering factors like pressure, electrode surface area, material, gel thickness, and duration. The on-chip machine learning processor, implemented in 180 nm CMOS, occupies a minimal 2.52 mm² of active area while consuming only 0.87 µJ of energy per classification. The performance of this ML processor is validated using the Old Dominion University ASD dataset.

An efficient ANN SoC for detecting Alzheimer's disease based on recurrent computing

Alzheimer's Disease (AD) is an irreversible, degenerative condition that, while incurable, can have its progression slowed or impeded. While there are numerous methods utilizing neural networks for AD detection, there is a scarcity of High-performance AD detection chips. Moreover, excessively complex neural networks are not conducive to on-chip implementation and clinical applications. This study addresses the challenges of high misdiagnosis rates and significant hardware costs inherent in traditional AD detection techniques. A novel and efficient AD detection framework based on a recurrent computational strategy is proposed. The framework harnesses an Artificial Neural Network (ANN) embedded within a System on Chip (SoC) to perform sophisticated Electroencephalogram (EEG) analysis. The approach began by employing a reduced IEEE754 single-precision encoding method to hardware-encode the preprocessed EEG data, thereby minimizing the memory storage area. Next, data remapping techniques were utilized to ensure the continuity of the input data read addresses and reduce the memory access pressure during neural network computations. Subsequently, hierarchical and Processing Element (PE) reuse technologies were leveraged to perform the multiply-accumulate operations of the ANN. Finally, a step function was chosen to establish binary classification circuits dedicated to AD detection. Experimental results indicate that the optimized SoC achieves a 70 % reduction in area and a 50 % reduction in power consumption compared to traditional designs. For various neural network models, the detection model proposed in this paper incurs less overhead, with a training speed 3 to 4 times faster than other traditional models, and a high accuracy rate of 98.53 %.

Brain Feature Extraction With an Artifact-Tolerant Multiplexed Time-Encoding Neural Frontend for True Real-Time Closed-Loop Neuromodulation

Closed-loop neuromodulation is emerging as a more effective and targeted solution for the treatment of neurological symptoms compared to traditional open-loop stimulation. The majority of the present designs lack the ability to continuously record brain activity during electrical stimulation; hence they cannot fully monitor the treatment's effectiveness. This is due to the large stimulation artifacts that can saturate the sensitive readout circuits. To overcome this challenge, this work presents a rapid-artifact-recovery time-multiplexed neural readout frontend in combination with backend linear interpolation to reconstruct the artifact-corrupted local field potentials' (LFP) features. Our hybrid technique is an alternative approach to avoid power-hungry large-dynamic-range readout architectures or large and complex artifact template subtraction circuits. We discuss the design and measurements of a prototype implementation of the proposed readout frontend in 180-nm CMOS. It combines time multiplexing and time-domain conversion in a novel 13-bit incremental ADC, requiring only 0.0018 mm2/channel of readout area despite the large 180-nm CMOS process used, while consuming only 4.51 μW/channel. This is the smallest reported area for stimulation-voltage-compatible technologies (i.e. ≥ 65 nm). The frontend also yields a best-in-class peak total harmonic distortion of -72.6 dB @2.5-mVpp input, thanks to its implicit DAC mismatch-error shaping property. We employ the chip to measure brain LFP signals corrupted with artifacts, then perform linear interpolation and feature extraction on the measured signals and evaluate the reconstruction quality, using a set of sixteen commonly used features and three stimulation scenarios. The results show relative accuracies above 95% with respect to the situation without artifacts. This work is an ideal candidate for integration in high-channel-count true closed-loop neuromodulation systems.

A Deep Neural Network-Based Model for Quantitative Evaluation of the Effects of Swimming Training

This paper analyzes the quantitative assessment model of the swimming training effect based on the deep neural network by constructing a deep neural network model and designing a quantitative assessment model of the swimming training effect. This paper addresses the problem of not considering the influence of the uncertainties existing in the virtual environment when evaluating swimming training and adds the power of the delays in the actual training operation environment, which is used to improve the objectivity and usability of swimming training evaluation results. To better measure the degree of influence of uncertainties, a training evaluation software module is developed to validate the usability of the simulated training evaluation method using simulated case data and compare it with the data after training evaluation using the unimproved evaluation method to verify the correctness and objectivity of the evaluation method in this paper. In the experiments, the feature extractor is a deep neural network, and the classifier is a gradient-boosting decision tree with integrated learning advantages. In the experimental comparison, we can achieve more than 60% accuracy and no more than a 1.00% decrease in recognition rate on DBPNN + GBDT, 78.5% parameter reduction, and 54.5% floating-point reduction on DPBNN. We can effectively reduce 32.1% of video memory occupation. It can be concluded from the experiments that deep neural network models are more effective and easier to obtain relatively accurate experimental results than shallow learning when facing high-dimensional sparse features. At the same time, deep neural networks can also improve the prediction results of external learning models. Therefore, the experimental results of this model are most intuitively accurate when combining deep neural networks with gradient boosting decision trees.

A machine learning-based diagnostic model for children with autism spectrum disorders complicated with intellectual disability

Background

Early detection of children with autism spectrum disorder (ASD) and comorbid intellectual disability (ID) can help in individualized intervention. Appropriate assessment and diagnostic tools are lacking in primary care. This study aims to explore the applicability of machine learning (ML) methods in diagnosing ASD comorbid ID compared with traditional regression models.

Method

From January 2017 to December 2021, 241 children with ASD, with an average age of 6.41 ± 1.96, diagnosed in the Developmental Behavior Department of the Children's Hospital Affiliated with the Medical College of Zhejiang University were included in the analysis. This study trained the traditional diagnostic models of Logistic regression (LR), Support Vector Machine (SVM), and two ensemble learning algorithms [Random Forest (RF) and XGBoost]. Socio-demographic and behavioral observation data were used to distinguish whether autistic children had combined ID. The hyperparameters adjustment uses grid search and 10-fold validation. The Boruta method is used to select variables. The model's performance was evaluated using discrimination, calibration, and decision curve analysis (DCA).

Result

Among 241 autistic children, 98 (40.66%) were ASD comorbid ID. The four diagnostic models can better distinguish whether autistic children are complicated with ID, and the accuracy of SVM is the highest (0.836); SVM and XGBoost have better accuracy (0.800, 0.838); LR has the best sensitivity (0.939), followed by SVM (0.952). Regarding specificity, SVM, RF, and XGBoost performed significantly higher than LR (0.355). The AUC of ML (SVM, 0.835 [95% CI: 0.747-0.944]; RF, 0.829 [95% CI: 0.738-0.920]; XGBoost, 0.845 [95% CI: 0.734-0.937]) is not different from traditional LR (0.858 [95% CI: 0.770-0.944]). Only SVM observed a good calibration degree. Regarding DCA, LR, and SVM have higher benefits in a wider threshold range.

Conclusion

Compared to the traditional regression model, ML model based on socio-demographic and behavioral observation data, especially SVM, has a better ability to distinguish whether autistic children are combined with ID.

Identification of Ferroptosis-Related Molecular Clusters and Immune Characterization in Autism Spectrum Disorder

Introduction: Autism spectrum disorder (ASD) is a neurodevelopmental disorder with clinical presentation and prognostic heterogeneity. Ferroptosis is a regulated non-apoptotic cell death program implicated in the occurrence and progression of various diseases. Therefore, we aimed to explore ferroptosis-related molecular subtypes in ASD and further illustrate the potential mechanism.

Methods: A total of 201 normal samples and 293 ASD samples were obtained from the Gene Expression Omnibus (GEO) database. We used the unsupervised clustering analysis to identify the molecular subtypes based on ferroptosis-related genes (FRGs) and evaluate the immune characteristics between ferroptosis subtypes. Ferroptosis signatures were identified using the least absolute shrinkage and selection operator regression (LASSO) and recursive feature elimination for support vector machines (SVM-RFE) machine learning algorithms. The ferroptosis scores based on seven selected genes were constructed to evaluate the ferroptosis characteristics of ASD.

Results: We identified 16 differentially expressed FRGs in ASD children compared with controls. Two distinct molecular clusters associated with ferroptosis were identified in ASD. Analysis of immune infiltration revealed immune heterogeneity between the two clusters. Cluster2, characterized by a higher immune score and a larger number of infiltrated immune cells, exhibited a stronger immune response and was markedly enriched in immune response-related signaling pathways. Additionally, the ferroptosis scores model was capable of predicting ASD subtypes and immunity. Higher levels of ferroptosis scores were associated with immune activation, as seen in Cluster2. Lower ferroptosis scores were accompanied by relative immune downregulation, as seen in Cluster1.

Conclusion: Our study systematically elucidated the intricate correlation between ferroptosis and ASD and provided a promising ferroptosis score model to predict the molecular clusters and immune infiltration cell profiles of children with ASD.

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.