Vascular dementia is the second most common form of dementia and a leading cause of death. Brain stroke and brain atrophy are the major degenerative pathologies associated with vascular dementia. Timely detection of these progressive pathologies is critical to avoid brain damage. Brain imaging is an important diagnostic tool and determines future treatment options available to the patient. Traditional medical technologies are expensive, require extensive supervision and are not easily accessible. This paper presents a novel concept of low- complexity wearable sensing system for the detection of brain stroke and brain atrophy using RF sensors. This multimodal RF sensing system provides a first-of-its-kind RF sensing solution for the detection of cerebral blood density variations and blood clots at an initial stage of neurodegeneration. A customized microwave imaging algorithm is presented for the reconstruction of images in affected areas of the brain. Designs are validated using software simulations and hardware modeling. Fabricated sensors are experimentally validated and can effectively detect blood density variation (1050 ± 50 Kg/m ³ ), artificial stroke targets with a volume of 27 mm ³ and density of 1025-1050 Kg/m3, and brain atrophy with a cavity of 58 mm ³ within a realistic brain phantom. The safety of the proposed wearable RF sensing system is studied through the evaluation of the Specific Absorption Rate (SAR < 1.4 W/Kg, 100mW) and thermal conductivity of the brain (< 0.152°C). The results indicate that the device is viable as an efficient, portable, and low-cost substitute for vascular dementia detection.

Cerebral blood flow (CBF) signifies the rate at which blood circulates within the brain’s vascular network. CBF irregularities can lead to insufficient blood delivery to the brain, impacting cerebral metabolic processes. Consequently, this leads to gradual deterioration of neuronal health, potentially leading to cognitive decline, vascular dysfunction, dementia or stroke. Regular monitoring of CBF is critical for early detection of irregularities in the neurovascular system. The conventional neuroimaging techniques are costly, lack easy accessibility and necessitate significant supervision to operate. This paper proposes a novel Radio Frequency (RF) sensing system to effectively detect blood flow variations through backscattered RF signals. The non-invasive, cost-effective and portable sensing system features a novel miniaturized U-shaped antenna sensor integrated with eyeglasses for real-time monitoring. The sensor design is validated through microwave computational software and the fabricated sensing system is experimentally evaluated on an artificial brain model with an integrated arterial network of varying diameters. The results are measured on variable flow rates to accurately detect variations ranging from 10 to 90 mL/min. Machine Learning (ML) and Deep Learning (DL) methodologies are analyzed for classification into low, average and high CBF. A Gaussian noise feature data augmentation method is implemented on statistical feature and autonomous (AutoEncoders (AE) and Stacked AutoEncoders (SAE)) feature data. Ensemble bagged tree and Linear SVM offer a binary and multiclass classification accuracy of 96.2% and 88.9%, respectively on the statistical feature data augmented. Gaussian SVM has accuracies of 87.1% and 76.3% for binary and multi-class classification with SAE (32-16-32).

The strong association between hearing loss and cognitive decline has developed into a major health challenge that calls for early detection, diagnosis and prevention. Hearing loss usually results in severe health implications that include loss of mobility, communication problems and cognitive decline. This study provides an overview of the effects of hearing loss on cognition and progressive neurological disorders with a discussion on the future scope of microwave portable technologies in care homes arrangement. Moreover, the efficacy of hearing aids in reversing cognitive decline and dementia has been investigated. The interconnection between hearing loss, cognitive load and neurodegeneration is also explored. Furthermore, this study looks into the prospects of using portable microwave sensors for the detection and monitoring of cognitive load. For early detection of dementia, this study proposes the integration of microwave sensors with hearing aid devices. Implications and design challenges of portable antenna systems for neurodegeneration detection have also been considered. Future improvement areas regarding robust analysis and diagnosis, system accuracy and security, user-centricity and device privacy for a broader clinical implementation are also discussed.

Microstrip crescent antennas offer compactness, conformability, low profile, high sensitivity, multi-band operability, cost-effectiveness and ease of fabrication in contrast to bulky, rigid horn, helical and Vivaldi antennas. This work presents crescent sensors for monitoring brain pathology associated with stroke and atrophy. Single- and multi-element crescent sensors are designed and validated by software simulations. The fabricated sensors are integrated with glasses and experimentally evaluated using a realistic brain phantom. The performance of the sensors is compared in terms of peak gain, directivity, radiation performance, flexibility and detection capability. The crescent sensors can detect the pathologies through the monitoring of backscattered electromagnetic signals that are triggered by dielectric variations in the affected tissues. The proposed sensors can effectively detect stroke and brain atrophy targets with a volume of 25 mm³ and 56 mm³, respectively. The safety of the sensors is examined through the evaluation of Specific Absorption Rate (peak SAR < 1.25 W/Kg, 100 mW), temperature increase within brain tissues (max: 0.155 °C, min: 0.115 °C) and electric field analysis. The results suggest that the crescent sensors can provide a flexible, portable and non-invasive solution to monitor degenerative brain pathology.

Stroke occurs when the blood flow to a certain region of the brain is disrupted. It is a leading cause of long-term disability and can result in cognitive impairments, speech difficulties, and motor dysfunction. Regular monitoring and timely intervention are critical to minimizing the damage and improving outcomes. This article presents a novel Radio Frequency (RF) sensing and Artificial Intelligence (AI) based Digital Twin (DT) model for effective detection of stroke. Through backscattering RF signals, the proposed Ultra Wide Band (UWB) antenna provides stroke detection. The implementation of Machine Learning (ML) and Deep Learning (DL) technologies for stroke classification provides the necessary decision support to healthcare professionals in DT stroke patient monitoring. The statistical and autonomous (AutoEncoders (AE) and Stacked AutoEncoders (SAE) with structure 32-16-32, 64-32-16-32-64, and 128-64-32-16-32-64-128) feature data is enlarged through Gaussian noise feature data augmentation. The Fine KNN algorithm provides the 93.4% and 92.3% classification accuracies of binary and multi-class classification respectively. Out of the 4 autonomous feature extraction methods, the Fine KNN algorithm with SAE structure 64-32-16-32-64 provided the highest accuracies of 88.2% and 74.8% for binary and multi-class classification.

Facial expressions are a crucial aspect of non-verbal communication and often reflect underlying emotional states. Researchers often use facial emotion detection as a tool to gain insights into cognitive processes, emotional states and cognitive load. The conventional camera-based methods to sense human emotions are privacy intrusive, lack adaptability, and are sensitive to variability. These technologies have limited generalization and may not adapt well to variations in ambient lighting, facial landmark localization, facial occlusions and emotion intensity. Radio Frequency (RF) sensing offers promising avenues for improvement with contactless, non-invasive, privacy-preserving and reliable radar-based measurements. The proposed framework utilizes deep-learning techniques to classify facial micro-doppler signatures, generated from an ultra-wideband (UWB) radar. The method relies on continuous multi-level feature learning from radar time-frequency Doppler measurements. The spatiotemporal facial features are extracted from the radar data to train deep learning models. The proposed system achieves a high multiclass classification accuracy of 77% on the continuous streamed data covering basic emotions of anger, disgust, fear, happy, neutral and sadness. The system can transform next-generation multi-modal hearing aids with emotion-aware listening effort and cognitive load detection. This can be particularly useful in translating the emotion-assisted cognitive effort for real-time speech enhancement and personalized auditory experience.