Nanophotonics has garnered intensive attention due to its unique capabilities in molding the flow of light subwavelength regime. Metasurfaces (MSs) and photonic integrated circuits (PICs) enable realization mass-producible, cost-effective, highly efficient flat optical components for imaging, sensing, communications. In order nanophotonics with multi-purpose functionalities, chalcogenide phase-change materials (PCMs) have been introduced as a promising platform tunable reconfigurable...

Abstract In this paper, we demonstrate a computationally efficient new approach based on deep learning (DL) techniques for analysis, design and optimization of electromagnetic (EM) nanostructures. We use the strong correlation among features generic EM problem to considerably reduce dimensionality thus, computational complexity, without imposing considerable errors. By employing reduction concept using more recently demonstrated autoencoder technique, redefine conventional many-to-one in...

Efficient hybrid plasmonic-photonic metasurfaces that simultaneously take advantage of the potential both pure metallic and all-dielectric nanoantennas are identified as an emerging technology in flat optics. Nevertheless, post-fabrication tunable still elusive. Here, we present a reconfigurable metasurface platform by incorporating phase-change material Ge$_{2}$Sb$_{2}$Te$_{5}$ (GST) into metal-dielectric meta-atoms for active non-volatile tuning properties light. We systematically design...

We present here a new approach for using the intelligence aspects of artificial knowledge discovery rather than device optimization in electromagnetic (EM) nanostructures. This uses training data obtained through full-wave EM simulations series nanostructures to train geometric deep learning algorithms assess range feasible responses as well feasibility desired response from class To facilitate and reduce computation complexity, our combines dimensionality reduction technique (using an...

Here, for the first time to our knowledge, a Fano resonance metasurface made of HfO₂ is experimentally demonstrated generate wide range colors. We use novel deep-learning technique design and optimize metasurface.

Abstract Cardiac auscultation is an accessible diagnostic screening tool that can help to identify patients with heart murmurs for follow-up and treatment abnormal cardiac function. However, experts are needed interpret the sounds, limiting accessibility of care in resource-constrained environments. Therefore, George B. Moody PhysioNet Challenge 2022 invited teams develop algorithmic approaches detecting function from phonocardiogram (PCG) recordings sounds. For Challenge, we sourced 5272...

Here, we present a new approach based on manifold learning for knowledge discovery and inverse design with minimal complexity in photonic nanostructures. Our builds studying submanifolds of responses class nanostructures different complexities the latent space to obtain valuable insight about physics device operation guide more intelligent design. In contrast current methods nanostructures, which are limited preselected usually overcomplex structures, show that our method allows evolution...

Abstract Objective: This study aims to evaluate the efficacy of wearable physiology and movement sensors in identifying a spectrum challenging behaviors, including self-injurious behavior (SIB), children teenagers with autism disorder (ASD) real-world settings. Approach: We utilized long-short-term memory (LSTM) network features derived using wavelet scatter transform analyze physiological biosignals, electrodermal activity skin temperature, alongside three-dimensional data captured via...

Abstract In this paper, a deep learning‐based algorithm is presented, as purely mathematical platform, for providing intuitive understanding of the properties electromagnetic (EM) wave–matter interaction in nanostructures. This approach based on using dimensionality reduction (DR) technique to significantly reduce generic EM wave‐matter problem without imposing significant error. Such an implicitly provides useful information about role different features (such geometrical design parameters)...

We present a novel metric-learning approach based on combined triplet loss and mean-squared error for providing more functionality (e.g., effective similarity measures) to the machine-learning algorithms used knowledge discovery inverse design of nanophotonic structures compared commonly mean-absolute error. demonstrate main shortcoming existing metrics (or functions) in mapping responses into lower-dimensional spaces keeping similar close each other. show how systematic paradigm can resolve...

Abstract We report a new approach using artificial intelligence (AI) to study and classify the severity of COVID-19 1208 chest X-rays (CXRs) 396 patients obtained through course disease at Emory Healthcare affiliated hospitals (Atlanta, GA, USA). Using two-stage transfer learning technique train convolutional neural network (CNN), we show that algorithm is able four classes (normal, mild, moderate, severe) with average Area Under Curve (AUC) 0.93. In addition, outputs different layers CNN...

Mild cognitive impairment (MCI) involves decline beyond normal age and education expectations. It correlates with decreased socialization increased aimless motion. We aim to automate detection of these behaviors for improved longitudinal monitoring. used a privacy-preserving distributed camera network collect data from MCI patients in an indoor space. Movement social interaction features were developed using this train machine learning algorithms differentiate between higher lower...

ABSTRACT Bluetooth low energy (BLE)‐based indoor localization has been extensively researched due to its cost‐effectiveness, power consumption, and ubiquity. Despite these advantages, the variability of received signal strength indicator (RSSI) measurements, influenced by physical obstacles, human presence, electronic interference, poses a significant challenge accurate localization. In this work, we present an optimised method enhance accuracy utilising multiple BLE beacons in radio...

Abstract Objective: To determine whether historical behavior data can predict the
occurrence of high-risk behavioral or Seizure events in individuals with profound
Autism Spectrum Disorder (ASD), thereby facilitating early intervention and improved
support.Approach: We conducted an analysis nine years seizure
data from 353 ASD. Our focused on the seven most common
behaviors labeled by a human, while all other behaviors were grouped into...

In this Letter, we present a deep-learning-based method using neural networks (NNs) for inverse design of photonic nanostructures. We show that by dimensionality reduction in both the and response spaces, computational complexity algorithm is considerably reduced. As proof concept, apply to multi-layer thin-film structures composed consecutive layers two different dielectrics compare results our techniques those conventional NNs.

Spatial navigation patterns in indoor space usage can reveal important cues about the cognitive health of participants. In this work, we present a low-cost, scalable, open-source edge computing system using Bluetooth low energy (BLE) beacons for tracking movements large, 1700 m2 facility used to carry out therapeutic activities participants with mild impairment (MCI). The is instrumented 39 systems, along an on-premise fog server. BLE beacon, which signals are received and analyzed by...

The George B. Moody PhysioNet Challenge 2022 explored the detection of abnormal heart function from phonocardiogram (PCG) recordings.Although ultrasound imaging is becoming more common for investigating defects, PCG still has potential to assist with rapid and low-cost screening, automated annotation recordings further improve access.Therefore, this Challenge, we asked participants design working, opensource algorithms that use identify murmurs clinical outcomes.This makes several...

Camera-based activity monitoring systems are becoming an attractive solution for smart building applications with the advances in computer vision and edge computing technologies. In this paper, we present a feasibility study systematic analysis of camera-based indoor localization multi-person tracking system implemented on devices within large space. To end, deployed end-to-end pipeline that utilizes multiple cameras to achieve localization, body orientation estimation individuals...

Social interaction behaviors change as a result of both physical and psychiatric problems, it is important to identify subtle changes in group activity engagements for monitoring the mental health patients clinics. This work proposes system when where formations occur an approximately 1,700 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$m^{2}$</tex-math></inline-formula> therapeutic built environment using...

Poor sleep quality in Autism Spectrum Disorder (ASD) individuals is linked to severe daytime behaviors. This study explores the relationship between a prior night's structure and its predictive power for next-day behavior ASD individuals. The motion was extracted using low-cost near-infrared camera privacy-preserving way. Over two years, we recorded overnight data from 14 individuals, spanning over 2,000 nights, tracked challenging behaviors, including aggression, self-injury, disruption. We...

Poor sleep quality in Autism Spectrum Disorder (ASD) individuals is linked to severe daytime behaviors. This study explores the relationship between a prior night's structure and its predictive power for next-day behavior ASD individuals. The motion was extracted using low-cost near-infrared camera privacy-preserving way. Over two years, we recorded overnight data from 14 individuals, spanning over 2,000 nights, tracked challenging behaviors, including aggression, self-injury, disruption. We...

We present a hybrid device platform for creating an electrically reconfigurable metasurface formed by the integration of plasmonic nanostructures with phase-change material germanium antimony telluride (GST). By changing phase GST from amorphous to crystalline through Joule heating, large range responses can be achieved. Furthermore, using intermediate phases GST, interact incident light in both over-coupling and under-coupling regimes, leading inherently broadband response. Through detailed...

Objective: The purpose was to evaluate reader variability between experienced and in-training radiologists of COVID-19 pneumonia severity on chest radiograph (CXR), create a multireader database suitable for AI development. Methods: In this study, CXRs from polymerase chain reaction positive patients were reviewed. Six cardiothoracic two residents classified each CXR according severity. One radiologist performed the classification twice assess intraobserver variability. Severity assessed...

Spatial navigation of indoor space usage patterns reveals important cues about the cognitive health individuals. In this work, we present a low-cost, scalable, open-source edge computing system using Bluetooth Low Energy (BLE) and Inertial Measurement Unit sensors (IMU) for tracking movements large facility (over 1600 m^2) that was designed to facilitate therapeutic activities individuals with Mild Cognitive Impairment. The is instrumented 39 systems an on-premise fog server, subjects carry...