ECG waveform generation from radar signals: A deep learning perspective.

Cardiovascular diagnostics relies heavily on the ECG (ECG), which reveals significant information about heart rhythm and function. Despite their significance, traditional ECG measures employing electrodes have limitations. As a result of extended electrode attachments, patients may experience skin irritation or pain, and motion artifacts may interfere with signal accuracy. Additionally, ECG monitoring usually requires highly trained professionals and specialized equipment, which increases the treatment's complexity and cost. In critical care scenarios, such as continuous monitoring of hospitalized patients, wearable sensors for collecting ECG data may be difficult to use. Although there are issues with ECG, it remains a valuable tool for diagnosing and monitoring cardiac disorders due to its non-invasive nature and the detailed information it provides about the heart. The goal of this study is to present an innovative method for generating continuous ECG waveforms from non-contact radar data by using Deep Learning. The method can eliminate the need for invasive or wearable biosensors and expensive equipment to collect ECGs. In this paper, we propose the MultiResLinkNet, a one-dimensional convolutional neural network (1D CNN) model for generating ECG signals from radar waveforms. With the help of a publicly accessible radar benchmark dataset, an end-to-end DL architecture is trained and assessed. There are six ports of raw radar data in this dataset, along with ground truth physiological signals collected from 30 participants in five distinct scenarios: Resting, Valsalva, Apnea, Tilt-up, and Tilt-down. By using strong temporal and spectral measurements, we assessed our proposed framework's ability to convert ECG data from Radar signals in three distinct scenarios, namely Resting, Valsalva, and Apnea (RVA). ECG segmentation performed better by MultiResLinkNet than by state-of-the-art networks in both combined and individual cases. As a result of the simulations, the resting, valsalva, and RVA scenarios showed the highest average temporal values, respectively: 66.09523 ± 19.33, 60.13625 ± 21.92, and 61.86265 ± 21.37. In addition, it exhibited the highest spectral correlation values (82.4388 ± 18.42 (Resting), 77.05186 ± 23.26 (Valsalva), 74.65785 ± 23.17 (Apnea), and 79.96201 ± 20.82 (RVA)), along with minimal temporal and spectral errors in almost every case. The qualitative evaluation revealed strong similarities between generated and actual ECG waveforms. As a result of our method of forecasting ECG patterns from remote radar data, we can monitor high-risk patients, especially those undergoing surgery.

ViTab Transformer Framework for Predicting Induced Electric Field and Focality in Transcranial Magnetic Stimulation.

Transcranial magnetic stimulation is an electromagnetic induction-based non-invasive therapeutic technique for neurological diseases. For finding new clinical applications and enhancing the efficacy of TMS in existing neurological disorders, the current study focuses on a deep learning-based prediction model as an alternative to time-consuming electromagnetic (EM) simulation software. The main bottleneck of the existing prediction models is to consider very few input parameters of a standard coil such as coil type and coil position for predicting an output of electric field value. To overcome this limitation, a transformer-based prediction model titled as ViTab transformer is developed in this work to predict electric field (E-max), focality or area of stmulation (S-half), and volume of stimulation (V-half) by considering several input parameters such as sources of MRI images, types of coils, coil position, rate of change of current, brain tissues conductivity, and coil distance from the scalp. The proposed framework consists of a vision and a tab transformer to handle both image and tabular-type data. The prediction performance of the offered model is evaluated in terms of coefficient determination, R2 score, for E-max, V-half, and S-half in the testing phase. The obtained result in terms of R2 score for E-max, V-half, and S-half are found 0.97, 0.87, and 0.90 respectively. The results indicate that the suggested ViTab transformer model can predict electric field as well as focality more accurately than the current state-of-the-art methods. The reduced computational time, as well as efficient prediction accuracy, resembles that ViTab transformer can assist the neuroscientist and neurosurgeon prior to providing superior TMS treatment in near future.

Attention-assisted hybrid 1D CNN-BiLSTM model for predicting electric field induced by transcranial magnetic stimulation coil.

Deep learning-based models such as deep neural network (DNN) and convolutional neural network (CNN) have recently been established as state-of-the-art for enumerating electric fields from transcranial magnetic stimulation coil. One of the main challenges related to this electric field enumeration is the prediction time and accuracy. Despite the low computational cost, the performance of the existing prediction models for electric field enumeration is quite inefficient. This study proposes a 1D CNN-based bi-directional long short-term memory (BiLSTM) model with an attention mechanism to predict electric field induced by a transcranial magnetic stimulation coil. The model employs three consecutive 1D CNN layers followed by the BiLSTM layer for extracting deep features. After that, the weights of the deep features are redistributed and integrated by the attention mechanism and a fully connected layer is utilized for the prediction. For the prediction purpose, six input features including coil turns of single wing, coil thickness, coil diameter, distance between two wings, distance between head and coil position, and angle between two wings of coil are mapped with the output of the electric field. The performance evaluation is conducted based on four verification metrics (e.g. R2, MSE, MAE, and RMSE) between the simulated data and predicted data. The results indicate that the proposed model outperforms existing DNN and CNN models in predicting the induced electrical field with R2 = 0.9992, MSE = 0.0005, MAE = 0.0188, and RMSE = 0.0228 in the testing stage.

Analysis of Induced Field in the Brain Tissue by Transcranial Magnetic Stimulation Using Halo-V Assembly Coil.

As a noninvasive neuromodulation technique, transcranial magnetic stimulation (TMS) has already exhibited a great impact in clinical application and scientific research. This study presents a finite element method-based simulation of the Halo-V assembly (HVA) coil placed on the five-shell spherical human head model to examine the distributions of induced electric and magnetic fields. The performance of the designed HVA coil is evaluated by comparing the simulation results with the commercially available Halo-FO8 (HFA) assembly coil and standard single coils including the Halo and V coils. The simulation results indicate that the HVA coil shows an improved focality in terms of electric field distribution than the other single and assembly stimulation coils. Additionally, the effects of a magnetic shield plate and magnetic core on the designed HVA coil are investigated. Results indicate that the magnetic shield plate and magnetic core are proficient in further improving the stimulation focality. Therefore, the HVA TMS coil results in a safe and effective stimulation with enhanced focality of the target region as compared to the existing assembly coil.

Designing of Hollow Core Grapefruit Fiber Using Cyclo Olefin Polymer for the Detection of Fuel Adulteration in Terahertz Region.

A grapefruit-shape hollow-core liquid infiltrated photonic crystal fiber (LI-PCF) is proposed and evaluated to identify the percentage of kerosene in adulterated petrol. The proposed hollow-fiber sensor is designed with Cyclo Olefin Polymer (Zeonex) and likely to be filled with different samples of petrol which is adulated by the kerosene up to 100%. Considering the electromagnetic radiation in THz band, the sensing properties are thoroughly investigated by adopting finite element method (FEM) based COMSOL Multiphysics software. However, the proposed sensor offers a very high relative sensitivity (RS) of 97.27% and confinement loss (CL) less than 10-10 dB/m, and total loss under 0.07 dB/cm, at 2 THz operating frequency. Besides that, the sensor also possesses a low effective material loss (EML), high numerical aperture (NA), and large Marcuse spot size (MSS). The sensor structure is fabrication feasible through existing fabrication methodologies consequently making this petrol adulteration sensor a propitious aspirant for real-life applications of petrol adulteration measurements in commercial and industrial sensing.

Radio frequency energy harvesting from a feeding source in a passive deep brain stimulation device for murine preclinical research.

This paper presents the development of an energy harvesting circuit for use with a head-mountable deep brain stimulation (DBS) device. It consists of a circular planar inverted-F antenna (PIFA) and a Schottky diode-based Cockcroft-Walton 4-voltage rectifier. The PIFA has the volume of π × 10(2) × 1.5 mm(3), resonance frequency of 915 MHz, and bandwidth of 16 MHz (909-925 MHz) at a return loss of -10 dB. The rectifier offers maximum efficiency of 78% for the input power of -5 dBm at a 5 kΩ load resistance. The developed rectenna operates efficiently at 915 MHz for the input power within -15 dBm to +5 dBm. For operating a DBS device, the DC voltage of 2 V is recorded from the rectenna terminal at a distance of 55 cm away from a 26.77 dBm transmitter in free space. An in-vitro test of the DBS device is presented.

RF rectifiers for EM power harvesting in a Deep Brain Stimulating device.

A passive deep brain stimulation (DBS) device can be equipped with a rectenna, consisting of an antenna and a rectifier, to harvest energy from electromagnetic fields for its operation. This paper presents optimization of radio frequency rectifier circuits for wireless energy harvesting in a passive head-mountable DBS device. The aim is to achieve a compact size, high conversion efficiency, and high output voltage rectifier. Four different rectifiers based on the Delon doubler, Greinacher voltage tripler, Delon voltage quadrupler, and 2-stage charge pumped architectures are designed, simulated, fabricated, and evaluated. The design and simulation are conducted using Agilent Genesys at operating frequency of 915 MHz. A dielectric substrate of FR-4 with thickness of 1.6 mm, and surface mount devices (SMD) components are used to fabricate the designed rectifiers. The performance of the fabricated rectifiers is evaluated using a 915 MHz radio frequency (RF) energy source. The maximum measured conversion efficiency of the Delon doubler, Greinacher tripler, Delon quadrupler, and 2-stage charge pumped rectifiers are 78, 75, 73, and 76 % at -5 dBm input power and for load resistances of 5-15 kΩ. The conversion efficiency of the rectifiers decreases significantly with the increase in the input power level. The Delon doubler rectifier provides the highest efficiency at both -5 and 5 dBm input power levels, whereas the Delon quadrupler rectifier gives the lowest efficiency for the same inputs. By considering both efficiency and DC output voltage, the charge pump rectifier outperforms the other three rectifiers. Accordingly, the optimised 2-stage charge pumped rectifier is used together with an antenna to harvest energy in our DBS device.

Closed loop deep brain stimulation: an evolving technology.

Deep brain stimulation is an effective and safe medical treatment for a variety of neurological and psychiatric disorders including Parkinson's disease, essential tremor, dystonia, and treatment resistant obsessive compulsive disorder. A closed loop deep brain stimulation (CLDBS) system automatically adjusts stimulation parameters by the brain response in real time. The CLDBS continues to evolve due to the advancement in the brain stimulation technologies. This paper provides a study on the existing systems developed for CLDBS. It highlights the issues associated with CLDBS systems including feedback signal recording and processing, stimulation parameters setting, control algorithm, wireless telemetry, size, and power consumption. The benefits and limitations of the existing CLDBS systems are also presented. Whilst robust clinical proof of the benefits of the technology remains to be achieved, it has the potential to offer several advantages over open loop DBS. The CLDBS can improve efficiency and efficacy of therapy, eliminate lengthy start-up period for programming and adjustment, provide a personalized treatment, and make parameters setting automatic and adaptive.

Design and analysis of an antenna for wireless energy harvesting in a head-mountable DBS device.

This paper presents design and simulation of a circular meander dipole antenna at the industrial, scientific, and medical band of 915 MHz for energy scavenging in a passive head-mountable deep brain stimulation device. The interaction of the proposed antenna with a rat body is modeled and discussed. In the antenna, the radiating layer is meandered, and a FR-4 substrate is used to limit the radius and height of the antenna to 14 mm and 1.60 mm, respectively. The resonance frequency of the designed antenna is 915 MHz and the bandwidth of 15 MHz at a return loss of -10 dB in free space. To model the interaction of the antenna with a rat body, two aspects including functional and biological are considered. The functional aspect includes input impedance, resonance frequency, gain pattern, radiation efficiency of the antenna, and the biological aspect involves electric field distribution, and SAR value. A complete rat model is used in the finite difference time domain based EM simulation software XFdtd. The simulated results demonstrate that the specific absorption rate distributions occur within the skull in the rat model, and their values are higher than the standard regulated values for the antenna receiving power of 1W.

Compact stacked planar inverted-F antenna for passive deep brain stimulation implants.

A compact meandered three-layer stacked circular planar inverted-F antenna is designed and simulated at the UHF band (902.75 - 927.25 MHz) for passive deep brain stimulation implants. The UHF band is used because it offers small antenna size, and high data rate. The top and middle radiating layers are meandered, and low cost substrate and superstrate materials are used to limit the radius and height of the antenna to 5 mm and 1.64 mm, respectively. A dielectric substrate of FR-4 of ε(r)= 4.7 and δ= 0.018, and a biocompatible superstrate of silicone of er= 3.7 and d= 0.003 with thickness of 0.2 mm are used in the design. The resonance frequency of the proposed antenna is 918 MHz with a bandwidth of 24 MHz at return loss of -10 dB in free space. The antenna parameter such as 3D gain pattern of the designed antenna within a skin-tissue model is evaluated by using the finite element method. The compactness, wide bandwidth, round shape, and stable characteristics in skin make this antenna suitable for DBS. The feasibility of the wireless power transmission to the implant in the human head is also examined.