A Multichannel Electrochemical Sensor Interface IC for Bioreactor Monitoring.

This research article introduces a novel integrated circuit (IC) designed for bioreactor applications catering to multichannel electrochemical sensing. The proposed IC comprises 2x potentiometric, 2x potentiostat, 2x ISFET channels and 1x temperature channel. The potentiostat channel utilizes a current conveyor-based architecture with a programmable mirroring ratio, enabling an extensive measurement range of 114 dB. The potentiometric channel incorporates a customized electrostatic discharge (ESD) protection circuit to achieve ultra-low input leakage in the picoampere range, while the ISFET channel employs a constant-voltage, constant-current topology for accurate pH measurement. Combined with the die temperature sensor, this IC is well-suited for monitoring bioreactions in real-time. Additionally, all channels can be time-multiplexed to a reconfigurable analog backend, facilitating the conversion of input signals into digital codes. The prototype of the IC is fabricated using 0.18 µm standard CMOS technology, and each channel is experimentally characterized. The interface IC demonstrates a peak power consumption of 22 µW.

Protein-Protein Interaction in Multicomponent Reaction Enables Chemoselective, Site-Selective, and Modular Labeling of Native Proteins.

A protein's pool of functionalities presents a formidable challenge for its single-site modification. Here, we report a method to harness protein-protein interaction (PPI) to drive selective modification. It involves the chemoselective reversible generation of reactive intermediates and utilizes PPI-specificity to drive the subsequent site-selective irreversible step. The disintegrate (DIN) theory-driven multicomponent aza-Morita-Baylis-Hillman (aza-MBH) reaction offers homogeneous and modular single-site protein modification capable of late-stage mono- and dual-probe installation.

LSTM-only Model for Low-complexity HR Estimation from Wrist PPG.

Continuous and non-invasive cardiovascular monitoring has gained attention due to the miniaturization of wearable devices. Particularly, wrist-worn photoplethysmography (PPG) sensors present an alternative to electrocardiogram recording for heart rate (HR) monitoring as it is cheaper and non-intrusive for daily activities. Yet, the accuracy of PPG measurements is heavily affected by motion artifacts which are inherent to ambulatory environments. In this paper, we propose a low-complexity LSTM-only neural network for HR estimation from a single PPG channel during intense physical activity. This work explored the trade-off between model complexity and accuracy by exploring different model dataflows, number of layers, and number of training epochs to capture the intrinsic time-dependency between PPG samples. The best model achieves a mean absolute error of 4.47 ± 3.68 bpm when evaluated on 12 IEEE SPC subjects.Clinical relevance- This work aims to improve the quality of HR inference from PPG signals using neural network, enabling continuous vital signal monitoring with little interference in daily activities from embedded monitoring devices.

A 134 DB Dynamic Range Noise Shaping Slope Light-to-Digital Converter for Wearable Chest PPG Applications.

This paper presents a low power, high dynamic range (DR), light-to-digital converter (LDC) for wearable chest photoplethysmogram (PPG) applications. The proposed LDC utilizes a novel 2nd-order noise-shaping slope architecture, directly converting the photocurrent to a digital code. This LDC applies a high-resolution dual-slope quantizer for data conversion. An auxiliary noise shaping loop is used to shape the residual quantization noise. Moreover, a DC compensation loop is implemented to cancel the PPG signal's DC component, thus further boosting the DR. The prototype is fabricated with 0.18 µm standard CMOS and characterized experimentally. The LDC consumes 28 µW per readout channel while achieving a maximum 134 dB DR. The LDC is also validated with on-body chest PPG measurement.

Binary CorNET: Accelerator for HR Estimation From Wrist-PPG.

Research on heart rate (HR) estimation using wrist-worn photoplethysmography (PPG) sensors have progressed rapidly owing to the prominence of commercial sensing modules, used widely for lifestyle monitoring. Reported methodologies have been fairly successful in mitigating the effect of motion artifacts (MA) in ambulatory environment for HR estimation. Recently, a learning framework, CorNET, employing two-layer convolution neural networks (CNN) and two-layer long short-term network (LSTM) was successfully reported for estimating HR from MA-induced PPG signals. However, such a network topology with large number of parameters presents a challenge, towards low-complexity hardware implementation aimed at on-node processing. In this paper, we demonstrate a fully binarized network (bCorNET) topology and its corresponding algorithm-to-architecture mapping and energy-efficient implementation for HR estimation. The proposed framework achieves a MAE of 6.67 ± 5.49 bpm when evaluated on 22 IEEE SPC subjects. The design, synthesized with ST65 nm technology library achieving 3 GOPS @ 1 MHz, consumes 56.1 µJ per window with occupied 1634K NAND2 equivalent cell area and had a latency of 32 ms when estimating HR every 2 s from PPG signals.

MyoNet: A Transfer-Learning-Based LRCN for Lower Limb Movement Recognition and Knee Joint Angle Prediction for Remote Monitoring of Rehabilitation Progress From sEMG.

The clinical assessment technology such as remote monitoring of rehabilitation progress for lower limb related ailments rely on the automatic evaluation of movement performed along with an estimation of joint angle information. In this paper, we introduce a transfer-learning based Long-term Recurrent Convolution Network (LRCN) named as 'MyoNet' for the classification of lower limb movements, along with the prediction of the corresponding knee joint angle. The model consists of three blocks- (i) feature extractor block, (ii) joint angle prediction block, and (iii) movement classification block. Initially, the model is end-to-end trained for knee joint angle prediction followed by transferring the knowledge of a trained model to the movement classification through transfer-learning approach making a memory and computationally efficient design. The proposed MyoNet was evaluated on publicly available University of California (UC) Irvine machine learning repository dataset of the lower limb for 11 healthy subjects and 11 subjects with knee pathology for three movements type-walking, standing with knee flexion movements and sitting with knee extension movements. The average mean absolute error (MAE) resulted in the prediction of joint angle for healthy subjects and subjects with knee pathology are 8.1 % and 9.2 % respectively. Subsequently, an average classification accuracy of 98.1 % and 92.4 % were achieved for healthy subjects and subjects with knee pathology, respectively. Interestingly, the significance of this study in itself is promising with substantial improvement in the performance compared to state-of-the-art methodologies. The clinical significance of such surface electromyography signals (sEMG) based movement recognition and prediction of corresponding joint angle system could be beneficial for remote monitoring of rehabilitation progress by the physiotherapist using wearables.

A 769 µW Battery-Powered Single-Chip SoC With BLE for Multi-Modal Vital Sign Monitoring Health Patches.

An all-in-one battery powered low-power SoC for measuring multiple vital signs with wearables is proposed. All functionality needed in a typical wearable use case scenario, including dedicated readouts, power management circuitry, digital signal processing and wireless communication (BLE) is integrated in a single die. This high level of integration allows an unprecedented level of miniaturization leading to smaller component count which reduces cost and improves comfort and signal integrity. The SoC includes an ECG, Bio-Impedance and a fully differential PPG readout and can interface with external sensors (like an IMU). In a typical application scenario where all sensor readouts are enabled and key features (like heart rate) are calculated on the chip and streamed over the radio, the SoC consumes only 769 µW from the regulated 1.2 V supply.

Rehab-Net: Deep Learning Framework for Arm Movement Classification Using Wearable Sensors for Stroke Rehabilitation.

In this paper, we present a deep learning framework "Rehab-Net" for effectively classifying three upper limb movements of the human arm, involving extension, flexion, and rotation of the forearm, which, over the time, could provide a measure of rehabilitation progress. The proposed framework, Rehab-Net is formulated with a personalized, light weight and low-complex, customized convolutional neural network (CNN) model, using two-layers of CNN, interleaved with pooling layers, followed by a fully connected layer that classifies the three movements from tri-axial acceleration input data collected from the wrist. The proposed Rehab-Net framework was validated on sensor data collected in two situations: 1) semi-naturalistic environment involving an archetypal activity of "making-tea" with four stroke survivors and 2) natural environment, where ten stroke survivors were free to perform any desired arm movement for the duration of 120 min. We achieved an overall accuracy of 97.89% on semi-naturalistic data and 88.87% on naturalistic data which exceeded state-of-the-art learning algorithms namely, linear discriminant analysis, support vector machines, and k-means clustering with an average accuracy of 48.89%, 44.14%, and 27.64%. Subsequently, a computational complexity analysis of the proposed model has been discussed with an eye toward hardware implementation. The clinical significance of this study is to accurately monitor the clinical progress of the rehabilitated subjects under the ambulatory settings.

Motion Artifact Reduction for Wrist-Worn Photoplethysmograph Sensors Based on Different Wavelengths.

Long-term heart rate (HR) monitoring by wrist-worn photoplethysmograph (PPG) sensors enables the assessment of health conditions during daily life with high user comfort. However, PPG signals are vulnerable to motion artifacts (MAs), which significantly affect the accuracy of estimated physiological parameters such as HR. This paper proposes a novel modular algorithm framework for MA removal based on different wavelengths for wrist-worn PPG sensors. The framework uses a green PPG signal for HR monitoring and an infrared PPG signal as the motion reference. The proposed framework includes four main steps: motion detection, motion removal using continuous wavelet transform, approximate HR estimation and signal reconstruction. The proposed algorithm is evaluated against an electrocardiogram (ECG) in terms of HR error for a dataset of 6 healthy subjects performing 21 types of motion. The proposed MA removal method reduced the average error in HR estimation from 4.3, 3.0 and 3.8 bpm to 0.6, 1.0 and 2.1 bpm in periodic, random, and continuous non-periodic motion situations, respectively.

CorNET: Deep Learning Framework for PPG-Based Heart Rate Estimation and Biometric Identification in Ambulant Environment.

Advancements in wireless sensor network technologies have enabled the proliferation of miniaturized body-worn sensors, capable of long-term pervasive biomedical signal monitoring. Remote cardiovascular monitoring has been one of the beneficiaries of this development, resulting in non-invasive, photoplethysmography (PPG) sensors being used in ambulatory settings. Wrist-worn PPG, although a popular alternative to electrocardiogram, suffers from motion artifacts inherent in daily life. Hence, in this paper, we present a novel deep learning framework (CorNET) to efficiently estimate heart rate (HR) information and perform biometric identification (BId) using only a wrist-worn, single-channel PPG signal collected in ambulant environment. We have formulated a completely personalized data-driven approach, using a four-layer deep neural network. Two convolution neural network layers are used in conjunction with two long short-term memory layers, followed by a dense output layer for modeling the temporal sequence inherent within the pulsatile signal representative of cardiac activity. The final dense layer is customized with respect to the application, functioning as: regression layer-having a single neuron to predict HR; classification layer-two neurons that identify a subject among a group. The proposed network was evaluated on the TROIKA dataset having 22 PPG records collected during various physical activities. We achieve a mean absolute error of 1.47 ± 3.37 beats per minute for HR estimation and an average accuracy of 96% for BId on 20 subjects. CorNET was further evaluated successfully in an ambulant use-case scenario with custom sensors for two subjects.

BioTranslator: Inferring R-Peaks from Ambulatory Wrist-Worn PPG Signal.

Advancements in wireless sensor networks (WSN) technology and miniaturization of wearable sensors have enabled long-term continuous pervasive biomedical signal monitoring. Wrist-worn photoplethysmography (PPG) sensors have gained popularity given their form factor. However the signal quality suffers due to motion artifacts when used in ambulatory settings, making vital parameter estimation a challenging task. In this paper, we present a novel deep learning framework, BioTranslator, for computing the instantaneous heart rate (IHR), using wrist-worn PPG signals collected during physical activity. Using one-dimensional Convolution-Deconvolution Network, we translate a single channel PPG signal to an electrocardiogram(ECG)-like time series signal, from which relevant R-peak information can be inferred enabling IHR measures. The proposed network configuration was evaluated on 12 subjects of the TROIKA dataset, involved in physical activity. The proposed network identifies 92.8% of R-peaks, besides achieving a mean absolute error of 51±6.3ms with respect to reference ECG-derived IHR.

CNN based approach for activity recognition using a wrist-worn accelerometer.

In recent years, significant advancements have taken place in human activity recognition using various machine learning approaches. However, feature engineering have dominated conventional methods involving the difficult process of optimal feature selection. This problem has been mitigated by using a novel methodology based on deep learning framework which automatically extracts the useful features and reduces the computational cost. As a proof of concept, we have attempted to design a generalized model for recognition of three fundamental movements of the human forearm performed in daily life where data is collected from four different subjects using a single wrist worn accelerometer sensor. The validation of the proposed model is done with different pre-processing and noisy data condition which is evaluated using three possible methods. The results show that our proposed methodology achieves an average recognition rate of 99.8% as opposed to conventional methods based on K-means clustering, linear discriminant analysis and support vector machine.

Detecting Elementary Arm Movements by Tracking Upper Limb Joint Angles With MARG Sensors.

This paper reports an algorithm for the detection of three elementary upper limb movements, i.e., reach and retrieve, bend the arm at the elbow and rotation of the arm about the long axis. We employ two MARG sensors, attached at the elbow and wrist, from which the kinematic properties (joint angles, position) of the upper arm and forearm are calculated through data fusion using a quaternion-based gradient-descent method and a two-link model of the upper limb. By studying the kinematic patterns of the three movements on a small dataset, we derive discriminative features that are indicative of each movement; these are then used to formulate the proposed detection algorithm. Our novel approach of employing the joint angles and position to discriminate the three fundamental movements was evaluated in a series of experiments with 22 volunteers who participated in the study: 18 healthy subjects and four stroke survivors. In a controlled experiment, each volunteer was instructed to perform each movement a number of times. This was complimented by a seminaturalistic experiment where the volunteers performed the same movements as subtasks of an activity that emulated the preparation of a cup of tea. In the stroke survivors group, the overall detection accuracy for all three movements was 93.75% and 83.00%, for the controlled and seminaturalistic experiment, respectively. The performance was higher in the healthy group where 96.85% of the tasks in the controlled experiment and 89.69% in the seminaturalistic were detected correctly. Finally, the detection ratio remains close ( ±6%) to the average value, for different task durations further attesting to the algorithms robustness.

Shape memory alloy smart knee spacer to enhance knee functionality: model design and finite element analysis.

In this paper we introduce Shape Memory Alloy (SMA) for designing the tibial part of Total Knee Arthroplasty (TKA) by exploiting the shape-memory and pseudo-elasticity property of the SMA (e.g. NiTi). This would eliminate the drawbacks of the state-of-the art PMMA based knee-spacer including fracture, sustainability, dislocation, tilting, translation and subluxation for tackling the Osteoarthritis especially for the aged people of 45-plus or the athletes. In this paper a Computer Aided Design (CAD) model using SolidWorks for the knee-spacer is presented based on the proposed SMA adopting the state-of-the art industry-standard geometry that is used in the PMMA based spacer design. Subsequently Ansys based Finite Element Analysis is carried out to measure and compare the performance between the proposed SMA based model with the state-of-the art PMMA ones. 81% more bending is noticed in the PMMA based spacer compared to the proposed SMA that would eventually cause fracture and tilting or translation of spacer. Permanent shape deformation of approximately 58.75% in PMMA based spacer is observed compared to recoverable 11% deformation in SMA when same load is applied on both separately.

Recognizing upper limb movements with wrist worn inertial sensors using k-means clustering classification.

In this paper we present a methodology for recognizing three fundamental movements of the human forearm (extension, flexion and rotation) using pattern recognition applied to the data from a single wrist-worn, inertial sensor. We propose that this technique could be used as a clinical tool to assess rehabilitation progress in neurodegenerative pathologies such as stroke or cerebral palsy by tracking the number of times a patient performs specific arm movements (e.g. prescribed exercises) with their paretic arm throughout the day. We demonstrate this with healthy subjects and stroke patients in a simple proof of concept study in which these arm movements are detected during an archetypal activity of daily-living (ADL) - 'making-a-cup-of-tea'. Data is collected from a tri-axial accelerometer and a tri-axial gyroscope located proximal to the wrist. In a training phase, movements are initially performed in a controlled environment which are represented by a ranked set of 30 time-domain features. Using a sequential forward selection technique, for each set of feature combinations three clusters are formed using k-means clustering followed by 10 runs of 10-fold cross validation on the training data to determine the best feature combinations. For the testing phase, movements performed during the ADL are associated with each cluster label using a minimum distance classifier in a multi-dimensional feature space, comprised of the best ranked features, using Euclidean or Mahalanobis distance as the metric. Experiments were performed with four healthy subjects and four stroke survivors and our results show that the proposed methodology can detect the three movements performed during the ADL with an overall average accuracy of 88% using the accelerometer data and 83% using the gyroscope data across all healthy subjects and arm movement types. The average accuracy across all stroke survivors was 70% using accelerometer data and 66% using gyroscope data. We also use a Linear Discriminant Analysis (LDA) classifier and a Support Vector Machine (SVM) classifier in association with the same set of features to detect the three arm movements and compare the results to demonstrate the effectiveness of our proposed methodology.

Recognition of elementary arm movements using orientation of a tri-axial accelerometer located near the wrist.

In this paper we present a method for recognising three fundamental movements of the human arm (reach and retrieve, lift cup to mouth, rotation of the arm) by determining the orientation of a tri-axial accelerometer located near the wrist. Our objective is to detect the occurrence of such movements performed with the impaired arm of a stroke patient during normal daily activities as a means to assess their rehabilitation. The method relies on accurately mapping transitions of predefined, standard orientations of the accelerometer to corresponding elementary arm movements. To evaluate the technique, kinematic data was collected from four healthy subjects and four stroke patients as they performed a number of activities involved in a representative activity of daily living, 'making-a-cup-of-tea'. Our experimental results show that the proposed method can independently recognise all three of the elementary upper limb movements investigated with accuracies in the range 91-99% for healthy subjects and 70-85% for stroke patients.

A low-complexity ECG feature extraction algorithm for mobile healthcare applications.

This paper introduces a low-complexity algorithm for the extraction of the fiducial points from the Electrocardiogram (ECG). The application area we consider is that of remote cardiovascular monitoring, where continuous sensing and processing takes place in low-power, computationally constrained devices, thus the power consumption and complexity of the processing algorithms should remain at a minimum level. Under this context, we choose to employ the Discrete Wavelet Transform (DWT) with the Haar function being the mother wavelet, as our principal analysis method. From the modulus-maxima analysis on the DWT coefficients, an approximation of the ECG fiducial points is extracted. These initial findings are complimented with a refinement stage, based on the time-domain morphological properties of the ECG, which alleviates the decreased temporal resolution of the DWT. The resulting algorithm is a hybrid scheme of time and frequency domain signal processing. Feature extraction results from 27 ECG signals from QTDB, were tested against manual annotations and used to compare our approach against the state-of-the art ECG delineators. In addition, 450 signals from the 15-lead PTBDB are used to evaluate the obtained performance against the CSE tolerance limits. Our findings indicate that all but one CSE limits are satisfied. This level of performance combined with a complexity analysis, where the upper bound of the proposed algorithm, in terms of arithmetic operations, is calculated as 2:423N + 214 additions and 1:093N + 12 multiplications for N 861 or 2:553N + 102 additions and 1:093N +10 multiplications for N > 861 (N being the number of input samples), reveals that the proposed method achieves an ideal trade-off between computational complexity and performance, a key requirement in remote CVD monitoring systems.