Search

This paper aims to reduce the power consumption of electrocardiography based wearable healthcare devices, by introducing power reduction approaches and considerations at system level design, where we have the highest potential to influence power. It focuses, in particular, on algorithm design and implementation, data acquisition, and transmission under constrained resources. A thorough investigation of the suitability of nine existing algorithms for on-sensor QRS feature detection is conducted, with respect to metrics such as sensitivity, positive predictivity, power consumption, parameter choice and time delay. Optimisation of data acquisition on CPU-based IoT systems is performed, and the current consumption is reduced by a factor of 3 using a combination of direct memory access (DMA) list approach and low-level register manipulations for task delegation. The acquisition data rate, sampling rate, buffer and batch size are also optimised. To reduce the power consumption by data transmission, the effect of on-sensor versus off-sensor processing is investigated. While focusing on CPU-based systems with experiments performed on a generic low-power wearable platform, the design optimisation and considerations proposed in this work could be extended to custom designs and allow further investigation into QRS detection algorithm optimisation for wearable devices.

International audience; ICG (impedance cardiography) and ECG (electrocardiography) provide important indications about functioning of the heart and of overall cardiovascular system. Measuring ICG along with ECG using wearable devices will improve the quality of health monitoring, as ICG points to important hemodynamic parameters (such as time intervals, stroke volume, cardiac output, and their variability). In this work, various electrode locations (12 different setups) have been tested for possible joint ECG & ICG data acquisition (using the same electrodes) and signal quality has been evaluated for every setup. It is shown that, while typically ICG is acquired over the whole thorax, a wrist-based joint acquisition of ECG & ICG signals can achieve acceptable signal quality and therefore can be considered in wearable sensing.

International audience; This paper describes the study of an integrated system for the detection of the B-C-X characteristic points of impedance cardiography (ICG) signals, to evaluate the stroke volume of a patient. It compares a discrete-time digital approach and a continuous-time digital architecture, using a level-crossing Analog-to-Digital Conversion (LC-ADC). The results show that the measurement accuracy of the stroke volume, with a relative error between 9% and 13%, is sufficient for practical use and opens the opportunity for future fully integrated circuit solutions. This study also points out that, unlike ECG, the continuous-time digital approach does not bring any improvements for ICG-based systems.

Using smart wearable devices to monitor patients electrocardiogram (ECG) for real-time detection of arrhythmias can significantly improve healthcare outcomes. Convolutional neural network (CNN) based deep learning has been used successfully to detect anomalous beats in ECG. However, the computational complexity of existing CNN models prohibits them from being implemented in low-powered edge devices. Usually, such models are complex with lots of model parameters which results in large number of computations, memory, and power usage in edge devices. Network pruning techniques can reduce model complexity at the expense of performance in CNN models. This paper presents a novel multistage pruning technique that reduces CNN model complexity with negligible loss in performance compared to existing pruning techniques. An existing CNN model for ECG classification is used as a baseline reference. At 60% sparsity, the proposed technique achieves 97.7% accuracy and an F1 score of 93.59% for ECG classification tasks. This is an improvement of 3.3% and 9% for accuracy and F1 Score respectively, compared to traditional pruning with fine-tuning approach. Compared to the baseline model, we also achieve a 60.4% decrease in run-time complexity., 4 pages

The open-source event-driven ECG dataset is available at https://github.com/jedaiproject/Open-Source-Event-Driven-ECG-Dataset; International audience; In this article, non-uniformly sampled electrocardiogram (ECG) signals obtained from level-crossing analog-to-digital converters (LC-ADCs) are analyzed for event-driven classification and compression performance. The signal compression results show that it is important to assess the distortion in event-driven signals when simulating LC-ADC models, especially at lower resolutions and larger quantization steps. The effects of varying the LC-ADC parameters for the application of cardiac arrhythmia classifiers are also assessed using an artificial neural network (ANN) and the MIT-BIH Arrhythmia Database. In comparison with uniformly-sampled data, it is possible to achieve comparable classification accuracy at a much lower complexity with event-driven ECG signals. The results show the best event-driven model achieves over 97% accuracy with 79% reduction in ANN complexity with signal-to-distortion ratio (S/D)≥21dB. For S/D

Over the past several years, the electrocardiogram (ECG) has been investigated for its uniqueness and potential to discriminate between individuals. This paper discusses how this discriminatory information can help in continuous user authentication by a wearable chest strap which uses dry electrodes to obtain a single lead ECG signal. To the best of the authors' knowledge, this is the first such work which deals with continuous authentication using a genuine wearable device as most prior works have either used medical equipment employing gel electrodes to obtain an ECG signal or have obtained an ECG signal through electrode positions that would not be feasible using a wearable device. Prior works have also mainly dealt with using the ECG signal for identification rather than verification, or dealt with using the ECG signal for discrete authentication. This paper presents a novel algorithm which uses QRS detection, weighted averaging, Discrete Cosine Transform (DCT), and a Support Vector Machine (SVM) classifier to determine whether the wearer of the device should be positively verified or not. Zero intrusion attempts were successful when tested on a database consisting of 33 subjects.

Internet of Things (IoT) enabled wearable sensors for health monitoring are widely used to reduce the cost of personal healthcare and improve quality of life. The sleep apnea-hypopnea syndrome, characterized by the abnormal reduction or pause in breathing, greatly affects the quality of sleep of an individual. This paper introduces a novel method for apnea detection (pause in breathing) from electrocardiogram (ECG) signals obtained from wearable devices. The novelty stems from the high resolution of apnea detection on a second-by-second basis, and this is achieved using a 1-dimensional convolutional neural network for feature extraction and detection of sleep apnea events. The proposed method exhibits an accuracy of 99.56% and a sensitivity of 96.05%. This model outperforms several lower resolution state-of-the-art apnea detection methods. The complexity of the proposed model is analyzed. We also analyze the feasibility of model pruning and binarization to reduce the resource requirements on a wearable IoT device. The pruned model with 80\% sparsity exhibited an accuracy of 97.34% and a sensitivity of 86.48%. The binarized model exhibited an accuracy of 75.59% and sensitivity of 63.23%. The performance of low complexity patient-specific models derived from the generic model is also studied to analyze the feasibility of retraining existing models to fit patient-specific requirements. The patient-specific models on average exhibited an accuracy of 97.79% and sensitivity of 92.23%. The source code for this work is made publicly available., Accepted for discussion at the IEEE International Symposium on Circuits and Systems (ISCAS) 2021

The objective of Working Group (WG) 4 of the COST Action NET4Age-Friendly is to examine existing policies, advocacy, and funding opportunities and to build up relations with policy makers and funding organisations. Also, to synthesize and improve existing knowledge and models to develop from effective business and evaluation models, as well as to guarantee quality and education, proper dissemination and ensure the future of the Action. The Working Group further aims to enable capacity building to improve interdisciplinary participation, to promote knowledge exchange and to foster a cross-European interdisciplinary research capacity, to improve cooperation and co-creation with cross-sectors stakeholders and to introduce and educate students SHAFE implementation and sustainability (CB01, CB03, CB04, CB05). To enable the achievement of the objectives of Working Group 4, the Leader of the Working Group, the Chair and Vice-Chair, in close cooperation with the Science Communication Coordinator, developed a template (see annex 1) to map the current state of SHAFE policies, funding opportunities and networking in the COST member countries of the Action. On invitation, the Working Group lead received contributions from 37 countries, in a total of 85 Action members. The contributions provide an overview of the diversity of SHAFE policies and opportunities in Europe and beyond. These were not edited or revised and are a result of the main areas of expertise and knowledge of the contributors; thus, gaps in areas or content are possible and these shall be further explored in the following works and reports of this WG. But this preliminary mapping is of huge importance to proceed with the WG activities. In the following chapters, an introduction on the need of SHAFE policies is presented, followed by a summary of the main approaches to be pursued for the next period of work. The deliverable finishes with the opportunities of capacity building, networking and funding that will be relevant to undertake within the frame of Working Group 4 and the total COST Action. The total of country contributions is presented in the annex of this deliverable.

International audience; In this paper, a new methodology for choosing design parameters of level-crossing analog-to-digital converters (LC-ADCs) is presented that improves sampling accuracy and reduces the data stream rate. Using the MIT-BIH Arrhythmia dataset, several LC-ADC models are designed, simulated and then evaluated in terms of compression and signal-to-distortion ratio. A new one-dimensional convolutional neural network (1D-CNN) based classifier is presented. The 1D-CNN is used to evaluate the event-driven data from several LC-ADC models. With uniformly sampled data, the 1D-CNN has 99.49%, 92.4% and 94.78% overall accuracy, sensitivity and specificity, respectively. In comparison, a 7-bit LC-ADC with 2385Hz clock frequency and 6-bit clock resolution offers 99.2%, 89.98% and 91.64% overall accuracy, sensitivity and specificity, respectively. It also offers 3x data compression while maintaining a signal-to-distortion ratio of 21.19dB. Furthermore, it only requires 49% floating-point operations per second (FLOPS) for cardiac arrhythmia classification in comparison with the uniformly sampled ADC. Finally, an open-source event-driven arrhythmia database is presented.