Smart alarm based on sleep stages prediction

Non-Invasive Biosensing for Healthcare Using Artificial Intelligence: A Semi-Systematic Review

The rapid development of biosensing technologies together with the advent of deep learning has marked an era in healthcare and biomedical research where widespread devices like smartphones, smartwatches, and health-specific technologies have the potential to facilitate remote and accessible diagnosis, monitoring, and adaptive therapy in a naturalistic environment. This systematic review focuses on the impact of combining multiple biosensing techniques with deep learning algorithms and the application of these models to healthcare. We explore the key areas that researchers and engineers must consider when developing a deep learning model for biosensing: the data modality, the model architecture, and the real-world use case for the model. We also discuss key ongoing challenges and potential future directions for research in this field. We aim to provide useful insights for researchers who seek to use intelligent biosensing to advance precision healthcare.

Lightweight neural network based model for real-time precise HR monitoring during high intensity workout using consumer smartwatches

Mobile and wearable electronics is one of the rapidly developing areas of high technologies, which regularly appear new devices that offer new features for monitoring our health, level of physical exertion and everyday activity. From the point of view of medicine and sports, usually wearable devices are used to solve one of two tasks: round-the-clock continuous heart rate monitoring, and the control of the heart rate during workout. One of the drawbacks of such devices is the calculation errors that are caused by the motion artifacts. The most critical of them are those that arise in some cases when performing high-intensity training's, which are conjugate with intense hands movements, such as sprint running or boxing. In addition, limited resources of wearable devices do not always allow usage of very complex algorithms for processing certain events. In our work, an ultra-lightweight framework for a precise real-time heart rate monitoring during the high intensity physical exercises is developed. The model is a combination of a digital signal processing and deep convolutional and recurrent neural networks approaches. From the personalization point of view, the effect of anthropometric parameters has been studied. The model shows an average mean absolute error of 2.4±2.8 bpm during 5 fold cross-validation on an internal dataset, 2.9±3.4 bpm when evaluated on 12 IEEE SPC subjects, and 4.8±5.3 bpm when evaluated on 24 subjects from Wonkwang University dataset. Such results exceed the current state of the art solutions both in terms of the achieved accuracy of heart rate estimation and consumed computational resources. Clinical relevance- This work aims to provide a robust and lightweight neural network based framework for a real time heart rate estimation during high intensity physical exercises.

Neural network based algorithm for a spectrogram classification of wrist-type PPG using high-order harmonics processing

The importance of accurate and continuous heart rate monitoring during workout cannot be overestimated. Supporting heart rate in the desired range, you strengthen the heart muscle and the overall fitness level. Therefore, the precise heart rate measurements are important at each stage: before workout, during exercises and after completion. One of the most important problems for precise heart rate measurement during high intensive exercises with the help of wearable devices is the movement artifacts. Even the smallest movement of the muscles, the turn of the wrist, the movement of the fingers or even the displacement of the fitness tracker per millimeter - all this very much distorts the useful signal. To solve the problem of motion artifacts, both digital signal processing approaches are used, as well as deep learning methods. In this paper, we offer a new method of processing the signal of wearable devices during workout, in particular to solve the motion artifacts problem, using deep neural networks. A distinctive feature of the model is the use of higher signal harmonics to determine the shape and type of signal. In particular, a method is proposed for classifying the signal spectrogram to noise, movement and useful component. During cross-validation on an available datasets, we compared the effectiveness of the proposed approach for spectrogram classification and received an improvement of averaged ROC AUC (area under the receiver operating characteristic curve) and F1 Score by 5% by using higher harmonics. Clinical relevance- This work aims to provide an approach for a wearable devices PPG signal spectrogram classification using neural networks and high-order harmonics processing.

Verification methodology for Smart Awakening Systems

A mental and physical recovery after an awakening moment depends not only on the overall sleep duration and quality but mostly on the sleep stage in the waking moment. The most comfortable awakening moment is during the Light or Wake sleep stages. But the fix-time alarm clock doesn't take into account the sleep stage in the awakening moment, which often results in awakening during the Deep or Rapid Eyes Movement stages. To reduce the negative recovery effect, big companies and research groups develop various awakening systems. Such systems recognize sleep stages based on wearable sensors' data (mostly from accelerometer sensors) and thus can find the easiest awakening moment time with minimal recovery effects.However, it is quite hard to measure and verify the efficiency of such systems without using polysomnography (which can be performed only in clinical conditions by medical experts). To solve this problem we developed a methodology based on questionnaires and psychological tests. Such an approach has big scalability, does not require special medical equipment, and can be evaluated in a home environment with minimal support effort. The proposed verification approach has been tested on smartwatches with the sleep stages forecast model. The proposed model accuracy was 78%. Results of our experiment show that the majority of users demonstrated a correlation between awakening quality and the verification tests performance.

Consumer Smartwatches As a Portable PSG: LSTM Based Neural Networks for a Sleep-Related Physiological Parameters Estimation

Recently, mobile and wearable devices have become an increasingly integral part of our lives. They provide a possibility of detailed health monitoring using noninvasive and user-friendly techniques. However, lack of continuous monitoring, the need of specific sensors, and the limitations in memory and power consumption are only some of the potential drawbacks of such devices. In the current paper a system based on a deep recurrent neural network is developed for an automatic continuous monitoring of sleep-related physiological parameters by means of a wearable biosignal monitoring systems. Smartwatches based algorithm for non-invasive monitoring of sleep stages, respiratory events (including sleep apnea and hypopnea), snore and blood oxygen saturation is developed. Our experimental results demonstrate that proposed model constitutes a noninvasive and inexpensive screening system for sleep-related physiological parameters and pathological states. The model has shown a 77 % accuracy in sleep stages prediction, more than 80 % accuracy in epoch-by-epoch respiratory events classification, above 60 % accuracy in snore events classification and above 70 % accuracy in blood oxygen saturation (SpO₂) level classification (for a two class problem with a SpO₂ threshold of 95 %).