Derivative Method to Detect Sleep and Awake States through Heart Rate Variability Analysis Using Machine Learning Algorithms.

Sleep disorders can have harmful consequences in both the short and long term. They can lead to attention deficits, as well as cardiac, neurological and behavioral repercussions. One of the most widely used methods for assessing sleep disorders is polysomnography (PSG). A major challenge associated with this method is all the cables needed to connect the recording devices, making the examination more intrusive and usually requiring a clinical environment. This can have potential consequences on the test results and their accuracy. One simple way to assess the state of the central nervous system (CNS), a well-known indicator of sleep disorder, could be the use of a portable medical device. With this in mind, we implemented a simple model using both the RR interval (RRI) and its second derivative to accurately predict the awake and napping states of a subject using a feature classification model. For training and validation, we used a database providing measurements from nine healthy young adults (six men and three women), in which heart rate variability (HRV) associated with light-on, light-off, sleep onset and sleep offset events. Results show that using a 30 min RRI time series window suffices for this lightweight model to accurately predict whether the patient was awake or napping.

Removal of Motion Artifacts in Capacitive Electrocardiogram Acquisition: A Review.

Capacitive electrocardiogram (cECG) systems are increasingly used for the monitoring of cardiac activity. They can operate within the presence of a small layer of air, hair or cloth and do not require a qualified technician. They can be integrated into wearables, clothing or objects of daily life, such as beds or chairs. While they offer many advantages over conventional electrocardiogram systems (ECG) that rely on wet electrodes, they are more prone to be affected by motion artifacts (MAs). These effects, which are due to the relative movement of the electrode in relation to the skin, are several orders of magnitude higher than ECG signal amplitudes, they occur in frequencies that might overlap with the ECG signal, and they may saturate the electronics in the most severe cases. In this paper, we provide a detailed description of MA mechanisms that translate into capacitance variations due to electrode-skin geometric changes or into triboelectric effects due to electrostatic charge redistribution. A state-of-the-art overview of the different approaches based on materials and construction, analog circuits and digital signal processing is provided as well as the trade-offs to be made using these techniques, to mitigate MAs efficiently.

Early-detection scheme based on sequential tests for low-latency communications.

We propose an early-detection scheme to reduce communications latency based on sequential tests under finite blocklength regime for a fixed-rate transmission without any feedback channel. The proposed scheme processes observations sequentially to decide in favor of one of the candidate symbols. Such a process stops as soon as a decision rule is satisfied or waits for more samples under a given accuracy. We first provide the optimal achievable latency in additive white Gaussian noise channels for every channel code given a probability of block error. For example, for a rate R = 0.5 and a blocklength of 500 symbols, we show that only 63 % of the symbol time is needed to reach an error rate equal to 10 - 5 . Then, we prove that if short messages can be transmitted in parallel Gaussian channels via a multi-carrier modulation, there exists an optimal low-latency strategy for every code. Next, we show how early detection can be effective with band-limited orthogonal frequency-division multiplexing signals while maintaining a given spectral efficiency by random coding or pre-coding random matrices. Finally, we show how the proposed early-detection scheme is effective in multi-hop systems.

Graphene-based terahertz reconfigurable printed ridge gap waveguide structure.

Graphene-based microwave devices have enabled reconfigurability, thus paving the way to the realization of flexible wireless terahertz systems with featured performances. Despite great progress in the development of graphene-based terahertz devices in the literature, high insertion loss and wide tunable range are still significant challenges at such high frequencies. In this work, we introduce the use of graphene to implement a reconfigurable printed ridge gap waveguide (RPRGW) structure over the terahertz frequency range for the first time. This guiding structure is suitable for both millimeter and terahertz wave applications due to its supporting quasi-TEM mode, which exhibits low dispersion compared to other traditional guiding structures. The presented solution is featured with low loss as the signal propagates in a lossless air gap, which is separated from the lossy graphene elements responsible for the reconfigurable behavior. In addition, this guiding structure is deployed to implement a tunable RPPGW power divider as an application example for the proposed structure.

Measuring Disentanglement: A Review of Metrics.

Learning to disentangle and represent factors of variation in data is an important problem in artificial intelligence. While many advances have been made to learn these representations, it is still unclear how to quantify disentanglement. While several metrics exist, little is known on their implicit assumptions, what they truly measure, and their limits. In consequence, it is difficult to interpret results when comparing different representations. In this work, we survey supervised disentanglement metrics and thoroughly analyze them. We propose a new taxonomy in which all metrics fall into one of the three families: intervention-based, predictor-based, and information-based. We conduct extensive experiments in which we isolate properties of disentangled representations, allowing stratified comparison along several axes. From our experiment results and analysis, we provide insights on relations between disentangled representation properties. Finally, we share guidelines on how to measure disentanglement.

A Novel Sensor-Array System for Contactless Electrocardiogram Acquisition.

The cardiac ECG is one of the most important human biometrics. An electrocardiogram (ECG) or EKG, captures the electrical activity of the heart and allows a healthcare professional to evaluate, diagnose, and monitor patient cardiac condition. The standard method to capture electrocardiogram signals (ECG) involves skin preparation and attachment of wet electrodes to the skin, which is not comfortable for the patient and requires a trained technician. In this work, a novel contactless-based ECG system is proposed, where 128 sensors are deployed on a mattress to capture the ECG information from the back of the patient. The proposed system can capture the ECG through clothing and is more comfortable to the patients. The measurements captured by the proposed system provides a 100% accuracy of QRS complex detection and heartbeat rate estimation and a maximum of 4% error in other major ECG features compared to a hospital-grade standard system. This paper shows that ECG features can be accurately extracted from contactless electrodes, through clothing and from the back of the patient.

Contactless Capacitive Electrocardiography Using Hybrid Flexible Printed Electrodes.

Traditional capacitive electrocardiogram (cECG) electrodes suffer from limited patient comfort, difficulty of disinfection and low signal-to-noise ratio in addition to the challenge of integrating them in wearables. A novel hybrid flexible cECG electrode was developed that offers high versatility in the integration method, is well suited for large-scale manufacturing, is easy to disinfect in clinical settings and exhibits better performance over a comparable rigid contactless electrode. The novel flexible electrode meets the frequency requirement for clinically important QRS complex detection (0.67-5 Hz) and its performance is improved over rigid contactless electrode across all measured metrics as it maintains lower cut-off frequency, higher source capacitance and higher pass-band gain when characterized over a wide spectrum of patient morphologies. The results presented in this article suggest that the novel flexible electrode could be used in a medical device for cECG acquisition and medical diagnosis. The novel design proves also to be less sensitive to motion than a reference rigid electrode. We therefore anticipate it can represent an important step towards improving the repeatability of cECG methods while requiring less post-processing. This would help making cECG a viable method for remote cardiac health monitoring.

Bag-Level Aggregation for Multiple-Instance Active Learning in Instance Classification Problems.

A growing number of applications, e.g., video surveillance and medical image analysis, require training recognition systems from large amounts of weakly annotated data, while some targeted interactions with a domain expert are allowed to improve the training process. In such cases, active learning (AL) can reduce labeling costs for training a classifier by querying the expert to provide the labels of most informative instances. This paper focuses on AL methods for instance classification problems in multiple instance learning (MIL), where data are arranged into sets, called bags, which are weakly labeled. Most AL methods focus on single-instance learning problems. These methods are not suitable for MIL problems because they cannot account for the bag structure of data. In this paper, new methods for bag-level aggregation of instance informativeness are proposed for multiple instance AL (MIAL). The aggregated informativeness method identifies the most informative instances based on classifier uncertainty and queries bags incorporating the most information. The other proposed method, called cluster-based aggregative sampling, clusters data hierarchically in the instance space. The informativeness of instances is assessed by considering bag labels, inferred instance labels, and the proportion of labels that remain to be discovered in clusters. Both proposed methods significantly outperform reference methods in extensive experiments using benchmark data from several application domains. Results indicate that using an appropriate strategy to address MIAL problems yields a significant reduction in the number of queries needed to achieve the same level of performance as single-instance AL methods.