Background: Wearable devices have evolved as screening tools for atrial fibrillation (AF). A photoplethysmographic (PPG) AF detection algorithm was developed and applied to a convenient smartphone-based device with good accuracy. However, patients with paroxysmal AF frequently exhibit premature atrial complexes (PACs), which result in poor unmanned AF detection, mainly because of rule-based or handcrafted machine learning techniques that are limited in terms of diagnostic accuracy and reliability. Objective: This study aimed to develop deep learning (DL) classifiers using PPG data to detect AF from the sinus rhythm (SR) in the presence of PACs after successful cardioversion. Methods: We examined 75 patients with AF who underwent successful elective direct-current cardioversion (DCC). Electrocardiogram and pulse oximetry data over a 15-min period were obtained before and after DCC and labeled as AF or SR. A 1-dimensional convolutional neural network (1D-CNN) and recurrent neural network (RNN) were chosen as the 2 DL architectures. The PAC indicator estimated the burden of PACs on the PPG dataset. We defined a metric called the confidence level (CL) of AF or SR diagnosis and compared the CLs of true and false diagnoses. We also compared the diagnostic performance of 1D-CNN and RNN with previously developed AF detectors (support vector machine with root-mean-square of successive difference of RR intervals and Shannon entropy, autocorrelation, and ensemble by combining 2 previous methods) using 10 5-fold cross-validation processes. Results: Among the 14,298 training samples containing PPG data, 7157 samples were obtained during the post-DCC period. The PAC indicator estimated 29.79% (2132/7157) of post-DCC samples had PACs. The diagnostic accuracy of AF versus SR was 99.32% (70,925/71,410) versus 95.85% (68,602/71,570) in 1D-CNN and 98.27% (70,176/71,410) versus 96.04% (68,736/71,570) in RNN methods. The area under receiver operating characteristic curves of the 2 DL classifiers was 0.998 (95% CI 0.995-1.000) for 1D-CNN and 0.996 (95% CI 0.993-0.998) for RNN, which were significantly higher than other AF detectors (P<.001). If we assumed that the dataset could emulate a sufficient number of patients in training, both DL classifiers improved their diagnostic performances even further especially for the samples with a high burden of PACs. The average CLs for true versus false classification were 98.56% versus 78.75% for 1D-CNN and 98.37% versus 82.57% for RNN (P<.001 for all cases). Conclusions: New DL classifiers could detect AF using PPG monitoring signals with high diagnostic accuracy even with frequent PACs and could outperform previously developed AF detectors. Although diagnostic performance decreased as the burden of PACs increased, performance improved when samples from more patients were trained. Moreover, the reliability of the diagnosis could be indicated by the CL. Wearable devices sensing PPG signals with DL classifiers should be validated as tools to screen for AF.

Background: Continuous photoplethysmography (PPG) monitoring with a wearable device may aid the early detection of atrial fibrillation (AF). Objective: We aimed to evaluate the diagnostic performance of a ring-type wearable device (CardioTracker, CART), which can detect AF using deep learning analysis of PPG signals. Methods: Patients with persistent AF who underwent cardioversion were recruited prospectively. We recorded PPG signals at the finger with CART and a conventional pulse oximeter before and after cardioversion over a period of 15 min (each instrument). Cardiologists validated the PPG rhythms with simultaneous single-lead electrocardiography. The PPG data were transmitted to a smartphone wirelessly and analyzed with a deep learning algorithm. We also validated the deep learning algorithm in 20 healthy subjects with sinus rhythm (SR). Results: In 100 study participants, CART generated a total of 13,038 30-s PPG samples (5850 for SR and 7188 for AF). Using the deep learning algorithm, the diagnostic accuracy, sensitivity, specificity, positive-predictive value, and negative-predictive value were 96.9%, 99.0%, 94.3%, 95.6%, and 98.7%, respectively. Although the diagnostic accuracy decreased with shorter sample lengths, the accuracy was maintained at 94.7% with 10-s measurements. For SR, the specificity decreased with higher variability of peak-to-peak intervals. However, for AF, CART maintained consistent sensitivity regardless of variability. Pulse rates had a lower impact on sensitivity than on specificity. The performance of CART was comparable to that of the conventional device when using a proper threshold. External validation showed that 94.99% (16,529/17,400) of the PPG samples from the control group were correctly identified with SR. Conclusions: A ring-type wearable device with deep learning analysis of PPG signals could accurately diagnose AF without relying on electrocardiography. With this device, continuous monitoring for AF may be promising in high-risk populations. Trial Registration: ClinicalTrials.gov NCT04023188; https://clinicaltrials.gov/ct2/show/NCT04023188

Localization has been extensively studied owing to its huge potential in various areas, such as Internet of Things, 5G, and unmanned aerial vehicle services. Its wide applications include home automation, advanced production automation, and unmanned vehicle control. In this study, we propose a novel localization method that utilizes convolutional neural network (CNN) and ultra-wideband (UWB) signals. A localization problem is converted to a regression problem with the proposed CNN, in which the ranging and positioning phases are integrated. By integrating the ranging and positioning phases, the proposed CNN estimates the location of UWB transmitter directly without any additional step. To integrate both phases of localization, a simple-yet efficient input image generation method is proposed. In the proposed input image generation method, three oversampled two-dimensional input images are generated from the three received UWB signals and they are provided to the designed CNN through the three channels, which are represented by red-, green-, and blue-color channels, respectively. The proposed CNN-based localization system then estimates the location of the UWB transmitter directly using the three-channel image as an input of the CNN. Simulation results verify that the proposed CNN-based localization method outperforms the traditional threshold-based and existing CNN-based methods. Also, it is observed that the proposed method performs well under an asymmetric environment, unlike the existing method.

In this Letter, the authors propose a novel convolutional neural network (CNN)‐based estimation of the distance between an ultra‐wideband (UWB) transmitter and receiver for a localisation. By exploiting the UWB signal characteristics, such as high‐resolution in the time domain, the CNN is designed. The proposed CNN‐based method estimates the distance from only the received signals, without signal‐to‐noise ratio information which is used for the conventional time of arrival (TOA)‐based methods. Furthermore, as verified by simulation, the proposed CNN‐based method significantly outperforms the conventional TOA‐based method with respect to the distance estimation accuracy.

In this paper, a multiuser space-time line code (STLC) system is proposed. In the proposed multiuser STLC system, a zero-forcing (ZF)-based precoder decomposes multiuser multiple-input multiple-output (MIMO) channels into multiple single-user MIMO channels, and the STLC is performed with the effective single user MIMO channel independently for each user. Here, to maximize the sum rate, an optimal power allocation method is designed based on a water-filling strategy. Also, a simple suboptimal method called fairness-aware per-user (FAPU) power allocation is devised. It is analytically and numerically verified that each user of the proposed ZF-based STLC system asymptotically achieves the maximum of single-user achievable rate as the number of transmit antennas increases. The numerical results of rigorous simulation justify that the proposed ZF-based STLC with FAPU power allocation provides near optimal performance and outperforms the existing ZF-based maximum Eigen beamforming scheme and conventional multiuser STLC schemes. Furthermore, two simple search algorithms to find the optimal number of users that maximizes sum rate are devised. Numerical results verify that the proposed algorithms can effectively find the optimal number of users by reducing the search interval.

A 900-MHz high-sensitivity split-channel binary frequency-shift keying (SC-BFSK) reconfigurable data/wake-up receiver (RX) for low-power wide-area networks (LPWANs) is presented. In the data mode, the proposed RX demodulates data through the RF/analog front end (RXFE), the analog-to-digital converter (ADC), and the modulator-demodulator (MODEM). The MODEM implemented in the external microcontroller unit (MCU) applies additional digital signal processing to improve about 17-dB sensitivity. In the wake-up mode, the proposed RX saves the power dissipation by turning off all blocks except for the RXFE and wake-up preamble detector (WuPD). The WuPD following the RXFE provides a 17-dB sensitivity improvement in place of the MODEM of the data RX. Adopting the proposed SC-BFSK, in which other channels are inter-allocated between the BFSK tones of one channel, increases the number of channels while taking advantage of wide tone spacing, which improves the bit error rate (BER) in a multipath fading channel. To implement the ultra-low-power (ULP) SC-BFSK RX, the RXFE employs the 2:1 LO sliding-IF architecture and a band-pass filter (BPF)-based frequency-to-energy detection baseband demodulator. Implemented in 55-nm CMOS, the proposed RX, including both data and wake-up RXs, exhibits -123-dBm sensitivity with 0.39-kbps data rate and 81.92-ms wake-up latency, while the RX chip dissipates 0.88 mW.