It can be life-saving to monitor the respiratory rate (RR) even for healthy people in real-time. It is reported that the infected people with coronavirus disease 2019 (COVID-19), generally develop mild respiratory symptoms in the early stage. It will be more important to continuously monitor the RR of people in nursing homes and houses with a non-contact method. Conventional, contact-based, methods are not suitable for long-term health monitoring especially in-home care services. The potentials of wireless radio signals for health care applications, such as fall detection, etc., are examined in literature. In this paper, we focus on a device-free real-time RR monitoring system using wireless signals. In our recent study, we proposed a non-contact RR monitoring system with a batch processing (delayed) estimation method. In this paper, for real-time monitoring, we modify the standard joint unscented Kalman filter (JUKF) method for this new and time-critical problem. Due to the nonlinear structure of the RR estimation problem with respect to the measurements, a novel modification is proposed to transform measurement errors into parameter errors by using the hyperbolic tangent function. It is shown in the experiments conducted with the real measurements taken using healthy volunteers that the proposed modified joint unscented Kalman filter (ModJUKF) method achieves the highest accuracy according to the windowing-based methods in the time-varying RR scenario. It is also shown that the ModJUKF not only reduces the computational complexity approximately 8.54% but also improves the accuracy 36.7% with respect to the standard JUKF method.

Machines are becoming indispensable in our lives and the requirements of the human-machine interactions are increasing. Conventional devices, such as a keyboard or touch screen, may not be preferred in future’s entertainment, home, and industrial applications. Device-free (non-contact) solutions will be even more popular. These solutions often use visual and acoustic technologies which have some disadvantages. The use of radio frequency (RF) waves for human-machine interaction such as air-writing (Wri), is a new and challenging problem. We propose a device-free machine learning-based air-writing recognition framework called RF-Wri which can effectively distinguish 26 capital letters. Two-channel low-cost software-defined radios (SDR) and oppositely polarized antennas are used to provide polarization diversity which makes the accuracy of classification superior. Another critical novelty is the usage of Discrete Cosine Transform (DCT) coefficients as new features to represent RF waveform which provides writing speed and user invariant recognition. Discrete Wavelet Transform (DWT) filters and letter segmentation algorithm are used for signal de-noising and separating the air-writing activities, respectively. It is shown that Support Vector Machine (SVM) can successfully classify the measured RF waves of air-written letters. It is verified with various real measurements that the proposed framework, RF-Wri, achieves 95.15% accuracy in the classification of all 26 air-written letters and outperforms the fairly new WiFi-based air-writing recognition approaches.

Respiratory rate (RR) monitoring of an adult or an infant during sleep or in steady position can be lifesaving especially in home care systems. In this paper, we examine the potentials of wireless radio frequency (RF) signals to monitor the RR. A new noncontact RR monitoring system is proposed. The system includes a simple motion detection algorithm based on adaptive thresholding to eliminate the effects of the large-scale body movements on the RR estimation. In the proposed system, the high resolution subspace-based parametric spectral estimation approaches, estimation of signal parameters by rotational invariance technique (ESPRIT) and multiple signal classification (MUSIC), are presented as the RR estimation algorithms. According to our knowledge, the ESPRIT algorithm, which estimates spectrum without searching, is used for the first time in this study for RR estimation. It is shown that ESPRIT is computationally efficient and works approximately 49 times faster than the MUSIC algorithm. It is also shown with various experiments conducted with 10 volunteers that the proposed noncontact RR monitoring system attains 0.13 breath per minute (bpm) error rate with the limited number of data and outperforms the periodogram method commonly used as the benchmark.

A recent trend for human activity recognition, fall detection, health-care applications, etc., which is using the non-contact radio-frequency (RF) signals, is known as the RF sensing. State-of-the-art radar and Wi-Fi based human sensing systems utilize high bandwidth and require high computational burden. In this paper, a machine learning (ML) framework is proposed for device-free through-the-wall (TTW) human detection using narrow-band continuous RF signals that are transmitted and captured by low-cost software-defined radio (SDR) modules. To be more realistic the double TTW scenario, where both transmitter and receiver are placed outside the walls of the monitored area, is considered. Three different classes are defined as empty (human-free), moving human, and additionally the static human (only breathing, not moving) which addresses the unconscious or sleeping person. In this framework, the variance of the respiratory rate (RR) estimates of the subject and overall signal variances are used as distinguishing features. RR estimates are obtained using nonlinear least-squares (NLS) approach. It is shown in the experiments conducted with real measurements from different environments that the proposed ML framework achieves over 99% classification accuracy using a Decision Tree (DT) classifier. In addition, it is also shown that the proposed framework achieves over 95% accuracy in a completely different environment where the model is not trained. This indicates that the proposed ML framework can be applied generally without requiring specific re-training for different environments and conditions.

In this paper, the spatio-temporal (multi-channel) linear models, which use temporal and the neighbouring wind speed measurements around the target location, for the best short-term wind speed forecasting are investigated. Multi-channel autoregressive moving average (MARMA) models are formulated in matrix form and efficient linear prediction coefficient estimation techniques are first used and revised. It is shown in detail how to apply these MARMA models to the spatially distributed wind speed measurements. The proposed MARMA models are tested using real wind speed measurements which are collected from the five stations around Canakkale region of Turkey. According to the test results, considerable improvements are observed over the well known persistence, autoregressive (AR) and multi-channel/vector autoregressive (VAR) models. It is also shown that the model can predict wind speed very fast (in milliseconds) which is suitable for the immediate short-term forecasting.

In this study, a new solar photovoltaic (PV) panel output power model is proposed. The model is constructed as a function of ambient temperature and solar radiations for two types (fixed panel and sun tracking panel) of PV systems. The proposed models are tested and verified on the Renewable Energy Research Home (RERH) system that was installed at the Anadolu University campus in Eskişehir, Turkey. The model is deliberately constructed for the winter season, where cloudliness, rain and snow constitute more challenging conditions for modeling. The developed model outcomes are compared to the outputs of state of the art methods that use global solar radiation and temperature data. A total of eight algebraic models are constructed for the purpose of depicting the solar radiation-to-electric power behavior. It is observed that even the least successful one of these eight variants are performing better than the most accurate method in the literature. It is argued that mathematical incorporation of the proposed novel hysteresis functions to the solar radiation-to-power conversion curves results in a richer class of functions and causes a significant accuracy improvement on the mathematical power generation model, even for the most challenging season of winter.