Ensemble method for multiclassification of COVID-19 virus using spatial and frequency domain features over X-ray images

In early 2020, WHO declared COVID-19, a pandemic disease, which severely infected human inhabitant and health. Researchers, doctors, etc., are finding ways to combat the disease. RT-PCR testing is the initial type of testing that was used to detect whether a patient is COVID (+) or COVID (−).This test kit is costly and the result takes around 6hours. So testing a heavy chunk of the population with RT-PCR is a difficult task. To counter this, X-rays/CT scan-based testing can be used to detect COVID (+) cases to control its spread. X-rays are preferable to CT as they are cheaper and even produce low radiations. The second issue that was noticed during this pandemic period was the availability of doctors. To resolve this issue, a robust automated system for early prediction is essential. Automated systems using machine learning (ML), deep learning (DL) approaches are giving promising results in the detection of COVID (+) cases. In this chapter, we propose a framework for automatic recognition of COVID (+), normal, and pneumonia cases (i.e., multiclassification) over X-ray images. In the proposed method, a dataset of COVID (+), normal, and pneumonia images is used. Initially, the dataset is preprocessed, followed by feature extraction using gray level cooccurrence matrix (GLCM), gray level difference method (GLDM), wavelet transform (WT), and fast Fourier transform (FFT) methods. Features extracted are concatenated to construct a feature pool and these features are used for multiclassification using ML algorithms: support vector machines (SVM) and XG Boost. XG Boost performs better than SVM. © 2022 Elsevier Inc. All rights reserved.

Text as signal. A tutorial with case studies focusing on social media (Twitter).

Sentiment analysis is the automated coding of emotions expressed in text. Sentiment analysis and other types of analyses focusing on the automatic coding of textual documents are increasingly popular in psychology and computer science. However, the potential of treating automatically coded text collected with regular sampling intervals as a signal is currently overlooked. We use the phrase "text as signal" to refer to the application of signal processing techniques to coded textual documents sampled with regularity. In order to illustrate the potential of treating text as signal, we introduce the reader to a variety of such techniques in a tutorial with two case studies in the realm of social media analysis. First, we apply finite response impulse filtering to emotion-coded tweets posted during the US Election Week of 2020 and discuss the visualization of the resulting variation in the filtered signal. We use changepoint detection to highlight the important changes in the emotional signals. Then we examine data interpolation, analysis of periodicity via the fast Fourier transform (FFT), and FFT filtering to personal value-coded tweets from November 2019 to October 2020 and link the variation in the filtered signal to some of the epoch-defining events occurring during this period. Finally, we use block bootstrapping to estimate the variability/uncertainty in the resulting filtered signals. After working through the tutorial, the readers will understand the basics of signal processing to analyze regularly sampled coded text.

Off-the-Shelf Solution for Measurement and Calculation of Respiration and Heart Rates for COVID-19 Diagnosis and Monitoring

In this paper, we present hardware-software methodology to measure and calculate heart and respiratory rates by using single, low-cost microcontroller chip of limited computation and memory performances, as ATTINY85. Sensors and analog front-end are very simple, directly interfaced to microcontroller pins. Implemented time and frequency domain signal processing algorithms are optimized for low-bits, low-memory architectures and allow fast reading of rates, provide satisfactory accuracy, noise immunity and low power consumption. The same methodology can be used in similar applications to determine dominant spectral frequency of slow signal, from a smaller number of points. © 2022 IEEE.

Non-invasive Machine Learning approach for classifying Blood Pressure using PPG Signals in COVID situation

Blood pressure is one of the possible factors that cause cardiovascular diseases. It is one of the useful parameters for early detection, using which we can diagnose and treat cardiac diseases. Continuous monitoring of blood pressure can help us to maintain good health and to have a longer life span. At present, BP estimation is principally based on cuff-based techniques[1] which can cause inconvenience or discomfort to patients. ECG is one of the cuff-based methods to estimate or classify Blood Pressure. Nowadays, Studies are taking place on non-invasive and cuff-less-based methods and one of them is PPG signals (photoplethysmography). PPG is a non-invasive optical method for estimating the blood volume changes per pulse[21]. We can also say that the PPG signal indicates the mechanical activity of the heart[8]. In this paper, we proposed a non-invasive method using a whole-based approach that uses raw values from PPG signals to classify blood pressure. Using Machine learning algorithms to classify blood pressure is a feasible way for the analysis and predicting the results. In this paper, we applied various machine learning models(Random forest, Gradient boost, and XGBoost). In order to avoid overfitting, we used Repeated-stratified k-fold cross-validation and obtained enough accuracy in classifying the BP. when compared to the parameter-based method, our method(whole based method) is independent of the PPG waveform of a signal. © 2021 IEEE.