The Institute of Electronics and Computer (IEC) is a leading scientific membership society working to advance electronics and computer for the benefit of all. We have a worldwide membership from enthusiatic amateurs to those at the top of their fields in academia, business, education and government. Our purpose is to gather, inspire, guide, represent and celebrate all who share a passion for electronics and computers. And, in our role as a charity, we are here to ensure that electronics and computer delivers on its exceptional potential to benefit society. Alongside professional support for our members, we engage with policymakers and the public to increase awareness and understanding of the value that electronics and computer holds for all of us. With a portfolio including journals, book series, and conference proceedings, we focus on electonics, computer, astronomy and astrophysics, environmental sciences, biosciences, mathematics and education. IEC Science also publishes on behalf of other scientific organisations and represents their needs and those of their members.

This paper investigates new feature extraction and regression methods for predicting cuffless blood pressure from PPG signals. Cuffless blood pressure is a technology that measures blood pressure without needing a cuff. This technology can be used in various medical applications, including home health monitoring, clinical uses, and portable devices. The new feature extraction method involves extracting meaningful features (time and chaotic features) from the PPG signals in the prediction of systolic blood pressure (SBP) and diastolic blood pressure (DBP) values. These extracted features are then used as inputs to regression models, which are used to predict cuffless blood pressure. The regression model performances were evaluated using root mean squared error (RMSE), R², mean square error (MSE), and the mean absolute error (MAE). The obtained RMSE was 4.277 for systolic blood pressure (SBP) values using the Matérn 5/2 Gaussian process regression model. The obtained RMSE was 2.303 for diastolic blood pressure (DBP) values using the rational quadratic Gaussian process regression model. The results of this study have shown that the proposed feature extraction and regression models can predict cuffless blood pressure with reasonable accuracy. This study provides a novel approach for predicting cuffless blood pressure and can be used to develop more accurate models in the future.

In this paper, a study on the classification of violin and viola instrument sounds in the same notes that are hard for people to distinguish is presented. First, 16 statistical features defined in the time and frequency domain for 512 violin note recordings and 512 viola note recordings are extracted. Classification algorithms including Linear Distinction Analysis (LDA), k-nearest neighbors (k-NN), Support Vector Machines (SVM), and Random Forests (RF) classifiers are used to recognize violin and viola instrument sounds. The classification operation is performed on three different sets of features: only time domain features (12), only frequency domain features (4), and both time domain and frequency domain features (16). Simulation results show that the highest accuracy rate is obtained when using the Random Forests classifier with both time and frequency domain attributes. With Random Forest classifier, while obtaining 64.4% classification accuracy with 10 times cross-validity using only time domain and only frequency domain features, 79.6% classification success is achieved with both time and frequency domain features.

Graphs of ECG signals in time domain have an important place in the diagnosis of heart diseases. ECG (fetal ECG-FECG) signals from fetuses also reveal heart problems, particularly changes in ST interval, that the baby experiences before birth. The rapid, reliable and cost-effective transmission of health data through telemedicine applications is increasing when the distance between health service providers and health care providers increases. In this work, a new method for compressing FECG signals received from the PhysioNet database is proposed. This proposed method is variance and neighborhood based data compression (VNBDC) algorithm. In the signal compression, the FECG signals were divided into 5 ms, 10 ms, and 20 ms segments. Then, the column-based variances of each segmented FECG signal were calculated. Differences between binary adjacent variance values were calculated through the column and then a threshold value was determined by averaging these differences between them. In the FECG signal, the variances of adjacent distributions on a column basis were compared with this threshold value, and those larger than this threshold value were discarded and the signal was compressed by removing similar columns. In the study, a non-interference fetal ECG database was used and it was observed that there was not a significant change (mean change 0.05%) in the time domain features of FECG signals compressed with raw FECG signal, while a compression of approximately 20% to 40% was obtained in the end result. Based on the results obtained, this proposed compression method has been shown to be safely used in biotelemetry systems.