A Fetal Well-Being Diagnostic Method Based on Cardiotocographic Morphological Pattern Utilizing Autoencoder and Recursive Feature Elimination

Cardiotocography (CTG), which measures the fetal heart rate (FHR) and maternal uterine contractions (UC) simultaneously, is used for monitoring fetal well-being during delivery or antenatally at the third trimester. Baseline FHR and its response to uterine contractions can be used to diagnose fetal distress, which may necessitate therapeutic intervention. In this study, a machine learning model based on feature extraction (autoencoder), feature selection (recursive feature elimination), and Bayesian optimization, was proposed to diagnose and classify the different conditions of fetuses (Normal, Suspect, Pathologic) along with the CTG morphological patterns. The model was evaluated on a publicly available CTG dataset. This research also addressed the imbalance nature of the CTG dataset. The proposed model has a potential application as a decision support tool to manage pregnancies. The proposed model resulted in good performance analysis metrics. Using this model with Random Forest resulted in a model accuracy of 96.62% for fetal status classification and 94.96% for CTG morphological pattern classification. In rational terms, the model was able to accurately predict 98% Suspect cases and 98.6% Pathologic cases in the dataset. The combination of predicting and classifying fetal status as well as the CTG morphological patterns shows potential in monitoring high-risk pregnancies.

Attention-assisted hybrid 1D CNN-BiLSTM model for predicting electric field induced by transcranial magnetic stimulation coil

Deep learning-based models such as deep neural network (DNN) and convolutional neural network (CNN) have recently been established as state-of-the-art for enumerating electric fields from transcranial magnetic stimulation coil. One of the main challenges related to this electric field enumeration is the prediction time and accuracy. Despite the low computational cost, the performance of the existing prediction models for electric field enumeration is quite inefficient. This study proposes a 1D CNN-based bi-directional long short-term memory (BiLSTM) model with an attention mechanism to predict electric field induced by a transcranial magnetic stimulation coil. The model employs three consecutive 1D CNN layers followed by the BiLSTM layer for extracting deep features. After that, the weights of the deep features are redistributed and integrated by the attention mechanism and a fully connected layer is utilized for the prediction. For the prediction purpose, six input features including coil turns of single wing, coil thickness, coil diameter, distance between two wings, distance between head and coil position, and angle between two wings of coil are mapped with the output of the electric field. The performance evaluation is conducted based on four verification metrics (e.g. R2, MSE, MAE, and RMSE) between the simulated data and predicted data. The results indicate that the proposed model outperforms existing DNN and CNN models in predicting the induced electrical field with R2 = 0.9992, MSE = 0.0005, MAE = 0.0188, and RMSE = 0.0228 in the testing stage.

Pregnancy in the time of COVID-19: towards Fetal monitoring 4.0

On the outbreak of the global COVID-19 pandemic, high-risk and vulnerable groups in the population were at particular risk of severe disease progression. Pregnant women were one of these groups. The infectious disease endangered not only the physical health of pregnant women, but also their mental well-being. Improving the mental health of pregnant women and reducing their risk of an infectious disease could be achieved by using remote home monitoring solutions. These would allow the health of the mother and fetus to be monitored from the comfort of their home, a reduction in the number of physical visits to the doctor and thereby eliminate the need for the mother to venture into high-risk public places. The most commonly used technique in clinical practice, cardiotocography, suffers from low specificity and requires skilled personnel for the examination. For that and due to the intermittent and active nature of its measurements, it is inappropriate for continuous home monitoring. The pandemic has demonstrated that the future lies in accurate remote monitoring and it is therefore vital to search for an option for fetal monitoring based on state-of-the-art technology that would provide a safe, accurate, and reliable information regarding fetal and maternal health state. In this paper, we thus provide a technical and critical review of the latest literature and on this topic to provide the readers the insights to the applications and future directions in fetal monitoring. We extensively discuss the remaining challenges and obstacles in future research and in developing the fetal monitoring in the new era of Fetal monitoring 4.0, based on the pillars of Healthcare 4.0.

Intrapartum cardiotocography: an exploratory analysis of interpretational variation

Our aim was to evaluate the intra- and inter-operator agreement in cardiotocography (CTG) traces analysis using the 2015 FIGO classification guidelines, and whether the educational background and the knowledge of anamnestic data can influence the interpretation of CTG traces. A retrospective interpretation of 73 intrapartum CTGs at time 0 (T0) for a first blind interpretation and at time 1 (T1) two months later with additional anamnestic pregnancy information was made by eight different operators (four obstetricians and four midwives with different years of work experience). The intra-observer agreement demonstrates that midwifes are more concordant than obstetricians with a mean of 77.05% versus a mean of 65.75%. There is moderate inter-observer agreement in classifying a CTG trace as 'normal'; on the contrary, there is no consensus on the 'suspect' and 'pathological' classification category.IMPACT STATEMENTWhat is already known on this subject? Interpretation of intrapartum CTG is affected by significant subjective variables with relevant intra- and inter-observer lack of optimal agreement, especially in case of abnormal o pathologic findings.What do the results of this study add? Clinical data seem to play a role in interpretation of suspicious and pathological traces while they do not affect the rate of agreement for normal traces. Midwives tend to be less influenced by anamnestic data in visual CTG interpretation. Instead, obstetricians tend to be more focussed on clinical data and clinical setting that, as a consequence, tend to have great impact on CTG trace interpretation.What are the implications of these findings for clinical practice and/or further research? Cooperation among obstetricians and between obstetricians and midwives should be encouraged in order to optimise CTG reading and improve maternal and neonatal outcomes. Regarding the influence of clinical parameters in classification of intrapartum CTG traces, especially in case of abnormal CTG traces, it should be conceivable to improve medical skills in CTG blind interpretation and further investigate which clinical parameters are mainly related with an augmented risk of foetal asphyxia and adverse neonatal outcomes.

Multiparametric Investigation of Dynamics in Fetal Heart Rate Signals

In the field of electronic fetal health monitoring, computerized analysis of fetal heart rate (FHR) signals has emerged as a valid decision-support tool in the assessment of fetal wellbeing. Despite the availability of several approaches to analyze the variability of FHR signals (namely the FHRV), there are still shadows hindering a comprehensive understanding of how linear and nonlinear dynamics are involved in the control of the fetal heart rhythm. In this study, we propose a straightforward processing and modeling route for a deeper understanding of the relationships between the characteristics of the FHR signal. A multiparametric modeling and investigation of the factors influencing the FHR accelerations, chosen as major indicator of fetal wellbeing, is carried out by means of linear and nonlinear techniques, blockwise dimension reduction, and artificial neural networks. The obtained results show that linear features are more influential compared to nonlinear ones in the modeling of HRV in healthy fetuses. In addition, the results suggest that the investigation of nonlinear dynamics and the use of predictive tools in the field of FHRV should be undertaken carefully and limited to defined pregnancy periods and FHR mean values to provide interpretable and reliable information to clinicians and researchers.

A Comprehensive Review of Techniques for Processing and Analyzing Fetal Heart Rate Signals

The availability of standardized guidelines regarding the use of electronic fetal monitoring (EFM) in clinical practice has not effectively helped to solve the main drawbacks of fetal heart rate (FHR) surveillance methodology, which still presents inter- and intra-observer variability as well as uncertainty in the classification of unreassuring or risky FHR recordings. Given the clinical relevance of the interpretation of FHR traces as well as the role of FHR as a marker of fetal wellbeing autonomous nervous system development, many different approaches for computerized processing and analysis of FHR patterns have been proposed in the literature. The objective of this review is to describe the techniques, methodologies, and algorithms proposed in this field so far, reporting their main achievements and discussing the value they brought to the scientific and clinical community. The review explores the following two main approaches to the processing and analysis of FHR signals: traditional (or linear) methodologies, namely, time and frequency domain analysis, and less conventional (or nonlinear) techniques. In this scenario, the emerging role and the opportunities offered by Artificial Intelligence tools, representing the future direction of EFM, are also discussed with a specific focus on the use of Artificial Neural Networks, whose application to the analysis of accelerations in FHR signals is also examined in a case study conducted by the authors.

Multi-Stage Optimization of Induction Machines Using Methods for Model and Parameter Selection

Optimization methods are increasingly used for the design process of electrical machines. The quality of the optimization result and the necessary simulation effort depend on the optimization methods, machine models and optimization parameters used. This paper presents a multi-stage optimization environment for the design optimization of induction machines. It uses the strategies of simulated annealing, evolution strategy and pattern search. Artificial neural networks are used to reduce the solution effort of the optimization. The selection of the electromagnetic machine model is made in each optimization stage using a methodical model selection approach. The selection of the optimization parameters is realized by a methodical parameter selection approach. The optimization environment is applied on the basis of an optimization for the design of an electric traction machine using the example of an induction machine and its suitability for the design of a machine is verified by a comparison with a reference machine.

A Multi-Level World Comprehensive Neural Network Model for Maximum Annual Solar Irradiation on a Flat Surface

With the growing demand for clean and economically feasible renewable energy, solar photovoltaic (PV) system usage has increased. Among many factors, the tilt and azimuth angles are of great importance and influence in determining the photovoltaic panel’s efficiency to generate electricity. Although much research was conducted related to solar PV panels’ performance, this work critically determined the tilt and azimuth angles for PV panels in all countries worldwide. The optimum tilt and azimuth angles are estimated worldwide by the photovoltaic geographic information system (PVGIS). Also, annual and average daily solar irradiation incident on the tilted and oriented plate optimally (AR1 and DR1) are calculated. Besides, annual and average daily solar irradiation incident on plate tilt optimally and oriented because of the south in the northern hemisphere and because of the north in the southern hemisphere (AR2 and DR2) are estimated. PVGIS is also used to calculate the annual and average daily solar irradiation incident on the horizontal plate (AR3 and DR3). The data collected from PVGIS are used to develop an efficient and accurate artificial neural network model based on feed-forward neural network approach. This model is an essential subpart that can be used in an embedded system or an online system for further PV system analysis and optimization. The developed neural model reflected very high accuracy in predicting the PV panels’ optimal tilt and azimuth angles worldwide. The benefit of tilting is generally increased by increasing the latitude. As the latitude increases, the tilt factor (F) increases because of the increase in the optimum tilt angle by increasing the latitude. The optimal orientation is due to the north in the southern hemisphere and due to the south in the northern hemisphere for most cities worldwide. In sum, it can be concluded that the optimum tilt angle is equal to or greater than the latitude until the latitude 30°. The optimum tilt angle becomes less than the latitude, and the difference is increased until it reaches more than 20°. Hence in this study the aim is to develop a simple neural network model which can accurately predict the annual radiation and optimum tilt and azimuth angle in any region of the world and can be easily implemented in a low-cost microcontroller.

Tree Search Fuzzy NARX Neural Network Fault Detection Technique for PV Systems with IoT Support

The photovoltaic (PV) panel’s output energy depends on many factors. As they are becoming the leading alternative energy source, it is essential to get the best out of them. Although the main factor for maximizing energy production is proportional to the amount of solar radiation reaching the photovoltaic panel surface, other factors, such as temperature and shading, influence them negatively. Moreover, being installed in a dynamic and frequently harsh environment causes a set of reasons for faults, defects, and irregular operations. Any irregular operation should be recognized and classified into faults that need attention and, therefore, maintenance or as being a regular operation due to changes in some surrounding factors, such as temperature or solar radiation. Besides, in case of faults, it would be helpful to identify the source and the cause of the problem. Hence, this study presented a novel methodology that modeled a PV system in a tree-like hierarchy, which allowed the use of a fuzzy nonlinear autoregressive network with exogenous inputs (NARX) to detect and classify faults in a PV system with customizable granularity. Moreover, the used methodology enabled the identification of the exact source of fault(s) in a fully automated way. The study was done on a string of eight PV panels; however, the paper discussed using the algorithm on a more extensive PV system. The used fuzzy NARX algorithm in this study was able to classify the faults that appeared in up to five out of the eight PV panels and to identify the faulty PV panels with high accuracy. The used hardware could be controlled and monitored through a Wi-Fi connection, which added support for Internet of Things applications.

Comparing Activation Functions in Modeling Shoreline Variation Using Multilayer Perceptron Neural Network

The study has modeled shoreline changes by using a multilayer perceptron (MLP) neural network with the data collected from five beaches in southern Taiwan. The data included aerial survey maps of the Forestry Bureau for years 1982, 2002, and 2006, which served as predictors, while the unmanned aerial vehicle (UAV) surveyed data of 2019 served as the respondent. The MLP was configured using five different activation functions with the aim of evaluating their significance. These functions were Identity, Tahn, Logistic, Exponential, and Sine Functions. The results have shown that the performance of an MLP model may be affected by the choice of an activation function. Logistic and the Tahn activation functions outperformed the other models, with Logistic performing best in three beaches and Tahn having the rest. These findings suggest that the application of machine learning to shoreline changes should be accompanied by an extensive evaluation of the different activation functions.

Toward Better PV Panel’s Output Power Prediction; a Module Based on Nonlinear Autoregressive Neural Network with Exogenous Inputs

Much work has been carried out for modeling the output power of photovoltaic panels. Using artificial neural networks (ANNS), one could efficiently model the output power of heterogeneous photovoltaic (HPV) panels. However, due to the existing different types of artificial neural network implementations, it has become hard to choose the best approach to use for a specific application. This raises the need for studies that develop models using the different neural networks types and compare the efficiency of these different types for that specific application. In this work, two neural network types, namely, the nonlinear autoregressive network with exogenous inputs (NARX) and the deep feed-forward (DFF) neural network, have been developed and compared for modeling the maximum output power of HPV panels. Both neural networks have four exogenous inputs and two outputs. Matlab/Simulink is used in evaluating the proposed two models under a variety of atmospheric conditions. A comprehensive evaluation, including a Diebold-Mariano (DM) test, is applied to verify the ability of the proposed networks. Moreover, the work further investigates the two developed neural networks using their actual implementation on a low-cost microcontroller. Both neural networks have performed very well; however, the NARX model performance is much better compared with DFF. Using the NARX network, a prediction of PV output power could be obtained, with half the execution time required to obtain the same prediction with the DFF neural network, and with accuracy of ±0.18 W.

Levenberg-Marquardt Neural Network Algorithm for Degree of Arteriovenous Fistula Stenosis Classification Using a Dual Optical Photoplethysmography Sensor

This paper proposes a noninvasive dual optical photoplethysmography (PPG) sensor to classify the degree of arteriovenous fistula (AVF) stenosis in hemodialysis (HD) patients. Dual PPG measurement node (DPMN) becomes the primary tool in this work for detecting abnormal narrowing vessel simultaneously in multi-beds monitoring patients. The mean and variance of Rising Slope (RS) and Falling Slope (FS) values between before and after HD treatment was used as the major features to classify AVF stenosis. Multilayer perceptron neural networks (MLPN) training algorithms are implemented for this analysis, which are the Levenberg-Marquardt, Scaled Conjugate Gradient, and Resilient Back-propagation, to identify the degree of HD patient stenosis. Eleven patients were recruited with mean age of 77 ± 10.8 years for analysis. The experimental results indicated that the variance of RS in the HD hand between before and after treatment was significant difference statistically to stenosis (p < 0.05). Levenberg-Marquardt algorithm (LMA) was significantly outperforms the other training algorithm. The classification accuracy and precision reached 94.82% and 92.22% respectively, thus this technique has a potential contribution to the early identification of stenosis for a medical diagnostic support system.