Passive Fetal Movement Recognition Approaches Using Hyperparameter Tuned LightGBM Model and Bayesian Optimization

Is it possible to monitor fetal movements with a wearable device? A review of novel technologies

Stillbirth is often preceded by reduced fetal movements and obstetric intervention is necessitated for stillbirth prevention. Yet, despite fetal movements being one of the few tangible ways a pregnant woman and the clinical team can assess the wellbeing of her baby, there are few validated, objective means for pregnant women to quantify the frequency and nature of an unborn baby's movements. Traditional methods of assessing fetal wellbeing such as cardiotocography and fetal movement charts have a lack of diagnostic accuracy, and often lead to false positive intervention. The need for fetal movement counting has led to the development of objective methods to attempt to quantify movements. Some are based on electrocardiography, others on the principles of accelerometery, phonography and optical fibre technology. This review paper not only explores these technologies and evaluates the state-of the-art fetal movement monitoring, but explains the engineering principles underpinning the various technologies, and explores the importance and practice of fetal movement monitoring. To this end, we conclude that there is still a need for the continued development of innovations which will enable a pregnant woman to carry out everyday activities, whilst confident in the knowledge that her unborn child's wellbeing is being accurately monitored, and that feedback from the monitoring device is readily accessible to her.

Wearable Sensors, Data Processing, and Artificial Intelligence in Pregnancy Monitoring: A Review

Pregnancy monitoring is always essential for pregnant women and fetuses. According to the report of WHO (World Health Organization), there were an estimated 287,000 maternal deaths worldwide in 2020. Regular hospital check-ups, although well established, are a burden for pregnant women because of frequent travelling or hospitalization. Therefore, home-based, long-term, non-invasive health monitoring is one of the hot research areas. In recent years, with the development of wearable sensors and related data-processing technologies, pregnancy monitoring has become increasingly convenient. This article presents a review on recent research in wearable sensors, physiological data processing, and artificial intelligence (AI) for pregnancy monitoring. The wearable sensors mainly focus on physiological signals such as electrocardiogram (ECG), uterine contraction (UC), fetal movement (FM), and multimodal pregnancy-monitoring systems. The data processing involves data transmission, pre-processing, and application of threshold-based and AI-based algorithms. AI proves to be a powerful tool in early detection, smart diagnosis, and lifelong well-being in pregnancy monitoring. In this review, some improvements are proposed for future health monitoring of pregnant women. The rollout of smart wearables and the introduction of AI have shown remarkable potential in pregnancy monitoring despite some challenges in accuracy, data privacy, and user compliance.

Early-Stage Prototype Assessment of Cost-Effective Non-Intrusive Wearable Device for Instant Home Fetal Movement and Distress Detection: A Pilot Study

Clinical fetal monitoring devices can only be operated by medical professionals and are overly costly, prone to detrimental false positives, and emit radiation. Thus, highly accurate, easily accessible, simplified, and cost-effective fetal monitoring devices have gained an enormous interest in obstetrics. In this study, a cost-effective and user-friendly wearable home fetal movement and distress detection device is developed and assessed for early-stage design progression by facilitating continuous, comfortable, and non-invasive monitoring of the fetus during the final trimester. The functionality of the developed prototype is mainly based on a microcontroller, a single accelerometer, and a specialized fetal phonocardiography (fPCG) acquisition board with a low-cost microphone. The developed system is capable of identifying fetal movement and monitors fetal heart rhythm owing to its considerable sensitivity. Further, the device includes a Global System for Mobile Communication (GSM)-based alert system for instant distress notifications to the mother, proxy, and emergency services. By incorporating digital signal processing, the system achieves zero false negatives in detecting fetal movements, which was validated against an open-source database. The acquired results clearly substantiated the efficacy of the fPCG acquisition board and alarm system, ensuring the prompt identification of fetal distress.

Machine learning based storm time modeling of ionospheric vertical total electron content over Ethiopia

Geomagnetic storms can cause variations in the ionization levels of the ionosphere, which is commonly studied using the total electron content (TEC). TEC is a crucial parameter to identify the possible effects of ionospheric variations on satellite communication and navigation. This paper assesses the performance of light gradient boosting machine (LGB) and deep neural network (DNN) machine learning algorithms in modeling ionospheric vertical TEC (VTEC) during geomagnetic disturbances. GPS VTEC data for years 2011-2016 from 13 dual-frequency receiver stations over Ethiopia was utilized. Input parameters for the models were derived from the factors that influence VTEC, such as time, location, geomagnetic activity, solar activity, solar wind, and the interplanetary magnetic field. The LGB model improved the predictions of the DNN model from root mean squared error (RMSE), mean absolute percentage error (MAPE), and R2 values of 5.45 TECU, 21%, and 0.93 to 4.98 TECU, 18%, and 0.94 on the testing data, respectively. The two machine learning models significantly outperformed the International Reference Ionosphere (IRI 2020) model during the selected geomagnetic storm periods. This study could provide insight into the impacts of ionosphere variations on satellite communication and navigation systems in the low-latitude ionospheric region.

Assessing the Influence of Sensor-Induced Noise on Machine-Learning-Based Changeover Detection in CNC Machines

The noise in sensor data has a substantial impact on the reliability and accuracy of (ML) algorithms. A comprehensive framework is proposed to analyze the effects of diverse noise inputs in sensor data on the accuracy of ML models. Through extensive experimentation and evaluation, this research examines the resilience of a LightGBM ML model to ten different noise models, namely, Flicker, Impulse, Gaussian, Brown, Periodic, and others. A thorough analytical approach with various statistical metrics in a Monte Carlo simulation setting was followed. It was found that the Gaussian and Colored noise were detrimental when compared to Flicker and Brown, which are identified as safe noise categories. It was interesting to find a safe threshold limit of noise intensity for the case of Gaussian noise, which was missing in other noise types. This research work employed the use case of changeover detection in (CNC) manufacturing machines and the corresponding data from the publicly funded research project (OBerA).

How Wearable Sensors Can Support the Research on Foetal and Pregnancy Outcomes: A Scoping Review

The application of innovative technologies, and in particular of wearable devices, can potentially transform the field of antenatal care with the aim of improving maternal and new-born health through a personalized approach. The present study undertakes a scoping review to systematically map the literature about the use wearable sensors in the research of foetal and pregnancy outcomes. Online databases were used to identify papers published between 2000-2022, from which we selected 30 studies: 9 on foetal outcomes and 21 on maternal outcomes. Included studies focused primarily on the use of wearable devices for monitoring foetal vital signs (e.g., foetal heart rate and movements) and maternal activity during pregnancy (e.g., sleep patterns and physical activity levels). There were many studies that focused on development and/or validation of wearable devices, even if often they included a limited number of pregnant women without pregnancy complications. Although their findings support the potential adoption of wearable devices for both antenatal care and research, there is still insufficient evidence to design effective interventions. Therefore, high quality research is needed to determine which and how wearable devices could support antenatal care.

Tree-Based Machine Learning Models with Optuna in Predicting Impedance Values for Circuit Analysis

The transmission characteristics of the printed circuit board (PCB) ensure signal integrity and support the entire circuit system, with impedance matching being critical in the design of high-speed PCB circuits. Because the factors affecting impedance are closely related to the PCB production process, circuit designers and manufacturers must work together to adjust the target impedance to maintain signal integrity. Five machine learning models, including decision tree (DT), random forest (RF), extreme gradient boosting (XGBoost), categorical boosting (CatBoost), and light gradient boosting machine (LightGBM), were used to forecast target impedance values. Furthermore, the Optuna algorithm is used to determine forecasting model hyperparameters. This study applied tree-based machine learning techniques with Optuna to predict impedance. The results revealed that five tree-based machine learning models with Optuna can generate satisfying forecasting accuracy in terms of three measurements, including mean absolute percentage error (MAPE), root mean square error (RMSE), and coefficient of determination (R2). Meanwhile, the LightGBM model with Optuna outperformed the other models. In addition, by using Optuna to tune the parameters of machine learning models, the accuracy of impedance matching can be increased. Thus, the results of this study suggest that the tree-based machine learning techniques with Optuna are a viable and promising alternative for predicting impedance values for circuit analysis.

Predicting and Analyzing Road Traffic Injury Severity Using Boosting-Based Ensemble Learning Models with SHAPley Additive exPlanations

Road traffic accidents are one of the world’s most serious problems, as they result in numerous fatalities and injuries, as well as economic losses each year. Assessing the factors that contribute to the severity of road traffic injuries has proven to be insightful. The findings may contribute to a better understanding of and potential mitigation of the risk of serious injuries associated with crashes. While ensemble learning approaches are capable of establishing complex and non-linear relationships between input risk variables and outcomes for the purpose of injury severity prediction and classification, most of them share a critical limitation: their “black-box” nature. To develop interpretable predictive models for road traffic injury severity, this paper proposes four boosting-based ensemble learning models, namely a novel Natural Gradient Boosting, Adaptive Gradient Boosting, Categorical Gradient Boosting, and Light Gradient Boosting Machine, and uses a recently developed SHapley Additive exPlanations analysis to rank the risk variables and explain the optimal model. Among four models, LightGBM achieved the highest classification accuracy (73.63%), precision (72.61%), and recall (70.09%), F1-scores (70.81%), and AUC (0.71) when tested on 2015–2019 Pakistan’s National Highway N-5 (Peshawar to Rahim Yar Khan Section) accident data. By incorporating the SHapley Additive exPlanations approach, we were able to interpret the model’s estimation results from both global and local perspectives. Following interpretation, it was determined that the Month_of_Year, Cause_of_Accident, Driver_Age and Collision_Type all played a significant role in the estimation process. According to the analysis, young drivers and pedestrians struck by a trailer have a higher risk of suffering fatal injuries. The combination of trailers and passenger vehicles, as well as driver at-fault, hitting pedestrians and rear-end collisions, significantly increases the risk of fatal injuries. This study suggests that combining LightGBM and SHAP has the potential to develop an interpretable model for predicting road traffic injury severity.