Counting fetal movements is essential for assessing fetal health, but manually recording these movements can be challenging and inconvenient for pregnant women. This study presents a wearable device designed to detect fetal movements across various settings, both within and outside medical facilities. The device integrates accelerometer and gyroscope sensors with Internet of Things (IoT) technology to accurately differentiate between fetal and non-fetal movements. Data were collected from 35 pregnant women at Suranaree University of Technology (SUT) Hospital. This study evaluated ten signal extraction methods, six machine learning algorithms, and four feature selection techniques to enhance classification performance. The device utilized Particle Swarm Optimization (PSO) for feature selection and Extreme Gradient Boosting (XGB) with PSO hyper-tuning. It achieved a sensitivity of 90.00%, precision of 87.46%, and an F1-score of 88.56%, reflecting commendable results. The IoT-enabled technology facilitated continuous monitoring with an average latency of 423.6 ms. It ensured complete data integrity and successful transmission, with the capability to operate continuously for up to 48 h on a single charge. The findings substantiate the efficacy of the proposed approach in detecting fetal movements, thereby demonstrating a practical and valuable technology for fetal movement detection applications.

Research focuses on the efficacy of Multi-Task Autoencoder (MTAE) models in signal classification due to their ability to handle many tasks while improving feature extraction. However, researchers have not thoroughly investigated the study of lung sounds (LSs) for pulmonary disease detection. This paper introduces a new framework that utilizes an MTAE model to detect lung diseases based on LS signals. The model integrates an autoencoder and a supervised classifier, simultaneously optimizing both classification accuracy and signal reconstruction. Furthermore, we propose a hybrid approach that combines an MTAE and a Support Vector Machine (MTAE-SVM) to enhance performance. We evaluated our model using LS signals from a publicly available database from King Abdullah University Hospital. The model attained an accuracy of 89.47% for four classes (normal, pneumonia, asthma, and chronic obstructive pulmonary disease) and 90.22% for three classes (normal, pneumonia, and asthma cases). Using the MTAE-SVM, the accuracy was further improved to 91.49% for four classes and 93.08% for three classes, respectively. The results indicate that the MTAE and MTAE-SVM have a considerable potential for detecting pulmonary diseases from lung sound signals. This could aid in the creation of more user-friendly and effective diagnostic tools.

Fetal movement monitoring (FMM) is crucial for assessing fetal well-being, traditionally relying on clinical assessments or maternal perception, each with inherent limitations. This study presents a novel lightweight deep learning framework for real-time FMM on edge devices. Data were collected from 120 participants using a wearable device equipped with an inertial measurement unit, which captured both accelerometer and gyroscope data, coupled with a rigorous two-stage labeling protocol integrating maternal perception and ultrasound validation. We addressed class imbalance using virtual-rotation-based augmentation and adaptive clustering-based undersampling. The data were transformed into spectrograms using the Short-Time Fourier Transform, serving as input for deep learning models. To ensure model efficiency suitable for resource-constrained microcontrollers, we employed knowledge distillation, transferring knowledge from larger, high-performing teacher models to compact student architectures. Post-training integer quantization further optimized the models, reducing the memory footprint by 74.8%. The final optimized model achieved a sensitivity (SEN) of 90.05%, a precision (PRE) of 87.29%, and an F1-score (F1) of 88.64%. Practical energy assessments showed continuous operation capability for approximately 25 h on a single battery charge. Our approach offers a practical framework adaptable to other medical monitoring tasks on edge devices, paving the way for improved prenatal care, especially in resource-limited settings.

Blood pressure (BP) monitoring is essential for cardiovascular health management, yet traditional cuff-based methods face limitations including patient discomfort and inapplicability for certain populations. This study presents a deep learning framework for cuffless BP estimation using phonocardiogram (PCG) signals. The proposed model integrates convolutional neural networks (CNNs) with Squeeze-and-Excitation (SE) blocks and demographic information to enhance prediction accuracy. Mel-Frequency Cepstral Coefficients (MFCCs), along with their delta and delta–delta coefficients, were employed to capture comprehensive acoustic characteristics of heart sounds. The results demonstrated that the proposed model achieved high predictive accuracy and strong consistency with reference BP measurements. Component analysis confirmed that the inclusion of SE blocks provided substantial performance gains, while demographic information further improved prediction stability. Clinical validation also verified that the model maintained close agreement with true BP values across the tested population, showing significant improvement over the baseline CNN implementation. These findings suggest potential for accessible, non-invasive BP monitoring systems suitable for continuous health tracking.

Congenital heart disease (CHD) is a major cause of infant morbidity and mortality, and timely diagnosis remains difficult where advanced imaging is not consistently available. Automated phonocardiogram (PCG) screening can support early triage, but pediatric multiclass classification is limited by subtle acoustic differences and class imbalance. This study proposes a five-class heart-sound framework (Normal, ASD, PDA, PFO, and VSD) using multi-domain feature fusion and a convolutional recurrent neural network (CRNN). A four-channel representation combining Log-Mel, PCEN-Mel, Gramian Angular Summation Field (GASF), and Markov Transition Field (MTF) is modeled with a CNN encoder, bidirectional GRU, and dual temporal pooling. Recordings are segmented with uniform 50% overlap and evaluated under a strict subject-wise protocol with macro-F1-guided model selection. Across five runs on the pediatric ZCHSound dataset, the five-class model achieves a mean macro F1-score of 78.61 ± 1.00% and a mean per-subject accuracy of 87.94 ± 0.87%. A dedicated Normal-versus-Abnormal model reaches 95.74% accuracy. These results suggest that multi-domain fusion with sequence-aware modeling is a promising approach for pediatric CHD auscultation support.

Background and Objectives: Maternal perception of fetal movement is widely used to monitor fetal activity; however, maternally perceived movements may not correspond directly to movements observed by ultrasonography. This study aimed to quantify same-window maternal recognition of ultrasound-observed fetal movements, characterize temporal concordance and directional discrepancies, and examine associated maternal and pregnancy-related factors. Materials and Methods: Pregnant women at ≥28 weeks of gestation underwent simultaneous 20 min fetal-movement assessment using real-time ultrasonography and maternal button-press reporting. The ultrasound observer pressed a designated button whenever fetal movement was visually observed, while participants independently pressed a separate button whenever they perceived fetal movement. Both responses were electronically timestamped using the same system clock and segmented into consecutive 5 s windows. Windows containing an ultrasound-observer button press were classified as ultrasound-positive, and those accompanied by a maternal response within the corresponding window were classified as temporally matched. Same-window maternal recognition was defined as the proportion of ultrasound-positive windows accompanied by a maternal response within the same 5 s analytical window. Associated factors were examined using fractional logistic regression with robust standard errors. Results: A total of 112 valid assessment sessions were analyzed. The median number of ultrasound-positive windows was 26.5 (IQR, 15.5–41.5), compared with 10.5 (IQR, 6.0–18.5) maternal-response windows. Median same-window maternal recognition was 20.3% (IQR, 8.3–38.5%; bootstrap percentile 95% CI, 15.7–23.1%), and median overall temporal concordance was 16.1% (IQR, 7.4–25.3%). Maternal-response window counts were lower than ultrasound-positive window counts in 101 of 112 assessment sessions (90.2%). After adjustment for maternal age, BMI, and fetal presentation, later gestational age was associated with lower same-window maternal recognition (β = −0.063, 95% CI −0.122 to −0.004; p = 0.037), corresponding to an average marginal effect of −1.12 percentage points per week (95% CI −2.15 to −0.09; p = 0.033). Conclusions: Maternal and ultrasound-observed fetal-movement counts showed limited same-window temporal correspondence during the 20 min observation period. A modest inverse association with gestational age was observed in the primary model, although the association was less precise in the denominator-aware and vertex-only sensitivity analyses. These findings reflect temporal matching under the predefined 5 s analytical framework and should not be interpreted as indicating that mothers perceive only a small proportion of fetal movements or that maternal perception becomes less reliable as pregnancy advances.