Lichuan Liu

Pediatric obesity remains a major public health challenge, yet substantial variability in treatment response limits the effectiveness of standardized intervention programs. Early assessment of short-term weight-change trajectories may provide useful information during an intervention. This study presents a clinically interpretable machine learning framework for predicting short-term pediatric obesity intervention outcomes using routinely collected demographic, anthropometric, body-composition, and early-response measurements from the ProActive Kids program. A systematic workflow including data understanding, clinical data preprocessing, feature engineering, and predictive modeling is developed. Three complementary machine learning paradigms, Logistic Regression, Random Forest, and Extreme Gradient Boosting (XGBoost), are comparatively evaluated to investigate predictive performance and feature importance. Baseline prediction models demonstrate limited predictive performance using only pre-intervention measurements, whereas incorporation of Week-3 early-response information substantially improves prediction across all three classifiers. Week-3 percentage weight change emerges as the dominant predictor of the Week-8 weight-reduction outcome. Waist-to-Hip Ratio, Body Fat Percentage, Body Mass Index, and Fat-Free Mass are also identified as influential baseline variables, although their individual importance should be interpreted cautiously because of correlations among anthropometric and body-composition measures. These findings demonstrate that machine learning can support short-term outcome prediction while identifying potentially clinically relevant patterns in routinely collected pediatric obesity data. The results highlight the predictive importance of early intervention response and may inform future studies of pediatric obesity intervention outcomes.

Impulsive noise poses a significant challenge to broadband feedforward active noise control (ANC) systems, particularly in sensitive environments such as infant incubators. This paper presents an adaptive impulsive noise cancellation approach based on the Kalman filter, designed to improve noise attenuation performance under nonstationary and impulsive interference. The proposed framework integrates impulsive noise detection with a Kalman filter-based suppression scheme. Simulation studies are conducted to evaluate the performance of the combined system in comparison to traditional ANC methods, such as Filtered-x Least Mean Square (FxLMS) and Filtered-x Normalized LMS (FxNLMS). Results demonstrate that the Kalman filter can effectively reduce the influence of impulsive disturbances without degrading overall broadband noise cancellation. A case study involving an infant incubator illustrates the practical effectiveness and robustness of the proposed technique in a real-world healthcare application. The findings support the integration of Kalman filter-based adaptive control in future ANC designs targeting impulsive noise environments.

Context: Respiratory morbidity is a leading cause of children’s consultations with general practitioners. Auscultation, the act of listening to breath sounds, is a crucial diagnostic method for respiratory system diseases. Problem: Parents and caregivers often lack the necessary knowledge and experience to identify subtle differences in children’s breath sounds. Furthermore, obtaining reliable feedback from young children about their physical condition is challenging. Methods: The use of a human–artificial intelligence (AI) tool is an essential component for screening and monitoring young children’s respiratory diseases. Using clinical data to design and validate the proposed approaches, we propose novel methods for recognizing and classifying children’s breath sounds. Different breath sound signals were analyzed in the time domain, frequency domain, and using spectrogram representations. Breath sound detection and segmentation were performed using digital signal processing techniques. Multiple features—including Mel–Frequency Cepstral Coefficients (MFCCs), Linear Prediction Coefficients (LPCs), Linear Prediction Cepstral Coefficients (LPCCs), spectral entropy, and Dynamic Linear Prediction Coefficients (DLPCs)—were extracted to capture both time and frequency characteristics. These features were then fed into various classifiers, including K-Nearest Neighbor (KNN), artificial neural networks (ANNs), hidden Markov models (HMMs), logistic regression, and decision trees, for recognition and classification. Main Findings: Experimental results from across 120 infants and preschoolers (2 months to 6 years) with respiratory disease (30 asthma, 30 croup, 30 pneumonia, and 30 normal) verified the performance of the proposed approaches. Conclusions: The proposed AI system provides a real-time diagnostic platform to improve clinical respiratory management and outcomes in young children, thereby reducing healthcare costs. Future work exploring additional respiratory diseases is warranted.

Accurate pronunciation of speech sounds is essential in communication. As children learn their native language, they refine the movements necessary for intelligible speech. While there is variability in the order of acquisition of speech sounds, there are some sounds that are more complex and are later developing. The rhotic /r/ is a later-developing sound in English, and some children require intervention to achieve accurate production. Additionally, individuals learning English as a second language may have difficulty learning accurate /r/ production, especially if their native language does not have an /r/, or the /r/ they produce is at a different place of articulation. The goal of this research is to provide a novel approach on how a knowledge-based intelligence program can provide immediate feedback on the accuracy of productions. In the proposed approach, the audio signals will first be detected, after which features of audio signals will be extracted, and finally, knowledge-based intelligent classification will be performed. Based on the obtained knowledge and application scenarios, novel features are proposed and used to classify various speaker scenarios.

This research proposes to develop a wireless communication integrated hybrid active noise control (ANC) system for infant incubators. The integrated ANC system will reduce the level of noise in the infant's ear and provide two-way wireless communication between infant and his/her parents/caregivers both inside and outside the Neonatal Intensive Care Unit (NICU). The proposed system will use the ANC technique to reduce the harmful noise. The wireless communication system will be used to reduce stress and improve bonding and language development. The real-time experiments show that the proposed system can significantly reduce the noise exposure to the infants who are placed in infant incubators. Consequently, a reduction in the health risk produced by high-level noise in NICU and improved bonding opportunities for infants and their parents will be seen.

A pseudo-linear optical transmission system analytical model is built for the numerical analysis of dispersion compensation schemes. The system performance under the influence of intra-channel nonlinear effects and the initial pulse power is discussed for the data rates of 10, 40, 100 and 160 Gbit/s, respectively. We get the conclusion for the first time as we know the optimal dispersion compensation scheme for the optimal system performance is closely related to the system data rate and the proportion of the pre-dispersion compensation should be decreased while that of the post-dispersion compensation be increased with the increasing of system data rate. When the system data rate is higher than 160 Gbit/s, we can use the post-dispersion compensation scheme directly.