Anemia, characterized by a deficiency in red blood cells (RBCs) or hemoglobin (HGB), poses significant global public health challenges. Accurate diagnosis and classification of anemia types, crucially dependent on hemoglobin (HGB) level estimation, is essential for effective management and treatment planning. This study investigates the prevalence, severity, and demographic associations of various anemia types among 364 adult patients using publicly available data from complete blood count (CBC) tests. The dataset includes 11 CBC attributes pivotal for anemia diagnosis, encompassing HGB levels and RBC counts. To address the complexities inherent in CBC data, such as variations in normal ranges based on age and gender, and challenges in data interpretation across diverse patient demographics, machine learning techniques are employed. Specifically, projected layers of long short-term memory networks (PLSTM) are utilized. These techniques require robust methodologies for data preprocessing, feature selection, and model optimization based on coefficient of determination R2, prioritizing realism and the preservation of critical medical information. This approach ensures accurate predictive modeling of anemia types based on hemoglobin (HGB) levels, classified as mild, moderate, or severe according to World Health Organization (WHO) guidelines. Insights derived from this study, leveraging PLSTM over traditional LSTM networks, contribute to enhancing diagnostic accuracy and developing personalized treatment strategies for anemia. This underscores the role of machine learning in tailoring approaches to complex medical datasets, thereby advancing healthcare outcomes.
This work deals with an adaptive disturbance rejection controller which combines the equivalent control based integral sliding mode control (ISMC) strategy and a Mamdani fuzzy inference system (FIS) for trajectory tracking of a quadrotor vehicle subject to Dryden-type wind gusts. The FIS carries out an on-line estimation of the time constant of a low-pass filter (LPF) to extract the equivalent control from the discontinuous control signal. This strategy dynamically estimates the disturbances and uncertainties acting on the plant. The estimated disturbances are compensated via a feedback control law making the system insensitive to these undesired effects. Finally, numerical simulations to evaluate the proposed controller performing a simulated quadrotor flying inspection task are presented.
This paper presents a control strategy for blood glucose regulation in the presence of an unknown time-varying delayed input. The proposed control scheme is based on an observer-based linear parameter varying (LPV) control with an $H$ criterion, designed for the Bergman minimal model (BMM) for type 1 diabetes mellitus patients. This control strategy regulates glucose levels in response to meal intake. A novel LPV system representation is used to mitigate the inherent conservativeness of the nonlinear system. The observer employs an event-triggered (ET) strategy to avoid unnecessary signal updates, enabling the estimation of the current state vector despite the delayed input, even when the delay is relatively long. Consequently, the control law ensures good performance despite a long unknown delay. The observer-based control scheme is validated under various meal disturbances and unknown delay.
Cardiovascular diseases (CVDs) remain the leading cause of global mortality, with significant contributions from ischemic heart disease and stroke. This study explores the multifaceted risk factors for heart disease hospitalizations in Mexico City, focusing on socioeconomic status (SES) and air pollution. Using a dataset of 11,031 hospitalization records from 2015 to 2020, we employ negative binomial regression and Gradient Boosting Machine (GBM) models to analyze the effects of economic and social SES components, as well as air pollution indices, on the frequency and severity of hospitalizations. Our results reveal that both economic and social aspects of SES, alongside exposure to particulate matter and carbon monoxide, significantly impact hospitalization rates for various heart disease categories. The study highlights that socioeconomic disparities and environmental pollution are crucial determinants of cardiovascular health, emphasizing the need for targeted public health policies and interventions in urban settings. By integrating detailed SES indicators and pollution data, our findings provide a nuanced understanding of the complex relationships influencing heart disease hospitalizations.
The increase in information technologies has generated the need to implement new methodologies to secure the exchange of information. This paper proposes a cryptographic algorithm based on the use of quantum differential geometry operators. These operators exhibit mathematical behaviors similar to quantum behavior, with the advantage that specialized equipment is not required to perform the encryption process. The algorithm is composed of two phases: In the first phase, a subkey is generated through an addition and multiplication process in Z_16 based on a user-defined key. In the second phase, three types of fundamental quantum operators are employed: creation, annihilation, and crossing, which are sequentially connected. The specific selection and configuration of these operators are based on their ability to avoid generating correlation between the data. The method proposed in this work is implemented using grayscale images, obtaining the Peak Signal-to-Noise Ratio (PSNR), the Structural Similarity Index Measure (SSIM), and the Correlation Value, in order to evaluate the fidelity and integrity of the recovered images.
