Rapid urbanization worldwide has significantly altered urban climates, creating a need to balance urban growth with thermal environmental quality for sustainable development. This study examines the relationship between land surface temperature (LST) and urban characteristics, particularly focusing on how green cover can mitigate urban heat and how air pollution can increase temperatures. Recognizing the predictive value of LST for urban heat island (UHI) intensity, we analyzed three distinct U.S. cities—Chicago, San Francisco, and Phoenix—each characterized by unique climate and urban planning features. This study investigates the relationship between atmospheric pollutants (SO2, NO2, CO, O3) and the Normalized Difference Vegetation Index (NDVI) with land surface temperature (LST) using regression and correlation analyses. The analysis aims to elucidate how changes in atmospheric pollutants and NDVI affect variations in land surface temperature. Regression analysis is employed to estimate the coefficients of independent variables and quantify their impact on LST. Correlation analysis assesses the linear relationships between variables, providing insights into their pairwise associations. The study also examines multicollinearity between independent variables to identify potential confounding factors. The results reveal significant associations between atmospheric pollutants, NDVI, and land surface temperature, contributing to our understanding of the environmental factors influencing LST dynamics and informing climate change mitigation strategies. The observed inconsistencies in correlations across cities highlight the importance of the local context in environmental studies. Understanding these variations can aid in developing tailored urban planning policies that consider unique city characteristics for more effective climate resilience. Furthermore, a positive association was consistently obtained between pollutants and LST, indicating that increased pollution levels contribute to higher surface temperatures across different urban settings.
Change detection in biomedical signals is crucial for understanding physiological processes and diagnosing medical conditions. This study evaluates various change detection methods, focusing on synthetic signals that mimic real-world scenarios. We examine the following three methods: classical statistical techniques (thresholding based on mean and standard deviation), Support Vector Machine (SVM) classification, and time–frequency analysis using Continuous Wavelet Transform (CWT). Each method’s performance is assessed using synthetic signals, including nonlinear signals and those with simulated anomalies. We calculated the F1-score to quantify performance, providing a balanced measure of precision and recall. Results showed that SVM classification outperformed both classical techniques and CWT analysis, achieving a higher F1-score in detecting changes. While all methods struggled with synthetic nonlinear signals, classical techniques and SVM successfully detected changes in signals with simulated anomalies, whereas CWT had difficulty with both types of signals. These findings underscore the importance of selecting appropriate change detection methods based on signal characteristics. Future research should explore advanced machine learning and signal processing techniques to improve detection accuracy in biomedical applications.