This paper examines the vulnerability of Small and Medium-sized Enterprises (SMEs) exposed to evolving climate changes in Pakistan, specifically the impacts of extreme weather events, including floods and drought. The earlier literature illustrates that SMEs are affected by climate-related risks, but the current study takes the discussion further by implementing machine learning algorithms to measure the vulnerabilities of SMEs more objectively. A mixed-methods design was used to combine surveys with machine-learning techniques. PyCaret was employed to tune instruments such as Logistic Regression (LR), Random Forest (RF), ordered logistic regression, LightGBM, ADA Boost, SVM, KNN, GBC, and Naïve Bayes, among others, in Python. The results show that SMEs located in rural regions are significantly more vulnerable to climate events than SMEs in urban areas. The best results were found by the Logistic Regression model: its accuracy was 63.3%, recall 63.3%, F1-score 55.2%, and Kappa value 0.23. Random Forest showed similar findings, but Logistic Regression proved stronger in diagnosing the influence of climate on business activity. Ordered logistic regression-based analyses show that awareness of temperature fluctuation (p = 0.035) and perceived financial impact (p = 0.018) significantly affect the degree to which firms are affected by climate-related impacts, while geographic locations (p = 0.057) and business tenure (p = 0.091) are only marginally important. Strict evaluation of empirical evidence has pointed out that the application of focused financial tools, extensive infrastructure, and governance framework transformation can help to make the small- and medium-sized enterprises, especially enterprises located in remote areas to be more resilient to climate-related risks.. Further studies may improve this analysis through a more detailed machine-learning framework and analysis of sector-specific effects of climate change in specific geographic areas.

High-dimensional gene expression datasets in chemometric and biomedical research present significant challenges for machine learning because the number of genes greatly exceeds the number of available samples, increasing the risk of overfitting and reducing classification reliability. Existing gene selection methods are often sensitive to noise and outliers, leading to unstable feature subsets and degraded classification performance. To address these limitations, this study proposes a Robust Masked Painter (RMP) framework that integrates robust measures of location and dispersion, namely the Median and the Rousseeuw & Croux statistic ($Q_n$), for reliable gene selection. The proposed framework operates in two stages. First, we identify informative genes using a round-robin strategy with a greedy search algorithm and robust core intervals to reduce the influence of noise and outliers. Second, Dominant Class (DC) analysis and Overlapping Scores (OS) further refine the selected gene subset by minimizing class overlap. We evaluate the proposed method on four publicly available gene expression datasets and compare it with several established feature selection methods using Random Forest, K-Nearest Neighbors, and Support Vector Machine classifiers. We assess classification performance using the Classification Error Rate. Experimental results and simulation studies demonstrate that the proposed RMP framework consistently outperforms competing methods by selecting highly informative genes that improve classification accuracy, robustness, and generalization.

Breast Cancer is a common type of cancer found in women. In this paper, we model breast cancer data using a new three parameter family of distribution, called the Three Parameter Gull Alpha Power Exponential (TP-GAPE) Distribution. The new distribution is more useful because it can correspond to various hazard rate functions, which are widely used in reliability investigations. With the help of the proposed model, data with rising, uni-modal, and modified uni-modal hazard rate functions can be analyzed. We determine the essential statistical and reliability properties of the suggested model. The goodness-of-fit criteria have been studied using two real-life data sets. The proposed model is compared to other current modifications of the exponential distribution with the aim of evaluating the model's efficacy using a variety of goodness of fit measures, including the Akaike Information Criterion, Bayesian Information Criterion, etc. These results suggest that the proposed model fits the cancer data as well as some other scientific data more precisely than any recently developed extensions of exponential distribution.