Background/Objectives: Stroke stands as a prominent global health issue, causing con-siderable mortality and debilitation. It arises when cerebral blood flow is compromised, leading to irreversible brain cell damage or death. Leveraging the power of machine learning, this paper presents a systematic approach to predict stroke patient survival based on a comprehensive set of factors. These factors include demographic attributes, medical history, lifestyle elements, and physiological metrics. Method: An effective random sampling method is proposed to handle the highly biased data of stroke. The stroke pre-diction using optimized boosting machine learning algorithms is supported with explainable AI using LIME and SHAP. This enables the models to discern intricate data patterns and establish correlations between selected features and patient survival. Results: The performance of three boosting algorithms is studied for stroke prediction, which include Gradient Boosting (GB), AdaBoost (ADB), and XGBoost (XGB) with XGB achieved the best outcome overall with a training accuracy of 96.97% and testing accuracy of 92.13%. Conclusions: Through this approach, the study seeks to uncover actionable insights to guide healthcare practitioners in devising personalized treatment strategies for stroke patients.

In traditional vehicle maintenance, there’s often no real-time data available, leaving drivers in the dark about important health and safety parameters. This gap can cause problems like low oil levels, poor oil quality, and overheating, which can put the vehicle and passengers at risk. This paper presents the intelligent engine health monitoring system for enhanced vehicle performance. The system uses ESP8266, ultrasonic sensor, light dependent resistor (LDR), and DS18B20 temperature sensors for continuous monitoring of the oil level, oil quality assessment, and engine temperature measurement in real-time. Oil quality assessment using RGB and white light transmission through a glass tube is proposed with improved accuracy in degradation detection. Blynk app interface in the proposed system produces the instant alert for exceeding threshold limit of sensor to ensures enhanced vehicle performance. Results demonstrate that blue light detects early-stage oil degradation, green light provides a balanced evaluation, and red light identifies severe degradation. A comparative analysis with optical color sensors and ultrasonic-based oil detection highlights the system's higher adaptability and real-time monitoring capabilities.