Heart failure continues to be one of the world's top causes of death, requiring reliable predictive models to enable prompt medical interventions. In order to solve class imbalance, this study offers a machine learning framework for heart failure survival prediction that makes use of an optimized XGBoost model combined with the Synthetic Minority Over-sampling Technique (SMOTE). To find the most significant predictors, we used Select K Best with Chi-square for feature selection using a dataset of 5000 clinical records that included features including age, ejection fraction, and serum creatinine. After analyzing several algorithms (such as Logistic Regression, Decision Tree, KNN, SVM, and Random Forest), the XGBoost model was chosen. It was then optimized to maximize hyperparameters, resulting in a test accuracy of 99.70%, precision, recall, and F1-scores close to 1.00, and an AUC-ROC of 0.9998. Our method performs better than the baseline Gradient Boosting Machine (GBM) with Adaptive Inertia Weight Particle Swarm Optimization (AIW-PSO) from earlier research, which attained 94% accuracy on a smaller dataset (299 patients). This is probably because of the larger dataset and sophisticated preprocessing. In addition to providing a scalable, high-accuracy tool for heart failure prognosis, this study demonstrates the effectiveness of XGBoost in conjunction with SMOTE for clinical predictive tasks and has the potential to enhance patient outcomes through accurate and prompt clinical decision-making.
Anees Sultana, S. Khanam· International Journal of AI...· 0 citations
The primary mechanism usually used to preserve democracy in a particular society is election. Blockchain (BC) and other recent technology developments have previously been used in earlier projects to implement unconventional e-Voting systems. The primary objective of these suggestions is to retain openness, confidence, and distant elections while offering the required degree of security and dependability. However, BC's notoriety and dispersed nature created additional privacy and performance trade-off issues. By combining smart contracts for dependability and transparency, Differential Privacy to improve vote anonymity, and Self-Sovereign Identities (SSI) for maintaining decentralized identity and verifiable credentials, this study seeks to overcome current privacy and performance difficulties in e-voting. Specifically, a novel (k, ε)-differential privacy strategy is created that allows statistical vote approximation while maintaining anonymity by using a randomly chosen candidate as a pivot to redistribute retrievable votes to other candidates. In order to improve user engagement, the system also incorporates a real-time notification system that, following completion of the voting process, sends a confirmation message to the user's registered mobile device, such as "Vote successfully cast". Different transaction arrival speeds (10–80 TX/s), total votes cast (10k–50k), and numbers of elected candidates (2–8) are among the parameters under which the suggested techniques are assessed. The smart contract is built on a cloudhosted, permissioned blockchain network utilizing Hyperledger Besu, with geographically dispersed nodes in Google's EU and USA data centers, in order to verify its realistic implementation. According to experimental data, BP-Vot outperforms current solutions in latency by 24% (≈ 1 s/TX vs. 1.24 s/TX). Additionally, the system regularly provides over 98% accuracy in estimated vote outcomes using a standardized Min-Max regression algorithm; accuracy increases linearly with vote volume. Additionally, the robustness of the suggested differential privacy model against reconstruction assaults is officially confirmed. KEYWORDS: leakage-resilient anonymous multi-receiver encryption (LR-AMRE), leakage-resilient anonymous heterogeneous multi-receiver hybrid encryption (LR-AHMR-HE)
I. Begum, S. Khanam· International Journal of AI...· 0 citations
This study suggests an enhanced safety helmet detection method based on YOLOv10 to solve the low detection accuracy of current algorithms for small objects and complicated settings in different situations.
Iqra Aziza Khatoon, S. Khanam· International Journal of Dat...· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
