Privacy-Preserving Federated Learning with Homomorphic Encryption: Alzheimer’s Detection Use-Case

Studies in computational intelligence, Journal Year: 2025, Volume and Issue: unknown, P. 111 - 125

Published: Jan. 1, 2025

Language: Английский

---

Enhancing Named Entity Recognition (NER) in Biomedical Texts: BIOBERT on CORD-19 Data set

Lecture notes in networks and systems, Journal Year: 2025, Volume and Issue: unknown, P. 355 - 365

Published: Jan. 1, 2025

Language: Английский

---

Adaptive Multi-Sport Smart Tracker for Athlete Talent Identification

Journal of Ambient Intelligence and Humanized Computing, Journal Year: 2025, Volume and Issue: unknown

Published: April 26, 2025

Language: Английский

---

Generation-Based Few-Shot BioNER via Local Knowledge Index and Dual Prompts

Interdisciplinary Sciences Computational Life Sciences, Journal Year: 2025, Volume and Issue: unknown

Published: May 10, 2025

Language: Английский

---

Enhanced Parkinson’s Diagnosis through Ensemble Learning with Stacking and Cross-Validation

Procedia Computer Science, Journal Year: 2025, Volume and Issue: 259, P. 250 - 259

Published: Jan. 1, 2025

Language: Английский

---

Process Mining Organization (PMO) Based on Machine Learning Decision Making for Prevention of Chronic Diseases

Eng—Advances in Engineering, Journal Year: 2024, Volume and Issue: 5(1), P. 282 - 300

Published: Feb. 5, 2024

This paper discusses a methodology to improve the prevention processes of chronic diseases such as diabetes and strokes. The research motivation is find new methodological approach design advanced Diagnostic Therapeutic Care Pathways (PDTAs) based on prediction disease using telemedicine technologies machine learning (ML) data processing techniques. aim decrease health risk avoid hospitalizations through prevention. proposed method defines Process Mining Organization (PMO) model, managing risks PDTA structured prevent risk. Specifically, analysis focused stroke First, we applied compared Random Forest (RF) Gradient Boosted Trees (GBT) supervised algorithms predict risk, then, Fuzzy c-Means unsupervised algorithm cluster information predicted results. application able increase efficiency healthcare human resources drastically care costs.

Language: Английский

---

Assessing the Reliability of Machine Learning Models Applied to the Mental Health Domain Using Explainable AI

Published: March 4, 2024

Machine Learning is increasingly and ubiquitously being used in the medical domain. Evaluation metrics like accuracy, precision, recall may indicate performance of models but not necessarily reliability their outcomes. This paper assesses effectiveness a number machine learning algorithms applied to an important dataset domain, specifically, mental health, by employing explainability methodologies. Using multiple model techniques, project provides insights into workings help determine algorithm predictions. The results are intuitive. It was found that were focusing significantly on less relevant features at times, unsound ranking make therefore argues it for research provide addition other accuracy. particularly applications critical domains such as healthcare. A future direction investigate methods quantify terms from explainability.

Language: Английский

---

Integrated feature selection and ensemble learning for heart disease detection: a 2-tier approach with ALAN and ET-ABDF machine learning model

International Journal of Information Technology, Journal Year: 2024, Volume and Issue: 16(7), P. 4489 - 4503

Published: July 5, 2024

Language: Английский

---

Explainable and Interpretable Model for the Early Detection of Brain Stroke Using Optimized Boosting Algorithms

Diagnostics, Journal Year: 2024, Volume and Issue: 14(22), P. 2514 - 2514

Published: Nov. 9, 2024

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 systematic approach predict stroke patient survival based on comprehensive set factors. These factors include demographic attributes, medical history, lifestyle elements, physiological metrics. Method: An effective random sampling method proposed handle highly biased data stroke. The pre-diction using optimized boosting learning algorithms supported with explainable AI LIME SHAP. This enables models discern intricate patterns establish correlations between selected features survival. Results: performance three studied for prediction, which Gradient Boosting (GB), AdaBoost (ADB), XGBoost (XGB) XGB achieved best outcome overall training accuracy 96.97% testing 92.13%. Conclusions: Through approach, study seeks uncover actionable insights guide healthcare practitioners in devising personalized treatment strategies patients.

Language: Английский

---

Expanding Applications of TINYML in Versatile Assistive Devices: From Navigation Assistance to Health Monitoring System Using Optimised NASNET-XGBOOST Transfer Learning

IEEE Access, Journal Year: 2024, Volume and Issue: 12, P. 168328 - 168338

Published: Jan. 1, 2024

Language: Английский

---