Lecture notes in networks and systems, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 10
Published: Jan. 1, 2024
Language: Английский
Lecture notes in networks and systems, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 10
Published: Jan. 1, 2024
Language: Английский
Applied Sciences, Journal Year: 2024, Volume and Issue: 14(19), P. 8884 - 8884
Published: Oct. 2, 2024
This systematic literature review employs the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to investigate recent applications of explainable AI (XAI) over past three years. From an initial pool 664 articles identified through Web Science database, 512 peer-reviewed journal met inclusion criteria—namely, being recent, high-quality XAI application published in English—and were analyzed detail. Both qualitative quantitative statistical techniques used analyze articles: qualitatively by summarizing characteristics included studies based on predefined codes, quantitatively analysis data. These categorized according their domains, techniques, evaluation methods. Health-related particularly prevalent, with a strong focus cancer diagnosis, COVID-19 management, medical imaging. Other significant areas environmental agricultural industrial optimization, cybersecurity, finance, transportation, entertainment. Additionally, emerging law, education, social care highlight XAI’s expanding impact. The reveals predominant use local explanation methods, SHAP LIME, favored its stability mathematical guarantees. However, critical gap results is identified, as most rely anecdotal evidence or expert opinion rather than robust metrics. underscores urgent need standardized frameworks ensure reliability effectiveness applications. Future research should developing comprehensive standards improving interpretability explanations. advancements are essential addressing diverse demands various domains while ensuring trust transparency systems.
Language: Английский
Citations
4Bioengineering, Journal Year: 2025, Volume and Issue: 12(2), P. 109 - 109
Published: Jan. 24, 2025
Seizure prediction is a critical challenge in epilepsy management, offering the potential to improve patient outcomes through timely interventions. This study proposes novel framework combining convolutional neural network (CNN) based on EfficientNet-B0 and an ensemble of six Support Vector Machines (SVMs) with voting mechanism for robust seizure prediction. The leverages normalized Short-Time Fourier Transform (STFT) channel correlation features extracted from EEG signals capture both spectral spatial information. methodology was validated CHB-MIT dataset across preictal windows 10, 20, 30 min, achieving accuracies 96.12%, 94.89%, 94.21%, sensitivities 95.21%, 93.98%, 93.55%, respectively. Comparing results state-of-the-art methods, we highlight framework’s robustness adaptability. backbone ensures high accuracy computational efficiency, while SVM enhances reliability by mitigating noise variability data.
Language: Английский
Citations
0Revue Neurologique, Journal Year: 2025, Volume and Issue: unknown
Published: March 1, 2025
Language: Английский
Citations
0Communications in computer and information science, Journal Year: 2025, Volume and Issue: unknown, P. 183 - 194
Published: Jan. 1, 2025
Language: Английский
Citations
0Elsevier eBooks, Journal Year: 2025, Volume and Issue: unknown, P. 175 - 211
Published: Jan. 1, 2025
Language: Английский
Citations
0Epiliepsy currents/Epilepsy currents, Journal Year: 2024, Volume and Issue: unknown
Published: March 31, 2024
Artificial intelligence, machine learning, and deep learning are increasingly being used in all medical fields including for epilepsy research clinical care. Already there have been resultant cutting-edge applications both the arenas of epileptology. Because is a need to disseminate knowledge about these approaches, how use them, their advantages, potential limitations, goal 2023 Merritt-Putnam Symposium this synopsis review that symposium has present background state art then draw conclusions on current future approaches through following: (1) Initially provide an explanation fundamental principles artificial learning. These presented first section by Dr Wesley Kerr. (2) Provide insights into screening medications neural organoids, general, particular. Sandra Acosta. (3) intelligence can predict response medication treatments. Patrick Kwan. (4) Finally, expanding detection analysis EEG signals intensive care, monitoring unit, intracranial situations, as below Gregory Worrell. The expectation that, coming decade beyond, increasing above will transform care supplement, but not replace, diligent work clinicians researchers.
Language: Английский
Citations
0Lecture notes in networks and systems, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 10
Published: Jan. 1, 2024
Language: Английский
Citations
0