Diagnosing Epilepsy from EEG Using Machine Learning and Welch Spectral Analysis

Traitement du signal, Journal Year: 2024, Volume and Issue: 41(2), P. 971 - 977

Published: April 30, 2024

Epilepsy is a neurological disorder that characterized by recurring seizures.Seizures are electrical disturbances in the brain develop suddenly and uncontrollably.They can cause various symptoms, depending on what part of affected.The epilepsy often unknown, but it be caused injury, infections, genetics, or other medical conditions.EEG analysis very important aspect diagnosis treatment epilepsy.It includes interpretation activity patterns recorded from electrodes.In this study, machine learning methods deep have been examined for diagnosis.Random Forest (RF), Naive Bayes (NB) algorithm, Support Vector Machine (SVM), Levenberg-Marguardt (LM), Long Short Term Memory (LSTM) were used classification, while Welch method has feature extraction.The Bonn EEG dataset application.As result, RF showed best accuracy as 99.87%.RF achieved 99.84% precision, 99.9% sensitivity, 99.87% F1-Score, 99.87 AUC.LSTM second degree 99.39%.LSTM 99.52% 99.29% 99.39% 99.40 AUC.LM, SVM, NB 98.82%, 97.90%, 97.66% classification accuracies respectively.LM 97.85% 99.97% 98.87% 98.92 AUC.SVM 96.10% 100% 97.99% 98.10 AUC.NB 98.80% 96.42% 97.27% 97.61 AUC.

Language: Английский

---

Blockchain Empowered Interoperable Framework for Smart Healthcare

Mathematical Modelling and Engineering Problems, Journal Year: 2024, Volume and Issue: 11(5), P. 1330 - 1340

Published: May 30, 2024

In the past, healthcare industry used paper-based systems to manage and store medical records.However, these are vulnerable data breaches, loss, errors.To overcome issues, a research study has been conducted create safe efficient Electronic Data Interchange (EDI) system for using blockchain technology.The utilized various tools methods including Python as programming language implement environment, pyQT5 library graphical user interface (GUI), MySQL database management repository Health Records (EHR) with DBeaver, cross-platform tool management.The work involves development of blockchain-based smart contract storage, exchange, retrieval EHR.Additionally, application based on is created provide users friendly GUI.The proposed provides secure platform storing managing EHR well enabling EDI among stakeholders like practices, doctors, labs, pharmacies.Furthermore, scalable user-friendly, includes features patient visits, history, appointment scheduling.Blockchain technology ensures integrity, EDI, confidentiality, while user-friendly enhances experience compared existing standards health level 7 (HL7).

Language: Английский

---

Predicting Global Energy Consumption Through Data Mining Techniques

International Journal of Design & Nature and Ecodynamics, Journal Year: 2024, Volume and Issue: 19(2), P. 397 - 406

Published: April 25, 2024

With the explosion of global population and technological progress, electricity demand has skyrocketed.To ensure a consistent flow power, it's essential to accurately predict energy usage ahead time.Failure do so could lead potential outages disrupt our daily lives.This research reviews previous in field using data mining techniques analyze consumption data, optimize performance buildings, various industries.The study also aims uncover patterns, correlations, rules worldwide techniques.The analysis is performed techniques, such as simple K-Means Expectation Maximization (EM).This selection based on their prominent applications for similar problems literature.The EM algorithms showed successful outcomes dataset, which evident clustering plots.Further, Hierarchical Clustering algorithm was not up desired standard.This probably due nature available dataset.These will provide valuable resource decision-makers stakeholders sector, it deeper understanding patterns trends.This sustainable future.

Language: Английский

---

High-Dimension EEG Biometric Authentication Leveraging Sub-Band Cube-Code Representation

Traitement du signal, Journal Year: 2023, Volume and Issue: 40(5), P. 1983 - 1995

Published: Oct. 30, 2023

Advancements in EEG biometric technologies have been hindered by two persistent challenges: the management of large data sizes and unreliability resulting from various measurement environments.Addressing these challenges, this study introduces a novel methodology termed 'Cube-Code' for cognitive authentication.As preliminary step, Automatic Artifact Removal (AAR) leveraging wavelet Independent Component Analysis (wICA) is applied to signals.This step transforms signals into independent sub-components, effectively eliminating effects muscle movements eye blinking.Subsequently, unique 3-Dimensional (3-D) Cube-Codes are generated, each representing an individual subject database.Each Cube-Code constructed stacking alpha, beta, theta sub-band partitions, obtained channel during task, back-to-back.This forms third-order tensor.The three subbands within not only prevents dimension increase through concatenation but also permits direct utilization non-stationary data, bypassing need fiducial component detection.Higher-Order Singular Value Decomposition (HOSVD) then perform subspace analysis on Cube-Code, approach supported previous literature concerning its effectiveness 3-D tensors.Upon completion decomposition process, flattening operation executed extract lower-dimensional, taskindependent feature matrices subject.These employed five distinct deep learning architectures.The was tested signals, composed different tasks, PhysioNet Motor Movement/Imagery (EEGMMI) dataset.The results demonstrate authentication accuracy rate approximately 98%.In conclusion, provides highly accurate recognition, delivering new level reliability EEG-based authentication.

Language: Английский

---