Epileptic seizure classification of electroencephalogram signals using extreme gradient boosting classifier

Panigrahi, Millee; Behera, Dayal Kumar; Patra, Krishna Chandra

doi:10.11591/ijeecs.v25.i2.pp884-891

Cited by 3 publications

(2 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Furthermore, the XGBoost algorithm was selected for pregnancy risk monitoring with 96% accuracy [44] whereas an improvement of the proposed approach combining CNN and XGBoost methodology was proposed for renal stone diagnosis [45], breast cancer detection [46] and image classification [47] with accuracies of 99.5 %. Finally, feature selection combined with ensemble learning was proposed for epileptic seizure detection and classification from electroencephalogram signals with an effectiveness of 96% [48], [49]. Similarly, feature selection and ensemble learning were additionally proposed in the economic sector.…”

Section: Resultsmentioning

confidence: 99%

Predictive maintenance framework for assessing health state of centrifugal pumps

Mallioris,

Diamantis,

Bialas

et al. 2024

IJ-AI

View full text Add to dashboard Cite

Combined with advances in sensing technologies and big data analytics, critical information can be extracted from continuous production processes for predicting the health state of equipment and safeguarding upcoming failures. This research presents a methodology for applying predictive maintenance (PdM) solutions and showcases a PdM application for health state prediction and condition monitoring, increasing the safety and productivity of centrifugal pumps for a sustainable and resilient PdM ecosystem. Measurements depicting the healthy and maintenance-prone stages of two centrifugal pumps were collected on the university campus. The dataset consists of 5,118 records and includes both running and standstill values. Additionally, Spearman statistical analysis was conducted to measure the correlation of collected measurements with the predicted output of machine conditions and select the most appropriate features for model optimization. Several machine learning (ML) algorithms, namely random forest (RF), Naïve Bayes, support vector machines (SVM), and <a name="_Hlk137498016"></a>extreme gradient boosting (XGBoost) were analyzed and evaluated during the data mining process. The results indicated the effectiveness and efficiency of XGBoost for the health state prediction of centrifugal pumps. The contribution of this research is to propose an effective framework collectong multistage health data for PdM applications and showcase its effectiveness in a real-world use case.

show abstract

Section: Resultsmentioning

confidence: 99%

Predictive maintenance framework for assessing health state of centrifugal pumps

Mallioris,

Diamantis,

Bialas

et al. 2024

IJ-AI

View full text Add to dashboard Cite

show abstract

“…Increasing acceptability of arti cial intelligence in the eld of medical diagnostic, seizure classi cation from unprocessed EEG signals are carried out [11]. Various machine learning algorithms [12][13] like support vector machine (SVMs) [12], using auto regression feature [14], using Bayesian regularized shallow neural networks [15], bagging based ensemble framework [16], using extreme gradient based classi er [17], is used. Predominant usage of deep learning techniques [18][19][20] are witnessed.…”

Section: Introductionmentioning

confidence: 99%

Seven Epileptic Seizure Type Classification in Pre-Ictal, Ictal and Inter-Ictal Stages Using Machine Learning Techniques

Dutta

Manohar

Indira

et al. 2022

Preprint

View full text Add to dashboard Cite

Background Based on the symptoms experienced during the episode and the Electroencephalograph (EEG) recording made during the inter-ictal phase, the doctor makes the epileptic seizure type diagnosis. The fundamental issue, however, is that patients frequently struggle to explain their symptoms in the absence of an observer and identify traces in inter-ictal EEG patterns. Aims This study examines electroencephalographic (EEG) signals from epileptic seizures in order to diagnose seizures in pre-ictal, ictal, and inter-ictal stages and to categorize them into seven groups. Methods For the investigation, a licensed dataset from Temple University Hospital was used. Seven different seizure types are pre-processed from the seizure corpus and divided into pre-ictal, ictal, and inter-ictal stages. K-Nearest Neighbor (KNN), Random Forest, and other machine and deep learning techniques were used to perform the multi-class categorization. Result With 20 channels and an 80 − 20 train-test ratio, multiclass classification of seven different types of epileptic seizures was accomplished. For the pre-ictal, ictal, and inter-ictal stages, weighted KNN achieved accuracy levels of 94.7%, 94.7%, 69.0% during training and 94.46%, 94.46%, and 71.11% during testing. Conclusion Seven epileptic seizure type classification using machine learning techniques carried out with MATLAB software and weighted KNN shows better accuracy comparatively.

show abstract

Time and frequency domain pre-processing for epileptic seizure classification of epileptic EEG signals

Dutta,

Manohar,

Indira

2023

IFS

View full text Add to dashboard Cite

Although epilepsy is one of the most prevalent and ancient neurological disorder, but, still difficult to identify the specific type of seizure, due to artefacts, noise, and other disturbances, because of acquisition of Scalp EEG. It necessitating the use of skilled medical professionals as incorrect diagnosis lead to wrong Anti Seizure Drug (ASDs) and face it’s side effects. On the other hand machine learning plays a crucial role in seizure detection by analyzing and identifying patterns in brain activity data that are indicative of seizures. It can be used to develop predictive models that can detect the onset of seizures in real-time, allowing for early intervention and improved patient outcomes. Most of the research work focuses on seizure detection using various machine learning techniques pre-processed by different mathematical models. But, very less attention is paid towards seizure type detection. In this study, multiple Machine and Deep Learning algorithms were used in conjunction with time-domain and frequency-domain pre-processing to classify epileptic seizures into multiple types. The ictal period of various seizure types were extracted from Temple University Hospital EEG (TUHEEG) and the pre-processed data was tried out with multiple classifiers, including support vector classifiers (SVC), K- Nearest Neighbor (KNN), and Long short term memory (LSTM), among others. By using SVM, KNN, and LSTM, multiclass classification of seven types of epileptic seizures with 19 channels were considered for each EEG data and a 75–25 train–test ratio was accomplished with 90.41%, 94.46%, and 86.2% accuracy respectively. Epileptic seizure’s ictal phase EEG signals are categorized using a variety of machine learning(ML) and deep learning(DL) methods after being pre-processed using time domain and frequency domain approaches. The KNN yields the best results of all.

show abstract

Epileptic seizure classification of electroencephalogram signals using extreme gradient boosting classifier

Cited by 3 publications

References 17 publications

Predictive maintenance framework for assessing health state of centrifugal pumps

Predictive maintenance framework for assessing health state of centrifugal pumps

Seven Epileptic Seizure Type Classification in Pre-Ictal, Ictal and Inter-Ictal Stages Using Machine Learning Techniques

Time and frequency domain pre-processing for epileptic seizure classification of epileptic EEG signals

Contact Info

Product

Resources

About