Adopting Artificial Intelligence Powered ConvNet To Detect Epileptic Seizures

Mahajan, Arpana; Somaraj, Kavitha; Sameer, Mustafa

doi:10.1109/iecbes48179.2021.9398832

Cited by 18 publications

(5 citation statements)

References 21 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These automatically extracted features have shown promising results in speech recognition (Noda et al, 2015), image retrieval (Mahajan and Chaudhary, 2019), hand gesture recognition (Shanmuganathan et al, 2020), object classification (Robinson et al, 2020), genome analysis (Ramamurthy et al, 2020), COVID-19 detection (Poongodi et al, 2021;Nayak et al, 2021;Kumar et al, 2021), diabetic retinopathy (Thomas et al, 2021(Thomas et al, , 2020 and other biomedical applications (Ravi et al, 2017). In recent years, some groups have presented epileptic seizure detection system using deep learning techniques (Gupta et al, 2021;Mahajan et al, 2021). Convolutional neural network (CNN) was the first one having 13 layers (Acharya et al, 2018).…”

Section: Related Workmentioning

confidence: 99%

Automatic epileptic seizure detection using LSTM networks

Shekokar¹,

Dour

2021

WJE

View full text Add to dashboard Cite

Purpose The purpose of this work is to make a computer aided detection system for epileptic seizures. Epilepsy is a neurological disorder characterized as the recurrence of two or more unprovoked seizures. The common and significant tool for aiding in the identification of epilepsy is Electroencephalography (EEG). The EEG signals contain information about the electrical activity of the brain. Conventionally, clinicians study the EEG waveforms manually to detect epileptic abnormalities, which is very time-consuming and error-prone. Design/methodology/approach The authors have presented a three-layer long short-term memory network for the detection of epileptic seizures. Findings The network classifies between seizure and non-seizure with 99.5% accuracy only in 30 epochs. This makes the proposed methodology useful for real-time seizure detection. Originality/value This research work is original and not plagiarized.

show abstract

Section: Related Workmentioning

confidence: 99%

Automatic epileptic seizure detection using LSTM networks

Shekokar¹,

Dour

2021

WJE

View full text Add to dashboard Cite

show abstract

“…This learning ability definitely reduces the requirement for engineering special features, but the approach based on full end-to-end training of DL commonly require a critical number of samples. Training is important part of any DL framework where the network wants more than thousand numbers of images to be feed into to learn pixel esteems and edges [17]. However, datasets which are available publicly have not sufficient number of retinal images to train such a large network from beginning, so transfer learning approach comes into picture to utilize the pretrained networks.…”

Section: Methodsmentioning

confidence: 99%

A Transfer Learning Approach for Diabetic Retinopathy and Diabetic Macular Edema Severity Grading

Nasir¹,

Afreen²,

Patel³

et al. 2021

RIA

Self Cite

View full text Add to dashboard Cite

Diabetic Retinopathy (DR) and Diabetic Macular Edema (DME) are complication that occurs in diabetic patient especially among working age group that leads to vision impairment problem and sometimes even permanent blindness. Early detection is very much needed for diagnosis and to reduce blindness or deterioration. The diagnosis phase of DR consumes more time, effort and cost when manually performed by ophthalmologists and more chances of misdiagnosis still there. Research community is working on to design computer aided diagnosis system for prior detection and for DR grading based on its severity. Ongoing researches in Artificial Intelligence (AI) have set out the advancement of deep learning technique which comes as a best technique to perform analysis and classification of medical images. In this paper, research is applied on Resnet50 model for classification of DR and DME based on its severity grading on public benchmark dataset. Transfer learning approach accomplishes the best outcome on Indian Diabetic Retinopathy Image Dataset (IDRiD).

show abstract

“…To evaluate this study's epileptic seizure dataset through four scales resulting from the applied classifiers. Equations ( 7)- (10) show how accuracy, precision, recall and F1 score, respectively, are calculated [35]:…”

Section: Evaluation Metricsmentioning

confidence: 99%

“…Hence, discovering these features is a difficult task, and following each EEG signal is troublesome and time consuming [9]. Therefore, an automated approach for detecting seizures to diagnose epilepsy in a timely manner needs to be developed [10]. EEG is an effective tool for detecting areas of differences in neuronal activity correlated with epilepsy.…”

Section: Introductionmentioning

confidence: 99%

Effective Early Detection of Epileptic Seizures through EEG Signals Using Classification Algorithms Based on t-Distributed Stochastic Neighbor Embedding and K-Means

et al. 2023

View full text Add to dashboard Cite

Epilepsy is a neurological disorder in the activity of brain cells that leads to seizures. An electroencephalogram (EEG) can detect seizures as it contains physiological information of the neural activity of the brain. However, visual examination of EEG by experts is time consuming, and their diagnoses may even contradict each other. Thus, an automated computer-aided diagnosis for EEG diagnostics is necessary. Therefore, this paper proposes an effective approach for the early detection of epilepsy. The proposed approach involves the extraction of important features and classification. First, signal components are decomposed to extract the features via the discrete wavelet transform (DWT) method. Principal component analysis (PCA) and the t-distributed stochastic neighbor embedding (t-SNE) algorithm were applied to reduce the dimensions and focus on the most important features. Subsequently, K-means clustering + PCA and K-means clustering + t-SNE were used to divide the dataset into subgroups to reduce the dimensions and focus on the most important representative features of epilepsy. The features extracted from these steps were fed to extreme gradient boosting, K-nearest neighbors (K-NN), decision tree (DT), random forest (RF) and multilayer perceptron (MLP) classifiers. The experimental results demonstrated that the proposed approach provides superior results to those of existing studies. During the testing phase, the RF classifier with DWT and PCA achieved an accuracy of 97.96%, precision of 99.1%, recall of 94.41% and F1 score of 97.41%. Moreover, the RF classifier with DWT and t-SNE attained an accuracy of 98.09%, precision of 99.1%, recall of 93.9% and F1 score of 96.21%. In comparison, the MLP classifier with PCA + K-means reached an accuracy of 98.98%, precision of 99.16%, recall of 95.69% and F1 score of 97.4%.

show abstract

Adopting Artificial Intelligence Powered ConvNet To Detect Epileptic Seizures

Cited by 18 publications

References 21 publications

Automatic epileptic seizure detection using LSTM networks

Automatic epileptic seizure detection using LSTM networks

A Transfer Learning Approach for Diabetic Retinopathy and Diabetic Macular Edema Severity Grading

Effective Early Detection of Epileptic Seizures through EEG Signals Using Classification Algorithms Based on t-Distributed Stochastic Neighbor Embedding and K-Means

Contact Info

Product

Resources

About