FPGA implementation of Epileptic Seizure detection based on DWT, PCA and Support Vector Machine

Meddah, Karim; Zairi, Hadjer; Bessekri, Besma; Cherrih, Hachemi; Kedir-Talha, Malika

doi:10.1109/edis49545.2020.9296466

Cited by 10 publications

(6 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Serving as the final stage of the classifiers, the comparator compares the processed analog output with a predetermined threshold value, effectively distinguishing between seizure and nonseizure activity. In the final step, a comprehensive result analysis is conducted, demonstrating a significant reduction in dynamic power consumption, and on‐chip power consumption, and an enhancement in accuracy and sensitivity compared to previous works 4,6,17,25 …”

Section: Proposed Methodsmentioning

confidence: 98%

“…In the final step, a comprehensive result analysis is conducted, demonstrating a significant reduction in dynamic power consumption, and on-chip power consumption, and an enhancement in accuracy and sensitivity compared to previous works. 4,6,17,25…”

Section: Proposed Methodsmentioning

confidence: 99%

“…By using these two techniques, our model achieves exceptional accuracy (99.4%) and sensitivity (98.8%), while optimizing resource utilization and maintaining low dynamic power consumption (0.057 mW) at an operating frequency of 1 MHz. To validate its performance, the proposed system is compared with previously published works 4,6,17,25 based on the same dataset for a fair comparison.…”

Section: Introductionmentioning

confidence: 99%

“…Their resource‐optimized machine‐learning algorithm, implemented on a low‐power FPGA, exhibited a minimum detection latency of 10.2 μs and dynamic power consumption of 110 μW. However, the seizure detection response time was slow, with a nominal latency of 492 ms. Meddah et al 25 proposed an FPGA design model for detecting epileptic seizures, utilizing DWT and principal component analysis (PCA) techniques. Their method achieved an accuracy of 98.67% and a sensitivity of 96.15%, while the design exhibited a high power consumption of 284 mW, limiting its suitability for ultra‐low‐power devices.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Field programmable gate array‐based energy‐efficient and fast epileptic seizure detection using support vector machine and quadratic discriminant analysis classifier

Alam,

Hasan,

Farooq

et al. 2023

Engineering Reports

View full text Add to dashboard Cite

Epilepsy is a serious neurological disorder that results in seizures. It can be diagnosed by analyzing the brain's electrical activity using an electroencephalogram (EEG). However, the detection of seizures from massive EEG datasets is a challenging task. To address this challenge, researchers have developed several machine‐learning classifiers and feature extraction techniques for detecting seizures. This paper proposes an energy‐efficient and fast field programmable gate array (FPGA) architecture for detecting epileptic seizures using minimal computational resources. The seizure detection system uses the one Hjorth parameter (mobility) and another statistical parameter (nonlinear energy) as features and employs two efficient classifiers, quadratic discriminant analysis and linear support vector machine (LSVM), for classifying signals into seizure and nonseizure categories. The feature extractor block is connected individually to each of these classifiers. Subsequently, the performance of these two proposed models is evaluated in terms of accuracy, sensitivity, power consumption, resource utilization, and other metrics. The results demonstrate that the SVM classifier‐based model achieved the highest accuracy (99.4%) and sensitivity (98.8%) while consuming minimal dynamic power (0.057 mW) and utilizing the minimum FPGA resources. Thus, the proposed hardware system offers a reliable and energy‐efficient solution for detecting seizures in clinical and real‐time applications.

show abstract

Section: Proposed Methodsmentioning

confidence: 98%

Section: Proposed Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Field programmable gate array‐based energy‐efficient and fast epileptic seizure detection using support vector machine and quadratic discriminant analysis classifier

Alam,

Hasan,

Farooq

et al. 2023

Engineering Reports

View full text Add to dashboard Cite

show abstract

“…Table 2 presents several studies using FPGAs for the detection of epilepsy. Most research in Table 2, used datasets were from Bonn University [17][18][19]33] while others used datasets from Temple University Hospital [34]. For signal processing, all previous studies used a decomposition process, starting from DWT, CWT, and VMD, and the decomposition of EEG signals into the delta, theta, alpha, beta, and gamma signals.…”

Section: Comparison With Previous Researchmentioning

confidence: 99%

FPGA-Based Implementation for Real-Time Epileptic EEG Classification Using Hjorth Descriptor and KNN

2022

View full text Add to dashboard Cite

The EEG is one of the main medical instruments used by clinicians in the analysis and diagnosis of epilepsy through visual observations or computers. Visual inspection is difficult, time-consuming, and cannot be conducted in real time. Therefore, we propose a digital system for the classification of epileptic EEG in real time on a Field Programmable Gate Array (FPGA). The implemented digital system comprised a communication interface, feature extraction, and classifier model functions. The Hjorth descriptor method was used for feature extraction of activity, mobility, and complexity, with KNN was utilized as a predictor in the classification stage. The proposed system, run on a The Zynq-7000 FPGA device, can generate up to 90.74% accuracy in normal, inter-ictal, and ictal EEG classifications. FPGA devices provided classification results within 0.015 s. The total memory LUT resource used was less than 10%. This system is expected to tackle problems in visual inspection and computer processing to help detect epileptic EEG using low-cost resources while retaining high performance and real-time implementation.

show abstract

Catalogic Systematic Literature Review of Hardware-Accelerated Neurodiagnostic Systems

Mittal

Prince

2022

Biomedical Signals Based Computer-Aided Diagnosis for Neurological Disorders

View full text Add to dashboard Cite

FPGA implementation of Epileptic Seizure detection based on DWT, PCA and Support Vector Machine

Cited by 10 publications

References 11 publications

Field programmable gate array‐based energy‐efficient and fast epileptic seizure detection using support vector machine and quadratic discriminant analysis classifier

Field programmable gate array‐based energy‐efficient and fast epileptic seizure detection using support vector machine and quadratic discriminant analysis classifier

FPGA-Based Implementation for Real-Time Epileptic EEG Classification Using Hjorth Descriptor and KNN

Catalogic Systematic Literature Review of Hardware-Accelerated Neurodiagnostic Systems

Contact Info

Product

Resources

About