FPGA based real-time epileptic seizure prediction system

Coşgun, Ercan; Çelebi, Anıl

doi:10.1016/j.bbe.2021.01.006

Cited by 10 publications

(4 citation statements)

References 70 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The above figure1 specifies the Real-Time Mobile Epileptic Seizure Prediction [31] Using Deep Neural Network. The techniques and the procedures used in this methodology are explained in the following sections.…”

Section: Mstftmentioning

confidence: 99%

Design an Efficient FPGA Based Hardware Implementation for Real-Time Mobile Epileptic Seizure Prediction Using Deep Neural Network

Samanta

Hatai

Mal

2023

Preprint

View full text Add to dashboard Cite

Epilepsy is a neurological condition that distresses millions of individuals throughout the world. The lives of epileptic patients are greatly influenced by the early detection of impending seizures. In this paper, Design an Efficient FPGA Based Hardware Implementation for Real-Time Mobile Epileptic Seizure Prediction Using Deep Neural Network. This research study uses correlation deep learning replicas through an FPGA enactment of the modified short-time Fourier transform (MSTFT) block to improve epileptic seizure detection. EEG data is pre-processed for time-frequency analysis of EEG segments using an FPGA-based MSTFT. Mounting-based Matrix Factorization (MMF) extract frequency bands and feature space. Seizure detection using proposed Correlation-based deep learning neural Network (CDNN) for classification. Each layers hybrid using hyperparameter optimized using Entropy-based Grey Wolf Optimizer (EGWO) algorithm. The experimental outcomes will demonstrate that our presented technique passes the traditional techniques.

show abstract

Section: Mstftmentioning

confidence: 99%

Design an Efficient FPGA Based Hardware Implementation for Real-Time Mobile Epileptic Seizure Prediction Using Deep Neural Network

Samanta

Hatai

Mal

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Also, the proposed method achieves area efficiency of around 200 times in comparison with the existing methods. (5) Rusboosted Tree Classifier Specificity -77.30 44,801 332.3mW A. Ahmad et al (6) MLP Network Sensitivity -95.14 13,014 234.6mw Tahar et al (8) Deep Neural Network with 80 features Accuracy -75 58,800 1800mW…”

Section: Comparison With Previous Workmentioning

confidence: 99%

“…In (5) the authors have implemented a real time epileptic seizure prediction on a System on chip (SoC) FPGA. They have used EPILEPSIAE Database.…”

Section: Introductionmentioning

confidence: 99%

Power and Area Optimized Deep Learning Framework for Accurate Automatic Epileptic Seizure Detection

Ahamed,

Mastani

2023

IJST

View full text Add to dashboard Cite

Objectives: To design Hardware based system for detecting epileptic seizures automatically by processing the EEG signals, which could help the patients in protecting from adverse effects. Methods: In this paper, an efficient system for detecting the occurrence of epileptic seizures based on Novel features SCAR (Sum to Cumulative Average Ratio) and RHER (Rescaled Hurst Exponent Range). These features are then used to train a Multi-Layer Perceptron (MLP) network which employs 6 layers with 8 nodes in each layers. The MLP network is then optimized for power and area using Post Trained Quantization (PQT) technique which reduces the memory footprint of the network. Clock Gating and Multiple Operating Frequencies are used for optimizing Power. Findings: The classification accuracy in case of seizure detection is 100% for the MLP network. The system is implemented on a Artix7 FPGA for performing real time analysis. The total power consumption of the system is 35.628mW while total number of 1744 LUTS were required for the system. The overall utilization is just 12% of the available resources. The achieved results outperform all the existing works for the case of seizure detection using EEG signal processing. Improvement: A Low power, area optimized and highly accurate system is proposed in the proposed work. The power and Device utilization analysis showed the utility of the proposed system for practical applications.

show abstract

“…endüstriyel uygulamalar [14], tersine mühendislik [15], biyomedikal [16], [17] olmak üzere birçok alanda kullanılmaktadır. Bu çalışma alanlarından biri olan biyomedikal alanında da son yıllarda yoğun bir şekilde FPGA tabanlı çalışmalar yapılmaktadır.…”

Section: Introductionunclassified

VHDL ile NIBP, SpO2 ve ETCO2 Yaşamsal Sinyallerin FPGA Tabanlı Tasarımı ve Gerçek Zamanlı Uygulaması

KOYUNCU,

KARATAŞ,

ALÇIN

et al. 2023

Kırklareli Üniversitesi Mühendislik Ve Fen Bilimleri Dergisi

View full text Add to dashboard Cite

Son yıllarda, FPGA-tabanlı yaklaşımlar, biyomedikal mühendislik uygulamalarında yoğun bir şekilde kullanılmaktadır. Sunulan bu çalışmada, NIBP, ETCO2 ve SpO2 yaşamsal belirti sinyalleri Zynq-7000 serisi XC7Z020 FPGA çipi üzerinde, gerçek zamanlı biyomedikal uygulamalarında kullanılmak amacı ile gerçekleştirilmiştir. Çalışmada öncelikle, NIBP, ETCO2 ve SpO2 sinyalleri MATLAB ortamında nümerik olarak modellenmiştir. Sinyallerin sayısal modelleri, MIT-BIH aritmi veri bankası Physiobank ATM kısmında bulunan yaşamsal belirti sinyallerinin zaman ve genlik değerleri için uyumlu ve özgün olarak çıkartılmıştır. Ardından, bu sinyallerin bulunduğu FPGA-tabanlı sistem, VHDL ile Xilinx Vivado yazılımında tasarlanmıştır. Tasarımın matematiksel modelleri baz alınarak, FPGA-tabanlı sistemin ürettiği sonuçlar ve hata analizleri verilmiştir. Sonrasında, NIBP, ETCO2 ve SpO2 sinyallerini içeren tasarım Xilinx-Vivado ile Zynq-7000 XC7Z020 FPGA çipi için sentezlenmiş ve Place&Route işleminin sonucunda kaynak tüketim istatistikleri sunulmuştur. FPGA-tabanlı tasarımların maksimum çalışma frekansı 651.827 olarak elde edilmiştir. FPGA-tabanlı tasarımlanan NIBP, ETCO2 ve SpO2 yaşamsal belirti sinyalleri, geliştirme kitiyle çalışan 2 adet 14-bit AN9767 DA kartıyla 4 kanala sahip bir osiloskop üzerinden gerçek zamanlı gözlemlenmiştir. Çalışma ile FPGA-tabanlı tasarımı yapılarak doğrulanan NIBP, SpO2 ve ETCO2 yaşamsal belirti sinyallerinin biyomedikal uygulamalarda ve tıbbi cihazların kalibrasyon testleri için kullanılabileceği gösterilmiştir.

show abstract

FPGA based real-time epileptic seizure prediction system

Cited by 10 publications

References 70 publications

Design an Efficient FPGA Based Hardware Implementation for Real-Time Mobile Epileptic Seizure Prediction Using Deep Neural Network

Design an Efficient FPGA Based Hardware Implementation for Real-Time Mobile Epileptic Seizure Prediction Using Deep Neural Network

Power and Area Optimized Deep Learning Framework for Accurate Automatic Epileptic Seizure Detection

VHDL ile NIBP, SpO2 ve ETCO2 Yaşamsal Sinyallerin FPGA Tabanlı Tasarımı ve Gerçek Zamanlı Uygulaması

Contact Info

Product

Resources

About