Focal Epileptic Area Recognition Employing Cross EEG Rhythm Spectrum Images and Convolutional Neural Network

Modak, Sudip; Roy, Sayanjit Singha; Bose, Rohit; Chatterjee, Soumya

doi:10.1109/jsen.2021.3111102

Cited by 19 publications

(17 citation statements)

References 29 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…According to the classification of brain waves, the LFP’s power was divided into four bands: δ (0–4 Hz), θ (4–7 Hz), α (8–12 Hz) and β (13–30 Hz) [ 32 ]. The steps to extracting the slope of the δ wave [ 33 ]: (1) the signal was filtered into a δ wave by low-pass filtering (4 Hz); (2) the zero-crossing point was determined; (3) the extreme values on both sides of the zero-crossing point was determined; (4) the first segment slope of the δ wave was the slope of the positive deflection through the zero-crossing point, and the second segment slope of the δ wave was the slope of the negative deflection through the zero-crossing point; (5) the sum of the durations of adjacent positive and negative deflections should be longer than 0.25 s; and (6) the slopes of the two segments were averaged and counted.…”

Section: Methodsmentioning

confidence: 99%

PtNPs/Short MWCNT-PEDOT: PSS-Modified Microelectrode Array to Detect Neuronal Firing Patterns in the Dorsal Raphe Nucleus and Hippocampus of Insomnia Rats

Wang

Dai

et al. 2022

Micromachines

View full text Add to dashboard Cite

Research on the intracerebral mechanism of insomnia induced by serotonin (5-HT) deficiency is indispensable. In order to explore the effect of 5-HT deficiency-induced insomnia on brain regions related to memory in rats, we designed and fabricated a microelectrode array that simultaneously detects the electrical activity of the dorsal raphe nucleus (DRN) and hippocampus in normal, insomnia and recovery rats in vivo. In the DRN and hippocampus of insomnia rats, our results showed that the spike amplitudes decreased by 40.16 and 57.92%, the spike repolarization slope decreased by 44.64 and 48.59%, and the spiking rate increased by 66.81 and 63.40%. On a mesoscopic scale, the increased firing rates of individual neurons led to an increased δ wave power. In the DRN and hippocampus of insomnia rats, the δ wave power increased by 57.57 and 67.75%. Furthermore, two segments’ δ wave slopes were also increased in two brain regions of the insomnia rats. Our findings suggest that 5-HT deficiency causes the hyperactivity of neurons in the hippocampus and DRN; the DRN’s firing rate and the hippocampal neuronal amplitude reflect insomnia in rats more effectively. Further studies on alleviating neurons affected by 5-HT deficiency and on achieving a highly effective treatment for insomnia by the microelectrode array are needed.

show abstract

Section: Methodsmentioning

confidence: 99%

PtNPs/Short MWCNT-PEDOT: PSS-Modified Microelectrode Array to Detect Neuronal Firing Patterns in the Dorsal Raphe Nucleus and Hippocampus of Insomnia Rats

Wang

Dai

et al. 2022

Micromachines

View full text Add to dashboard Cite

show abstract

“…It should be noted here that the size of kernel can play a key in image at location ( x , y ) in the d th depth; w p , q , d and b denote the network performance. If the size of kernel function is small, it can cause significant information loss, whereas the large kernel function can cause redundant computation and increases the computational complexity of a network [17].…”

Section: Development Of Hybrid Deep Neural Networkmentioning

confidence: 99%

“…Pooling layer: Following CL, the PL reduces the size of output feature map by down sampling while a high degree of spatial and uniform information is kept. The pooling operation can be mathematically expressed as follows [17]:

{N}_{x,y,z}=p{l}_{(p,q)\in {R}_{x,y}}\left({I}_{p,q,z}\right)

…”

Section: Development Of Hybrid Deep Neural Networkmentioning

confidence: 99%

See 1 more Smart Citation

Convolutional neural network and Bi‐directional long short memory hybrid deep network aided infrared image classification framework for non‐contact monitoring of overhead insulators

Das

Deb

Chatterjee

et al. 2022

IET Signal Processing

Self Cite

View full text Add to dashboard Cite

In this paper, a novel vision-based automated framework for estimation of pollution severity of outdoor insulators is proposed. The correct estimation of pollution severity is important to prevent the premature flashover of insulators. Existing methods to determine the degree of contamination of insulator surface requires direct contact with the insulator, which is practically problematic. Considering the aforesaid fact, in this article, a novel infrared thermal (IRT) image-based automated framework is proposed for noncontact monitoring the surface condition of outdoor insulators. A large number of IRT images corresponding to different contamination levels were captured from several porcelain disc insulators using a thermal camera. The captured IRT images were initially segmented using mask region-based convolutional neural network to remove the effect of background. Then, a hybrid deep learning network consisting of convolutional neural network and Bi-directional long short memory (CNN-BiLSTM) is designed for automated classification of IRT images. It has been observed that the proposed network has achieved an accuracy of 98.86%, specificity of 99.72%, precision of 98.86% and F-1 score of 98.86%, respectively. A comparative study with other deep learning models indicated that the proposed CNN-BiLSTM network delivered better performance. Hence, the proposed framework can be used in real-life for non-contact condition monitoring of insulators.

show abstract

“…Analyzing biosignals in the image domain has been introduced in a recent work. In the work by Modak et al [15], the EEG signal is represented in the time-frequency domain using a cross wavelet transform followed by the convolutional neural network (CNN)-based feature extraction and classification of EEG signals. EEG is a popularly used tool that provides assistance in the detection of epileptic seizures by analyzing EEG signals [16].…”

Section: Introductionmentioning

confidence: 99%

Classification of Respiratory States Using Spectrogram with Convolutional Neural Network

Park

Lee

2022

Applied Sciences

View full text Add to dashboard Cite

This paper proposes an approach to the classification of respiration states based on a neural network model by visualizing respiratory signals using a spectrogram. The analysis and processing of human biosignals are still considered some of the most crucial and fundamental research areas in both signal processing and medical applications. Recently, learning-based algorithms in signal and image processing for medical applications have shown significant improvement from both quantitative and qualitative perspectives. Human respiration is still considered an important factor for diagnosis, and it plays a key role in preventing fatal diseases in practice. This paper chiefly deals with a contactless-based approach for the acquisition of respiration data using an ultra-wideband (UWB) radar sensor because it is simple and easy for use in an experimental setup and shows high accuracy in distance estimation. This paper proposes the classification of respiratory states by using a feature visualization scheme, a spectrogram, and a neural network model. The proposed method shows competitive and promising results in the classification of respiratory states. The experimental results also show that the method provides better accuracy (precision: 0.86 and specificity: 0.90) than conventional methods that use expensive equipment for respiration measurement.

show abstract

Focal Epileptic Area Recognition Employing Cross EEG Rhythm Spectrum Images and Convolutional Neural Network

Cited by 19 publications

References 29 publications

PtNPs/Short MWCNT-PEDOT: PSS-Modified Microelectrode Array to Detect Neuronal Firing Patterns in the Dorsal Raphe Nucleus and Hippocampus of Insomnia Rats

PtNPs/Short MWCNT-PEDOT: PSS-Modified Microelectrode Array to Detect Neuronal Firing Patterns in the Dorsal Raphe Nucleus and Hippocampus of Insomnia Rats

Convolutional neural network and Bi‐directional long short memory hybrid deep network aided infrared image classification framework for non‐contact monitoring of overhead insulators

Classification of Respiratory States Using Spectrogram with Convolutional Neural Network

Contact Info

Product

Resources

About