Analysis and classification of EEG signals using spectral analysis and recurrent neural networks

Naderi, Mohammad Ali; Mahdavi-Nasab, Homayoun

doi:10.1109/icbme.2010.5704931

Cited by 53 publications

(30 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Previous studies used RNN for emotional identification [21], classification of motors imagery [23], and neuropsychological identification [24]. While the RNN model achieved an accuracy of 100%, and the MLPNN model reached 98.93% for the identification of epilepsy [25].…”

Section: Recurrent Neural Networkmentioning

confidence: 99%

Emotion and Attention of Neuromarketing Using Wavelet and Recurrent Neural Networks

Rasyid¹,

Djamal²

2019

EECSI

View full text Add to dashboard Cite

One method concerning evaluating video ads is neuromarketing. This information comes from the viewer's mind, thus minimizing subjectivity. Besides, neuromarketing can overcome the difficulties of respondents who sometimes do not know the response to the video ads they watch. Neuromarketing involves information from what customers think is captured by an Electroencephalogram (EEG) device. Meanwhile, if the electrical signal information in the brain is corresponding to an understanding of one's psychology, it is called neuropsychology. This field consists of emotions, attention, and concentration variables. This research offered neuromarketing base on emotion and attention of EEG signal using Wavelet extraction and Recurrent Neural Networks. Measurement of EEG variable every two seconds while watching video ads. The results showed that Wavelet and Recurrent Neural Networks could provide training data accuracy of 100% and 89.73% for new data. The experiment also gave that the RMSprop optimization model for the weight correction contributed to higher correctness of 1.34% than the Adam model. Meanwhile, using Wavelet for extraction can increase accuracy by 5%.

show abstract

Section: Recurrent Neural Networkmentioning

confidence: 99%

Emotion and Attention of Neuromarketing Using Wavelet and Recurrent Neural Networks

Rasyid¹,

Djamal²

2019

EECSI

View full text Add to dashboard Cite

show abstract

“…Penelitian ini melakukan tiga tahapan proses yaitu fitur ekstraksi menggunakan metode Welch, mereduksinya menggunakan nilai statistik dan klasifikasi menggunakan Recurrent Neural Networks. Untuk menguji kinerja dari RNN dalam masalah klasifikasi yang sama maka digunakan multilayerperceptron neural network dengan menggunakan learning backpropagation yang tingkat akurasinya mencapai 100% sekalipun tidak dijelaskan waktu komputasinya [6] [1]. Metode ini dikembangkan dari improved particle swarm optimization yang mengusulkan penambahan bobot inersia untuk menyeimbangkan pencarian global dan local [7;8].…”

Section: Pendahuluanunclassified

Klasifikasi Aktivitas Mental Berdasarkan Data Eeg Menggunakan Metode Hibridneural Network Dan Fuzzy Particle Swarm Optimization Dengan Crossmutated Operation

Sakur¹,

Tjandrasa²

2016

JUTI

View full text Add to dashboard Cite

ABSTRAK Brain-computer Interface (BCI) I. PENDAHULUANrain-Computer Interface(BCI) menggunakan Electroencephalography (EEG) untuk mengukur sinyalaktivitas listrik pada otak yang merefleksikan keinginan ataupun tujuan dari pengguna sehingga dapat menyediakan keluaran nonmuscular baru untuk komunikasi dan kontrol sebagai sebuah teknologi antarmuka manusia dan komputer [1]. Invasive merupakan salah cara untuk mendapatkan aktivitas gelombang listrik dari otak dengan menanamkan elektroda secara langsung ke bagian celebral cortex sehingga gelombang listrik yang diperoleh tidak mengalami distorsi. Namun cara ini beresiko besar sehingga diperlukan alternatif lain yaitu pendekatan Non-Invasive, dimana aktivitas gelombang listrik di dapatkan melalui elektroda yang diletakkan pada permukaan kulit kepala sehingga aman. Akan tetapi gelombang yang diperoleh tidak sekuat tipe Invasive, karena aktivitas listrik yang di hasilkan oleh neuron -neuron dari otak celebral cortex dengan tegangan yang kecil (mV) akan dikirim melalui jaringan saraf menuju ke permukaan kulit kepala yang konsekuensinya akan mengalami distorsi yang cukup besar. Brain-Computer Interface bermanfaat bagi pengguna yang mengalami kerusakan total untuk saraf yang mengendalikan otot -otot gerak ataupun penyakit B

show abstract

“…The relationship between the input and the output determine network behavior [17]. Selection of the neural network inputs is the most important component in designing the neural network for pattern classification [18] EEG brainwave signal pattern of the stroke level in cognitive or thinking abilities had been studied by researchers [19]. RPR techniques were used to investigate the brainwave sub band characteristics for three different group of stroke level [19].…”

Section: Introductionmentioning

confidence: 99%

ANN classification of ischemic stroke severity using EEG sub band relative power ration

Omar¹,

Mohamad²,

Taib

et al. 2014

2014 IEEE Conference on Systems, Process and Control (ICSPC 2014)

View full text Add to dashboard Cite

This paper presents an intelligent system for the classification of ischemic stroke severity. The application of Artificial Neural Network (ANN) is proposed in this study to classify ischemic stroke severity using EEG sub bands Relative Power Ratio (RPR).There were 100 subjects from National Stroke Association of Malaysia NASAM, Petaling Jaya, Selangor, Malaysia divided into Early Group (EG), Intermediate Group (IG) and Advance Group (AG) with 33, 36 and 31 subjects for each group. The characteristic of the ischemic stroke brainwaves were determined due to the group rehabilitation progression. The result obtained showed the capability of ANN in analyzing the ischemic stroke severity hence beneficial for the further application such as grouping the ischemic stroke severity cases correctly classify were 85%. This system will be capable of applying the most appropriate classification method to each ischemic stroke level, which widely extends the research in the field of automatic classification. Index Terms-stroke; Electroencephalogram (EEG); relative power ratio, ANN I.978-1-4799-6106-

show abstract

Analysis and classification of EEG signals using spectral analysis and recurrent neural networks

Cited by 53 publications

References 6 publications

Emotion and Attention of Neuromarketing Using Wavelet and Recurrent Neural Networks

Emotion and Attention of Neuromarketing Using Wavelet and Recurrent Neural Networks

Klasifikasi Aktivitas Mental Berdasarkan Data Eeg Menggunakan Metode Hibridneural Network Dan Fuzzy Particle Swarm Optimization Dengan Crossmutated Operation

ANN classification of ischemic stroke severity using EEG sub band relative power ration

Contact Info

Product

Resources

About