RECOGNITION OF SLEEP STAGES BASED ON A COMBINED NEURAL NETWORK AND FUZZY SYSTEM USING WAVELET TRANSFORM FEATURES

2014 ◽  
Vol 26 (02) ◽  
pp. 1450029 ◽  
Author(s):  
Chuang-Chien Chiu ◽  
Bui Huy Hai ◽  
Shoou-Jeng Yeh
Keyword(s):  
Neural Network ◽  
Fuzzy System ◽  
Single Channel ◽  
Sleep Stages ◽  
Elman Neural Network ◽  
Sleep Studies ◽  
Average Accuracy ◽  
Wavelet Decompositions

Recognition of sleep stages is an important task in the assessment of the quality of sleep. Several biomedical signals, such as EEG, ECG, EMG and EOG are used extensively to classify the stages of sleep, which is very important for the diagnosis of sleep disorders. Many sleep studies have been conducted that focused on the automatic classification of sleep stages. In this research, a new classification method is presented that uses an Elman neural network combined with fuzzy rules to extract sleep features based on wavelet decompositions. The nine subjects who participated in this study were recruited from Cheng-Ching General Hospital in Taichung, Taiwan. The sampling frequency was 250 Hz, and a single-channel (C3-A1) EEG signal was acquired for each subject. The system consisted of a combined neural network and fuzzy system that was used to recognize sleep stages based on epochs (10-second segments of data). The classification results relied on the strong points of combined neural network and fuzzy system, which achieved an average specificity of approximately 96% and an average accuracy of approximately 94%.

scholarly journals KLASIFIKASI KUALITAS KAYU KELAPA MENGGUNAKAN ARSITEKTUR CNN

2021 ◽  
Vol 8 (1) ◽  
pp. 49
Author(s):  
Nurul Fathanah Mustamin ◽  
Yuslena Sari ◽  
Husnul Khatimi
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Classification Performance ◽  
Computer Visualization ◽  
Average Accuracy ◽  
Export Volume ◽  
The Right ◽  
Visualization Techniques

<p><em>The increase in the export volume of coconut logs, which are materials that can efficiently substitute for conventional wood, demands that the quality of coconut wood classified quickly. However, due to the limitations of a grader as a human being, it is necessary to have assistance from machines or technology that can classify coconut wood quickly. Techniques that used for rapid classification can use computer visualization. Convolutional Neural Network (CNN) with the right architecture makes this method able to recognize and detect objects well, which influenced by computerized factors, large datasets, and techniques to train deeper networks. This study uses </em><em>five</em><em> types of CNN architecture, AlexNet, GoogLeNet, ResNet101, ResNet18, and ResNet50. The research results obtained for the classification of the quality of coconut wood using </em><em>images </em><em>show that the GoogLeNet architecture has the best classification performance among other architectures</em><em>. </em><em>GoogLeNet</em><em> gets result</em><em> with an average accuracy of 84.89% in each layer, followed by RestNet101 architecture with an average accuracy of 78.41%, RestNet50 with an average accuracy of 77.18%, RestNet18 with an average accuracy of 72.94% and the lowest accuracy performance among other architectures obtained by AlexNet with an average accuracy of 65.84%.</em></p><p><em><strong>Keywords</strong></em><em>: Classification, Coconut Wood, Computer Visualization Techniques, CNN</em> </p><p><em>Meningkatnya volume ekspor kayu kelapa yang merupakan bahan pengganti kayu konvensional secara efisien menuntut klasifikasi kualitas kayu kelapa dengan cepat. Namun karena keterbatasan seorang grader sebagai manusia maka diperlukan bantuan mesin atau teknologi yang dapat mengklasifikasikan kayu kelapa dengan cepat. Teknik yang dapat digunakan untuk klasifikasi cepat dapat menggunakan teknik visualisasi komputer. Convolutional Neural Network (CNN) dengan arsitektur yang tepat menjadikan metode ini mampu mengenali dan mendeteksi objek dengan baik, yang sebagian besar dipengaruhi oleh faktor komputerisasi, dataset yang besar, dan teknik untuk melatih jaringan yang lebih dalam. Penelitian ini menggunakan lima jenis arsitektur CNN yaitu, AlexNet, GoogLeNet, ResNet101, ResNet18, dan ResNet50. Hasil penelitian yang diperoleh untuk klasifikasi kualitas kayu kelapa menggunakan citra menunjukkan bahwa arsitektur GoogLeNet memiliki performansi klasifikasi terbaik diantara arsitektur lainnya. GoogLeNet mendapatkan hasil dengan rata-rata akurasi 84,89% pada setiap lapisan, disusul arsitektur RestNet101 dengan akurasi rata-rata 78,41%, RestNet50 dengan akurasi rata-rata 77,18%, RestNet18 dengan akurasi rata-rata 72,94% dan kinerja akurasi terendah di antara arsitektur lainnya diperoleh AlexNet dengan akurasi rata-rata 65,84%.</em></p><p><em><strong>Kata kunci</strong></em><em>: Klasifikasi, Kayu Kelapa, Teknik Visualisasi Komputer, CNN</em></p>

scholarly journals Single‐channel EEG classification of sleep stages based on REM microstructure

2021 ◽  
Author(s):  
Irene Rechichi ◽  
Maurizio Zibetti ◽  
Luigi Borzì ◽  
Gabriella Olmo ◽  
Leonardo Lopiano
Keyword(s):  
Single Channel ◽  
Sleep Stages ◽  
Eeg Classification

scholarly journals A Convolutional Network for the Classification of Sleep Stages

Proceedings ◽  
2018 ◽  
Vol 2 (18) ◽  
pp. 1174 ◽  
Author(s):  
Isaac Fernández-Varela ◽  
Elena Hernández-Pereira ◽  
Vicente Moret-Bonillo
Keyword(s):  
Sleep Medicine ◽  
Sleep Stages ◽  
Kappa Index ◽  
Night Sleep ◽  
Convolutional Network ◽  
Sleep Study ◽  
Convolutional Networks ◽  
Sleep Studies ◽  
Automatic Methods

The classification of sleep stages is a crucial task in the context of sleep medicine. It involves the analysis of multiple signals thus being tedious and complex. Even for a trained physician scoring a whole night sleep study can take several hours. Most of the automatic methods trying to solve this problem use human engineered features biased for a specific dataset. In this work we use deep learning to avoid human bias. We propose an ensemble of 5 convolutional networks achieving a kappa index of 0.83 when classifying 500 sleep studies.

PROBABILISTIC NEURAL NETWORK AND ITS ADAPTIVE VERSION — A STOCHASTIC APPROACH TO PD PATTERN CLASSIFICATION TASK

2005 ◽  
Vol 02 (04) ◽  
pp. 333-344 ◽  
Author(s):  
B. KARTHIKEYAN ◽  
S. GOPAL ◽  
S. VENKATESH
Keyword(s):  
Neural Network ◽  
Pattern Classification ◽  
Probabilistic Neural Network ◽  
Stochastic Approach ◽  
Diagnostic Techniques ◽  
Single Type ◽  
Destructive Testing ◽  
Theoretical Concepts

The quality of electrical insulation of any power apparatus is an indispensable requirement for its successful and reliable operation. Partial Discharge (PD) phenomenon serves as an effective Non Destructive Testing (NDT) technique and provides an index on the quality of the insulation. The innovative trend of using Artificial Neural Network (ANN) towards the classification of PD patterns is cogent and discernible. In this paper a novel method for the classification of the PD patterns using the original Probabilistic Neural Network (PNN) as well as its variation is elucidated. A preprocessing scheme that extracts pertinent features of PD from the raw data towards achieving a compact ANN has been employed. The classification of single-type insulation defects such as voids, surface discharges and corona has been taken up. The first part of the paper gives a brief on PD, various diagnostic techniques and interpretation. The second part deals with the theoretical concepts of PNN and its adaptive version. The last part provides details on various results and comparisons of the PNN and its adaptive version in PD pattern classification.

Automatic sleep stage classification of single-channel EEG by using complex-valued convolutional neural network

2018 ◽  
Vol 63 (2) ◽  
pp. 177-190 ◽  
Author(s):  
Junming Zhang ◽  
Yan Wu
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Single Channel ◽  
Sleep Stage ◽  
Experimental Results ◽  
Sleep Stages ◽  
Stage Classification ◽  
Sleep Stage Classification ◽  
Complex Valued ◽  
Learned Features

AbstractMany systems are developed for automatic sleep stage classification. However, nearly all models are based on handcrafted features. Because of the large feature space, there are so many features that feature selection should be used. Meanwhile, designing handcrafted features is a difficult and time-consuming task because the feature designing needs domain knowledge of experienced experts. Results vary when different sets of features are chosen to identify sleep stages. Additionally, many features that we may be unaware of exist. However, these features may be important for sleep stage classification. Therefore, a new sleep stage classification system, which is based on the complex-valued convolutional neural network (CCNN), is proposed in this study. Unlike the existing sleep stage methods, our method can automatically extract features from raw electroencephalography data and then classify sleep stage based on the learned features. Additionally, we also prove that the decision boundaries for the real and imaginary parts of a complex-valued convolutional neuron intersect orthogonally. The classification performances of handcrafted features are compared with those of learned features via CCNN. Experimental results show that the proposed method is comparable to the existing methods. CCNN obtains a better classification performance and considerably faster convergence speed than convolutional neural network. Experimental results also show that the proposed method is a useful decision-support tool for automatic sleep stage classification.

WAVELET FEATURES BASED SLEEP STAGES DETECTION USING SINGLE CHANNEL EEG

2017 ◽  
Vol 5 (4) ◽  
pp. 99-102
Author(s):  
Vandana Roy ◽  
Anand Prakash ◽  
Shailja Shukla
Keyword(s):  
Feature Extraction ◽  
Wavelet Decomposition ◽  
Single Channel ◽  
Kappa Coefficient ◽  
Sleep Stages ◽  
Chi Square ◽  
Wavelet Features ◽  
Stage Classification ◽  
Selection Of

The sleep stages determination is important for the identification and diagnosis of different diseases. An efficient algorithm of wavelet decomposition is used for feature extraction of single channel EEG. The Chi-Square method is applied for the selection of the best attributes from the extracted features. The classification of different staged techniques is applied with the help AdaBoost.M1 algorithm. The accuracy of 89.82% achieved in the six stage classification. The weighted sensitivity of all stages is 89.8% and kappa coefficient of 77.93% is obtained in the six stage classification.

Sign in / Sign up

Export Citation Format

Share Document