scholarly journals Enhanced firefly optimizer with deep neural network for the detection of epileptic seizures using EEG signals

2020 ◽  
Vol 9 (5) ◽  
pp. 137-148
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Time Series Data ◽  
Optimization Technique ◽  
Epileptic Seizures ◽  
Experimental Simulation ◽  
Series Data ◽  
Eeg Signals ◽  
Mode Decomposition ◽  
Eeg Recordings

Currently, Electroencephalogram (EEG) is extensively used for diagnosing the epilepsy. The objective of this research is to investigate the changes in epilepsy frequency by proposing a new optimization based deep learning model. At first, the EEG recordings were acquired from two online databases; Bern Barcelona (BB), and Bonn University (BU). Then, Chebyshev type two filter was implemented to remove the unwanted artifacts from the acquired EEG signals. Further, Multivariate Variational Mode Decomposition (MVMD) methodology was applied to decompose the denoised EEG signals. The signal decomposition helps in finding the necessary information, which required to model the complex time series data. Then, the features were extracted from decomposed signals by using fifteen entropy, linear and statistical features. In addition, enhanced firefly optimization technique was proposed for optimizing the extracted features. In the enhanced firefly optimizer, a crossover operator of genetic algorithm was added for enhancing the local convergence rate that gives better classification. At last, the optimized feature vectors were classified by Deep Neural Network (DNN) that includes two circumstances (seizure and healthy), and (Interictal, ictal, and normal). From the experimental simulation, the proposed model improvement maximum of 1.4%, and 8.82% of accuracy in BU and BB EEG datasets, respectively related to the existing models.

scholarly journals Epileptic Detection from the Eeg Signal using the Anti colony Optimization Technique with Deep Neural Network

2020 ◽  
Vol 9 (1) ◽  
pp. 2726-2733
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Time Series Data ◽  
Optimization Technique ◽  
Signal Decomposition ◽  
Ant Colony ◽  
Series Data ◽  
Eeg Signal ◽  
Eeg Signals ◽  
Mode Decomposition

Extensively used technique to diagnose the epilepsy is EEG. The research objective is to check the variations of frequency found in the epileptic EEG signals.. The EEG dataset were acquired from online database of the Bonn University (BU). Then, butterworth type two filter was implemented to remove the unwanted artifacts from the acquired EEG signals. Further, Multivariate Variational Mode Decomposition (MVMD) methodology was applied to decompose the denoised EEG signals. The signal decomposition helps in finding the necessary information, which required to model the complex time series data. Then, the features were extracted from decomposed signals by using fifteen entropy, linear and statistical features. In addition, ant colony optimization technique was proposed for optimizing the extracted features. The optimized feature vectors were classified by Deep Neural Network (DNN) that includes two circumstances (seizure and healthy), and (Interictal, ictal, and normal). The accuracy attained using the ant colony with deep neural network is 98.12% using the BU EEG dataset, respectively related to the existing models.

scholarly journals An Ultrashort-Term Net Load Forecasting Model Based on Phase Space Reconstruction and Deep Neural Network

2019 ◽  
Vol 9 (7) ◽  
pp. 1487 ◽  
Author(s):  
Fei Mei ◽  
Qingliang Wu ◽  
Tian Shi ◽  
Jixiang Lu ◽  
Yi Pan ◽  
...  
Keyword(s):  
Neural Network ◽  
Phase Space ◽  
Deep Neural Network ◽  
Time Series Data ◽  
Load Forecasting ◽  
Phase Space Reconstruction ◽  
Series Data ◽  
Forecasting Model ◽  
Model Based ◽  
Net Load

Recently, a large number of distributed photovoltaic (PV) power generations have been connected to the power grid, which resulted in an increased fluctuation of the net load. Therefore, load forecasting has become more difficult. Considering the characteristics of the net load, an ultrashort-term forecasting model based on phase space reconstruction and deep neural network (DNN) is proposed, which can be divided into two steps. First, the phase space reconstruction of the net load time series data is performed using the C-C method. Second, the reconstructed data is fitted by the DNN to obtain the predicted value of the net load. The performance of this model is verified using real data. The accuracy is high in forecasting the net load under high PV penetration rate and different weather conditions.

scholarly journals Deep Neural Network Algorithm Feedback Model with Behavioral Intelligence and Forecast Accuracy

Symmetry ◽  
2020 ◽  
Vol 12 (9) ◽  
pp. 1465
Author(s):  
Taikyeong Jeong
Keyword(s):  
Neural Network ◽  
Classification Accuracy ◽  
Deep Neural Network ◽  
Time Series Data ◽  
Training Data ◽  
Series Data ◽  
Context Aware ◽  
Data Set ◽  
Feedback Model ◽  
Data Connection

When attempting to apply a large-scale database that holds the behavioral intelligence training data of deep neural networks, the classification accuracy of the artificial intelligence algorithm needs to reflect the behavioral characteristics of the individual. When a change in behavior is recognized, that is, a feedback model based on a data connection model is applied, an analysis of time series data is performed by extracting feature vectors and interpolating data in a deep neural network to overcome the limitations of the existing statistical analysis. Using the results of the first feedback model as inputs to the deep neural network and, furthermore, as the input values of the second feedback model, and interpolating the behavioral intelligence data, that is, context awareness and lifelog data, including physical activities, involves applying the most appropriate conditions. The results of this study show that this method effectively improves the accuracy of the artificial intelligence results. In this paper, through an experiment, after extracting the feature vector of a deep neural network and restoring the missing value, the classification accuracy was verified to improve by about 20% on average. At the same time, by adding behavioral intelligence data to the time series data, a new data connection model, the Deep Neural Network Feedback Model, was proposed, and it was verified that the classification accuracy can be improved by about 8 to 9% on average. Based on the hypothesis, the F (X′) = X model was applied to thoroughly classify the training data set and test data set to present a symmetrical balance between the data connection model and the context-aware data. In addition, behavioral activity data were extrapolated in terms of context-aware and forecasting perspectives to prove the results of the experiment.

scholarly journals A Double-Channel Hybrid Deep Neural Network Based on CNN and BiLSTM for Remaining Useful Life Prediction

Sensors ◽  
2020 ◽  
Vol 20 (24) ◽  
pp. 7109
Author(s):  
Chengying Zhao ◽  
Xianzhen Huang ◽  
Yuxiong Li ◽  
Muhammad Yousaf Iqbal
Keyword(s):  
Neural Network ◽  
Prediction Model ◽  
Spatial Data ◽  
Deep Neural Network ◽  
Time Series Data ◽  
Remaining Useful Life ◽  
Series Data ◽  
Useful Life ◽  
Lstm Network ◽  
Double Channel

In recent years, prognostic and health management (PHM) has played an important role in industrial engineering. Efficient remaining useful life (RUL) prediction can ensure the development of maintenance strategies and reduce industrial losses. Recently, data-driven based deep learning RUL prediction methods have attracted more attention. The convolution neural network (CNN) is a kind of deep neural network widely used in RUL prediction. It shows great potential for application in RUL prediction. A CNN is used to extract the features of time-series data according to the spatial feature method. This way of processing features without considering the time dimension will affect the prediction accuracy of the model. On the contrary, the commonly used long short-term memory (LSTM) network considers the timing of the data. However, compared with CNN, it lacks spatial data extraction capabilities. This paper proposes a double-channel hybrid prediction model based on the CNN and a bidirectional LSTM network to avoid those drawbacks. The sliding time window is used for data preprocessing, and an improved piece-wise linear function is used for model validating. The prediction model is evaluated using the C-MAPSS dataset provided by NASA. The predicted results show the proposed prediction model to have a better prediction performance compared with other state-of-the-art models.

scholarly journals Simulating Time-Series Data for Improved Deep Neural Network Performance

IEEE Access ◽  
2019 ◽  
Vol 7 ◽  
pp. 131248-131255 ◽  
Author(s):  
Jordan Yeomans ◽  
Simon Thwaites ◽  
William S. P. Robertson ◽  
David Booth ◽  
Brian Ng ◽  
...  
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Network Performance ◽  
Deep Neural Network ◽  
Time Series Data ◽  
Series Data

scholarly journals Vibration Anomaly Detection using Deep Neural Network and Convolutional Neural Network

2021 ◽  
pp. 19-28
Author(s):  
Crina Deac ◽  
◽  
Gicu Călin Deac ◽  
Radu Constantin Parpală ◽  
Cicerone Laurentiu Popa ◽  
...  
Keyword(s):  
Neural Network ◽  
Convolutional Neural Network ◽  
Deep Neural Network ◽  
Time Series Data ◽  
Real Data ◽  
Series Data ◽  
Health State ◽  
Optimal Learning ◽  
Accuracy And Precision ◽  
The Cost

Identifying the “health state” of the equipment is the domain of condition monitoring. The paper proposes a study of two models: DNN (Deep Neural Network) and CNN (Convolutional Neural Network) over an existent dataset provided by Case Western Reserve University for analyzing vibrations in fault diagnosis. After the model is trained on the windowed dataset using an optimal learning rate, minimizing the cost function, and is tested by computing the loss, accuracy and precision across the results, the weights are saved, and the models can be tested on other real data. The trained model recognizes raw time series data collected by micro electro-mechanical accelerometer sensors and detects anomalies based on former times series entries.

scholarly journals Vector Auto-Regressive Deep Neural Network: A Data-Driven Deep Learning-Based Directed Functional Connectivity Estimation Toolbox

2021 ◽  
Vol 15 ◽  
Author(s):  
Takuto Okuno ◽  
Alexander Woodward
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Functional Connectivity ◽  
Deep Neural Network ◽  
Time Series Data ◽  
Evaluation Framework ◽  
Series Data ◽  
Ground Truth Data ◽  
Functional Connectome ◽  
Auto Regressive

An important goal in neuroscience is to elucidate the causal relationships between the brain’s different regions. This can help reveal the brain’s functional circuitry and diagnose lesions. Currently there are a lack of approaches to functional connectome estimation that leverage the state-of-the-art in deep learning architectures and training methodologies. Therefore, we propose a new framework based on a vector auto-regressive deep neural network (VARDNN) architecture. Our approach consists of a set of nodes, each with a deep neural network structure. These nodes can be mapped to any spatial sub-division based on the data to be analyzed, such as anatomical brain regions from which representative neural signals can be obtained. VARDNN learns to reproduce experimental time series data using modern deep learning training techniques. Based on this, we developed two novel directed functional connectivity (dFC) measures, namely VARDNN-DI and VARDNN-GC. We evaluated our measures against a number of existing functional connectome estimation measures, such as partial correlation and multivariate Granger causality combined with large dimensionality counter-measure techniques. Our measures outperformed them across various types of ground truth data, especially as the number of nodes increased. We applied VARDNN to fMRI data to compare the dFC between 41 healthy control vs. 32 Alzheimer’s disease subjects. Our VARDNN-DI measure detected lesioned regions consistent with previous studies and separated the two groups well in a subject-wise evaluation framework. Summarily, the VARDNN framework has powerful capabilities for whole brain dFC estimation. We have implemented VARDNN as an open-source toolbox that can be freely downloaded for researchers who wish to carry out functional connectome analysis on their own data.

scholarly journals COMPARATIVE STUDY ON DEEP NEURAL NETWORK MODELS FOR CROP CLASSIFICATION USING TIME SERIES POLSAR AND OPTICAL DATA

2018 ◽  
Vol XLII-5 ◽  
pp. 675-681 ◽  
Author(s):  
G. S. Phartiyal ◽  
D. Singh
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Deep Neural Network ◽  
Time Series Data ◽  
Short Term Memory ◽  
Classification Task ◽  
Optical Data ◽  
Series Data ◽  
Study Region ◽  
Crop Classification

<p><strong>Abstract.</strong> Crop classification is an important task in many crop monitoring applications. Satellite remote sensing has provided easy, reliable, and fast approaches to crop classification task. In this study, a comparative analysis is made on the performances of various deep neural network (DNN) models for crop classification task using polarimetric synthetic aperture radar (PolSAR) and optical satellite data. For PolSAR data, Sentinel 1 dual pol SAR data is used. Sentinel 2 multispectral data is used as optical data. Five land cover classes including two crop classes of the season are taken. Time series data over the period of one crop cycle is used. Training and testing samples are measured and collected directly from the ground over the study region. Various convolutional neural network (CNN) and long short-term memory (LSTM) models are implemented, analysed, evaluated, and compared. Models are evaluated on the basis of classification accuracy and generalization performance.</p>

scholarly journals RAIM-NET: A Deep Neural Network for Receiver Autonomous Integrity Monitoring

2020 ◽  
Vol 12 (9) ◽  
pp. 1503
Author(s):  
Yuan Sun
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Fault Detection ◽  
Deep Neural Network ◽  
Time Series Data ◽  
Main Idea ◽  
Series Data ◽  
Model Parameters ◽  
Integrity Monitoring ◽  
Receiver Autonomous Integrity Monitoring

With the continuous popularization of Global Navigation Satellite System (GNSS) in various applications, the performance requirement for integrity is also increasing, especially in the field of safety-of-life. Although the existing Receiver Autonomous Integrity Monitoring (RAIM) algorithm has been embedded in the GNSS receiver as a standard method, it might still suffer from small fault detection and delay alarm problem for time series fault models. In an effort to solve this problem, a Deep Neural Network (DNN) for RAIM, named RAIM-NET, is investigated in this paper. The main idea of RAIM-NET is to propose a combination of feature vector extraction and DNN model to improve the performance of integrity monitoring, with a problem specifically designed for loss function, obtaining the model parameters. Inspired by the powerful advantages of Recurrent Neural Network (RNN) in time series data processing, a multilayer RNN is applied to build the DNN model structure and improve the detection rate for small faults and reduce the alarm delay for the time series fault event. Finally, real GNSS data experiments are designed to verify the performance of RAIM-NET in fault detection and time delay for integrity monitoring.

Sign in / Sign up

Export Citation Format

Share Document