scholarly journals A Fully Connected Deep Neural Network approach with multiple sub-frame consideration and phase recompense for noise suppression

2021 ◽  
Author(s):  
Rohun Nisa
Keyword(s):  
Neural Network ◽  
Mean Square Error ◽  
Deep Neural Network ◽  
Speech Quality ◽  
Hybrid Network ◽  
Speech Communication ◽  
Mean Square ◽  
Perceptual Evaluation ◽  
Speech Spectrum ◽  
Fully Connected

In the speech communication process, the desirable speech needs to be addressed under the influence of noise encountered in diverse environments that degrade the speech quality and intelligibility. In opposition to the unfavorable scenario particularly lowered signal-to-noiseratio, the progress of traditional noise suppressive algorithms is hindered, introducing further distortion in speech, making them non-applicable for real-time applications. In order to reduce the complicacies of current algorithms, a hybrid approach for upgrading the quality together with intelligibility of speech is proposed for dealing with real-world hearing scenario. For improving the intelligibility of speech of interest, multiple sub-frame analysis using over-spectral subtractive factor with phase recompense approach is implemented on the multi-channel noise corrupted speech, yielding approximated speech spectrum, that constitutes the pre-processing stage. The approximated speech spectrum and clean speech spectrum forming the training set are further fed to Fully Connected Layered Deep Neural Network to reduce the mean square error with the incorporation of regression network resulting in improved quality for speech. The proposed hybrid network results in upgraded intelligibility and quality in speech signal with improved SNR measured in terms of Short-Time-Objective-Intelligibility (STOI) score, Perceptual-Evaluation-of-Speech-Quality (PESQ) score, Segmental SNR level, and Mean Square Error (MSE) in contrast to prior noise suppressive algorithms together with less complexity of the hybrid network.<br>

scholarly journals A Fully Connected Deep Neural Network approach with multiple sub-frame consideration and phase recompense for noise suppression

2021 ◽  
Author(s):  
Rohun Nisa
Keyword(s):  
Neural Network ◽  
Mean Square Error ◽  
Deep Neural Network ◽  
Speech Quality ◽  
Hybrid Network ◽  
Speech Communication ◽  
Mean Square ◽  
Perceptual Evaluation ◽  
Speech Spectrum ◽  
Fully Connected

In the speech communication process, the desirable speech needs to be addressed under the influence of noise encountered in diverse environments that degrade the speech quality and intelligibility. In opposition to the unfavorable scenario particularly lowered signal-to-noiseratio, the progress of traditional noise suppressive algorithms is hindered, introducing further distortion in speech, making them non-applicable for real-time applications. In order to reduce the complicacies of current algorithms, a hybrid approach for upgrading the quality together with intelligibility of speech is proposed for dealing with real-world hearing scenario. For improving the intelligibility of speech of interest, multiple sub-frame analysis using over-spectral subtractive factor with phase recompense approach is implemented on the multi-channel noise corrupted speech, yielding approximated speech spectrum, that constitutes the pre-processing stage. The approximated speech spectrum and clean speech spectrum forming the training set are further fed to Fully Connected Layered Deep Neural Network to reduce the mean square error with the incorporation of regression network resulting in improved quality for speech. The proposed hybrid network results in upgraded intelligibility and quality in speech signal with improved SNR measured in terms of Short-Time-Objective-Intelligibility (STOI) score, Perceptual-Evaluation-of-Speech-Quality (PESQ) score, Segmental SNR level, and Mean Square Error (MSE) in contrast to prior noise suppressive algorithms together with less complexity of the hybrid network.<br>

scholarly journals High-Resolution PM2.5 Estimation Based on the Distributed Perception Deep Neural Network Model

2021 ◽  
Vol 13 (24) ◽  
pp. 13985
Author(s):  
Jiwei Liu ◽  
Yong Sun ◽  
Qun Li
Keyword(s):  
Neural Network ◽  
Missing Data ◽  
Mean Square Error ◽  
Relative Error ◽  
Network Model ◽  
Neural Network Model ◽  
Deep Neural Network ◽  
Mean Square ◽  
Linear Fitting ◽  
Ground Monitoring

The accurate measurement of the PM2.5 individual exposure level is a key issue in the study of health effects. However, the lack of historical data and the minute coverage of ground monitoring points are obstacles to the study of such issues. Based on the aerosol optical depth provided by NASA, combined with ground monitoring data and meteorological data, it is an effective method to estimate the near-ground concentration of PM2.5. With the deepening of related research, the models used have developed from univariate and multivariate linear models to nonlinear models such as support vector machine, random forest model, and deep learning neural network model. Among them, the depth neural network model has better performance. However, in the existing research, the variables used are input into the same neural network together, that is, the complex relationship caused by the lag effect of features and the correlation and partial correlation between features have not been considered. The above neural network framework can not be well applied to the complex situation of atmospheric systems and the estimation accuracy of the model needs to be improved. This is the first problem that we need to be overcome. Secondly, in the missing data value processing, the existing studies mostly use single interpolation methods such as linear fitting and Kriging interpolation. However, because the time and place of data missing are complex and changeable, a single method is difficult to deal with a large area of strip and block missing data. Moreover, the linear fitting method is easy to smooth out the special data in bad weather. This is the second problem that we need to overcome. Therefore, we construct a distributed perception deep neural network model (DP-DNN) and spatiotemporal multiview interpolation module to overcome problems 1 and 2. In empirical research, based on the Beijing–Tianjin–Hebei–Shandong region in 2018, we introduce 50 features such as meteorology, NDVI, spatial-temporal feature to analyze the relationship between AOD and PM2.5, and test the performance of DP-DNN and spatiotemporal multiview interpolation module. The results show that after applying the spatiotemporal multiview interpolation module, the average proportion of missing data decreases from 52.1% to 4.84%, and the relative error of the results is 27.5%. Compared with the single interpolation method, this module has obvious advantages in accuracy and level of completion. The mean absolute error, relative error, mean square error, and root mean square error of DP-DNN in time prediction are 17.7 μg/m3, 46.8%, 766.2 g2/m6, and 26.9 μg/m3, respectively, and in space prediction, they are 16.6 μg/m3, 41.8%, 691.5 μg2/m6, and 26.6 μg/m3. DP-DNN has higher accuracy and generalization ability. At the same time, the estimation method in this paper can estimate the PM2.5 of the selected longitude and latitude, which can effectively solve the problem of insufficient coverage of China’s meteorological environmental quality monitoring stations.

Detection of Biomedical Images by Using Bio-inspired Artificial Intelligent

2020 ◽  
Vol 38 (2A) ◽  
pp. 255-264
Author(s):  
Hanan A. R. Akkar ◽  
Sameem A. Salman
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Mean Square Error ◽  
Average Rate ◽  
Mean Square ◽  
Performance Measurements ◽  
Artificial Intelligent ◽  
Average Mean Square Error ◽  
Artificial Neural ◽  
Artificial Neural Network Ann

Computer vision and image processing are extremely necessary for medical pictures analysis. During this paper, a method of Bio-inspired Artificial Intelligent (AI) optimization supported by an artificial neural network (ANN) has been widely used to detect pictures of skin carcinoma. A Moth Flame Optimization (MFO) is utilized to educate the artificial neural network (ANN). A different feature is an extract to train the classifier. The comparison has been formed with the projected sample and two Artificial Intelligent optimizations, primarily based on classifier especially with, ANN-ACO (ANN training with Ant Colony Optimization (ACO)) and ANN-PSO (training ANN with Particle Swarm Optimization (PSO)). The results were assessed using a variety of overall performance measurements to measure indicators such as Average Rate of Detection (ARD), Average Mean Square error (AMSTR) obtained from training, Average Mean Square error (AMSTE) obtained for testing the trained network, the Average Effective Processing Time (AEPT) in seconds, and the Average Effective Iteration Number (AEIN). Experimental results clearly show the superiority of the proposed (ANN-MFO) model with different features.

Modelling response of infiltration loss toward water table depth using RBFN, RNN, ANFIS techniques

2021 ◽  
Vol 25 (2) ◽  
pp. 227-234
Author(s):  
Sandeep Samantaray ◽  
Abinash Sahoo
Keyword(s):  
Neural Network ◽  
Mean Square Error ◽  
Water Table ◽  
Environmental Sustainability ◽  
Model Development ◽  
Water Table Depth ◽  
Water Levels ◽  
Coefficient Of Determination ◽  
Mean Square ◽  
Inference System

Accurate prediction of water table depth over long-term in arid agricultural areas are very much important for maintaining environmental sustainability. Because of intricate and diverse hydrogeological features, boundary conditions, and human activities researchers face enormous difficulties for predicting water table depth. A virtual study on forecast of water table depth using various neural networks is employed in this paper. Hybrid neural network approach like Adaptive Neuro Fuzzy Inference System (ANFIS), Recurrent Neural Network (RNN), Radial Basis Function Neural Network (RBFN) is employed here to appraisal water levels as a function of average temperature, precipitation, humidity, evapotranspiration and infiltration loss data. Coefficient of determination (R2), Root mean square error (RMSE), and Mean square error (MSE) are used to evaluate performance of model development. While ANFIS algorithm is used, Gbell function gives best value of performance for model development. Whole outcomes establish that, ANFIS accomplishes finest as related to RNN and RBFN for predicting water table depth in watershed.

scholarly journals Predicting the discharge coefficient of oblique cylindrical weir using neural network techniques

2021 ◽  
Vol 14 (16) ◽  
Author(s):  
Adnan A. Ismael ◽  
Saleh J. Suleiman ◽  
Raid Rafi Omar Al-Nima ◽  
Nadhir Al-Ansari
Keyword(s):  
Neural Network ◽  
Mean Square Error ◽  
Radial Basis Function Network ◽  
Back Propagation ◽  
Back Propagation Neural Network ◽  
Superior Performance ◽  
Mean Square ◽  
The Third ◽  
Testing Stage ◽  
Inclination Angles

AbstractCylindrical weir shapes offer a steady-state overflow pattern, where the type of weirs can offer a simple design and provide the ease-to-pass floating debris. This study considers a coefficient of discharge (Cd) prediction for oblique cylindrical weir using three diameters, the first is of D1 = 0.11 m, the second is of D2 = 0.09 m, and the third is of D3 = 0.06.5 m, and three inclination angles with respect to channel axis, the first is of θ1 = 90 ͦ, the second is of θ2 = 45 ͦ, and the third is of θ3 = 30 ͦ. The Cd values for total of 56 experiments are estimated by using the radial basis function network (RBFN), in addition of comparing that with the back-propagation neural network (BPNN) and cascade-forward neural network (CFNN). Root mean square error (RMSE), mean square error (MSE), and correlation coefficient (CC) statics are used as metrics measurements. The RBFN attained superior performance comparing to the other neural networks of BPNN and CFNN. It is found that, for the training stage, the RBFN network benchmarked very small RMSE and MSE values of 1.35E-12 and 1.83E-24, respectively and for the testing stage, it also could benchmark very small RMSE and MSE values of 0.0082 and 6.80E-05, respectively.

scholarly journals Solar Irradiance Prediction using Neural Model

2018 ◽  
Vol 8 (3) ◽  
Author(s):  
Raj Kumar Yadav ◽  
Nivedita Sethy
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Renewable Energy ◽  
Mean Square Error ◽  
Solar Irradiance ◽  
Neural Model ◽  
Accurate Prediction ◽  
Solar Irradiation ◽  
National Renewable Energy Laboratory ◽  
Mean Square

The accurate prediction of solar irradiation has been a leading problem for better energy scheduling approach. Hence in this paper, an Artificial neural network based solar irradiance is proposed for five days duration the data is obtained from National Renewable Energy Laboratory, USA and the simulation were performed using MATLAB 2013. It was found that the neural model was able to predict the solar irradiance with a mean square error of 0.0355.

scholarly journals sEMG-Based Neural Network Prediction Model Selection of Gesture Fatigue and Dataset Optimization

2020 ◽  
Vol 2020 ◽  
pp. 1-17
Author(s):  
Fujun Ma ◽  
Fanghao Song ◽  
Yan Liu ◽  
Jiahui Niu
Keyword(s):  
Neural Network ◽  
Energy Consumption ◽  
Prediction Model ◽  
Mean Square Error ◽  
Short Term Memory ◽  
Experimental Results ◽  
Support Vector ◽  
Mean Square ◽  
Semg Signals ◽  
Research Studies

The fatigue energy consumption of independent gestures can be obtained by calculating the power spectrum of surface electromyography (sEMG) signals. The existing research studies focus on the fatigue of independent gestures, while the research studies on integrated gestures are few. However, the actual gesture operation mode is usually integrated by multiple independent gestures, so the fatigue degree of integrated gestures can be predicted by training neural network of independent gestures. Three natural gestures including browsing information, playing games, and typing are divided into nine independent gestures in this paper, and the predicted model is established and trained by calculating the energy consumption of independent gestures. The artificial neural networks (ANNs) including backpropagation (BP) neural network, recurrent neural network (RNN), and long short-term memory (LSTM) are used to predict the fatigue of gesture. The support vector machine (SVM) is used to assist verification. Mean square error (MSE), root mean square error (RMSE), and mean absolute error (MAE) are utilized to evaluate the optimal prediction model. Furthermore, the different datasets of the processed sEMG signal and its decomposed wavelet coefficients are trained, respectively, and the changes of error functions of them are compared. The experimental results show that LSTM model is more suitable for gesture fatigue prediction. The processed sEMG signals are appropriate for using as the training set the fatigue degree of one-handed gesture. It is better to use wavelet decomposition coefficients as datasets to predict the high-dimensional sEMG signals of two-handed gestures. The experimental results can be applied to predict the fatigue degree of complex human-machine interactive gestures, help to avoid unreasonable gestures, and improve the user’s interactive experience.

Challenging the Recognition of Facial Expression via Deep Learning

2014 ◽  
Vol 571-572 ◽  
pp. 717-720
Author(s):  
De Kun Hu ◽  
Yong Hong Liu ◽  
Li Zhang ◽  
Gui Duo Duan
Keyword(s):  
Neural Network ◽  
Facial Expression ◽  
Gradient Descent ◽  
Deep Neural Network ◽  
Back Propagation ◽  
Stochastic Gradient Descent ◽  
Excellent Performance ◽  
Proposed Model ◽  
Input Layer ◽  
Fully Connected

A deep Neural Network model was trained to classify the facial expression in unconstrained images, which comprises nine layers, including input layer, convolutional layer, pooling layer, fully connected layers and output layer. In order to optimize the model, rectified linear units for the nonlinear transformation, weights sharing for reducing the complexity, “mean” and “max” pooling for subsample, “dropout” for sparsity are applied in the forward processing. With large amounts of hard training faces, the model was trained via back propagation method with stochastic gradient descent. The results of shows the proposed model achieves excellent performance.

Modeling of Phenol Degradation in Spouted Bed Contactor Using Artificial Neural Network (ANN)

2008 ◽  
Vol 3 (2) ◽  
Author(s):  
Madhukar A. Dabhade ◽  
M. B. Saidutta ◽  
D. V. R. Murthy
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Mean Square Error ◽  
Model Prediction ◽  
Phenol Degradation ◽  
Mean Square ◽  
Ann Model ◽  
Spouted Bed ◽  
The Mean ◽  
Artificial Neural Network Ann

Presence of phenol and phenolic compounds in various wastewaters and its harmful effects has led to the use of different treatment methods. Work on biological methods shows the use of different microorganisms and different bioreactors so as to improve the removal efficiency economically. The present work deals with the use of N. hydrocarbonoxydans (NCIM 2386), an actinomycetes, for the degradation of phenol. N. hydrocarbonoxydans was immobilized on GAC and used in a spouted bed contactor for effective contact of microorganisms and the substrate. The contactor performance was studied by varying flow rates, influent concentrations and the solids loading in the contactor. The effect of these variables on phenol degradation was investigated and modeling study was carried out using the artificial neural network (ANN). A feed forward neural network with back propagation was used for the model development. The experiments were planned as per the face centered cube design (FCCD) and used for training of the model, whereas data from four other experimental runs were used for testing and validation of the model. The network was optimized for the number of neurons based on the mean square error. The ANN model with three layers with three input neurons, eight neurons in hidden layers and one output neuron was found to predict effectively the effluent concentration for the given operating conditions in the spouted bed contactor. The mean square error was found to be 9.318e-12 for this ANN model. Also the experimental data was used to develop second order nonlinear empirical model obtained using multiple regression (MR) and the results compared with ANN using correlation coefficient (R2), average absolute error (AAE) and root mean square error (RMSE). Results show that R2, AAE and RMSE values of MR model were 0.9363, 2.085 % and 2.338 % respectively, while in case of ANN model these values were 0.9995, 0.59 % and 1.263 % respectively. This shows that ANN model prediction is better than multiple regression model prediction.

scholarly journals The modelling of lead removal from water by deep eutectic solvents functionalized CNTs: artificial neural network (ANN) approach

2017 ◽  
Vol 76 (9) ◽  
pp. 2413-2426 ◽  
Author(s):  
Seef Saadi Fiyadh ◽  
Mohammed Abdulhakim AlSaadi ◽  
Mohamed Khalid AlOmar ◽  
Sabah Saadi Fayaed ◽  
Ako R. Hama ◽  
...  
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Root Mean Square Error ◽  
Mean Square Error ◽  
Back Propagation ◽  
Deep Eutectic Solvents ◽  
Lead Removal ◽  
Mean Square ◽  
Feed Forward Back Propagation ◽  
Artificial Neural Network Ann

Abstract The main challenge in the lead removal simulation is the behaviour of non-linearity relationships between the process parameters. The conventional modelling technique usually deals with this problem by a linear method. The substitute modelling technique is an artificial neural network (ANN) system, and it is selected to reflect the non-linearity in the interaction among the variables in the function. Herein, synthesized deep eutectic solvents were used as a functionalized agent with carbon nanotubes as adsorbents of Pb2+. Different parameters were used in the adsorption study including pH (2.7 to 7), adsorbent dosage (5 to 20 mg), contact time (3 to 900 min) and Pb2+ initial concentration (3 to 60 mg/l). The number of experimental trials to feed and train the system was 158 runs conveyed in laboratory scale. Two ANN types were designed in this work, the feed-forward back-propagation and layer recurrent; both methods are compared based on their predictive proficiency in terms of the mean square error (MSE), root mean square error, relative root mean square error, mean absolute percentage error and determination coefficient (R2) based on the testing dataset. The ANN model of lead removal was subjected to accuracy determination and the results showed R2 of 0.9956 with MSE of 1.66 × 10−4. The maximum relative error is 14.93% for the feed-forward back-propagation neural network model.

Sign in / Sign up

Export Citation Format

Share Document