scholarly journals Flatness Prediction of Cold Rolled Strip Based on Deep Neural Network with Improved Activation Function

Sensors ◽  
2022 ◽  
Vol 22 (2) ◽  
pp. 656
Author(s):  
Jingyi Liu ◽  
Shuni Song ◽  
Jiayi Wang ◽  
Maimutimin Balaiti ◽  
Nina Song ◽  
...  
Keyword(s):  
Neural Network ◽  
Loss Function ◽  
Deep Neural Network ◽  
Activation Function ◽  
Rolled Strip ◽  
Linear Network ◽  
Nonlinear Network ◽  
Shape Prediction ◽  
Cold Rolled

With the improvement of industrial requirements for the quality of cold rolled strips, flatness has become one of the most important indicators for measuring the quality of cold rolled strips. In this paper, the strip production data of a 1250 mm tandem cold mill in a steel plant is modeled by an improved deep neural network (the improved DNN) to improve the accuracy of strip shape prediction. Firstly, the type of activation function is analyzed, and the monotonicity of the activation function is deemed independent of the convexity of the loss function in the deep network. Regardless of whether the activation function is monotonic, the loss function is not strictly convex. Secondly, the non-convex optimization of the loss functionextended from the deep linear network to the deep nonlinear network, is discussed, and the critical point of the deep nonlinear network is identified as the global minimum point. Finally, an improved Swish activation function based on batch normalization is proposed, and its performance is evaluated on the MNIST dataset. The experimental results show that the loss of an improved Swish function is lower than that of other activation functions. The prediction accuracy of a deep neural network (DNN) with an improved Swish function is 0.38% more than that of a deep neural network (DNN) with a regular Swish function. For the DNN with the improved Swish function, the mean square error of the prediction for the flatness of cold rolled strip is reduced to 65% of the regular DNN. The accuracy of the improved DNN is up to and higher than the industrial requirements. The shape prediction of the improved DNN will assist and guide the industrial production process, reducing the scrap yield and industrial cost.

Breast cancer diagnosis using multiple activation deep neural network

2021 ◽  
pp. 1063293X2110251
Author(s):  
K Vijayakumar ◽  
Vinod J Kadam ◽  
Sudhir Kumar Sharma
Keyword(s):  
Breast Cancer ◽  
Neural Network ◽  
Deep Neural Network ◽  
Breast Cancer Diagnosis ◽  
Activation Function ◽  
Linear Functions ◽  
Cancer Data ◽  
Final Layer ◽  
Improved Performance ◽  
Hidden Layer

Deep Neural Network (DNN) stands for multilayered Neural Network (NN) that is capable of progressively learn the more abstract and composite representations of the raw features of the input data received, with no need for any feature engineering. They are advanced NNs having repetitious hidden layers between the initial input and the final layer. The working principle of such a standard deep classifier is based on a hierarchy formed by the composition of linear functions and a defined nonlinear Activation Function (AF). It remains uncertain (not clear) how the DNN classifier can function so well. But it is clear from many studies that within DNN, the AF choice has a notable impact on the kinetics of training and the success of tasks. In the past few years, different AFs have been formulated. The choice of AF is still an area of active study. Hence, in this study, a novel deep Feed forward NN model with four AFs has been proposed for breast cancer classification: hidden layer 1: Swish, hidden layer, 2:-LeakyReLU, hidden layer 3: ReLU, and final output layer: naturally Sigmoidal. The purpose of the study is twofold. Firstly, this study is a step toward a more profound understanding of DNN with layer-wise different AFs. Secondly, research is also aimed to explore better DNN-based systems to build predictive models for breast cancer data with improved accuracy. Therefore, the benchmark UCI dataset WDBC was used for the validation of the framework and evaluated using a ten-fold CV method and various performance indicators. Multiple simulations and outcomes of the experimentations have shown that the proposed solution performs in a better way than the Sigmoid, ReLU, and LeakyReLU and Swish activation DNN in terms of different parameters. This analysis contributes to producing an expert and precise clinical dataset classification method for breast cancer. Furthermore, the model also achieved improved performance compared to many established state-of-the-art algorithms/models.

Quality of Third Generation Sequencing

2020 ◽  
Vol 17 (12) ◽  
pp. 5205-5209
Author(s):  
Ali Elbialy ◽  
M. A. El-Dosuky ◽  
Ibrahim M. El-Henawy
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Gc Content ◽  
Error Rates ◽  
Third Generation ◽  
Third Generation Sequencing ◽  
Long Reads ◽  
Generation Sequencing

Third generation sequencing (TGS) relates to long reads but with relatively high error rates. Quality of TGS is a hot topic, dealing with errors. This paper combines and investigates three quality related metrics. They are basecalling accuracy, Phred Quality Scores, and GC content. For basecalling accuracy, a deep neural network is adopted. The measured loss does not exceed 5.42.

scholarly journals Continuous vocoder applied in deep neural network based voice conversion

2019 ◽  
Vol 78 (23) ◽  
pp. 33549-33572
Author(s):  
Mohammed Salah Al-Radhi ◽  
Tamás Gábor Csapó ◽  
Géza Németh
Keyword(s):  
Neural Network ◽  
Speech Synthesis ◽  
Deep Neural Network ◽  
Signal To Noise Ratio ◽  
Geometric Approach ◽  
Objective Evaluation ◽  
Voice Conversion ◽  
Listening Tests ◽  
Alignment Errors

Abstract In this paper, a novel vocoder is proposed for a Statistical Voice Conversion (SVC) framework using deep neural network, where multiple features from the speech of two speakers (source and target) are converted acoustically. Traditional conversion methods focus on the prosodic feature represented by the discontinuous fundamental frequency (F0) and the spectral envelope. Studies have shown that speech analysis/synthesis solutions play an important role in the overall quality of the converted voice. Recently, we have proposed a new continuous vocoder, originally for statistical parametric speech synthesis, in which all parameters are continuous. Therefore, this work introduces a new method by using a continuous F0 (contF0) in SVC to avoid alignment errors that may happen in voiced and unvoiced segments and can degrade the converted speech. Our contribution includes the following. (1) We integrate into the SVC framework the continuous vocoder, which provides an advanced model of the excitation signal, by converting its contF0, maximum voiced frequency, and spectral features. (2) We show that the feed-forward deep neural network (FF-DNN) using our vocoder yields high quality conversion. (3) We apply a geometric approach to spectral subtraction (GA-SS) in the final stage of the proposed framework, to improve the signal-to-noise ratio of the converted speech. Our experimental results, using two male and one female speakers, have shown that the resulting converted speech with the proposed SVC technique is similar to the target speaker and gives state-of-the-art performance as measured by objective evaluation and subjective listening tests.

scholarly journals Analysis Model of the Impact of Refined Intervention in Operating Room on Patients’ Recovery Quality and Complications after Thoracic Surgery Based on Deep Neural Network

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Jun He ◽  
Jing Wen
Keyword(s):  
Neural Network ◽  
Thoracic Surgery ◽  
Operating Room ◽  
Test Data ◽  
Deep Neural Network ◽  
Quality Of Recovery ◽  
Network Algorithm ◽  
Neural Network Algorithm ◽  
Room Nursing

To improve the nursing effect in patients after thoracic surgery, this paper proposes a refined intervention method in the operating room based on traditional operating room nursing and applies this method to the nursing of patients after thoracic surgery. Moreover, this paper improves the traditional neural network algorithm and uses the deep neural network algorithm to process test data. In addition, it includes patients accepted by the hospital as samples for test analysis and formulates detailed intervention methods for the operating room. Finally, this paper collects the corresponding test data by setting up test and control groups and visually displays the data using mathematical statistics. The statistical parameters of the experiment in this paper include the quality of recovery, complications, satisfaction score, and recovery effect. The comparative test shows that the refined intervention in the operating room based on the neural network proposed in this paper can achieve a certain effect in the postoperative nursing of thoracic surgery, effectively promote the quality of recovery, and reduce the possibility of complications.

Multilevel and Color Image Segmentation by NSGA II Based OptiMUSIG Activation Function

2016 ◽  
pp. 321-348 ◽  
Author(s):  
Sourav De ◽  
Siddhartha Bhattacharyya ◽  
Susanta Chakraborty
Keyword(s):  
Neural Network ◽  
Image Segmentation ◽  
Color Image ◽  
Activation Function ◽  
Color Image Segmentation ◽  
Nsga Ii ◽  
Segmented Images ◽  
Single Objective ◽  
Self Organizing

A self-supervised image segmentation method by a non-dominated sorting genetic algorithm-II (NSGA-II) based optimized MUSIG (OptiMUSIG) activation function with a multilayer self-organizing neural network (MLSONN) architecture is proposed to segment multilevel gray scale images. In the same way, another NSGA-II based parallel version of the OptiMUSIG (ParaOptiMUSIG) activation function with a parallel self-organizing neural network (PSONN) architecture is purported to segment the color images in this article. These methods are intended to overcome the drawback of their single objective based counterparts. Three standard objective functions are employed as the multiple objective criteria of the NSGA-II algorithm to measure the quality of the segmented images.

Sign in / Sign up

Export Citation Format

Share Document