scholarly journals Effects of Parameter Change on Neural Network and Deep Neural Network

2021 ◽  
Author(s):  
Soufia Naseri
Keyword(s):  
Neural Network ◽  
Gaussian Noise ◽  
Deep Neural Network ◽  
Additive Noise ◽  
Computation Time ◽  
The Other ◽  
Decision Boundary ◽  
Data Complexity ◽  
Parameter Change ◽  
Weak Learner

Parameters in neural network such as number of neurons and layers have a direct effect on efficiency and accuracy of the network. On the other hand, it is observed that structure of a network is dependent on data complexity. It is perceived that choosing a complex network for a simple data (e.g. linearly separable data) may not only result in a weak learner but also an increase in computation time. Here, accuracy of the network has been challenged by adding Gaussian Noise to these data to investigate the effect of noise. This additive noise flags overcomplexity thus, decision boundary is generalized which it directs the learner to have better classification as if the number of parameters have been decreased. Throughout these comparisons, other constrains have been minimized in MATLAB to solely observe the effect of each change.

scholarly journals Effects of Parameter Change on Neural Network and Deep Neural Network

2021 ◽  
Author(s):  
Soufia Naseri
Keyword(s):  
Neural Network ◽  
Gaussian Noise ◽  
Deep Neural Network ◽  
Additive Noise ◽  
Computation Time ◽  
The Other ◽  
Decision Boundary ◽  
Data Complexity ◽  
Parameter Change ◽  
Weak Learner

Parameters in neural network such as number of neurons and layers have a direct effect on efficiency and accuracy of the network. On the other hand, it is observed that structure of a network is dependent on data complexity. It is perceived that choosing a complex network for a simple data (e.g. linearly separable data) may not only result in a weak learner but also an increase in computation time. Here, accuracy of the network has been challenged by adding Gaussian Noise to these data to investigate the effect of noise. This additive noise flags overcomplexity thus, decision boundary is generalized which it directs the learner to have better classification as if the number of parameters have been decreased. Throughout these comparisons, other constrains have been minimized in MATLAB to solely observe the effect of each change.

scholarly journals Fast Accurate and Automatic Brushstroke Extraction

2021 ◽  
Vol 17 (2) ◽  
pp. 1-24
Author(s):  
Yunfei Fu ◽  
Hongchuan Yu ◽  
Chih-Kuo Yeh ◽  
Tong-Yee Lee ◽  
Jian J. Zhang
Keyword(s):  
Neural Network ◽  
Efficient Algorithm ◽  
Deep Neural Network ◽  
High Efficiency ◽  
State Of The Art ◽  
High Reliability ◽  
The Other ◽  
Manual Annotation ◽  
Stroke Extraction ◽  
Art Research

Brushstrokes are viewed as the artist’s “handwriting” in a painting. In many applications such as style learning and transfer, mimicking painting, and painting authentication, it is highly desired to quantitatively and accurately identify brushstroke characteristics from old masters’ pieces using computer programs. However, due to the nature of hundreds or thousands of intermingling brushstrokes in the painting, it still remains challenging. This article proposes an efficient algorithm for brush Stroke extraction based on a Deep neural network, i.e., DStroke. Compared to the state-of-the-art research, the main merit of the proposed DStroke is to automatically and rapidly extract brushstrokes from a painting without manual annotation, while accurately approximating the real brushstrokes with high reliability. Herein, recovering the faithful soft transitions between brushstrokes is often ignored by the other methods. In fact, the details of brushstrokes in a master piece of painting (e.g., shapes, colors, texture, overlaps) are highly desired by artists since they hold promise to enhance and extend the artists’ powers, just like microscopes extend biologists’ powers. To demonstrate the high efficiency of the proposed DStroke, we perform it on a set of real scans of paintings and a set of synthetic paintings, respectively. Experiments show that the proposed DStroke is noticeably faster and more accurate at identifying and extracting brushstrokes, outperforming the other methods.

scholarly journals Novel Spatiotemporal Feature Extraction Parallel Deep Neural Network for Forecasting Confirmed Cases of Coronavirus Disease 2019

2020 ◽  
Author(s):  
Chiou-Jye Huang ◽  
Yamin Shen ◽  
Ping-Huan Kuo ◽  
Yung-Hsiang Chen
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Absolute Error ◽  
Mean Absolute Percentage Error ◽  
The Other ◽  
Percentage Error ◽  
Model Assessment ◽  
Absolute Percentage Error ◽  
Spatiotemporal Feature ◽  
The Mean

AbstractThe coronavirus disease 2019 pandemic continues as of March 26 and spread to Europe on approximately February 24. A report from April 29 revealed 1.26 million confirmed cases and 125 928 deaths in Europe. This study proposed a novel deep neural network framework, COVID-19Net, which parallelly combines a convolutional neural network (CNN) and bidirectional gated recurrent units (GRUs). Three European countries with severe outbreaks were studied—Germany, Italy, and Spain—to extract spatiotemporal feature and predict the number of confirmed cases. The prediction results acquired from COVID-19Net were compared to those obtained using a CNN, GRU, and CNN-GRU. The mean absolute error, mean absolute percentage error, and root mean square error, which are commonly used model assessment indices, were used to compare the accuracy of the models. The results verified that COVID-19Net was notably more accurate than the other models. The mean absolute percentage error generated by COVID-19Net was 1.447 for Germany, 1.801 for Italy, and 2.828 for Spain, which were considerably lower than those of the other models. This indicated that the proposed framework can accurately predict the accumulated number of confirmed cases in the three countries and serve as a crucial reference for devising public health strategies.

scholarly journals Two particle picking procedures for filamentous proteins: SPHIRE-crYOLO filament mode and SPHIRE-STRIPER

2020 ◽  
Author(s):  
Thorsten Wagner ◽  
Luca Lusnig ◽  
Sabrina Pospich ◽  
Markus Stabrin ◽  
Fabian Schönfeld ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Molecular Complexes ◽  
High Accuracy ◽  
The Other ◽  
Line Detection ◽  
Data Sets ◽  
Detection Approach ◽  
Selection Of

AbstractStructure determination of filamentous molecular complexes involves the selection of filaments from cryo-EM micrographs. The automatic selection of helical specimens is particularly difficult and thus many challenging samples with issues such as contamination or aggregation are still manually picked. Here we present two approaches for selecting filamentous complexes: one uses a trained deep neural network to identify the filaments and is integrated in SPHIRE-crYOLO, the other one, called SPHIRE-STRIPER, is based on a classical line detection approach. The advantage of the crYOLO based procedure is that it accurately performs on very challenging data sets and selects filaments with high accuracy. Although STRIPER is less precise, the user benefits from less intervention, since in contrast to crYOLO, STRIPER does not require training. We evaluate the performance of both procedures on tobacco mosaic virus and filamentous F-actin data sets to demonstrate the robustness of each method.

Artificial neural network–based internal leakage fault detection for hydraulic actuators: An experimental investigation

2017 ◽  
Vol 232 (4) ◽  
pp. 369-382 ◽  
Author(s):  
Zhikai Yao ◽  
Yongping Yu ◽  
Jianyong Yao
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Artificial Neural Network ◽  
Experimental Investigation ◽  
Signal Processing ◽  
Deep Neural Network ◽  
Detection Method ◽  
The Other ◽  
Detection Accuracy ◽  
Artificial Neural

Internal leakage is a typical fault in the hydraulic systems, which may be caused by seal damage, and result in deteriorated performance of the system. To study this issue, this article carries out an experimental investigation of artificial neural network–based detection method for internal leakage fault. A period of pressure signal at one chamber of the actuator was taken in response to sinusoidal-like inputs for the closed-loop controlled system as a basic signal unit, and totally, 1000 periodic signal units are obtained from the experiments. The above experimental measurements are repetitively implemented with 11 different active exerted internal leakage levels, that is, totally 11,000 basic signal units are obtained. For signal processing, the pressure signal in the operation condition without active exerted leakage is chosen to generate a baseline with suitable pre-proceed, and the relative values of the other basic signal units (D-value between the baseline and other original signals) act as the global samples of the following artificial neural networks, traditional back propagation neural network, deep neural network, convolution neural network and auto-encoder neural network, separately; 8800 samples by random extraction as train samples to train the above neural networks and the other samples different from the train samples act as test samples to examine the detection accuracy of the proposed method. It is shown that the deep neural network with five layers can obtain a best detection accuracy (92.23%) of the above-mentioned neural networks. In addition, the methods based on wavelet transform and Hilbert–Huang transform are also applied, and a comparison of these methods is provided at last. From the comparison, it is shown that the proposed detection method obtains a good result without a need to model the internal leakage or a complicated signal processing.

scholarly journals Deep Neural Network based Abdominal Aortic Aneurysm Identification with PSO Optimization

2020 ◽  
Vol 9 (3) ◽  
pp. 3209-3215
Keyword(s):  
Neural Network ◽  
Abdominal Aortic Aneurysm ◽  
Aortic Aneurysm ◽  
Deep Neural Network ◽  
Research Work ◽  
Computation Time ◽  
Watershed Segmentation ◽  
Treatment Needs ◽  
Abdominal Aortic ◽  
Significant Performance

Converting the ongoing advancement of abdominal aortic aneurysm (AAA) development and rebuilding information for prescient treatment needs a significant and computational perspective demonstration system. Also abdominal aortic aneurysm is fatal and rupture hence an effective treatment is needed. The aim of this research work is to develop an algorithm that focuses on the accurate detection of the AAA image. In this proposed work, the input AAA images preprocessed to transform the RGB format into gray scale image using adaptive filter, also the pixels which are corrupted by noise is too determined. Then watershed segmentation is applied before extracting the highlighted feature from AAA images. The features of AAA are extracted by genetic algorithm. After the extraction, the best features are selected by using particle swarm optimization and finally for classification and recognition, deep neural network classifier is applied. The proposed system is appropriate to accomplish our aim in foreseeing the AAA progress and in figuring the propagation vulnerability. The performance of our system is measured using accuracy, precision, f-score and computation time are utilized. The comparative analysis of the outcomes showed the significant performance of the proposed approach over the existing SVM and CNN classifier.

A Novel Hybrid Deep Multi-Criteria Model for Recommender System

2021 ◽  
Author(s):  
Nour Salim Nassar
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Recommender Systems ◽  
Recommender System ◽  
Real World ◽  
Deep Neural Network ◽  
Recommendation Systems ◽  
The Other ◽  
Learning Techniques ◽  
Novel Model

Abstract Recommender systems are everywhere books, products, movies, and more. Traditional recommender systems typically use a single criterion in the recommendation, while studies have shown that multi-criteria recommending is more accurate. Novel deep learning techniques have produced remarkable achievements in many fields. The use of such techniques in recommendation systems has started to get attention recently, and several models of recommendation have been proposed based on deep learning. However, there is still no work for using deep learning in hybrid multi-criteria recommender systems. In this work, a model for a hybrid deep multi-criteria recommender system was presented. The model mainly includes two major parts: In the first one, the model obtains the user ID, item ID, and the item metadata to be used as input to a deep neural network in order to predict the criteria ratings. In the second part, the obtained ratings act as an input to another deep neural network, where the overall rating is predicted. Our experiments were conducted on a real-world dataset. They demonstrated the superiority of the proposed novel model over the other models in all measures used to evaluate performance. This indicates the successful use of hybrid deep multi-criteria in the recommendation systems.

Novel Intelligent Pigging Tool For Deposit Inspection Using Electrical Tomography with High Computational Efficiency Enabled Through Neural Networks

2021 ◽  
Author(s):  
Antti Nissinen ◽  
Ossi Lehtikangas ◽  
Arto Voutilainen ◽  
Pasi Laakkonen ◽  
Anssi Lehikoinen
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Electrical Properties ◽  
Computational Efficiency ◽  
Deep Neural Network ◽  
Computation Time ◽  
Electrical Tomography ◽  
Deposit Thickness ◽  
The Neural Network ◽  
Pipe Line

Objectives/Scope Deposition inspection sensor based on electrical tomography has been proposed recently. In this work, a next generation electrical tomography sensor is introduced and a novel mathematical approach for the estimation of the deposit thickness is described. It is essential for the pipeline operators to keep the lines open for smooth flow and high flow efficiency. Deposit thickness, deposit type and location of deposit is required for optimal pipeline cleaning. The usage of chemicals as well as number of cleaning pig runs can be optimized based on the information that intelligent pig is giving. Methods, Procedures, Process In electrical tomography, electrodes are attached on the surface of the sensor and excitations are applied to some electrodes and responses are measured from other electrodes. The electrical properties of the medium are estimated based on these measurements. In pigging applications, the distribution of electrical properties between the PIG surface and metal pipe is estimated. The thickness and type of deposit (wax/scale) can be identified from the estimated electrical properties. In the proposed approach the estimation of the parameters is done by using a novel deep neural network based approach. In practice, number of measurements that are analyzed after each PIG run can be hundreds of thousands. The neural network based approach was chosen in order to achieve reasonable computational efficiency (computation time) in real applications with large amounts of data. Results, Observations, Conclusions The introduced sensor is for 12-inch lines and designed to be used when the oil line is filled with water. This sensor was tested in a laboratory test line with artificial deposit samples. After these tests and calibration, the sensor is deployed to be used in real pipe line inspections. The major challenges in pipe line runs include the movement of the sensor during measurements, electrical noise and changing excitations. In the neural network model, the position of the PIG is estimated simultaneously with the electrical properties and the effect of all these aforementioned uncertainties are also modelled. Based on the results conclusions can be drawn on the efficiency and performance using neural networks and the high suitability of electrical tomography for deposit mapping. Novel/Additive Information In this study, it is shown that intelligent pig based on the electrical tomography can be used reliable for deposit inspection. Furthermore, the computation approach based on the deep neural network is computationally efficient and it is tolerable for measurement noise and other uncertainties in real measurements.

scholarly journals Determining the Rolling Window Size of Deep Neural Network Based Models on Time Series Forecasting

2021 ◽  
Vol 2078 (1) ◽  
pp. 012011
Author(s):  
Li Shen ◽  
Zijin Wei ◽  
Yangzhu Wang
Keyword(s):  
Neural Network ◽  
Time Series ◽  
Gaussian Noise ◽  
Deep Neural Network ◽  
Window Size ◽  
Time Series Forecasting ◽  
Time Series Models ◽  
Arima Models ◽  
Information Theoretic ◽  
Rolling Window

Abstract Time series forecasting has always been a significant task in various domains. In this paper, we propose DeepARMA, a LSTM-based recurrent neural network to tackle this problem. DeepARMA is derived from an existing time series forecasting baseline, DeepAR, overcoming two of its weaknesses: (1) rolling window size determination: the way DeepAR determines rolling window size is casual and vulnerable, which may lead to the unnecessary computation and inefficiency of the model;(2) neglect of the noise: pure autoregressive model cannot deal with the condition where data are composed of various kinds of noise, neither do most of time series models including DeepAR. In order to solve these two problems, we first combine a classic information theoretic criterion, AIC, with the network to determine the proper rolling window size. Then, we propose a jointly-learned neural network fusing white Gaussian noise series given by ARIMA models to DeepAR’s input. That is exactly why we name the network ‘DeepARMA’. Our experiments on a real-world dataset demonstrate that our improvement settles those two problems put forward above.

scholarly journals Two particle-picking procedures for filamentous proteins: SPHIRE-crYOLO filament mode and SPHIRE-STRIPER

2020 ◽  
Vol 76 (7) ◽  
pp. 613-620
Author(s):  
Thorsten Wagner ◽  
Luca Lusnig ◽  
Sabrina Pospich ◽  
Markus Stabrin ◽  
Fabian Schönfeld ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Molecular Complexes ◽  
High Accuracy ◽  
The Other ◽  
Line Detection ◽  
Data Sets ◽  
Detection Approach ◽  
Selection Of

Structure determination of filamentous molecular complexes involves the selection of filaments from cryo-EM micrographs. The automatic selection of helical specimens is particularly difficult, and thus many challenging samples with issues such as contamination or aggregation are still manually picked. Here, two approaches for selecting filamentous complexes are presented: one uses a trained deep neural network to identify the filaments and is integrated in SPHIRE-crYOLO, while the other, called SPHIRE-STRIPER, is based on a classical line-detection approach. The advantage of the crYOLO-based procedure is that it performs accurately on very challenging data sets and selects filaments with high accuracy. Although STRIPER is less precise, the user benefits from less intervention, since in contrast to crYOLO, STRIPER does not require training. The performance of both procedures on Tobacco mosaic virus and filamentous F-actin data sets is described to demonstrate the robustness of each method.

Sign in / Sign up

Export Citation Format

Share Document