Filters








57,450 Hits in 3.2 sec

Deep Neural Networks Under Stress

Micael Carvalho, Matthieu Cord, Sandra Avila, Nicolas Thome, Eduardo Valle
2016 2016 IEEE International Conference on Image Processing (ICIP)  
By introducing perturbations to image descriptions extracted from a deep convolutional neural network, we change their precision and number of dimensions, measuring how it affects the final score.  ...  The properties of their features remain, however, largely unstudied under the transfer perspective.  ...  INTRODUCTION Deep Convolutional Neural Networks have swept the Computer Vision community, with state-of-the-art performance for many tasks [1, 2, 3] .  ... 
doi:10.1109/icip.2016.7533200 dblp:conf/icip/CarvalhoCATV16 fatcat:7qw7qv4zi5dpxndjda2s6mcvi4

High spatially sensitive quantitative phase imaging assisted with deep neural network for classification of human spermatozoa under stressed condition [article]

Ankit Butola, Daria Popova, Dilip K Prasad, Azeem Ahmad, Anowarul Habib, Jean Claude Tinguely, Purusotam Basnet, Ganesh Acharya, Paramasivam Senthilkumaran, Dalip Singh Mehta, Balpreet Singh Ahluwalia
2020 arXiv   pre-print
Total of seven feedforward deep neural networks (DNN) were employed for the classification of the phase maps for normal and stress affected sperm cells.  ...  We developed a partially spatially coherent digital holographic microscope (PSC-DHM) for quantitative phase imaging (QPI) in order to distinguish normal sperm cells from sperm cells under different stress  ...  Figure 7 : 7 Sensitivity, specificity and classification accuracy of different deep neural network.  ... 
arXiv:2002.07377v1 fatcat:762bcroryvaktkkpi35stbcjwi

High spatially sensitive quantitative phase imaging assisted with deep neural network for classification of human spermatozoa under stressed condition

Ankit Butola, Daria Popova, Dilip K. Prasad, Azeem Ahmad, Anowarul Habib, Jean Claude Tinguely, Purusotam Basnet, Ganesh Acharya, Paramasivam Senthilkumaran, Dalip Singh Mehta, Balpreet Singh Ahluwalia
2020 Scientific Reports  
Total of seven feedforward deep neural networks (DNN) are employed for the classification of the phase maps for normal and stress affected sperm cells.  ...  We developed a partially spatially coherent digital holographic microscope (PSC-DHM) for quantitative phase imaging (QPI) in order to distinguish normal sperm cells from sperm cells under different stress  ...  Table 3 . 3 Training time of total 7 deep neural network for the classification of normal and stressed affected phase map of sperm cell. https://doi.org/10.1038/s41598-020-69857-4 Deep neural network for  ... 
doi:10.1038/s41598-020-69857-4 pmid:32753627 fatcat:qukzgcclf5bbzajoxofusl42wq

Stress detection using deep neural networks

Russell Li, Zhandong Liu
2020 BMC Medical Informatics and Decision Making  
To address this deficiency, we developed two deep neural networks: a 1-dimensional (1D) convolutional neural network and a multilayer perceptron neural network.  ...  Deep neural networks do not require hand-crafted features but instead extract features from raw data through the layers of the neural networks.  ...  Conclusions We developed two deep neural networks: a deep 1D convolutional neural network and a deep multilayer perceptron neural network.  ... 
doi:10.1186/s12911-020-01299-4 pmid:33380334 fatcat:hspx35nvsbcnncsdv6pqrhyeve

Short communication: A case study of stress monitoring with non-destructive stress measurement and deep learning algorithms

Y. Ji, Q. Lu, Q. Yao
2022 Mechanical Sciences  
neural network, CNN, and long short-term memory, LSTM).  ...  Specifically, we applied the experimental magnetic signals from steel samples to validate the feasibility and efficiency of two deep learning models for stress prediction.  ...  Deep learning models There are two types of widely used deep learning models: convolutional neural network (CNN) and recurrent neural network (RNN).  ... 
doi:10.5194/ms-13-291-2022 doaj:ee4a23aeac214f83b0d829ab101c64c7 fatcat:grxosooxwfczxozjgdpsvdbymu

Prediction Method of College Students' Psychological Pressure Based on Deep Neural Network

Bing Wang, Sitong Liu, M Pallikonda Rajasekaran
2021 Scientific Programming  
combined with the deep neural network algorithm of gray theory.  ...  neural network is proposed.  ...  Aiming at the above problems, a prediction method of College Students' psychological stress based on deep neural network is proposed.  ... 
doi:10.1155/2021/2943678 fatcat:dlltuatcyrbapjp2un7hkieolq

Traction Force Microscopy by Deep Learning [article]

Yu-Li Wang, Yun-Chu Lin
2020 bioRxiv   pre-print
Here we applied neural network-based deep learning as a novel approach for TFM. We modified a network for processing images to process vector fields of stress and strain.  ...  Furthermore, we adapted a mathematical model for cell migration to generate large sets of simulated stresses and strains for training the network.  ...  Xinhan Li for drafting the neural network architecture. This study was supported by NIH grant R01 GM118998. .  ... 
doi:10.1101/2020.05.20.107128 fatcat:veorlfjw4zdy5d33prel2bbfem

A single Long Short-Term Memory network for enhancing the prediction of path-dependent plasticity with material heterogeneity and anisotropy [article]

Ehsan Motevali Haghighi, SeonHong Na
2022 arXiv   pre-print
This study presents the applicability of conventional deep recurrent neural networks (RNN) to predict path-dependent plasticity associated with material heterogeneity and anisotropy.  ...  The proposed neural network architecture is then used to model elastoplastic responses of a two-dimensional transversely anisotropic material associated with computational homogenization (FE2).  ...  deep neural networks.  ... 
arXiv:2204.01466v2 fatcat:sdtgivbpknd3xkxk4t2sheggnm

A Novel Deep Learning Model to Predict Ultimate Strength of Ship Plates under Compression

So-jeong Cho, Im-jun Ban, Sung-chul Shin
2022 Applied Sciences  
using a deep learning model.  ...  To obtain the training data for the deep-learning model, 4050 cases were selected and analyzed using the ANSYS.  ...  In this study, based on a deep neural network, the ultimate strength of the curved plate was predicted over a wider range under a transverse load in various scenarios.  ... 
doi:10.3390/app12052522 fatcat:g3kkanlt5vcd7pjsvadtk4a6pa

A Design Method for a New Type of Cylindrical Roller Bearing Based on Edge Effect

Yao Qishui, Yang Wen, Li Chao, Yu Jianghong
2016 The Open Mechanical Engineering Journal  
maximum stress by BP neural network learning algorithm and to obtain the objective function required for structural optimization of genetic algorithm.  ...  cylindrical roller bearing edge; to determine the BP neural network sample data using orthogonal test and finite element methods; to establish mapping relationship between the design variables and the  ...  The numerical analysis was conducted under FEM and the sample for BP neural network was setup.  ... 
doi:10.2174/1874129001610010098 fatcat:7iuphejkwzetlninacrtjcry4q

Advanced Stochastic Optimization Algorithm for Deep Learning Artificial Neural Networks in Banking and Finance Industries

Jamilu Auwalu Adamu
2019 Risk and Financial Management  
This research is expected to open the "Black-Box" of Deep Learning Artificial Neural networks.  ...  Learning Artificial Neural Network.  ...  Deep Learning Artificial Neural Network Learning processes.  ... 
doi:10.30560/rfm.v1n1p8 fatcat:akgthk2xdnbenmjmq7pze66ysa

Stress Classification using Deep Learning with 1D Convolutional Neural Networks

Abdulrazak Yahya Saleh, Lau Khai Xian
2021 Knowledge Engineering and Data Science  
Therefore, the primary purpose of this paper is to evaluate the performance of 1D Convolutional Neural Networks (1D CNNs) for stress classification.  ...  Deep Learning (DL) has created an impact in the field of Artificial Intelligence as it can perform tasks with high accuracy.  ...  Universiti Malaysia Sarawak (UNIMAS) supported and funded this work under the CDRG Cross-Disciplinary Research (F04/CDRG/1839/2019). Declarations  ... 
doi:10.17977/um018v4i22021p145-152 fatcat:b3t2gqm2bjgelnnppr2clxu5n4

StressedNets: Efficient Feature Representations via Stress-induced Evolutionary Synthesis of Deep Neural Networks [article]

Mohammad Javad Shafiee, Brendan Chwyl, Francis Li, Rongyan Chen, Michelle Karg, Christian Scharfenberger, Alexander Wong
2018 arXiv   pre-print
are imposed upon the synapses of a deep neural network during training to induce stress and steer the synthesis process towards the production of more efficient deep neural networks over successive generations  ...  The proposed stress-induced evolutionary synthesis approach is evaluated on a variety of different deep neural network architectures (LeNet5, AlexNet, and YOLOv2) on different tasks (object classification  ...  The factor β imposes minor stress to the deep neural network at the epoch level.  ... 
arXiv:1801.05387v1 fatcat:3r53yksey5e4vjfh7qq7bpltbm

Enhanced physics-informed neural networks for hyperelasticity [article]

Diab W. Abueidda, Seid Koric, Erman Guleryuz, Nahil A. Sobh
2022 arXiv   pre-print
However, physics-informed neural network models suffer from several issues and can fail to provide accurate solutions in many scenarios.  ...  Physics-informed neural networks have gained growing interest. Specifically, they are used to solve partial differential equations governing several physical phenomena.  ...  Deep feedforward neural networks Deep feedforward neural networks are layers of interlinked individual unit cells, named neurons, connected to other neurons' layers.  ... 
arXiv:2205.14148v1 fatcat:7ykazsqr2jg6hngieb4uzun4bu

A Deep Learning Approach to Automated Structural Engineering of Prestressed Members

Ahmed A. Torky, Anas A. Aburawwash
2018 International Journal of Structural and Civil Engineering Research  
Index Terms-deep learning, structural engineering, prestressing, artificial neural networks, economic design  ...  A simple prestressed beam is presented as an initial example to show the viability of neural networks against the traditional approaches.  ...  NEURAL NETWORKS A. Network Architecture A deep learning neural network comprises of at least one input layer, one output layer and several hidden layers in between [7] .  ... 
doi:10.18178/ijscer.7.4.347-352 fatcat:jzungepwlbgmloaxlovrci6dte
« Previous Showing results 1 — 15 out of 57,450 results