scholarly journals From microstructural images to properties - an interpretable deep learning approach to predict elastic-plastic properties of fiber composites

2021 ◽  
Author(s):  
Sathiskumar Anusuya Ponnusami
Keyword(s):  
Deep Learning ◽  
Volume Fraction ◽  
Training Dataset ◽  
Learning Approach ◽  
Plastic Properties ◽  
Elastic Plastic ◽  
Materials Engineering ◽  
Fully Connected ◽  
Unidirectional Fibre ◽  
Single Regression

The application of machine learning in the field of materials engineering can facilitate materials design and enable faster discovery of novel materials. This paper presents a deep learning approach for the prediction of the transverse elastic and plastic properties of unidirectional fibre reinforced composites directly from images of their microstructures. The training dataset consists of finite element predictions of the elastic-plastic properties of a set of 2D representative volume elements of unidirectional composites with different volume fraction and fiber diameter. Single-regression, Fully-connected Neural Networks (FcNNs) and a multi-regression Convolutional Neural Network (CNN) are designed and trained to predict 5 mechanical properties, using as input the images of the material’s microstructure. The performance of the FcNNs and of the CNN are compared; the CNN is shown to perform the most effective regression, predicting the properties of the composites with an accuracy of 99%. A key value addition in this research lies in the explainability of the otherwise ‘blackbox’ CNN model, guiding the reader through the model’s predictive process. We test the CNN on real, relatively low-resolution micrographs of composite microstructures and we find that this provides accurate predictions.

scholarly journals Analyses and Modeling of Neural Machine Translation for English-to-Khasi

2020 ◽  
Vol 9 (2) ◽  
pp. 115-118
Keyword(s):  
Deep Learning ◽  
Machine Translation ◽  
Statistical Machine Translation ◽  
Language Barrier ◽  
Attention Mechanism ◽  
Training Dataset ◽  
Learning Approach ◽  
Neural Machine Translation ◽  
Community Or ◽  
North East

Language barrier is a common issue faced by humans who move from one community or group to another. Statistical machine translation has enabled us to solve this issue to a certain extent, by formulating models to translate text from one language to another. Statistical machine translation has come a long way but they have their limitations in terms of translating words that belongs to an entirely different context that is not available in the training dataset. This has paved way for neural Machine Translation (NMT), a deep learning approach in solving sequence to sequence translation. Khasi is a language popularly spoken in Meghalaya, a north-east state in India. Its wide and unexplored. In this paper we will discuss about the modeling and analyzing of a NMT base model and a NMT model using Attention mechanism for English to Khasi.

scholarly journals Deep Learning-Based Question Answering System for Intelligent Humanoid Robot

2020 ◽  
Author(s):  
Widodo Budiharto ◽  
Vincent Andreas ◽  
Alexander Agung Santoso Gunawan
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Humanoid Robot ◽  
Question Answering ◽  
Training Dataset ◽  
Learning Approach ◽  
Exact Match ◽  
Learning Capability ◽  
Question Answering Systems ◽  
Self Learning

Abstract The development of intelligent Humanoid Robot focuses on question answering systems to be able to interact with people is very rare. In this research, we would like to propose a Humanoid Robot with the self-learning capability for accepting and giving a response from people based on Deep Learning and big data from the internet. This kind of robot can be used widely in hotels, universities and public services. The Humanoid Robot should consider the style of questions and conclude the answer through conversation between robot and user. In our scenario, the robot will detect the user’s face and accept commands from the user to do an action, where the question from the user will be processed using deep learning, and the result will be compared with knowledge on the system. We proposed our deep learning approach, based on use GRU/LSTM, CNN and BiDAF with big data SQuAD as training dataset. Our experiment indicates that using GRU/LSTM encoder with BiDAF gives higher Exact Match and F1 Score, than CNN with the BiDAF model.

Experimental Observation of the Effect of Crystallographic Orientation on Mechanical Behavior of Single Crystal Cu6Sn5 Intermetallic

2013 ◽  
Author(s):  
Soud Farhan Choudhury ◽  
Leila Ladani
Keyword(s):  
Heat Dissipation ◽  
Solder Joints ◽  
Volume Fraction ◽  
Electron Backscatter Diffraction ◽  
Strain Hardening Exponent ◽  
Analysis Model ◽  
Creep Ductility ◽  
Plastic Properties ◽  
Elastic Plastic ◽  
Large Volume Fraction

Solder joints in electronic packages and devices serve as mechanical and electrical connections as well as thermal paths for heat dissipation. Due to the miniaturization of electronic packaging, nowadays solder joints contain large volume fraction of IMCs. It has been observed that solder joint strength is controlled largely by intermetallic strength at higher strain rate. Macroscopic properties such as tensile and shear strength, creep, ductility depend on Intermetallic layer’s properties of solder joints. This study is carried out to determine elastic-plastic properties of Cu6Sn5 intermetallic in Sn-3.5Ag/Cu system with reflow soldering by nanoindentation. Elastic properties such as elastic modulus and hardness were determined from the load-depth curve. A widely used reverse analysis model described by Dao et al. [1] was considered to extract plastic properties such as yield strength and strain hardening exponent using nanoindentation results. Anisotropy of Cu6Sn5 was taken into consideration to see if that has any effect on the mechanical properties. Our study considered crystallographic grain orientation along normal to the growth axis of Cu6Sn5 IMC which was extracted using Electron backscatter diffraction (EBSD) mapping. Statistically indistinguishable properties were observed for Cu6Sn5 IMC. Average elastic-plastic properties of Cu6Sn5 were than compared with already published results in literatures.

scholarly journals Computational Offloading in Mobile Edge with Comprehensive and Energy Efficient Cost Function: A Deep Learning Approach

Sensors ◽  
2021 ◽  
Vol 21 (10) ◽  
pp. 3523
Author(s):  
Ziaul Haq Abbas ◽  
Zaiwar Ali ◽  
Ghulam Abbas ◽  
Lei Jiao ◽  
Muhammad Bilal ◽  
...  
Keyword(s):  
Deep Learning ◽  
Energy Consumption ◽  
Cost Function ◽  
Energy Efficient ◽  
Training Dataset ◽  
Learning Approach ◽  
Service Delay ◽  
Division Process ◽  
Computational Offloading ◽  
The Cost

In mobile edge computing (MEC), partial computational offloading can be intelligently investigated to reduce the energy consumption and service delay of user equipment (UE) by dividing a single task into different components. Some of the components execute locally on the UE while the remaining are offloaded to a mobile edge server (MES). In this paper, we investigate the partial offloading technique in MEC using a supervised deep learning approach. The proposed technique, comprehensive and energy efficient deep learning-based offloading technique (CEDOT), intelligently selects the partial offloading policy and also the size of each component of a task to reduce the service delay and energy consumption of UEs. We use deep learning to find, simultaneously, the best partitioning of a single task with the best offloading policy. The deep neural network (DNN) is trained through a comprehensive dataset, generated from our mathematical model, which reduces the time delay and energy consumption of the overall process. Due to the complexity and computation of the mathematical model in the algorithm being high, due to trained DNN the complexity and computation are minimized in the proposed work. We propose a comprehensive cost function, which depends on various delays, energy consumption, radio resources, and computation resources. Furthermore, the cost function also depends on energy consumption and delay due to the task-division-process in partial offloading. None of the literature work considers the partitioning along with the computational offloading policy, and hence, the time and energy consumption due to task-division-process are ignored in the cost function. The proposed work considers all the important parameters in the cost function and generates a comprehensive training dataset with high computation and complexity. Once we get the training dataset, then the complexity is minimized through trained DNN which gives faster decision making with low energy consumptions. Simulation results demonstrate the superior performance of the proposed technique with high accuracy of the DNN in deciding offloading policy and partitioning of a task with minimum delay and energy consumption for UE. More than 70% accuracy of the trained DNN is achieved through a comprehensive training dataset. The simulation results also show the constant accuracy of the DNN when the UEs are moving which means the decision making of the offloading policy and partitioning are not affected by the mobility of UEs.

Comparison of various Activation Functions A Deep Learning Approach

2018 ◽  
Vol 6 (3) ◽  
pp. 122-126
Author(s):  
Mohammed Ibrahim Khan ◽  
◽  
Akansha Singh ◽  
Anand Handa ◽  
◽  
...  
Keyword(s):  
Deep Learning ◽  
Learning Approach ◽  
Activation Functions

A Deep Learning based Arabic Script Recognition System: Benchmark on KHAT

2020 ◽  
Vol 17 (3) ◽  
pp. 299-305 ◽  
Author(s):  
Riaz Ahmad ◽  
Saeeda Naz ◽  
Muhammad Afzal ◽  
Sheikh Rashid ◽  
Marcus Liwicki ◽  
...  
Keyword(s):  
Deep Learning ◽  
Character Recognition ◽  
Data Augmentation ◽  
Short Term Memory ◽  
Recognition System ◽  
Learning Approach ◽  
Arabic Text ◽  
Data Set ◽  
Processing Step ◽  
Handwritten Arabic

This paper presents a deep learning benchmark on a complex dataset known as KFUPM Handwritten Arabic TexT (KHATT). The KHATT data-set consists of complex patterns of handwritten Arabic text-lines. This paper contributes mainly in three aspects i.e., (1) pre-processing, (2) deep learning based approach, and (3) data-augmentation. The pre-processing step includes pruning of white extra spaces plus de-skewing the skewed text-lines. We deploy a deep learning approach based on Multi-Dimensional Long Short-Term Memory (MDLSTM) networks and Connectionist Temporal Classification (CTC). The MDLSTM has the advantage of scanning the Arabic text-lines in all directions (horizontal and vertical) to cover dots, diacritics, strokes and fine inflammation. The data-augmentation with a deep learning approach proves to achieve better and promising improvement in results by gaining 80.02% Character Recognition (CR) over 75.08% as baseline.

Sign in / Sign up

Export Citation Format

Share Document