Deep learning based hybrid sequence modeling for optical response retrieval in metasurfaces for STPV applications

The interpretation of Myocardial Infarction (MI) via electrocardiogram (ECG) signal is a challenging task. ECG signals’ morphological view show significant variation in different patients under different physical conditions. Several learning algorithms have been studied to interpret MI. However, the drawback of machine learning is the use of heuristic features with shallow feature learning architectures. To overcome this problem, a deep learning approach is used for learning features automatically, without conventional handcrafted features. This paper presents sequence modeling based on deep learning with recurrent network for ECG-rhythm signal classification. The recurrent network architecture such as a Recurrent Neural Network (RNN) is proposed to automatically interpret MI via ECG signal. The performance of the proposed method is compared to the other recurrent network classifiers such as Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU). The objective is to obtain the best sequence model for ECG signal processing. This paper also aims to study a proper data partitioning ratio for the training and testing sets of imbalanced data. The large imbalanced data are obtained from MI and healthy control of PhysioNet: The PTB Diagnostic ECG Database 15-lead ECG signals. According to the comparison result, the LSTM architecture shows better performance than standard RNN and GRU architecture with identical hyper-parameters. The LSTM architecture also shows better classification compared to standard recurrent networks and GRU with sensitivity, specificity, precision, F1-score, BACC, and MCC is 98.49%, 97.97%, 95.67%, 96.32%, 97.56%, and 95.32%, respectively. Apparently, deep learning with the LSTM technique is a potential method for classifying sequential data that implements time steps in the ECG signal.

Download Full-text

Deep learning for blocking in entity matching

Proceedings of the VLDB Endowment ◽

10.14778/3476249.3476294 ◽

2021 ◽

Vol 14 (11) ◽

pp. 2459-2472

Author(s):

Saravanan Thirumuruganathan ◽

Han Li ◽

Nan Tang ◽

Mourad Ouzzani ◽

Yash Govind ◽

...

Keyword(s):

Deep Learning ◽

Real World ◽

Simple Form ◽

State Of The Art ◽

Structured Data ◽

Training Data ◽

Entity Matching ◽

Large Space ◽

Sequence Modeling ◽

Textual Data

Entity matching (EM) finds data instances that refer to the same real-world entity. Most EM solutions perform blocking then matching. Many works have applied deep learning (DL) to matching, but far fewer works have applied DL to blocking. These blocking works are also limited in that they consider only a simple form of DL and some of them require labeled training data. In this paper, we develop the DeepBlocker framework that significantly advances the state of the art in applying DL to blocking for EM. We first define a large space of DL solutions for blocking, which contains solutions of varying complexity and subsumes most previous works. Next, we develop eight representative solutions in this space. These solutions do not require labeled training data and exploit recent advances in DL (e.g., sequence modeling, transformer, self supervision). We empirically determine which solutions perform best on what kind of datasets (structured, textual, or dirty). We show that the best solutions (among the above eight) outperform the best existing DL solution and the best existing non-DL solutions (including a state-of-the-art industrial non-DL solution), on dirty and textual data, and are comparable on structured data. Finally, we show that the combination of the best DL and non-DL solutions can perform even better, suggesting a new venue for research.

Download Full-text

Optical Character Recognition using CRNN

International Journal of Innovative Technology and Exploring Engineering - Special Issue ◽

10.35940/ijitee.h6264.069820 ◽

2020 ◽

Vol 9 (8) ◽

pp. 115-120

Keyword(s):

Neural Network ◽

Deep Learning ◽

Character Recognition ◽

Web Application ◽

Optical Character Recognition ◽

Recognition System ◽

Feature Maps ◽

Sequence Modeling ◽

Optical Character ◽

Network Component

Optical Character Recognition (OCR) is a computer vision technique which recognizes text present in any form of images, such as scanned documents and photos. In recent years, OCR has improved significantly in the precise recognition of text from images. Though there are many existing applications, we plan on exploring the domain of deep learning and build an optical character recognition system using deep learning architectures. In the later stage, this OCR system is developed to form a web application which provides the functionalities. The approach applied to achieve this is to implement a hybrid model containing three components namely, the Convolutional Neural Network component, the Recurrent Neural Network component and the Transcription component which decodes the output from RNN into the corresponding label sequence. The process of solving problems involving text recognition required CNN to extract feature maps from images. These sequence of feature vectors undergo sequence modeling through the RNN component predicting label distributions which are later translated using the Connectionist Temporal Classification technique in the transcription layer. The model implemented acts as the backend of the web application developed using the Flask web framework. The complete application is later containerized into an image using Docker. This helps in easy deployment on the application along with its environment across any system.

Download Full-text

A cyclical deep learning based framework for simultaneous inverse and forward design of nanophotonic metasurfaces

Scientific Reports ◽

10.1038/s41598-020-76400-y ◽

2020 ◽

Vol 10 (1) ◽

Author(s):

Abhishek Mall ◽

Abhijeet Patil ◽

Amit Sethi ◽

Anshuman Kumar

Keyword(s):

Genetic Algorithm ◽

Deep Learning ◽

Design Space ◽

Optical Response ◽

Inverse Design ◽

Electromagnetic Response ◽

Design And Optimization ◽

Half Wave ◽

Wide Range ◽

Optimization Mechanism

Abstract The conventional approach to nanophotonic metasurface design and optimization for a targeted electromagnetic response involves exploring large geometry and material spaces. This is a highly iterative process based on trial and error, which is computationally costly and time consuming. Moreover, the non-uniqueness of structural designs and high non-linearity between electromagnetic response and design makes this problem challenging. To model this unintuitive relationship between electromagnetic response and metasurface structural design as a probability distribution in the design space, we introduce a framework for inverse design of nanophotonic metasurfaces based on cyclical deep learning (DL). The proposed framework performs inverse design and optimization mechanism for the generation of meta-atoms and meta-molecules as metasurface units based on DL models and genetic algorithm. The framework includes consecutive DL models that emulate both numerical electromagnetic simulation and iterative processes of optimization, and generate optimized structural designs while simultaneously performing forward and inverse design tasks. A selection and evaluation of generated structural designs is performed by the genetic algorithm to construct a desired optical response and design space that mimics real world responses. Importantly, our cyclical generation framework also explores the space of new metasurface topologies. As an example application of the utility of our proposed architecture, we demonstrate the inverse design of gap-plasmon based half-wave plate metasurface for user-defined optical response. Our proposed technique can be easily generalized for designing nanophtonic metasurfaces for a wide range of targeted optical response.

Download Full-text