(SoE) School of Engineering

<p>Shiv Nadar University is a comprehensive, multidisciplinary, research-focused, and student-centric University offering a full range of academic programs at the undergraduate, postgraduate and doctoral level. With state-of-the-art infrastructure, the University comprises of academic wings, sophisticated labs, international standard sports facilities, amphitheaters, auditorium, conference rooms and smart classrooms. The University&rsquo;s goal is to become internationally recognized for the quality of its research and creative endeavors and their applicability to improving quality of life, generating new insights and expanding the boundaries of human knowledge creativity. Committed to excellence in teaching, research and service, the University aims to serve the higher education needs of India and the world beyond.</p>

Shiv Nadar University

Cognitive/mental task classification using single/limited channel(s) electroencephalogram (EEG) signals in real-time play an important role in designing portable brain-computer interface (BCI) and neurofeedback (NFB) systems. However, real-time recorded EEG signals are often contaminated with ocular artifacts (OAs) and muscle artifacts (MAs), which deteriorate the hand-crafted features extracted from EEG signal, resulting inadequate classification of cognitive tasks. Therefore, we investigate the use of deep learning techniques which do not require manual feature extraction or artifact suppression. In this paper, we propose a shallow one-dimensional convolutional neural network (1D-CNN) architecture for cognitive task classification. The robustness of the proposed architecture is evaluated using artifact-free and artifact-contaminated EEG signals taken from two publicly available databases (i.e, Keirn and Aunon (K) database and EEGMAT (E) database) and in-house (R) database recorded using single-channel device in performing not only cognitive/non-cognitive binary task classification but also cognitive/cognitive multi-tasks classification. Evaluation results demonstrate that the proposed architecture achieves the highest subject-independent classification accuracy of 99.70% and 100.00% for multi-class classification and pair-wise classification respectively in database K. Further, subject-independent classification accuracies of 99.00% and 98.00% are achieved in databases E and R respectively. Comparative performance analysis demonstrates that the proposed architecture outperforms existing approaches not only in terms of classification accuracy but also in robustness against artifacts. © 2022 Elsevier Ltd

World University root node

Electrical Engineering

Fulltext

Biomedical Signal Processing and Control

One-dimensional convolutional neural network architecture for classification of mental tasks from electroencephalogram

A hybrid computational fluid dynamics-artificial neural network approach is implemented to predict the thermo-hydraulic performance factor of a solar air heater with rotating circular ribs. Effects of rib height, rib pitch, and rib rotating speed are investigated for Reynolds numbers ranging from 3800 to 18000. A total of 432 different cases are simulated using CFD. Based on these data sets, an optimized ANN model is developed to predict thermo-hydraulic performance. The optimized ANN model has an architecture of 4-17-17-1 and it has a mean squared error of 3.89 × 10−6 for the testing data sets. The maximum thermo-hydraulic performance achieved is 1.57 for rib height of 1.4 mm, rib pitch of 25 mm, rib rotating speed of 10000 rpm at Reynolds number = 3800. The generalization capacity of the optimized ANN model is tested using experimental results and it is found that ANN predictions are in agreement with CFD simulation results. A comparison of computational time is also performed and approximately 100% reduction in computational time is achieved using the optimized artificial neural network model. This research establishes that ANN can be an excellent design tool for assessing the performance of novel solar air heaters. © 2022 The Author(s)

Mechanical Engineering

Energy Reports

Solar air heater with rotating circular ribs: Hybrid CFD-ANN approach for prediction of thermo-hydraulic performance

This article is intended to study the bending and vibration response of the exponentially graded FGM plate using the closed-form solution. The governing equations of motions are formulated on the basis of Hamilton's principle, whereas the Navier method has been used to solve the governing equation with simply supported boundary conditions. The results have been validated for non-dimensional deflection values of a square plate subjected to transverse loading. Apart from these, the exponential gradation model has been considered for calculating the effective material properties of a functionally graded plate and its mechanical properties are assumed to vary in the thickness direction. Bending analysis and non-dimensional frequency has been evaluated for various modes of vibration of functionally graded thin and thick plates. © 2022, Springer Nature Singapore Pte Ltd.

Lecture Notes in Mechanical Engineering

Bending and Free Vibration Analysis of Exponential Graded FG Plate Using Closed-Form Solution

In this paper, a low-cost gain switchable antenna system operating at 28 GHz is proposed for 5G applications. The antenna system consists of a 3×1 element series fed array antenna on one side and a single inset fed patch antenna on the opposite side on same substrate. The proposed antenna has a compact size with overall dimensions of 38.76mm x 6.83mm x 0.66mm. A low-cost flexible polycarbonate of 500μm thickness and relative permittivity, ϵr of 2.9 is used as substrate. The simulated and measured results are presented. The proposed antenna system can be integrated with modern 5G smartphones. © 2022 IEEE.

2022 IEEE Region 10 Symposium, TENSYMP 2022

Low-Cost Gain Switchable Antenna System for 5G Smartphones

Two-dimensional thin structural elements, such as plates, shells, and membranes, are used to introduce pre-stress while loading. Lateral vibrations and elastic stability are very common problems associated with thin-walled industrial structures, posing a high risk of structural failure in the buckling mode. This paper aims to test the possibility of detecting bucking failure of steel plates utilising vibration response obtained from surface-bonded lead zirconate titanate (PZT) patches and the global vibration and electromechanical impedance (EMI) approach. Experimental proof-of-concept testing is carried out on elastically constrained flat plates in the form of steel columns. The plates are loaded under compression till the onset of the buckling phenomenon. In addition, the test specimens are subjected to both EMI and global vibration techniques, in order to find critical buckling parameters for thin structural elements. While structural instability creeps into the system, the fundamental frequencies of global vibrations are calibrated and compared to see whether there is any shift. It is found that both the PZT-based low-frequency global vibration and the EMI technique are capable to detect the buckling prognosis, though the former technique is more expedient. This study also included the arrangement of pin-pin end connection through an experimental setup to yield the thin plate buckling. The sensor results for the Global vibration technique and Electro-mechanical impedance (EMI) technique are satisfactory for the pin-pin connection. © 2022, Springer Nature Switzerland AG.

Civil Engineering

Innovative Infrastructure Solutions

Vibration-based pre-emptive detection of plate buckling using piezo-transducers

The recent application of deep learning for structural health monitoring systems for damage detection has potential for improvised structure performance and maintenance for long term durability, and reliable strength. Advancements in electro-mechanical impedance (EMI) techniques have sparked attention among researchers to develop novel monitoring techniques for structural monitoring and evaluation. This study aims to determine the performance of EMI techniques using a piezo sensor to monitor the development of bond strength in reinforced concrete through a pull-out test. The concrete cylindrical samples with embedded steel bars were prepared, cured for 28 days, and a pull-out test was performed to measure the interfacial bond between them. The piezo coupled signatures were obtained for the PZT patch bonded to the steel bar. The damage qualification is performed through the statistical indices, i.e., root-mean-square deviation (RMSD) and correlation coefficient deviation metric (CCDM), were obtained for different displacements recorded for axial pull. Furthermore, this study utilizes a novel Convolutional Neural Network-Long Short-Term Memory (CNN-LSTM)-based hybrid model, an effective regression model to predict the EMI signatures. These results emphasize the efficiency and potential application of the deep learning-based hybrid model in predicting EMI-based structural signatures. The findings of this study have several implications for structural health diagnosis using a deep learning-based model for monitoring and conservation of building heritage. © 2022 by the authors.

Sensors

A Novel CNN-LSTM Hybrid Model for Prediction of Electro-Mechanical Impedance Signal Based Bond Strength Monitoring

A hybrid computational fluid dynamics-artificial neural network approach is applied to predict the thermo-hydraulic performance factor (THPF) of a solar air heater with vertical cylindrical ribs. 3-D CFD analysis considering effects of rib height, rib diameter, rib pitches are simulated for Re ranging 5000–24000. A total of 504 data sets for different cases are generated using CFD. Based on these data sets, an optimized ANN model is developed to predict the thermo-hydraulic performance. The optimized ANN model has an architecture of 5-25-1 and the mean squared error for this ANN model is 0.000051 for the testing data sets. The maximum THPF value achieved is 1.43 for rib height of 3.5 mm, rib diameter of 3 mm, rib transverse pitch of 20 mm and relative roughness pitch of 10 at Re = 8000. Global sensitivity analysis is also performed based on SHAP (SHapley Additive exPlanations) for the ANN model—Reynolds number is observed to be the most influencing factor with mean absolute SHAP value of 0.031 in predicting THPF along with transverse pitch which has SHAP value very close to Re. Computational CPU time comparison is also performed and approximately 100% reduction is achieved using the optimized ANN model. This research proposed a novel approach that could be successfully implemented in assessing thermal performance of solar-thermal collector systems. © 2022 The Author(s)

ANN model for prediction of thermo-hydraulic performance of a solar air heater with vertical cylindrical ribs

The present article investigates the effect of cutouts, porosity inclusion, and hygro-thermal environment on the vibrational characteristics of sandwich functionally graded material (FGM) plates resting on Pasternak elastic foundation. The governing equations for the sandwich FGM plates have been developed using the finite element method (FEM) with the conjunction of non-polynomial-based higher-order shear deformation theory (HSDT). The trigonometric shear-strain shape function has been used for the first time for sandwich FGM plates. The effective material properties with porosity inclusions have been computed using modified power–law distribution. The present results have been acquired by employing a C0 continuity isoparametric finite element (FE), using 4-noded elements with 7-DOF's per node. The accuracy of the current solution has been confirmed by convergence and validation studies. The influence of circular cutout, elastic foundations, hygro-thermal conditions, and geometric and boundary conditions on the vibrational frequency of porous sandwich FGM plates have been discussed in detail. © 2022 Taylor & Francis Group, LLC.

Mechanics Based Design of Structures and Machines

Influence of circular cutouts and elastic foundation on vibration characteristics of porous sandwich FGM plates under hygro-thermal environments

Very large scale integration (VLSI)-based neuromorphic systems have been evolving quickly in recent years. These systems have been used in complex cognitive tasks such as image classification and pattern recognition. A neuromorphic encoder is an essential component in a neuromorphic system, which converts sensory data into spike trains. The advancement in CMOS technology nodes leads to various reliability issues. Bias temperature instability (BTI) and hot carrier injection (HCI) are major reliability issues in analog/mixed VLSI circuits. This paper implements a temporal neuromorphic encoder, and a corresponding mathematical model is derived for image processing applications. The relationship between an input image pixel value and output of the encoder, that is, interspike interval (ISI), is found to be exponential. The impact of BTI and HCI on the temporal neuromorphic encoder is analyzed. The degradation analysis revealed a loss of encoding functionality for which three mitigation techniques are discussed. Finally, a reliability-aware neuromorphic encoder is proposed to minimize the effect of degradation over its lifetime. The power consumption of conventional and proposed reliability-aware neuromorphic encoders is also presented. © 2021 John Wiley & Sons, Ltd.

International Journal of Circuit Theory and Applications

Reliability-aware design of temporal neuromorphic encoder for image recognition

Assigning the right task to the right worker remains a challenge to an assembly line manager. This work is proposed to use digital-twin technologies for Assembly line worker assignment and balancing problems (ALWABP) for a collaborative assembly system. Applications of the Internet of Things, Data analytics and Learning algorithms are proposed to estimate the worker's work skill and task performance. Assembly line Digital Twin and collaborative robot (CoBot) work simulation tools are proposed to estimate the CoBot's assembly task performing ability and execution time. ALWABP framework is proposed to optimize the work allocation between the worker and the CoBot. Assembly line digital twin is furthermore proposed to simulate the ALWABP output during the decision-making process of the assembly line manager by considering the Human-in-the-loop decision-making system. Copyright © 2022 The Authors. This is an open access article under the CC BY-NC-ND license.