scispace - formally typeset
Search or ask a question
Author

Akshay Joshi

Bio: Akshay Joshi is an academic researcher. The author has contributed to research in topics: Materials science & Medicine. The author has an hindex of 1, co-authored 3 publications receiving 77 citations.

Papers
More filters
Journal ArticleDOI
TL;DR: The cuckoos behaviour & their egg laying strategy in the nests of other host birds is explained and a proper strategy for tuning the cuckoo search parameters is defined.

127 citations

Journal ArticleDOI
TL;DR: In this paper , the authors propose an approach for unsupervised learning of hyperelastic constitutive laws with physics-consistent deep neural networks, where the absence of stress labels is compensated for by leveraging a physics-motivated loss function based on the conservation of linear momentum to guide the learning process.
Abstract: We propose a new approach for unsupervised learning of hyperelastic constitutive laws with physics-consistent deep neural networks. In contrast to supervised learning, which assumes the availability of stress-strain pairs, the approach only uses realistically measurable full-field displacement and global reaction force data, thus it lies within the scope of our recent framework for Efficient Unsupervised Constitutive Law Identification and Discovery (EUCLID) and we denote it as NN-EUCLID. The absence of stress labels is compensated for by leveraging a physics-motivated loss function based on the conservation of linear momentum to guide the learning process. The constitutive model is based on input-convex neural networks, which are capable of learning a function that is convex with respect to its inputs. By employing a specially designed neural network architecture, multiple physical and thermodynamic constraints for hyperelastic constitutive laws, such as material frame indifference, (poly-)convexity, and stress-free reference configuration are automatically satisfied. We demonstrate the ability of the approach to accurately learn several hidden isotropic and anisotropic hyperelastic constitutive laws - including e.g., Mooney-Rivlin, Arruda-Boyce, Ogden, and Holzapfel models - without using stress data. For anisotropic hyperelasticity, the unknown anisotropic fiber directions are automatically discovered jointly with the constitutive model. The neural network-based constitutive models show good generalization capability beyond the strain states observed during training and are readily deployable in a general finite element framework for simulating complex mechanical boundary value problems with good accuracy.

28 citations

Journal ArticleDOI
TL;DR: In this paper , an unsupervised Bayesian learning framework for discovery of parsimonious and interpretable constitutive laws with quantifiable uncertainties is proposed, where the authors leverage domain knowledge by including features based on existing, both physics-based and phenomenological, constitutive models.

14 citations

Journal ArticleDOI
TL;DR: In this article , a micro-pyramid-decorated wound healing dressing with individualized design and with bio-compatible gelatin methacryloyl to contact the wounded areas is presented.
Abstract: Medical dressings play an important role in the field of tissue engineering owing to their ability to accelerate the process of wound healing. Great efforts have been made to fabricate wound dressings with distinctive features for promoting wound healing. However, most of the current synthesis methods either generate dressings of uniform size or involve complex fabrication techniques, thus limiting their commercialization for the personalized dressings. We report here a dressing, which presents a paradigm shift in the design of the dressing from uniform films to a micro-patterned film. The hypothesis driving the design is the ability of the 3D patterns to provide an efficient transient matrix filling the depth of the wound rather than just providing a barrier and slight re-epithelialization. We demonstrate the use of the digital light processing 3D printing technique to generate micro-pyramid-decorated wound healing dressings with individualized design and with bio-compatible gelatin methacryloyl to contact the wounded areas. In addition to providing better adhesion to the migratory cells, the micro-pyramids also enable covalent conjugation of heparin, providing capability to sequester endogenous growth factors (GFs). Based on these advantages, the developed dressing not only adheres strongly to the wound bed but also promotes the treatment of a rat wound model by utilizing the power of endogenous GFs for tissue regeneration. Thus, it is believed that the developed dressing can break through the limitation of traditional wound treatment and be an ideal candidate for wound healing.

2 citations

Journal ArticleDOI
TL;DR: In this paper , the authors focus on optimizing the flexo process parameters for 40 microns 3-layer polyethylene (PE) film with Blue Nitrocellulose (NC) ink to reduce overall manufacturing cost while maintaining the print quality for diaper application.
Abstract: The flexo process parameters play an important role in ink transfer and will lead to wastage of inks, substrate, solvents and printed stocks if not monitored and controlled. The work focuses on optimizing the flexo process parameters for 40 microns 3-layer polyethylene (PE) film with Blue Nitrocellulose (NC) ink to reduce overall manufacturing cost while maintaining the print quality for diaper application. An experimental design was conducted for the response Ink GSM (grams per square meter), ?E and Print Mottle with factors such as ink viscosity, anilox volume, plate dot shape and substrate opacity. The data was analyzed through Main Effect, Interaction Plot and Analysis of Variance (ANOVA). The regression models were developed for the response to validate the predictive ability of model. The process optimization resulted in reduction of Ink GSM, ?E and Print Mottle by 18%, 52% and 1% respectively. The ink consumption reduced by 18.26% with minimized print defects, thereby reducing the overall manufacturing cost.

2 citations


Cited by
More filters
Journal ArticleDOI
TL;DR: This paper aims to undertake a comprehensive review on meta-heuristic algorithms and related variants which have been applied on PV cell parameter identification and presents some perspectives and recommendations for future development.

212 citations

Journal ArticleDOI
TL;DR: In this paper, an extreme learning machine integrated with cuckoo search algorithm was developed to predict and optimize the process parameters of microwave irradiation-assisted transesterification process conditions.

190 citations

Journal ArticleDOI
TL;DR: Dijkstra ’s Algorithm (DA) is considered a benchmark solution and Constricted Particle Swarm Optimization (CPSO) is found performing better than other meta-heuristic approaches in unknown environments.

92 citations

Journal ArticleDOI
TL;DR: Multiple hybrid machine-learning models were developed to address parameter optimization limitations and enhance the spatial prediction of landslide susceptibility models to confirm the ability of metaheuristic algorithms to improve model performance.
Abstract: In this study, we developed multiple hybrid machine-learning models to address parameter optimization limitations and enhance the spatial prediction of landslide susceptibility models. We created a geographic information system database, and our analysis results were used to prepare a landslide inventory map containing 359 landslide events identified from Google Earth, aerial photographs, and other validated sources. A support vector regression (SVR) machine-learning model was used to divide the landslide inventory into training (70%) and testing (30%) datasets. The landslide susceptibility map was produced using 14 causative factors. We applied the established gray wolf optimization (GWO) algorithm, bat algorithm (BA), and cuckoo optimization algorithm (COA) to fine-tune the parameters of the SVR model to improve its predictive accuracy. The resultant hybrid models, SVR-GWO, SVR-BA, and SVR-COA, were validated in terms of the area under curve (AUC) and root mean square error (RMSE). The AUC values for the SVR-GWO (0.733), SVR-BA (0.724), and SVR-COA (0.738) models indicate their good prediction rates for landslide susceptibility modeling. SVR-COA had the greatest accuracy, with an RMSE of 0.21687, and SVR-BA had the least accuracy, with an RMSE of 0.23046. The three optimized hybrid models outperformed the SVR model (AUC = 0.704, RMSE = 0.26689), confirming the ability of metaheuristic algorithms to improve model performance.

82 citations

Journal ArticleDOI
TL;DR: A systematic review and meta-analysis of the related studies and recent developments on Backtracking search optimisation algorithm and indicates that BSA is statistically superior than the aforementioned algorithms in solving different cohorts of numerical optimisation problems such as problems with different levels of hardness score, problem dimensions, and search spaces.

59 citations