2023 International Conference on Smart Systems for applications in Electrical Sciences (ICSSES) Smart Systems for applications in Electrical Sciences (ICSSES), 2023 International Conference on. :1-4 Jul, 2023
Jayadeva, Sujay Mugaloremutt, Prasad Krishnam, Nagendra, Raja Mannar, B., Prakash Dabral, Amar, Buddhi, Dharam, and Garg, Neha
2023 3rd International Conference on Advance Computing and Innovative Technologies in Engineering (ICACITE) Advance Computing and Innovative Technologies in Engineering (ICACITE), 2023 3rd International Conference on. :487-491 May, 2023
Absract The disruptive effects of the Fourth Industrial Revolution (IR4) have the capacity to rapidly alter the course of India's social and economic progress. For the healthcare sector, plagued by poor infrastructure and latency, advances in big data computing and Machine Learning (ML) can have a transformative impact. However, in a socio-political landscape marred by historic hierarchies of exclusion and disparity, the data-driven technology of ML may serve to mechanise and automate social divergence based on class, caste, sex, religion or region. The research frames the issue of medical ML in India as one of lethal biases and data privacy. Through an analysis of the two, the ecosystem of such technology has been brought to light. As instances of bias in ML systems reveal more about social hierarchy and discrimination than they do technological prowess, the dissertation aims to evaluate the ethical dimensions of medical ML in India. Technology is found to not only mediate the actions of individuals but also power dynamics of human and nonhuman actants within the social whole. Notwithstanding the challenges of integrating medical ML in India, the research highlights the ethics of design and the ethics of use to ameliorate the risks of machines with lethal consequences. With a focus on the Indian subaltern,...
Zaki, Mohd, Jayadeva, Mausam, and Krishnan, N. M. Anoop
Computer Science - Computation and Language and Condensed Matter - Materials Science
Information extraction and textual comprehension from materials literature are vital for developing an exhaustive knowledge base that enables accelerated materials discovery. Language models have demonstrated their capability to answer domain-specific questions and retrieve information from knowledge bases. However, there are no benchmark datasets in the materials domain that can evaluate the understanding of the key concepts by these language models. In this work, we curate a dataset of 650 challenging questions from the materials domain that require the knowledge and skills of a materials student who has cleared their undergraduate degree. We classify these questions based on their structure and the materials science domain-based subcategories. Further, we evaluate the performance of GPT-3.5 and GPT-4 models on solving these questions via zero-shot and chain of thought prompting. It is observed that GPT-4 gives the best performance (~62% accuracy) as compared to GPT-3.5. Interestingly, in contrast to the general observation, no significant improvement in accuracy is observed with the chain of thought prompting. To evaluate the limitations, we performed an error analysis, which revealed conceptual errors (~64%) as the major contributor compared to computational errors (~36%) towards the reduced performance of LLMs. We hope that the dataset and analysis performed in this work will promote further research in developing better materials science domain-specific LLMs and strategies for information extraction.
Bishnoi, Suresh, Bhattoo, Ravinder, Jayadeva, Ranu, Sayan, and Krishnan, N M Anoop
Computer Science - Machine Learning, Condensed Matter - Disordered Systems and Neural Networks, Condensed Matter - Materials Science, and Physics - Computational Physics
The time evolution of physical systems is described by differential equations, which depend on abstract quantities like energy and force. Traditionally, these quantities are derived as functionals based on observables such as positions and velocities. Discovering these governing symbolic laws is the key to comprehending the interactions in nature. Here, we present a Hamiltonian graph neural network (HGNN), a physics-enforced GNN that learns the dynamics of systems directly from their trajectory. We demonstrate the performance of HGNN on n-springs, n-pendulums, gravitational systems, and binary Lennard Jones systems; HGNN learns the dynamics in excellent agreement with the ground truth from small amounts of data. We also evaluate the ability of HGNN to generalize to larger system sizes, and to hybrid spring-pendulum system that is a combination of two original systems (spring and pendulum) on which the models are trained independently. Finally, employing symbolic regression on the learned HGNN, we infer the underlying equations relating the energy functionals, even for complex systems such as the binary Lennard-Jones liquid. Our framework facilitates the interpretable discovery of interaction laws directly from physical system trajectories. Furthermore, this approach can be extended to other systems with topology-dependent dynamics, such as cells, polydisperse gels, or deformable bodies.
Sonia, R., Jayadeva, Sujay Mugaloremutt, Ragavendiran, S D Prabu, N, Revathi, Arumugam, Jeevanantham, and Kumar, S Sandeep
2022 6th International Conference on Electronics, Communication and Aerospace Technology Electronics, Communication and Aerospace Technology (ICECA), 2022 6th International Conference on. :432-437 Dec, 2022
Hettiarachchi, Lasal Sandeepa, Jayadeva, Senura Vihan, Bandara, Rusiru Abhisheak Vikum, Palliyaguruge, Dilmi, Arachchillage, Udara Srimath S. Samaratunge, and Kasthurirathna, Dharshana
2022 13th International Conference on Computing Communication and Networking Technologies (ICCCNT) Computing Communication and Networking Technologies (ICCCNT), 2022 13th International Conference on. :1-6 Oct, 2022
education policy, Europe, universities, higher education, media, Students, bic Book Industry Communication::J Society & social sciences::JN Education::JNF Educational strategies & policy, bic Book Industry Communication::J Society & social sciences::JN Education::JNK Organization & management of education::JNKS Students & student organisations, and bic Book Industry Communication::J Society & social sciences::JN Education::JNM Higher & further education, tertiary education
EPDF available Open Access under CC-BY-NC-ND licence. Amid debates about the future of both higher education and Europeanisation, this book is the first full-length exploration of how Europe’s 35 million students are understood by key social actors across different nations. The various chapters compare and contrast conceptualisations in six nations, held by policymakers, higher education staff, media and students themselves. With an emphasis on students’ lived experiences, the authors provide new perspectives about how students are understood, and the extent to which European higher education is homogenising. They explore various prominent constructions of students – including as citizens, enthusiastic learners, future workers and objects of criticism.
Bishnoi, Suresh, Jayadeva, Ranu, Sayan, and Krishnan, N. M. Anoop
Computer Science - Machine Learning and Condensed Matter - Disordered Systems and Neural Networks
Neural networks (NNs) that exploit strong inductive biases based on physical laws and symmetries have shown remarkable success in learning the dynamics of physical systems directly from their trajectory. However, these works focus only on the systems that follow deterministic dynamics, for instance, Newtonian or Hamiltonian dynamics. Here, we propose a framework, namely Brownian graph neural networks (BROGNET), combining stochastic differential equations (SDEs) and GNNs to learn Brownian dynamics directly from the trajectory. We theoretically show that BROGNET conserves the linear momentum of the system, which in turn, provides superior performance on learning dynamics as revealed empirically. We demonstrate this approach on several systems, namely, linear spring, linear spring with binary particle types, and non-linear spring systems, all following Brownian dynamics at finite temperatures. We show that BROGNET significantly outperforms proposed baselines across all the benchmarked Brownian systems. In addition, we demonstrate zero-shot generalizability of BROGNET to simulate unseen system sizes that are two orders of magnitude larger and to different temperatures than those used during training. Altogether, our study contributes to advancing the understanding of the intricate dynamics of Brownian motion and demonstrates the effectiveness of graph neural networks in modeling such complex systems.
Zaki, Mohd, Sharma, Siddhant, Gurjar, Sunil Kumar, Goyal, Raju, Jayadeva, and Krishnan, N. M. Anoop
Computer Science - Computer Vision and Pattern Recognition, Condensed Matter - Materials Science, and Electrical Engineering and Systems Science - Image and Video Processing
Cement is the most used construction material. The performance of cement hydrate depends on the constituent phases, viz. alite, belite, aluminate, and ferrites present in the cement clinker, both qualitatively and quantitatively. Traditionally, clinker phases are analyzed from optical images relying on a domain expert and simple image processing techniques. However, the non-uniformity of the images, variations in the geometry and size of the phases, and variabilities in the experimental approaches and imaging methods make it challenging to obtain the phases. Here, we present a machine learning (ML) approach to detect clinker microstructure phases automatically. To this extent, we create the first annotated dataset of cement clinker by segmenting alite and belite particles. Further, we use supervised ML methods to train models for identifying alite and belite regions. Specifically, we finetune the image detection and segmentation model Detectron-2 on the cement microstructure to develop a model for detecting the cement phases, namely, Cementron. We demonstrate that Cementron, trained only on literature data, works remarkably well on new images obtained from our experiments, demonstrating its generalizability. We make Cementron available for public use.
Due to their disordered structure, glasses present a unique challenge in predicting the composition-property relationships. Recently, several attempts have been made to predict the glass properties using machine learning techniques. However, these techniques have the limitations, namely, (i) predictions are limited to the components that are present in the original dataset, and (ii) predictions towards the extreme values of the properties, important regions for new materials discovery, are not very reliable due to the sparse datapoints in this region. To address these challenges, here we present a low complexity neural network (LCNN) that provides improved performance in predicting the properties of oxide glasses. In addition, we combine the LCNN with physical and chemical descriptors that allow the development of universal models that can provide predictions for components beyond the training set. By training on a large dataset (~50000) of glass components, we show the LCNN outperforms state-of-the-art algorithms such as XGBoost. In addition, we interpret the LCNN models using Shapely additive explanations to gain insights into the role played by the descriptors in governing the property. Finally, we demonstrate the universality of the LCNN models by predicting the properties for glasses with new components that were not present in the original training set. Altogether, the present approach provides a promising direction towards accelerated discovery of novel glass compositions. Comment: 15 pages, 3 figures