Search

Your search keyword '"Lahoti, Mukund"' showing total 48 results
Start Over Author "Lahoti, Mukund"
48 results on '"Lahoti, Mukund"'

10. TabSynDex: A Universal Metric for Robust Evaluation of Synthetic Tabular Data

Author

Chundawat, Vikram S, Tarun, Ayush K, Mandal, Murari, Lahoti, Mukund, and Narang, Pratik

Subjects
Computer Science - Machine Learning
Abstract

Synthetic tabular data generation becomes crucial when real data is limited, expensive to collect, or simply cannot be used due to privacy concerns. However, producing good quality synthetic data is challenging. Several probabilistic, statistical, generative adversarial networks (GANs), and variational auto-encoder (VAEs) based approaches have been presented for synthetic tabular data generation. Once generated, evaluating the quality of the synthetic data is quite challenging. Some of the traditional metrics have been used in the literature but there is lack of a common, robust, and single metric. This makes it difficult to properly compare the effectiveness of different synthetic tabular data generation methods. In this paper we propose a new universal metric, TabSynDex, for robust evaluation of synthetic data. The proposed metric assesses the similarity of synthetic data with real data through different component scores which evaluate the characteristics that are desirable for ``high quality'' synthetic data. Being a single score metric and having an implicit bound, TabSynDex can also be used to observe and evaluate the training of neural network based approaches. This would help in obtaining insights that was not possible earlier. We present several baseline models for comparative analysis of the proposed evaluation metric with existing generative models. We also give a comparative analysis between TabSynDex and existing synthetic tabular data evaluation metrics. This shows the effectiveness and universality of our metric over the existing metrics. Source Code: \url{https://github.com/vikram2000b/tabsyndex}, Comment: IEEE Transactions on Artificial Intelligence

Published
2022

17. A Feasibility Study on the Potential Usage of Engineered Cementitious Composites in Indian Pavements

Author

Dhaka, Saahil, Lahoti, Mukund, Pranav, Shreyas, di Prisco, Marco, Series Editor, Chen, Sheng-Hong, Series Editor, Vayas, Ioannis, Series Editor, Kumar Shukla, Sanjay, Series Editor, Sharma, Anuj, Series Editor, Kumar, Nagesh, Series Editor, Wang, Chien Ming, Series Editor, Hau, Kong Kian, editor, Gupta, Ashok Kumar, editor, Chaudhary, Sandeep, editor, and Gupta, Tanmay, editor

Published
2023
Full Text
View/download PDF

39. Performance of ternary blended basalt polypropylene fibre reinforced cementitious composite at elevated temperatures

Author

Tangirala, Aniruddha, Rawat, S, and Lahoti, Mukund

Abstract

This paper aims to provide a sustainable alternative to traditional concrete with improved fire resistance. A total of 76 % cement replacement was achieved with ternary blend of flyash (65 %) and silica fume (11 %). Also, Basalt and polypropylene fibres were incorporated to simultaneously improve the ambient and high temperature performance of the cementitious composite. Cylindrical specimens were exposed to elevated temperature between 200 and 800 °C at an interval of 200 °C. The chosen matrix with fibre combination demonstrated excellent resistance against spalling and provided high strength retention up to 600 °C. Remarkable stability against surface cracking was also observed even at the highest exposure temperature. Scanning electron micrographs are further used to corroborate the trend of residual compressive performance.

Published
2023
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results