Browsing by Author "Ravi, S."

Filter results by typing the first few letters
Now showing 1 - 6 of 6
  • No Thumbnail Available
    Item
    Effect of Surface Topography and Roughness on the Wetting Characteristics of an Indigenously Developed Green Cutting Fluid (GCF)
    (CRC Press, 2023) Edachery, V.; Ravi, S.; Badiuddin, A.F.; Tomy, A.; Suvin, P.S.; Kailas, S.V.
    The production of cutting fluids from petroleum-based products has resulted in significant improvements in the current and rising machining sector. However, the majority of cutting fluids are costly, harmful, and unsustainable mineral base oils. A vital concern lies in their improper disposal, as it can cause pollution of groundwater, as well as pollute agro-based farm products. To counter these hazardous effects, the synthesis of an eco-friendly alternative was crucial. By mixing nontoxic emulsifiers and natural ingredients, a coconut oil-based Green Cutting Fluid (GCF) was created. Many of the defining requirements of commercial formulations are satisfied by GCF while yet being ecologically friendly. This study’s goal is to determine how surface topography and roughness affect the GCF’s ability to wet surfaces made of EN31 steel, titanium alloy Ti6Al4V, and aluminum alloy AA5052. Also, experiments are conducted to determine an optimum concentration of usage of the GCF for the aforementioned surfaces. The findings provide strong, clear proof that the GCF is a practical, long-term replacement for mineral oil-based cutting fluids for its superior wetting qualities and advantages for the environment. © 2024 selection and editorial matter Ravi Kant, Hema Gurung and Shashikant Yadav; individual chapters, the contributors.
  • No Thumbnail Available
    Item
    Image in-painting techniques - A survey and analysis
    (2013) Ravi, S.; Pasupathi, P.; Muthukumar., S.; Krishnan, N.
    Digital in-painting is relatively a young research area, yet a large variety of techniques were proposed by the researchers to correct the occlusion. Image in-painting aims to restore images with partly information loss and tries to make in-painting results as these missing parts in such a way that the reconstructed image looks natural. Many different types of image in-painting algorithms exist in the literature. However no recent study has been undertaken for a comparative evaluation of these algorithms to provide a comprehensive visualization. This paper compares different types of image in-painting algorithms. The algorithms are analyzed in both theoretical and experimental ways, which have made the suitability of these image in-painting algorithms over different kinds of applications in diversified areas. � 2013 IEEE.
  • No Thumbnail Available
    Item
    LSTM-Attention Architecture for Online Bilingual Sexism Detection
    (CEUR-WS, 2023) Ravi, S.; Kelkar, S.; Anand Kumar, M.
    The paper describes the results submitted by ‘Team-SMS’ at EXIST 2023. A dataset of 6920 tweets for training, 1038 for validation, and 2076 tweets for testing was provided by the task organizers to train and test our models. Our models include LSTM models coupled with attention layers and without attention. For calculation of soft scores according to the task we tried to mimic human performance by taking an average of different machine learning model predictions using Multinomial Naive Bayes, Linear Support Vector Classifier, Multi Layer Perceptron, XGBoost, LSTM using GloVe embeddings, and LSTM using fastText embeddings. We discuss our approach to remove the ambiguity in the labeling process and detailed description of our work. © 2023 Copyright for this paper by its authors.
  • No Thumbnail Available
    Item
    Modified Dual Domain Network for SAR Change Detection
    (Institute of Electrical and Electronics Engineers Inc., 2024) Kevala, V.D.; Ravi, S.; Surya Kaushik, B.N.; Lal, S.
    Synthetic Aperture Radar (SAR) images are utilised for change detection analysis due to their all-weather imaging capabilities. This paper proposes modified dual domain network (MDDNet) for SAR change detection. We introduced the atrous spatial pyramid pooling block to extract multiscale characteristics in the spatial domain. The MDDNet extracts features from both the spatial and frequency domains. The proposed network is trained unsupervised with pre-classification output. The performances of proposed and existing SAR change detection models are evaluated on four bitemporal SAR datasets. The experimental results indicate that the results of proposed MDDNet is better than existing change detection models on four bitemporal SAR dataset. © 2024 IEEE.
  • No Thumbnail Available
    Item
    Multimodal Propaganda Detection in Memes with Tolerance-Based Soft Computing Method
    (Springer Science and Business Media Deutschland GmbH, 2024) Kelkar, S.; Ravi, S.; Ramanna, S.; Anand Kumar, M.
    This paper presents a tolerance-based near sets-based classifier applied to multimodal propaganda detection task using text and image data originating from Memes. Memes on the internet consist of an image superimposed with text and are very popular in social media. They are often used as a part of disinformation campaign whereby social media users are influenced via a number of rhetorical and psychological techniques known as persuasion techniques. The focus of this paper is on a subtask of the SemEval-2024 Multilingual Detection of Persuasion Techniques Competition in Memes to detect the presence or absence of a persuasion technique. We introduce a multimodal Tolerance Near Sets Classifier (MTNSC) trained on a combination of word embeddings (RoBERTa) and pre-trained image features (ResNet and ResNet-Memes) using the competition data. This work extends our earlier work in the Natural Language Processing domain where a tolerance-based near sets-based sentiment classifier was introduced. The proposed MTNSC achieves a macro F1 score of 70.15% and micro-F1 score of 75.33% on the test dataset demonstrating satisfactory performance of TNS-based classifiers in a multimodal setting. Our findings point to the model’s effectiveness when compared to a few leading submissions based on deep learning techniques. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.
  • No Thumbnail Available
    Item
    Wetting behaviour of a Green cutting fluid (GCF); influence of surface roughness and surface energy of AA5052, Ti6Al4V and EN31
    (Elsevier Ltd, 2022) Edachery, V.; Ravi, S.; Badiuddin, A.F.; Tomy, A.; Kailas, S.V.; Suvin, P.S.
    Green Cutting fluids (GCFs) are biodegradable and eco-friendly alternatives that can be employed in metalworking processes. They facilitate better tool service life and surface quality by removing the heat built, reducing coefficients of friction at tool-chip, and tool-work interfaces, flushing away the chip and preventing the formation of Built-up edges (BUEs). Conventionally, mineral oil (MO) based CFs are used, which can cause serious health hazards in humans as well as negatively impact the environment. Sustainable Green-cutting fluids (GCF) were found to be the solution for reducing the issues raised by the MO-based cutting fluids. The GCF used in the present study was synthesized using coconut oil (Cocos Nucifera) as the base, which is a clean, bio-degradable and eco-friendly substitute for petroleum-based mineral oils. This work is focused on experimentally determining the effectiveness of green cutting fluids on surfaces of (Aluminium)AA5052, (Titanium alloy)Ti6AL4V and Steel(EN31) with various surface topographies. In order to do so, the wetting properties were measured by a stable contact angle θ between the solid–liquid surface and the vapour-liquid interface. Wettability responses from the roughened surfaces in the range of 0.06–2.1 µm was evaluated using a profilometer and contact angle goniometer. Results show that the wetting characteristics of GCF are comparable to that of the MO-based CFs and can be a viable alternative, thus reducing the adverse effects on the environment. In conclusion, this study shows the potential of GCFas an alternative to MO-based cutting fluids used in machining operations in the manufacturing industries. © 2022