LBLaxmi A. Bewoor

Laxmi A. Bewoor

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Laxmi A. Bewoor has a total of 39 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Comparative Performance Analysis of Large and Small Language Models on Text Summarization

    by Naziya Mahimkar, Ratnakar Patil, Laxmi Bewoor, Gopal Deshmukh

  • AUTOMATED DETECTION OF ALZHEIMER’S DISEASE IN EARLY STAGES BY USING ADAPTIVE DEEP CAPSULE NETWORK WITH GRAPH CONVOLUTION NETWORK-BASED FEATURES EXTRACTION ON MULTIMODALITY DATA

    by Virendra V. Bagade, Yashwant V. Dongre, Laxmi Bewoor

    Alzheimer’s Disease (AD) is a neurological condition that affects a large number of people.”Brain atrophy is a result of this neurological condition, which can result in memory loss, cognitive disabilities, and death. In its early stages, AD is difficult to identify. Thus, an early diagnosis and effective treatment of AD are more beneficial and create fewer complexities. AD is a common brain condition that is hard to recognize, and its classification procedures require a biased representation of traits to distinguish similar brain patterns. Multimodal neuro-image integrates numerous clinical images, which assist in identifying and diagnosing AD with better accuracy and effectiveness. Here, an efficient deep learning-based technique is developed to detect AD from“the multi-modal data.”Online resources are used to collect the necessary multimodal data, which includes Magnetic Resonance Imaging (MRI), Positron Emission Tomography (PET), and genetic data in the beginning. In this study, the developed model used 89 affected subjects and 90 healthy control subjects. Then, the collected MRI, PET, and genetic data are fed into the preprocessing stage. Here, genetic data is pre-processed using the data-filling approach. Likewise, the “MRI and PET images are used for the Regions of Interest (ROI) segmentation phase, and it is executed via Dilated TransUNet (DTUNet). To reduce processing time, the ROI segmentation process removes specific regions from MRI and PET images. The pre-processed MRI, PET, and genetic data are passed to the Graph Convolutional Networks (GCNs) to extract the features. From the extracted features, the relevant features are selected using the Enhanced Secretary Bird Optimization (ESBO) algorithm, and this feature is multiplied by the optimal weight selected that is selected using the same ESBO to form the weighted fused features. The final stage involves giving the weighted fused features to the Adaptive Deep CapsNet (ADCapsNet) to diagnose AD. Here, the effectiveness of the ADCapsNet is also enhanced by tuning the parameters using ESBO. Finally, the analysis procedures are executed to prove the proposed framework’s efficiency. In the evaluation, the accuracy of the developed model is 95.17, which is 7.11%, 2.3%, 4.3%, and 1.46% better than “Convolutional Neural Networks (CNNs), Residual Neural Network (ResNet), Visual Geometry Group 16 (VGG-16), and Deep CapsNet (DcapsNet).” The developed approach’s ability to detect AD at an early stage is demonstrated in the experimental outcome, which allows for better planning and improved quality of life for individuals.

  • Open Access

    Deep learning-based classifier for geometric dimensioning and tolerancing symbols

    by Laxmi Bewoor, Anand Bewoor, Pravin P. Hujare, Praveen Rathod, Vedant Yetekar, Shrish Dollin

    This research investigates the recognition of geometric dimensioning and tolerancing (GD&T) symbols using a deep learning model for object detection. GD&T, playing a pivotal role in engineering and manufacturing, provides essential specifications for product design and production. Manual processes for GD&T are often time-consuming and error prone. The study demonstrates outstanding accuracy in automating GD&T symbol recognition in engineering applications using YOLOv8. A carefully curated dataset, encompassing a wide range of GD&T symbols, was employed for training and evaluating the model. The YOLOv8 architecture, renowned for its robust performance, was meticulously fine-tuned to cater to the specific requirements of GD&T symbol detection. This research not only addresses the challenges in manual GD&T processes but also showcases practical implications for improved quality control and streamlined engineering workflows. By automating GD&T symbol recognition, this study contributes to the efficiency and precision crucial in the engineering and manufacturing domains.

  • Open Access

    A multimodal machine learning approach to generate news articles from geo-tagged images

    by Abhay Gotmare, Gandharva Thite, Laxmi Bewoor

    Classical machine learning algorithms typically operate on unimodal data and hence it can analyze and make predictions based on data from a single source (modality). Whereas multimodal machine learning algorithm, learns from information across multiple modalities, such as text, images, audio, and sensor data. The paper leverages the functionalities of multimodal machine learning (ML) application for generating text from images. The proposed work presents an innovative multimodal algorithm that automates the creation of news articles from geo-tagged images by leveraging cutting-edge developments in machine learning, image captioning, and advanced text generation technologies. Employing a multimodal approach that integrates machine learning and transformer algorithms, such as visual geometry group network16 (VGGNet16), convolutional neural network (CNN) and a long short-term memory (LSTM) based system, the algorithm initiates by extracting the location from exchangeable image file format (Exif) data from the image. The features are extracted from the image and corresponding news headline is generated. The headlines are used for generating a comprehensive article with contemporary large language model (LLM). Further, the algorithm generates the news article big-science large open-science open-access multilingual language model (BLOOM). The algorithm was tested on real time photographs as well as images from the internet. In both the cases the news articles generated were validated with ROUGE and BULE score. The proposed work is found to be successful attempt in journalism field.


  • Open Access

    Transformer Based Implementation for Automatic Book Summarization

    by Siddhant Porwal, Laxmi Bewoor, Vivek Deshpande

    Document Summarization is the procedure of generating a meaningful and concise summary of a given document with the inclusion of relevant and topic-important points. There are two approaches: one is picking up the most relevant statements from the document itself and adding it to the Summary known as Extractive and the other is generating sentences for the Summary known as Abstractive Summarization. Training a machine learning model to perform tasks that are time-consuming or very difficult for humans to evaluate is a major challenge. Book Abstract generation is one of such complex tasks. Traditional machine learning models are getting modified with pre-trained transformers. Transformer based language models trained in a self-supervised fashion are gaining a lot of attention; when fine-tuned for Natural Language Processing(NLP) downstream task like text summarization. This work is an attempt to use Transformer based techniques for Abstract generation.

  • Open Access

    Applications of firefly algorithm in hydrology

    by Jatoth Heeraman, Laxmi A. Bewoor, Anand Bewoor, S. Kaliappan, Pravin P. Patil, S. Socrates

    Water management is the sophisticated aspect of the earth in these deteriorating situations. Water is the main source of agriculture and it requires certain monitoring action with the latest techniques. There is a large scope of research for the management of water resources worldwide. Hydrology is still a challenging problem having nonlinear functions with a variety of constraints & decision variables. Heuristic methods were proposed which find an approximate solution in reasonable computation time by selecting the solution from a set of feasible solutions and improving the same by applying heuristic function in a trial and error manner. This study is focused on the application of the Firefly Algorithm (FA) in hydrology. The implementation process of FA is discussed in detail in this chapter. Performance of the original FA can be enhanced by hybridization with other evolutionary/ non-evolutionary tools & techniques. The results of FA are found superior.


  • Open Access

    Fine Tuning Transformer Based BERT Model for Generating the Automatic Book Summary

    by Prottyee Howlader, Prapti Paul, Meghana Madavi, Laxmi Bewoor, V.S. Deshpande

    Major text summarization research is mainly focusing on summarizing short documents and very few works is witnessed for long document summarization. Additionally, extractive summarization is more addressed as compared with abstractive summarization. Abstractive summarization, unlike extractive summarization, does not only copy essential words from the original text but requires paraphrasing to get close to human generated summary. The machine learning, deep learning models are adapted to contemporary pre-trained models like transformers. Transformer based Language models gaining a lot of attention because of self-supervised training while fine-tuning for Natural Language Processing (NLP) downstream task like text summarization. The proposed work is an attempt to investigate the use of transformers for abstraction. The proposed work is tested for book especially as a long document for evaluating the performance of the model.