Conference Papers

Permanent URI for this collectionhttps://idr.nitk.ac.in/handle/123456789/28506

Browse

Author: search.filters.author.Agrawal, S.Has files: No

Search Results

Now showing 1 - 8 of 8
  • No Thumbnail Available
    Item
    Optimized low power low cost pulse oximeter for remote patient monitoring
    (IEEE Computer Society, 2013) Agrawal, N.; Agrawal, S.; Kumar, A.; Ramesh Kini, R.M.
    Pulsoximeter is a medical instrument for monitoring the blood oxygenation of a patient. This type of monitoring is especially useful for new born infants, during surgery and in determining Hypoxia. Blood oxygen content is an important indicator of human patient health and during anaesthesia. This aspect can be monitored by measuring the oxygen percentage in the blood timely and accurately with the help of our device. As our device is non invasive it proves out to be comfortable for the new born. Our slight modification to the standard approach that utilises pulse oximeter or Photoplethysmograph for this purpose, assures considerable decrease in current consumption thereby reducing overall power consumption which makes our device a low power device that can be used with much ease at places where power consumption is an issue. Patient's health parameters can be continuously monitored over a low power wireless network which aids in mobile monitoring. © 2013 IEEE.
  • No Thumbnail Available
    Item
    Blockchain based Framework for Student Identity and Educational Certificate Verification
    (Institute of Electrical and Electronics Engineers Inc., 2021) Chowdhary, A.; Agrawal, S.; Rudra, B.
    With the rise in digitization of documents stored online, it is important to have a document verification process. It involves customized verification and authentication of a document based on the content of the document. Among all the certificates, the educational certificate is one of the most important certificates, especially for students. Unfortunately, it is very easy to fake documents that are hard to identify nowadays and are often considered original. Blockchain has recently emerged as a potential alternative to manual verification of certificates. It provides a distributed ledger that is verifiable with cryptographic mechanisms. Also, it provides a common platform for easily sharing, storing, and accessing documents. The identity of the students can be verified using government authorized identity proofs. This paper proposes the use of such unique identity number and secret phrase provided by the student to further improve the security of the certificate verification system. The student's identity and document are both verified by matching the hashes already present in the Blockchain. Also, in the proposed method the documents are linked to the student to add another layer of verification. The implementation of this proposed platform can be used to issue, receive and verify the certificates. © 2021 IEEE.
  • No Thumbnail Available
    Item
    Machine Learning based COVID-19 Mortality Prediction using Common Patient Data
    (Institute of Electrical and Electronics Engineers Inc., 2022) Agrawal, S.; Patil, N.
    COVID-19 was declared a pandemic in 2020, and it caused havoc worldwide. The fact that it is unpredictable adds to its lethality. The world has already seen various COVID-19 infection waves, subsequent waves being even more deadly. Many patients are asymptomatic initially but suddenly develop breathing problems. More than four million people have died due to COVID-19. It is necessary to forecast a patient's likelihood of dying so that appropriate precautions can be implemented. In this study, a COVID-19 mortality prediction model which uses machine learning is proposed. Most of the current research work requires several patient features and lab test results to predict mortality. However, we suggest a simpler and more efficient technique that relies solely on X-rays and basic patient information such as age and gender. Several ensemble-based models were evaluated and compared using a variety of metrics, and the best method was able to achieve a classification accuracy of 92.6% and AUPRC of 0.95. © 2022 IEEE.
  • No Thumbnail Available
    Item
    Linear Voltage Amplifier for High Voltage Applications
    (Institute of Electrical and Electronics Engineers Inc., 2022) Nithin Reddy, G.N.; Iyer, S.R.; Agrawal, S.; Reddy B, S.
    High voltage measurements require precision high voltage instruments for dielectric measurements and for other high voltage applications. The present work requires linear, high voltage, and high-frequency bandwidth supply, which must be precisely monitored and controlled. High voltage engineers crave automated control of supply through safer control techniques. The paper presents a high voltage supply used as a linear high voltage amplifier that amplifies the low voltage input of ±5 V with a gain of 40 per unit this is obtained using TINA software. The novel linear high-voltage amplifier circuit proposed will be useful for insulation measurements, electrostatic applications, dielectric measurements, and other industrial applications. An attempt is made to develop the hardware for the proposed amplifier. © 2022 IEEE.
  • No Thumbnail Available
    Item
    Seismic Image Retrieval and Classification with Novel Slice Shuffling Data Augmentation
    (Institute of Electrical and Electronics Engineers Inc., 2024) Gowhar, S.G.; Agrawal, S.; Reddy, M.S.; Anand Kumar, M.
    This paper introduces a framework for automating the analysis of seismic images, which is essential for geological studies. Leveraging the intersection of Computer Vision and Geology, it addresses the scarcity of automated solutions in this domain. Developed within the Reflection Connection challenge, the framework facilitates query-based retrieval of seismic images and identifying structural features. Techniques such as fine-tuning pre-trained architectures and employing one-shot classification methods were explored. Additionally, a novel data augmentation method, Slice Shuffling Augmentation for Geological features that enhanced the model performance was developed. © 2024 IEEE.
  • No Thumbnail Available
    Item
    Speech de-identification data augmentation leveraging large language model
    (Institute of Electrical and Electronics Engineers Inc., 2024) Dhingra, P.; Agrawal, S.; Veerappan, C.S.; Ho, T.N.; Chng, E.S.; Tong, R.
    This work addresses the challenge of limited real-world speech data in speech de-identification, the process of removing Personally Identifiable Information (PII). We formulate speech de-identification as a named entity recognition (NER) task specifically for spoken English. To overcome data scarcity and enhance NER performance, we propose a data augmentation approach. This approach leverages a large language model to generate synthetic speech style text data enriched with diverse PII entities. The generated data undergoes an iterative process using a customized NER model for semi-automatic PII annotation. Our analysis demonstrates the effectiveness of this data augmentation strategy in significantly improving NER performance on spoken language text. Furthermore, to gain deeper insights into the specific errors made during NER, we employ performance analysis using alternative evaluation metrics. © 2024 IEEE.
  • No Thumbnail Available
    Item
    Enhancing Speech De-Identification with LLM-Based Data Augmentation
    (Institute of Electrical and Electronics Engineers Inc., 2024) Dhingra, P.; Agrawal, S.; Veerappan, C.S.; Chng, E.S.; Tong, R.
    This paper addresses the challenge of data scarcity in speech de-identification by introducing a novel, fully automated data augmentation method leveraging large language models. Our approach overcomes the limitations of human annotation, enabling the creation of extensive training datasets. To enhance de-identification performance, we compare pipeline and end-to-end models. While the pipeline approach sequentially applies speech recognition and named entity recognition, the end-to-end model jointly learns these tasks. Experimental results demonstrate the effectiveness of our data augmentation strategy and the superiority of the end-to-end model in improving PII detection accuracy and robustness. © 2024 IEEE.
  • No Thumbnail Available
    Item
    Enhanced Conditional Random Field Models for Cause and Effect Detection in Financial Documents
    (Institute of Electrical and Electronics Engineers Inc., 2024) Agrawal, S.; Phadatare, A.; Anand Kumar, M.
    This paper addresses the Financial Document Causality Detection Task (FinCausal-2023), aiming to uncover the intricate causal relationships embedded in financial texts. The methodology proposed incorporates diverse natural language processing techniques, including Word2Vec embeddings, BERT embeddings, contextual encoding with BERT, token classification using SVM, and Conditional Random Fields (CRF). The study proposes a novel method to enhance the performance of CRFs using features created from a contextual based classification model and compares the same with the SOTA methods. Evaluation metrics, including precision, recall, F1-score, and an exact match percentage, assess the effectiveness of the proposed methodologies.The literature review section provides insights into previous work in financial causality detection, covering shared tasks, and models such as sequence labeling, etc. The paper concludes with results presented and a discussion of their implications, contributing to the ongoing discourse on causality detection in financial narratives. © 2024 IEEE.