Search

Your search keyword '"Thiyagarajan, A."' showing total 10,462 results
Start Over Author "Thiyagarajan, A."
10,462 results on '"Thiyagarajan, A."'

1. Guide-LLM: An Embodied LLM Agent and Text-Based Topological Map for Robotic Guidance of People with Visual Impairments

Author

Song, Sangmim, Kodagoda, Sarath, Gunatilake, Amal, Carmichael, Marc G., Thiyagarajan, Karthick, and Martin, Jodi

Subjects
Computer Science - Robotics, Computer Science - Artificial Intelligence, Computer Science - Computation and Language
Abstract

Navigation presents a significant challenge for persons with visual impairments (PVI). While traditional aids such as white canes and guide dogs are invaluable, they fall short in delivering detailed spatial information and precise guidance to desired locations. Recent developments in large language models (LLMs) and vision-language models (VLMs) offer new avenues for enhancing assistive navigation. In this paper, we introduce Guide-LLM, an embodied LLM-based agent designed to assist PVI in navigating large indoor environments. Our approach features a novel text-based topological map that enables the LLM to plan global paths using a simplified environmental representation, focusing on straight paths and right-angle turns to facilitate navigation. Additionally, we utilize the LLM's commonsense reasoning for hazard detection and personalized path planning based on user preferences. Simulated experiments demonstrate the system's efficacy in guiding PVI, underscoring its potential as a significant advancement in assistive technology. The results highlight Guide-LLM's ability to offer efficient, adaptive, and personalized navigation assistance, pointing to promising advancements in this field.

Published
2024

2. Optimizing Disease Prediction with Artificial Intelligence Driven Feature Selection and Attention Networks

Author

Dhinakaran, D., Raja, S. Edwin, Thiyagarajan, M., Jasmine, J. Jeno, and Raghavan, P.

Subjects
Computer Science - Machine Learning, Computer Science - Artificial Intelligence
Abstract

The rapid integration of machine learning methodologies in healthcare has ignited innovative strategies for disease prediction, particularly with the vast repositories of Electronic Health Records (EHR) data. This article delves into the realm of multi-disease prediction, presenting a comprehensive study that introduces a pioneering ensemble feature selection model. This model, designed to optimize learning systems, combines statistical, deep, and optimally selected features through the innovative Stabilized Energy Valley Optimization with Enhanced Bounds (SEV-EB) algorithm. The objective is to achieve unparalleled accuracy and stability in predicting various disorders. This work proposes an advanced ensemble model that synergistically integrates statistical, deep, and optimally selected features. This combination aims to enhance the predictive power of the model by capturing diverse aspects of the health data. At the heart of the proposed model lies the SEV-EB algorithm, a novel approach to optimal feature selection. The algorithm introduces enhanced bounds and stabilization techniques, contributing to the robustness and accuracy of the overall prediction model. To further elevate the predictive capabilities, an HSC-AttentionNet is introduced. This network architecture combines deep temporal convolution capabilities with LSTM, allowing the model to capture both short-term patterns and long-term dependencies in health data. Rigorous evaluations showcase the remarkable performance of the proposed model. Achieving a 95% accuracy and 94% F1-score in predicting various disorders, the model surpasses traditional methods, signifying a significant advancement in disease prediction accuracy. The implications of this research extend beyond the confines of academia., Comment: 16 Pages, 4 Figures

Published
2024
Full Text
View/download PDF

9. BDC Dataset: A Comprehensive Dataset for Automated Build Damage Classification

Author

Zi, Xing, Shi, Yunxiao, Zhu, Taoyuan, Jin, Kairui, Tao, Xian, Li, Jun, Thiyagarajan, Karthick, Prasad, Mukesh, Goos, Gerhard, Series Editor, Hartmanis, Juris, Founding Editor, Bertino, Elisa, Editorial Board Member, Gao, Wen, Editorial Board Member, Steffen, Bernhard, Editorial Board Member, Yung, Moti, Editorial Board Member, Sheng, Quan Z., editor, Dobbie, Gill, editor, Jiang, Jing, editor, Zhang, Xuyun, editor, Zhang, Wei Emma, editor, Manolopoulos, Yannis, editor, Wu, Jia, editor, Mansoor, Wathiq, editor, and Ma, Congbo, editor

Published
2025
Full Text
View/download PDF

11. Empowering Interdisciplinary Research with BERT-Based Models: An Approach Through SciBERT-CNN with Topic Modeling

Author

Likhareva, Darya, Sankaran, Hamsini, and Thiyagarajan, Sivakumar

Subjects
Computer Science - Computation and Language, Computer Science - Machine Learning
Abstract

Researchers must stay current in their fields by regularly reviewing academic literature, a task complicated by the daily publication of thousands of papers. Traditional multi-label text classification methods often ignore semantic relationships and fail to address the inherent class imbalances. This paper introduces a novel approach using the SciBERT model and CNNs to systematically categorize academic abstracts from the Elsevier OA CC-BY corpus. We use a multi-segment input strategy that processes abstracts, body text, titles, and keywords obtained via BERT topic modeling through SciBERT. Here, the [CLS] token embeddings capture the contextual representation of each segment, concatenated and processed through a CNN. The CNN uses convolution and pooling to enhance feature extraction and reduce dimensionality, optimizing the data for classification. Additionally, we incorporate class weights based on label frequency to address the class imbalance, significantly improving the classification F1 score and enhancing text classification systems and literature review efficiency.

Published
2024

12. Automatic Creative Selection with Cross-Modal Matching

Author

Kim, Alex, Huang, Jia, Monarch, Rob, Kwac, Jerry, Kamath, Anikesh, Khurd, Parmeshwar, Thiyagarajan, Kailash, and Gu, Goodman

Subjects
Computer Science - Computer Vision and Pattern Recognition, Computer Science - Information Retrieval
Abstract

Application developers advertise their Apps by creating product pages with App images, and bidding on search terms. It is then crucial for App images to be highly relevant with the search terms. Solutions to this problem require an image-text matching model to predict the quality of the match between the chosen image and the search terms. In this work, we present a novel approach to matching an App image to search terms based on fine-tuning a pre-trained LXMERT model. We show that compared to the CLIP model and a baseline using a Transformer model for search terms, and a ResNet model for images, we significantly improve the matching accuracy. We evaluate our approach using two sets of labels: advertiser associated (image, search term) pairs for a given application, and human ratings for the relevance between (image, search term) pairs. Our approach achieves 0.96 AUC score for advertiser associated ground truth, outperforming the transformer+ResNet baseline and the fine-tuned CLIP model by 8% and 14%. For human labeled ground truth, our approach achieves 0.95 AUC score, outperforming the transformer+ResNet baseline and the fine-tuned CLIP model by 16% and 17%.

Published
2024

18. Infectious etiology of intussusception in Indian children less than 2 years old: a matched case-control analysis

Author

Praharaj, Ira, Reddy, Samarasimha Nusi, Nair, Nayana Prabhakaran, Tate, Jacqueline Elizabeth, Giri, Sidhartha, Thiyagarajan, Varunkumar, Mohan, Venkata Raghava, Revathi, Rajendiran, Maheshwari, Kalaivanan, Hemavathy, Priya, Kumar, Nirmal, Gupte, Mohan Digambar, Arora, Rashmi, Senthamizh, Sowmiya, Mekala, Suhasini, Goru, Krishna Babu, Pamu, Padmalatha, Badur, Manohar, Pradhan, Subal, Dash, Mrutunjay, Mohakud, Nirmal Kumar, Ray, Rajib Kumar, Gathwala, Geetha, Gupta, Madhu, Kanojia, Ravi, Gupta, Rajkumar, Goyal, Suresh, Sharma, Pramod, Mathew, Mannancheril Abraham, Kochukaleekal Jacob, Tarun John, Sundaram, Balasubramanian, Girish Kumar, Chethrapilly Purusothaman, Dorairaj, Priyadarshini, Pitchumani, Ramasubramaniam, Maniam, Raghul, Kumaravel, Sambandan, Jain, Hemant, Goswami, Jayanta Kumar, Wakhlu, Ashish, Gupta, Vineeta, Liu, Jie, Houpt, Eric R., Parashar, Umesh D., and Kang, Gagandeep

Published
2024
Full Text
View/download PDF

23. Impact of the 2008 economic crisis on the burden of hepatitis B and C diseases in Southern European countries

Author

Palladino, Claudia, Ramis, Rebeca, Ezeonwumelu, Ifeanyi Jude, Biondi, Antonio, Carreras, Giulia, Fischer, Florian, Gallus, Silvano, Golinelli, Davide, Gorini, Giuseppe, Hassan, Shoaib, Kabir, Zubair, Koyanagi, Ai, Lazarus, Jeffrey V., Mentis, Alexios-Fotios A., Meretoja, Tuomo J., Mokdad, Ali H., Monasta, Lorenzo, Mulita, Francesk, Postma, Maarten J., Tabarés-Seisdedos, Rafael, Thiyagarajan, Arulmani, Taveira, Nuno, and Briz, Verónica

Published
2024
Full Text
View/download PDF

31. Evaluating Enterprise Architecture Frameworks for Digital Transformation in Agriculture

Author

Kalaiarasi Sonai Muthu Anbananthen, Saravanan Muthaiyah, Sabareswari Thiyagarajan, Baarathi Balasubramaniam, Yunus Bin Yousif, Suraya Mohammad, and Khairul Shafee Kalid

Subjects
agriculture, enterprise architecture framework, comparative study, modern technology, digital transformation., Human ecology. Anthropogeography, GF1-900, Meteorology. Climatology, QC851-999
Abstract

This study aims to identify the most suitable Enterprise Architecture (EA) framework for driving digital transformation within Malaysia's agricultural sector. The objective is to evaluate and compare four leading EA frameworks—the Zachman Framework (ZFEA), the Department of Defense Architecture Framework (DoDAF), the Federal Enterprise Architecture Framework (FEAF), and The Open Group Architecture Framework (TOGAF)—using eight key criteria: adaptability, scalability, ease of implementation, support for modern technologies, cost-effectiveness, compliance, traceability, and risk management. A systematic comparative analysis assessed these frameworks' effectiveness in addressing the agricultural sector's specific needs. The findings indicate that TOGAF is the most appropriate framework due to its high adaptability, scalability, and robust support for modern technologies, making it ideal for the sector's requirements. In contrast, ZFEA, though versatile, faces significant challenges in practical implementation and scalability. DoDAF’s defense-centric focus limits its applicability in agriculture, and while FEAF is adaptable, it lacks strong support for modern technological integration. This study provides novel insights and practical recommendations for policymakers and practitioners to select the most effective EA framework, thereby supporting Malaysia's agricultural sector's digital transformation and modernization. Doi: 10.28991/HEF-2024-05-04-015 Full Text: PDF

Published
2024
Full Text
View/download PDF

32. Breeding Resilience: Exploring Lodging Resistance Mechanisms in Rice

Author

Durga Prasad Mullangie, Kalaimagal Thiyagarajan, Manonmani Swaminathan, Jagadeesan Ramalingam, Sritharan Natarajan, and Senthilkumar Govindan

Subjects
rice, lodging resistance, breaking and bending type lodging, culm strength, SCM gene, prl gene, Plant culture, SB1-1110
Abstract

Lodging is more than just plants falling over; it incurs significant economic losses for farmers leading to a decrease in both yield and quality of the final produce. Human management practices, such as dense sowing, excessive nitrogen fertilizer applications, inappropriate sowing dates, and upland rice cultivation, exacerbate the risk of lodging in rice. While breeders have developed high-yielding rice varieties utilizing the sd1 gene, relying solely on this gene is insufficient to enhance lodging resistance. Identifying the traits that contribute to lodging resistance is crucial. Key factors include biochemical, anatomical, and morphological traits, such as the levels of lignin, cellulose, hemicellulose, silicon, and potassium, along with the number and area of vascular bundles and the thickness, diameter, and length of the culm. Moreover, markers associated with lodging-related genes, like SCM2, SCM3, SCM4, and prl4, can be utilized effectively in marker-assisted backcrossing to develop rice varieties with desirable culm traits. This literature review aims to aid rice breeders in addressing the issue of lodging by examining traits that influence lodging resistance, developing phenotyping strategies for these traits, identifying suitable instrumentation, exploring methods for screening lodging-resistant plants, understanding the mathematical relationships involved, and considering molecular breeding aspects for pyramiding genes related to lodging.

Published
2024
Full Text
View/download PDF

44. Comparative Efficacy of Baclofen and Diazepam in Treating Spasticity Following Acquired Spinal Cord Injuries: A Randomized Controlled Trial

Author

Hemalatha Thiyagarajan, Karunai Kadhir Veluchamy, Sooraj Rajagopal, and Raj Kishore Mahato

Subjects
spinal cord injury, muscle disorder, clinical trial, accidents, muscle relaxants, Medicine
Abstract

Introduction: Spasticity is a pervasive and debilitating condition. Anti-spastic medications like Baclofen and Diazepam are most commonly used for spasticity management. Objectives: The study aimed to evaluate and compare the efficacy of Baclofen with that of Diazepam in the management of spasticity following acquired spinal cord injuries. Methods: In this randomised open-label study involving 60 patients, 30 patients received 5 mg of oral Baclofen thrice daily and 30 patients received 5 mg of oral Diazepam thrice daily for the management of spasticity. The extent of spasticity was measured by Modified Ashworth Scale (MAS). The efficacy of these drugs was measured with the mean improvement in the above parameters on days 7, 14, 28, 56 and 90 from the start of pharmacotherapy. Results: Baseline muscle spasticity scores were comparable. At the endpoint, mean improvement in tone of right and left hip flexors (1.43 vs. 0.87), hip adductors (1.30 vs. 0.87), knee flexors (0.80 vs. 0.37), ankle plantar flexors (0.80 vs. 0.37) and ankle dorsiflexors (1.23 vs. 0.93) were significantly higher in Baclofen group (p

Published
2024
Full Text
View/download PDF

47. Synergistic Configuration of Binary Rhodium Single Atoms in Carbon Nanofibers for High‐Performance Alkaline Water Electrolyzer

Author

Natarajan Logeshwaran, Gyuchan Kim, Pandiarajan Thangavel, Sun Seo Jeon, Kaliannan Thiyagarajan, Kampara Roopa Kishore, Hyunjoo Lee, Inseok Seo, Hongseok Yun, Sungho Lee, Byung‐Hyun Kim, and Young Jun Lee

Subjects
anion exchange membrane water electrolyzer, carbon nanofiber, hydrogen evolution reaction, interface engineering, single atom dispersion, Science
Abstract

Abstract Electrochemical alkaline water electrolysis offers significant economic advantages; however, these benefits are hindered by the high kinetic energy barrier of the water dissociation step and the sluggish kinetics of the hydrogen evolution reaction (HER) in alkaline media. Herein, the ensemble effect of binary types of Rh single atoms (Rh‐Nx and Rh‐Ox) on TiO2‐embedded carbon nanofiber (Rh‐TiO2/CNF) is reported, which serves as potent active sites for high‐performance HER in anion exchange membrane water electrolyzer (AEMWE). Density functional theory (DFT) analyses support the experimental observations, highlighting the critical role of binary types of Rh single atoms facilitated by the TiO2 sites. The Rh‐TiO2/CNF demonstrates an impressive areal current density of 1 A cm−2, maintaining extended durability for up to 225 h in a single‐cell setup. Furthermore, a 2‐cell AEMWE stack utilizing Rh‐TiO2/CNF is tested under industrial‐scale conditions. This research makes a significant contribution to the commercialization of next‐generation high‐performance and durable AEMWE stacks for clean hydrogen production.

Published
2025
Full Text
View/download PDF

48. Forging Trust

Author

Damodaran, Dhinakaran, primary, Damodaran, Selvaraj, additional, Thiyagarajan, M., additional, and Srinivasan, L., additional

Published
2024
Full Text
View/download PDF

50. A simplified approach for efficiency analysis of machine learning algorithms

Author

Muthuramalingam Sivakumar, Sudhaman Parthasarathy, and Thiyagarajan Padmapriya

Subjects
Machine learning efficiency, Composite efficiency score, Analytic Hierarchy Process (AHP), Metric normalization, Algorithm performance evaluation, Medical image analysis, Electronic computers. Computer science, QA75.5-76.95
Abstract

The efficiency of machine learning (ML) algorithms plays a critical role in their deployment across various applications, particularly those with resource constraints or real-time requirements. This article presents a comprehensive framework for evaluating ML algorithm efficiency by incorporating metrics, such as training time, prediction time, memory usage, and computational resource utilization. The proposed methodology involves a multistep process: collecting raw metrics, normalizing them, applying the Analytic Hierarchy Process (AHP) to determine weights, and computing a composite efficiency score. We applied this framework to two distinct datasets: medical image data and agricultural crop prediction data. The results demonstrate that our approach effectively differentiates algorithm performance based on the specific demands of each application. For medical image analysis, the framework highlights strengths in robustness and adaptability, whereas for agricultural crop prediction, it emphasizes scalability and resource management. This study provides valuable insights into optimizing ML algorithms, and offers a versatile tool for practitioners to assess and enhance algorithmic efficiency across diverse domains.

Published
2024
Full Text
View/download PDF

Catalog

Books, media, physical & digital resources
See catalog results