M.N Arjun Pillai

Dr. M.N Arjun Pillai

orcid

Research Focus & Metrics

Academic Career Length

4Years (2023-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 January 2025 in Eurasian Journal of Medicine and Oncology
Verified
Journal Article
Open access
PDF file
HSHemalatha S
Hemalatha S
MPM.N Arjun Pillai
M.N Arjun Pillai
SSSomavarapu N. C. Shekhar
Somavarapu N. C. Shekhar
APAnbarasa A. Pandian
Anbarasa A. Pandian
PKPullela Kumar
Pullela Kumar
RTRamesh Tumaati
Ramesh Tumaati
The integration of artificial intelligence (AI) through virtual assistants and chatbots is transforming oncology care by providing continuous, personalized, and accessible support. This study aims to evaluate the role of AI-powered tools in improving patient engagement, symptom management, emotional support, and treatment adherence in oncology. A qualitative methodology was employed, which included an extensive review of peer-reviewed literature from 2015 to 2023 and the development of a conceptual framework for oncology-specific chatbot systems. This framework incorporates natural language processing, machine learning, and personalized response algorithms. Key findings from this study indicate that these AI tools enhance access to healthcare information, empower patients, and reduce the burden on healthcare systems, particularly in remote or underserved regions. However, challenges remain concerning data privacy, accuracy, and the need for human intervention in complex cases. The study underscores the importance of maintaining a balance between innovative AI applications and human-centered care, advocating the integration of AI-based technologies as complementary tools in oncology.

3 April 2023 in International Journal on Recent and Innovation Trends in Computing and Communication
Verified
Journal Article
Open access
PDF file
NCNARENDER CHINTHAMU
NARENDER CHINTHAMU
Chandrasekar VenkatachalamChandrasekar Venkatachalam
Chandrasekar Venkatachalam
MPM.N Arjun Pillai
M.N Arjun Pillai
SASetti Vidya Sagar Appaji
Setti Vidya Sagar Appaji
MMM. Murali
M. Murali
The technology of big data has become highly popular in numerous industries owing to its various characteristics such as high value, large volume, rapid velocity, wide variety, and significant variability. Nevertheless, big data presents several difficulties that must be addressed, including lengthy processing times, high computational complexity, imprecise features, significant sparsity, irrelevant terms, redundancy, and noise, all of which can have an adverse effect on the performance of feature extraction. The objective of this research is to tackle these issues by utilizing the Partial Least Square Generalized Linear Regression (G-PLSGLR) approach to decrease the high dimensionality of text data. The suggested algorithm is made up of four stages: Firstly, gathering featured data in vector space model (VSM) and training it with bootstrap technique. Second, grouping trained feature samples using a Pearson correlation coefficient and graph-based technique. Third, getting rid of unimportant features by ranking significant group features using PLSGR. Lastly, choosing or extracting significant features using Bayesian information criterion (BIC). The G-PLSGLR algorithm surpasses current methods by achieving a high reduction rate and classification performance, while minimizing feature redundancy, time consumption, and complexity. Furthermore, it enhances the accuracy of features by 35%.

1 January 2024 in Journal of Advances in Information Technology
Verified
Journal Article
Open access
HSHemalatha S
Hemalatha S
KVKandasamy Valarmathi
Kandasamy Valarmathi
GNG. Nagappan
G. Nagappan
MPM.N Arjun Pillai
M.N Arjun Pillai
LMLakshmana Phaneendra Maguluri
Lakshmana Phaneendra Maguluri
IVI. V. Veeranjaneyulu
I. V. Veeranjaneyulu
JAIT is a scientific open access journal which focuses on empirical research results and critical analysis of technology development, use, management and impacts in information technology.

1 January 2024 in SSRN Electronic Journal
Verified
Preprint
Open access
RLR. Monica Lakshmi
R. Monica Lakshmi
MPM.N Arjun Pillai
M.N Arjun Pillai
SPS. Prasiddhi
S. Prasiddhi
PRParvathareddy Kavya Reddy
Parvathareddy Kavya Reddy
PMPellakuru Mahathi
Pellakuru Mahathi
SASerah Anna Ajith
Serah Anna Ajith
The problems encountered in India are numerous, especially in the area of waste management. Population growth and improvements in economic status enhance the rate of generation of waste; however, the improvement in the infrastructure and proper treatment processes lag behind. Open dumping and burning by inadequate availability of proper landfills and due to financial problems affect the nation and its environment, as well as people’s health. Akin to another level of waste management innovation that involves technology and connectivity for proper waste disposal, one comes across sensor equipped dustbins and the eConnect application. It is these smart dustbins that are able to sense when the dustbins are full and send real-time information on the fill level and other features. The eConnect app has options such as alert notification, GPS, and public chat, improving the process of collectors and making cities cleaner. The alert system emphasizes the work zones that need attention; the GPS tracking system gives real location information for timely response; and the public chat lets citizens report problems and give opinions. This has the ability to provide efficient routing of waste collection, establish data for contexts where resources are to be distributed, and show the flow of waste management. The dustbin numbers along with the data of the particular area are delivered to the municipal corporation to arrange waste collection. This concept corresponds to the innovative measures for cities, and it is a major step towards the proper usage of waste management systems.


2 June 2026 in Computers
Verified
Journal Article
Open access
PDF file
RKRAJAGOPAL K
RAJAGOPAL K
VKV.Sheeja Kumari
V.Sheeja Kumari
MPM.N Arjun Pillai
M.N Arjun Pillai
RAR. H. Aswathy
R. H. Aswathy
VRVijayalakshmi Ramakumar
Vijayalakshmi Ramakumar
Indra Neel PulidindiIndra Neel Pulidindi
Indra Neel Pulidindi
Precise segmentation of kidney tumors in medical images is crucial for diagnosis, treatment planning, and prognosis assessment. In this work, we present a newly proposed hybrid deep learning model that combines the merits of U-Net and the Swin Transformer architectures in order to enhance the segmentation performance. Although U-Net has great spatial localization ability thanks to the encoder–decoder structure, which works in a hierarchical way, it is still difficult to capture global context well. The Swin Transformer instead captures long-range dependencies and assists in local detail extraction, while attention pooling might also smear fine boundary details. This motivates our hybrid integration. To attempt to resolve these issues, we extend U-Net with the Swin Transformer blocks in the backbone encoder path in order to efficiently perform multi-scale semantic feature extraction while preserving structural consistency. We trained and cross-validated the model on the publicly available Kidney Tumor Segmentation Challenge 2021 (KiTS21) dataset with extensive data augmentation as well as custom loss functions to address class imbalance and boundary obscureness. Experiments demonstrated that it achieved better performance when compared with the solo models, seeking a similar multi-task learning objective on not only U-Net and the Swin Transformer but also other baseline architectures in terms of the average Dice similarity coefficient (average DSC), intersection over union score (IoU) and Hausdorff distance. The proposed model achieved a Dice similarity coefficient (DSC) of 0.91, an IoU of 0.87, a PR-AUC of 0.89, and an overall voxel-wise accuracy of 98%, demonstrating robust and precise kidney tumor segmentation across varying tumor sizes and shapes. Moreover, the integrated solution is more robust and generalizes better, particularly in challenging cases with diverse anatomical variations. These findings demonstrate the power of Transformer-based hybrid models for medical image segmentation. Our results have positive implications for the design of computer-aided diagnostic systems and their association with other prevalent medical imaging tasks besides organ-specific or pathology-focused tasks.