NCNavaneethan Chenniappan

Navaneethan Chenniappan

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

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Navaneethan Chenniappan has a total of 14 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    From task-specific networks to foundation models in diabetes care: a critical review of opportunities, evaluation gaps, and safety frontiers

    by M. Nanda Kishore, C. Navaneethan

    Artificial intelligence in diabetes care has historically relied on task-specific supervised learning, such as bespoke networks for retinopathy grading, kidney disease prediction, and glucose forecasting. The emergence of foundation models (FMs: large models pretrained on broad data, typically with self-supervision, and adapted to many downstream tasks) is displacing this paradigm across diabetes-relevant modalities: ophthalmic models such as RETFound, pretrained on 1.6 million retinal photographs, have been reported to outperform task-specific networks on retinopathy grading and systemic disease prediction, especially when labeled data are scarce; transformer-based time-series models are replacing long short-term memory (LSTM) pipelines for continuous glucose monitoring (CGM) forecasting; clinical large language models (LLMs) such as Med-PaLM and GPT-4 attain expert-level scores on medical question-answering benchmarks; and generative models supply synthetic CGM and electronic health record (EHR) data. This review provides a critical, modality-organized synthesis of this transition. We (i) formalize a three-era taxonomy: rule-based risk scores (era I), task-specific deep learning (era II, 2016–2020), and foundation models (era III, from 2021), and map the diabetes literature onto it; (ii) survey foundation-model architectures, pretraining objectives, and adaptation strategies across retinal imaging, CGM, longitudinal EHR, and multimodal data; (iii) expose an evaluation crisis: benchmark contamination of LLM medical evaluations, a near-universal absence in the literature we reviewed of external and prospective validation for retinal and CGM foundation models, miscalibration under dataset shift, and, to our knowledge and within the reviewed literature (January 2016–December 2025; negative findings are time-sensitive), the absence of any randomized evaluation of a foundation model in a diabetes workflow; and (iv) analyze safety risks: hallucinated insulin-dosing advice, automation bias, inherited algorithmic inequity, and privacy exposure during adaptation. We conclude that the decisive open problem is no longer representation learning but grounded, calibrated, causally informed deployment, requiring contamination-resistant evaluation, prospective trials, and hybrid architectures coupling foundation-model representations with treatment-effect estimation.

  • Open Access

    A systematic review of DoS and DDoS attack detection in cloud environments: evolutionary trends and the emerging role of meta-learning for cross-domain adaptability

    by Amit Tiwari, C. Navaneethan

    Denial of Service (DoS) and Distributed Denial of Service (DDoS) attacks continue to be one of the most persistent and rapidly evolving threats to current network infrastructures as they are becoming more sophisticated and increasingly disrupting the availability, reliability and security of cloud-based systems, Software-Defined Networks (SDNs), Internet of Things (IoT) ecosystems and next generation communication environments. This paper provides a systematic review of the literature on DoS and DDoS attack detection and mitigation, covering the various stages of evolutions in the field from early statistical and anomaly-based methods to adaptive machine learning and deep learning, as well as domain specific detection methods. The review, which is based on a thorough examination of 120 papers (114 primary studies and 6 supplementary studies), provides a synthesis of the latest advances in network and application-layer detection, protocol-specific detection frameworks, cloud-based intrusion detection systems, SDN-enabled programmable detection, IoT/Fog/Edge architectures, ensemble and hybrid models, transfer learning, and blockchain-based security mechanisms. A systematic review of benchmark datasets, feature engineering techniques and comparative performance shows that current deep learning systems attain almost perfect classification rates in experimental environments, but fundamental limitations in their generalizability, computational efficiency, preservation of privacy and explainability remain a constraint for their deployment in real-world environments. Importantly, this is a lot of work, but less than 6 % of the reviewed studies (seven out of 120) use meta-learning, transfer learning or few-shot approaches explicitly, which reflects the ongoing lack of capability in the field of adaptive generalization and a deficiency in addressing zero-day attacks and domain shift in dynamic cloud environments. We propose the emerging paradigm of meta-learning as the most promising one for next-generation cloud-based intrusion detection, which can be adapted to new domains with very few labeled examples — directly overcoming the three key limitations of existing approaches, namely the zero-day detection gap, domain shift limitations and label scarcity. This review offers a structured basis for researchers and practitioners designing explainable, privacy-preserving and computationally efficient detection systems and highlights the critical need for moving along the path of designing cloud-based intrusion detection systems based on meta-learning.

  • Open Access

    Quantifying the imputation paradox and XAI inconsistency in multi-source diabetes prediction: a 353,680-record leakage-free stacking ensemble with dynamic routing architecture

    by M. Nanda Kishore, C. Navaneethan

    Diabetes affects 537 million adults globally, a figure projected to reach 783 million by 2045. Despite over 4,200 ML prediction studies, clinical translation remains hindered by an over-reliance on benchmark datasets, unmeasured information costs of multi-source fusion, and untested XAI convergence assumptions. We address these issues by evaluating 353,680 records (from 455,446 candidates) across a Clinical-Biomarker Set (CBS) and a Lifestyle-Survey Set (LSS) using a strict leakage-free protocol. Under this protocol, normalisation, imputation, and SMOTE synthesis were fitted exclusively on training data. We formally define the Imputation Paradox as the AUC loss that occurs when critical diagnostic biomarkers are median-imputed under structural MNAR missingness. An Optuna-tuned stacking ensemble (Random Forest, XGBoost, LightGBM) achieves an AUC-ROC of 0.8481 on a held-out 70,736-sample test set. While a simple average baseline marginally exceeded stacking on pure discrimination (AUC 0.8521), stacking was retained for its superior precision (0.3439) and interpretable meta-learner trust weights, yielding a cross-validation AUC of 0.8491 ± 0.0014 and a Wilcoxon-significant improvement over baselines ( p < 0.001, n = 1,000 replicates). A CBS sub-model trained on complete HbA1c and glucose data achieves an AUC of 0.9781. The resulting 0.130-unit gap quantifies this fusion-induced information cost. To recover this, our end-to-end dynamic routing pipeline routes 28.1% of patients to the CBS sub-model and 71.9% to the stacking ensemble, achieving a blended AUC of 0.8496. At a 0.30 mass screening threshold, the model identifies ~16,600 additional diabetic patients per million screened, with decision curve analysis confirming net benefit across the 5–30% threshold range. XAI conflict analysis yields Spearman correlations of r = −0.4561 (SHAP/permutation, p = 0.141), r = +0.2417 (SHAP/LIME, p = 0.737), and r = +0.1494 (permutation/LIME, p = 0.350). While non-significant at n = 12 features (critical r = ±0.576, α = 0.05), this provides preliminary directional evidence that these methods capture structurally different aspects of feature relevance.

  • Open Access

    Colorectal cancer prognosis based on dietary pattern using synthetic minority oversampling technique with K-nearest neighbors approach

    by S. Thanga Prasath, C. Navaneethan

    Generally, a person’s life span depends on their food consumption because it may cause deadly diseases like colorectal cancer (CRC). In 2020, colorectal cancer accounted for one million fatalities globally, representing 10% of all cancer casualties. 76,679 males and 78,213 females over the age of 59 from ten states in the United States participated in this analysis. During follow-up, 1378 men and 981 women were diagnosed with colon cancer. This prospective cohort study used 231 food items and their variants as input features to identify CRC patients. Before labelling any foods as colorectal cancer-causing foods, it is ethical to analyse facts like how many grams of food should be consumed daily and how many times a week. This research examines five classification algorithms on real-time datasets: K-Nearest Neighbour (KNN), Decision Tree (DT), Random Forest (RF), Logistic Regression with Classifier Chain (LRCC), and Logistic Regression with Label Powerset (LRLC). Then, the SMOTE algorithm is applied to deal with and identify imbalances in the data. Our study shows that eating more than 10 g/d of low-fat butter in bread (RR 1.99, CI 0.91–4.39) and more than twice a week (RR 1.49, CI 0.93–2.38) increases CRC risk. Concerning beef, eating in excess of 74 g of beef steak daily (RR 0.88, CI 0.50–1.55) and having it more than once a week (RR 0.88, CI 0.62–1.23) decreases the risk of CRC, respectively. While eating beef and dairy products in a daily diet should be cautious about quantity. Consuming those items in moderation on a regular basis will protect us against CRC risk. Meanwhile, a high intake of poultry (RR 0.2, CI 0.05–0.81), fish (RR 0.82, CI 0.31–2.16), and pork (RR 0.67, CI 0.17–2.65) consumption negatively correlates to CRC hazards.


  • Open Access

    Deep Learning Framework for Colorectal Cancer Classification Using ResNet18 Based on Dietary Habits Related to Meat Intake and Cooking Methods

    by S. Thanga Prasath, C. Navaneethan

    Abstract Colorectal cancer (CRC) is a serious health problem globally, needing early identification for optimal treatment. Ingestion of mutagens such as heterocyclic amines (HCA), which are produced when meat is cooked at high temperatures, is believed to increase the risk of colorectal cancer. The present study’s objective was to investigate the relationship between different meats cooked at different temperatures and CRC formation. Automated colorectal cancer detection methods that analyze regular dietary patterns will aid clinicians. This study employed the PLCO dataset of 1,54,892 individuals aged 55 to 74 (76,679 men and 78,213 females). A deep learning framework was designed with a classification and prediction phase. Two distinctive methods were applied to categorize meats cooked by various cooking methods in the Resnet18 (convolutional 1D) model. In the first approach, we uploaded the complete dataset for classification, whereas the second separated them into 30 segments and tested them. The prediction layer then predicted cancer patients’ ages. The classification and prediction layers were created using Resnet18 (convolutional 1D) with the Root Mean Squared Propagation (RMSProp) and Adam optimizers. We estimated risk ratios (RR) with 95% confidence intervals (CI) for the association between meat intake or cooking style and CRC risk. Our primary finding was a positive link with CRC for pan-fried hamburgers (RR: 1.86, CI: 1.09-3.18) and bacon (RR: 1.1, CI: 0.79-1.53), while a negative relationship was detected between pan-fried chicken (RR: 0.8, CI: 0.51-1.27) and beef steak (RR: 0.43, CI: 0.06-3.01). The broiled chicken intake (RR: 0.8, CI: 0.78-1.67) decreased CRC risks, but broiled beef steak (RR: 1.46, CI: 0.96-2.24) and meat (RR: 1.25, CI: 0.98-1.60) have statistically elevated the CRC risk. Grilled or barbecued hamburgers (RR: 2.06, CI: 0.79-3.42) and beef steaks (RR: 1.31; CI: 0.76-2.25) showed a favorable connection with CRC. Meanwhile, adverse associations were found between grilled or barbecued poultry (RR: 0.84, CI: 0.52-1.34) and pork chops (RR: 0.46, CI: 0.11-1.82). Pan-fried hamburgers and bacon, broiled and barbecued beef steak may be involved in the etiology of colorectal cancer.


  • Open Access

    A comprehensive survey on several fire management approaches in wireless sensor networks

    by Swetha Rajendran, Navaneethan Chenniappan

    The majority of the fires are activated through environmental reasons although a minority of them are self-activated. To detect fires several safety systems were introduced. There are wired systems, cameras, satellite systems, and bluetooth feasible to provide a complete image of the world but after a long search period. These systems are not perfect since it prevents fire from finding just at the time, the fire initiates. But, recent technological development in wireless sensor networks (WSN) has spread out its fire detection application. A comprehensive survey on several fire management approaches in WSN propose to discuss various fire detection approaches like early fire detection, energy efficient fire detection, mobile agent-based fire detection, unmanned aerial vehicle (UAV)-based fire detection, threshold-based fire detection, machine learning based fire detection and secure fire detection approaches. Moreover, the comprehensive tabular study of the fire management technique is given that will assist in the suitable selection of approaches to be applied for the detection of fire. Furthermore, WSN uses the clustering method to minimize redundant dataandsecure fire detection approaches collect authenticated data related to fire detection. Early fire detection approaches detects the fire early. Machine learning algorithm detects the fire efficiently.


  • Modelling of Different On-chip Inductors for Radio Frequency Integrated Circuits

    by Dhamodaran Muneeswaran, Jegadeesan Subramani, Thanapal Pandi, Navaneethan Chenniappan, Meenatchi Shanmugam

    This paper presents a typical frequency-dependent modelling of different on-chip inductors for RFICs design problems. Modern RF circuits often feature on-chip inductors required by modern circuit design. A comparison of different inductor geometrics includes a planar spiral inductor and novel multilayer inductors are analyzed. An electromagnetic model with fewer assumptions than empirical equations and higher efficiency than full-field solvers would be welcome. So would facile comparisons of different inductor structures. This paper describes recent work on the electromagnetic modelling of on-chip inductor structures, applied to the comparison of inductor geometries, including the traditional spiral inductor and a novel multilayer inductor. The electromagnetic modelling of the investigative model is also presented.