arXiv subjects

Chittaranjan Hota

Publications and source records attributed to Chittaranjan Hota.

4 recordsLinked to original sources

arXiv2026

Agentic Anomaly Detection with ORCA-Style Dynamic Inductive Bias Adaptation in Multimodal Wearable Time Series Data

Wireless Body Area Networks (WBANs) generate multivariate physiological time series that are highly nonstationary and must often be processed under strict computational and memory constraints. A critical yet underexplored challenge in this setting is selecting an appropriate temporal receptive field, which serves as a strong inductive bias for anomaly detection models. Existing approaches typically rely on fixed temporal contexts, which can perform inconsistently across heterogeneous signal regimes and require dataset-specific tuning. We propose ORCA, an agentically controlled anomaly detection framework that dynamically adapts the temporal receptive field at inference time based on lightweight signal statistics. Rather than introducing additional trainable parameters or learned policies, ORCA employs a supervisory controller that autonomously selects among discrete temporal contexts, enabling state-dependent inductive bias adaptation without retraining. Across a custom WBAN dataset, ORCA achieves performance comparable to the strongest fixed-context baselines (AUROC = 0.99) while eliminating the need to tune temporal horizons in advance. We further evaluate ORCA on MIMIC-IV as a challenging out-of-distribution benchmark, observing conservative generalization behavior without performance collapse under heterogeneous clinical conditions. These results highlight adaptive temporal inductive bias control as a practical and robust design principle for anomaly detection in resource-constrained, nonstationary physiological time series.

cs.LG↗

arXiv2026

DEM: A Distilled Explanation Model for Interpretable Anomaly Detection in Physiological Sensor Networks

Anomaly detection in physiological sensor data from Wireless Body Area Networks (WBANs) can be caused by sensor faults, network disruptions, or missing data, leading to false alarms. Hence, it demands both high predictive accuracy and clinically interpretable explanations. Existing approaches rely either on black-box models that achieve strong performance but offer no transparency, or on post-prediction explanation methods such as SHAP and LIME. In this paper, we propose the Distilled Explanation Model (DEM), a three-stage glass-box framework that distills the non-linear knowledge of a gradient boosting expert into an interpretable decision tree operating on residuals relative to a linear baseline, so that the explanation is not an approximation but the prediction itself. DEM introduces a novel distillation fidelity metric that quantifies how faithfully the explanation tree captures the expert model's non-linear contribution, providing a principled measure of explanation trustworthiness absent from prior interpretable models. Evaluated across four physiological datasets, including MIMIC-IV, WESAD, eICU, and an in-house SmartNet WBAN corpus, DEM achieves an AUC of 0.9964 on clinical contextual anomaly detection and 0.9047 on wearable stress detection while producing human-readable if-then rules at a controllable depth. Inference requires 0.17ms per 1000 samples, rendering DEM 1235x faster than SHAP-based post-hoc explanation and suitable for real-time physiological monitoring. Ablation studies confirm that the XGBoost distillation step provides measurable gains over naive residual fitting, and depth-sensitivity analysis demonstrates an explicit, user-controlled accuracy-interpretability trade-off unique to DEM among existing intrinsically interpretable models.

cs.LG↗

arXiv2015

Adaptive Lookup for Unstructured Peer-to-Peer Overlays

Scalability and efficient global search in unstructured peer-to-peer overlays have been extensively studied in the literature. The global search comes at the expense of local interactions between peers. Most of the unstructured peer-to-peer overlays do not provide any performance guarantee. In this work we propose a novel Quality of Service enabled lookup for unstructured peer-to-peer overlays that will allow the user's query to traverse only those overlay links which satisfy the given constraints. Additionally, it also improves the scalability by judiciously using the overlay resources. Our approach selectively forwards the queries using QoS metrics like latency, bandwidth, and overlay link status so as to ensure improved performance in a scenario where the degree of peer joins and leaves are high. User is given only those results which can be downloaded with the given constraints. Also, the protocol aims at minimizing the message overhead over the overlay network.

cs.NI↗

arXiv2013

Real-time Peer-to-Peer Botnet Detection Framework based on Bayesian Regularized Neural Network

Over the past decade, the Cyberspace has seen an increasing number of attacks coming from botnets using the Peer-to-Peer (P2P) architecture. Peer-to-Peer botnets use a decentralized Command & Control architecture. Moreover, a large number of such botnets already exist, and newer versions- which significantly differ from their parent bot- are also discovered practically every year. In this work, the authors propose and implement a novel hybrid framework for detecting P2P botnets in live network traffic by integrating Neural Networks with Bayesian Regularization. Bayesian Regularization helps in achieving better generalization of the dataset, thereby enabling the detection of botnet activity even of those bots which were never used in training the Neural Network. Hence such a framework is suitable for detection of newer and unseen botnets in live traffic of a network. This was verified by testing the Framework on test data unseen to the Detection module (using untrained botnet dataset), and the authors were successful in detecting this activity with an accuracy of 99.2 %.

cs.NI↗