Vivekananda Institute of Medical Sciences

FedPerKD privacy aware personalized federated learning with knowledge distillation for edge oriented tomato leaf disease detection

Abstract Tomato leaf diseases threaten global food security by reducing crop yield and quality. Centralized deep-learning detectors require farms to share raw images, which raises privacy, bandwidth, and data-sovereignty concerns. We present FedPer-KD, a privacy-aware federated f...

Tracking upper respiratory microbiome dynamics in patients admitted to intensive care unit: insights from a pilot study

Patients in intensive care units (ICUs) are highly susceptible to nosocomial infections, yet data on respiratory microbiome dynamics in non-ventilated patients with respiratory failure remain limited. In this pilot study, upper respiratory tract (URT) microbiota in 21 ICU patient...

Reliability of Bonini's semiological classification in frontal lobe seizures: A video‐ EEG based study

Abstract Objective Frontal lobe seizures have heterogeneous semiology, making electroclinical localization challenging. Bonini et al. proposed a semiological classification based on rostrocaudal frontal lobe organization. We evaluated its interobserver and intraobserver reliabili...