Publications by authors named "Sandesh Achar"
Sensor networks generate vast amounts of data in real-time, which challenges existing predictive maintenance frameworks due to high latency, energy consumption, and bandwidth requirements. This research addresses these limitations by proposing an edge-cloud hybrid framework, leveraging edge devices for immediate anomaly detection and cloud servers for in-depth failure prediction. A K-Nearest Neighbors (KNNs) model is deployed on edge devices to detect anomalies in real-time, reducing the need for continuous data transfer to the cloud.
View Article and Find Full Text PDFArticle Synopsis
- Security grids utilizing HD IoT cameras are increasingly popular for perimeter surveillance, but they face challenges with high bandwidth and storage needs for cloud video transmission.
- This paper introduces a Machine Vision at the IoT Edge (Mez) technology combined with a Grid Sensing (GRS) algorithm to reduce cloud resource costs, showing a 31.29% decrease in bandwidth and 22.43% in storage.
- The system optimizes video frame processing and automatically ranks bandwidth needs of IoT nodes to enhance overall efficiency and minimize resource usage.