Suganthi K | Searcharxiv

arXiv2023

Epidemic outbreak prediction using machine learning models

In today's world,the risk of emerging and re-emerging epidemics have increased.The recent advancement in healthcare technology has made it possible to predict an epidemic outbreak in a region.Early prediction of an epidemic outbreak greatly helps the authorities to be prepared with the necessary medications and logistics required to keep things in control. In this article, we try to predict the epidemic outbreak (influenza, hepatitis and malaria) for the state of New York, USA using machine and deep learning algorithms, and a portal has been created for the same which can alert the authorities and health care organizations of the region in case of an outbreak. The algorithm takes historical data to predict the possible number of cases for 5 weeks into the future. Non-clinical factors like google search trends,social media data and weather data have also been used to predict the probability of an outbreak.

cs.LG↗

arXiv2019

A Novel Hybrid Opportunistic Scalable Energy Efficient Routing Design For Low Power, Lossy Wireless Sensor Networks

Opportunistic Routing (OR) scheme increases the transmission reliability despite the lossy wireless radio links by exploiting the broadcast nature of the wireless medium. However, OR schemes in low power Wireless Sensor Network (WSN) leads to energy drain in constrained sensor nodes due to constant overhearing, periodic beaconing for Neighbourhood Management (NM) and increase in packet header length to append priority wise sorted Forwarding Candidates Set (FCS) prior to data transmission. The focus of this work is to propose a hybrid opportunistic energy efficient routing design for large scale, low power and lossy WSN. This design avoids periodic 'hello' beacons for NM, limits constant overhearing and increase in packet header length. There are two modes of operation i) opportunistic ii) unicast mode. The sender node adopts opportunistic forwarding for its initial data packet transmission and instead of pre-computing the FCS, it is dynamically computed in a completely distributed manner. The nodes part of FCS based on cross layered multi-metrics and fuzzy decision logic determines its priority level to compute Dynamic Holding Delay (DHD) for effective timer coordination. The differentiated back off implementation along with DHD enables the higher priority candidate that had received data packet to forward the packet first and facilitates others to cancel its timer upon overhearing. The sender node switches to unicast mode for successive transmissions to achieve energy efficiency till link-level transmission error occur. Opportunistic mode is used as the first and last resort to increase the transmission reliability. Simulation results in NS2 show significant increase in Packet Delivery Ratio (PDR), decrease in both average energy consumption per node and Normalized Energy Consumption (NEC) per packet in comparison with existing protocols.

cs.NI↗