Task offloading in edge computing for machine learning-based smart healthcare

Recent advances in networking and mobile technologies such as 5G, long-term evolution (LTE), LiFi, wireless broadband (WiBro), WiFi-Direct, Bluetooth Low Energy (BLE) have paved the way for intelligent and smart services. With an average of more than 6.5 devices per person, a plethora of applications are being developed especially related to healthcare. Although, current edge devices such as smartphone and smartwatch are becoming increasingly more powerful and more affordable, there are certain tasks such as those involving machine learning that require higher computational resources, thereby resulting in higher energy consumption in the case of edge devices. Offloading tasks to co-located edge nodes such as fog (a cloud-like localized, smaller resource pool), or a femto-cloud (integration of multiple edge nodes) is one viable solution to address the issues such as performing compute-intensive tasks, and managing energy consumption. The outbreak of coronavirus disease 2019 (COVID-19) and becoming a pandemic has also made a case for edge computing (involving smartphone, wearables, health sensors) for the detection of symptoms to quarantine potential carriers of the virus. We focus on how various forms of smart and opportunistic healthcare (oHealth) can be provided by leveraging edge computing that makes use of a machine learning-based approach. We apply k-nearest neighbors (kNN), naive Bayes (NB), and support vector classification (SVC) algorithms on real data trace for the healthcare and safety-related scenarios we considered. The empirical results obtained provide useful insights into machine learning-based task offloading in edge computing.