Exploiting Offloading in IoT-Based Microfog: Experiments with Face Recognition and Fall Detection

Abstract

The growth in many countries of the population in need of healthcare and with reduced mobility in many countries shows the demand for the development of assistive technologies to cater for this public, especially when they require home treatment after being discharged from the hospital. To this end, interactive applications on mobile devices are often integrated into intelligent environments. Such environments usually have limited resources, which are not capable of processing great volumes of data and can expend much energy due to devices being in communication to a cloud. Some approaches have tried to minimize these problems by using fog microdatacenter networks to provide high computational capabilities. However, full outsourcing of the data analysis to a microfog can generate a reduced level of accuracy and adaptability. In this work, we propose a healthcare system that uses data offloading to increase performance in an IoT-based microfog, providing resources and improving health monitoring. The main challenge of the proposed system is to provide high data processing with low latency in an environment with limited resources. Therefore, the main contribution of this work is to design an offloading algorithm to ensure resource provision in a microfog and synchronize the complexity of data processing through a healthcare environment architecture. We validated and evaluated the system using two interactive applications of individualized monitoring: (1) recognition of people using images and (2) fall detection using the combination of sensors (accelerometer and gyroscope) on a smartwatch and smartphone. Our system improves by 54% and 15% on the processing time of the user recognition and Fall Decision applications, respectively. In addition, it showed promising results, notably (a) high accuracy in identifying individuals, as well as detecting their mobility; and (b) efficiency when implemented in devices with scarce resources.

ENLACE: A Combination of Layer-Based Architecture and Wireless Communication for Emotion Monitoring in Healthcare

“…where C x is the transmission rate of the network interface, V t is the device voltage, and I t is the chain read during a time interval d t [25,26]. It should be noted that the execution of the service on the local server and in the cloud must consider the round trip time in the transmissions between the devices.…”

“…Both T x and R x are de ned by the device voltage and the electric current. It is worth pointing out that the electric current has di erent values for transmitting and receiving data because the signal strengths di er [25,26]. At each new execution, the ENLACE compares the costs of the rst run and the estimated values of the new data sample for the o oading decision regarding the processing layer.…”

Monitoring and Smart Decision Architecture for DRONE-FOG Integrated Environment

“…Its infrastructure can provide resources for IoT services at the network edge, which are called fog nodes. They can be resource-poor devices, such as access points, set-top-boxes, routers, switches, end devices, and base stations, or resource-rich machines, such as cloudlet, i.e., light-weight cloud servers that are typically one hop away from mobile devices; and microfog, a subset of fog node (e.g., two Raspberry Pis) enabled by fog cluster to handle data from a sensor linked to a specific IoT service [Torres Neto et al 2019]. The gain of an offloading operation, however, is determined by its ability to infer where the execution of code/data will represent less computational effort for the drone, so that, by deciding where to offload correctly, the drone obtains a benefit [Yi et al 2015, Shakarami et al 2020].…”

“…UAVs [Torres Neto et al 2019]. Thus, further work will consist of increasing the spectrum of offloading opportunities, considering a heterogeneous architecture composed of cloudlet, microfog, access points, and gateways.…”

A Secure and Verifiable Outsourcing Scheme for Assisting Mobile Device Training Machine Learning Model

“…Therefore, it is a good choice to outsource some calculations in machine learning algorithms. Neto et al [10] used mobile devices for health monitoring and outsourced data to improve the practical application problems caused by the limited resources of mobile devices. However, there is usually a long distance between the user and the cloud (This not only includes the distance in space; in fact, the user also needs to pass through many nodes in the network to the cloud.…”