A Survey of Approaches to Unobtrusive Sensing of Humans

Abstract

The increasing amount of human-related and/or human-originated data in current systems is both an opportunity and a challenge. Nevertheless, despite relying on the processing of large amounts of data, most of the so-called smart systems that we have nowadays merely consider humans as sources of data, not as system beneficiaries or even active “components.” For truly smart systems, we need to create systems that are able to understand human actions and emotions, and take them into account when deciding on the system behavior. Naturally, in order to achieve this, we first have to empower systems with human sensing capabilities, possibly in ways that are as inconspicuous as possible. In this context, in this article we survey existing approaches to unobtrusive monitorization of human beings, namely, of their activity, vital signs, and emotional states. After setting a taxonomy for human sensing, we proceed to present and analyze existing solutions for unobtrusive sensing. Subsequently, we identify and discuss open issues and challenges in this area. Although there are surveys that address some of the concerned fields of research, such as healthcare, human monitorization, or even the use-specific techniques like channel state information or image recognition, as far as we know this is the first comprehensive survey on unobtrusive sensing of human beings.

A Dataset on CSI-based Activity Recognition in Real-World Environments

“…Hence, H is an estimate how the WiFi signal is propagated from the transmitter to the receiver. Thus, H also contains information on, e.g., human activities in the signal propagation path [4], [7], [57], [61].…”

“…WiFi-based sensing is interesting for activity recognition, healthcare, and environmental monitoring, in particular, when device-free systems are required, which do not require users to wear or carry any devices on their bodies [9], [52]- [55]. Moreover, since WiFi networks are verily ubiquitous, the only additional hardware required for sensing purposes is a receiver or passive observer as more commonly refer to it [56], [57]. This can be a commercial off-the-shelf (COTS) radio, resulting in a low-cost solution for the mentioned applications.…”

“…This data is typically processed by pattern recognition (i.e., machine and deep learning) algorithms that infer what changes in the environment might have led to the received CSI amplitude and phase variations [58]- [60]. To this end, a classification or regression model is first trained using labeled CSI data and then used to classify or estimate previously unseen data [7], [56], [57], [61].…”

Human Sensing by Using Radio Frequency Signals: A Survey on Occupancy and Activity Detection

“…Fernandes et al assess existing approaches for human monitoring and give an analysis of existing solutions addressing channel status information and picture recognition [14]. The authors also discuss the current issues.…”

Machine Learning Sensors for Diagnosis of COVID-19 Disease Using Routine Blood Values for Internet of Things Application

“…The prompt diagnosis of COVID-19 seems to be a promising advancement for applying at-home health care and AAL [ 42 ]. The digitalization of healthcare calls for effective applications of human body sensors [ 43 ] and human sensing [ 44 ], including ML sensors, to continuously monitor various parameters of the human body in everyday life with the help of the IoT [ 45 ]. Everyday human body sensors testify to the growing number of applications in IoT-enabled ambient intelligence (AmI) systems [ 46 ].…”