A Study on Mobile Crowd Sensing Systems for Healthcare Scenarios

Abstract

Due to the growing capabilities of mobile phones and devices, mobile crowd sensing (MCS) is rapidly gaining popularity among researchers in different fields, given its ability to collect data at scale and low cost. MCS is particularly important in the healthcare domain since it provides opportunities to collect health, wellness, and Quality of Life information from a large and diverse population. For example, MCS can be used to detect early signs of emerging health conditions, track the spread of infectious diseases, and assess the effectiveness of interventions without the need for frequent clinical visits. Consequently, MCS can also reduce healthcare costs and help overcome barriers to healthcare access. This article takes a closer look at MCS systems that have been used to collect data for research in the medical and healthcare domains. We provide a thorough analysis of selected systems based on their different health-related objectives, such as monitoring physical activity, detecting and preventing disorders, and providing medical treatment. We also adopt a three-layered architecture to structure health-centric MCS frameworks, consisting of application, data, and sensing layers. In the application layer, we analyze participant recruitment, incentive mechanisms, and task allocation strategies. In the data layer, we analyze the types of data collected and how they are stored and processed for future use. The sensing layer specifies the sensing methods and explains the fundamental requirements at a lower level. Additionally, we explore the significant challenges faced by existing MCS systems and domains that offer promising avenues for future research, which are user privacy, resource utilization, data quality, and user compliance. This work provides insights into some practical applications of MCS, highlights challenges faced by existing MCS solutions, and how they can be addressed, all of which can help catalyze future research in MCS development.

Keywords

• Mobile health
• mobile crowd sensing
• opportunistic sensing
• participatory sensing