[Paper Review] MakeSense: An IoT Testbed for Social Research of Indoor Activities

Jie Jiang, Riccardo Pozza+2 more|arXiv (Cornell University)|Aug 9, 2019

Context-Aware Activity Recognition Systems34 references4 citations

TL;DR

MakeSense is an IoT testbed designed for large-scale social research on indoor human activities, enabling non-intrusive, real-time data collection through low-cost, easily deployable IoTEgg sensors and a secure, scalable cloud infrastructure. It supports flexible deployment in homes and offices, ensures privacy via encryption and pseudonymisation, and facilitates remote monitoring and extensible sensor integration for validating behavioral practices alongside traditional methods like time-use diaries.

ABSTRACT

There has been increasing interest in deploying IoT devices to study human behaviour in locations such as homes and offices. Such devices can be deployed in a laboratory or `in the wild' in natural environments. The latter allows one to collect behavioural data that is not contaminated by the artificiality of a laboratory experiment. Using IoT devices in ordinary environments also brings the benefits of reduced cost, as compared with lab experiments, and less disturbance to the participants' daily routines which in turn helps with recruiting them into the research. However, in this case, it is essential to have an IoT infrastructure that can be easily and swiftly installed and from which real-time data can be securely and straightforwardly collected. In this paper, we present MakeSense, an IoT testbed that enables real-world experimentation for large scale social research on indoor activities through real-time monitoring and/or situation-aware applications. The testbed features quick setup, flexibility in deployment, the integration of a range of IoT devices, resilience, and scalability. We also present two case studies to demonstrate the use of the testbed, one in homes and one in offices.

Motivation & Objective

• To address the limitations of lab-based and living lab studies by enabling real-world, large-scale social research on indoor human activities.
• To develop an IoT infrastructure that is non-intrusive, cost-efficient, and easily deployable in natural indoor environments such as homes and offices.
• To ensure high data privacy and security through end-to-end encryption and pseudonymisation, minimizing participant disturbance.
• To support real-time monitoring and remote control of data collection for social researchers.
• To provide a flexible, extensible platform for integrating both commercial-off-the-shelf and custom sensor suites.

Proposed method

• The testbed uses low-cost, modular IoTEgg sensor nodes equipped with commodity sensors and standard Wi-Fi/BLE radios for seamless connectivity and deployment.
• A cloud-based infrastructure enables secure, real-time data ingestion, storage, and visualization with automated recovery mechanisms like logging and service re-spawning.
• The system supports over-the-air firmware updates and automated deployment via shell scripts and Docker images to streamline large-scale setup.
• Privacy is enforced through data encryption and pseudonymisation, with no personally identifiable information stored.
• The platform provides extensible APIs to integrate diverse sensor types, including COTS and self-developed devices.
• The design emphasizes resilience through watchdogs and logging systems to reduce manual intervention during long-term deployments.

Experimental results

Research questions

• RQ1 How can an IoT testbed be designed to support large-scale, real-world social research on indoor human activities without disrupting daily routines?
• RQ2 What technical and privacy mechanisms are necessary to ensure secure, reliable, and non-intrusive data collection in natural indoor environments?
• RQ3 To what extent can a flexible, low-cost IoT infrastructure support diverse sensor integration and remote monitoring in social science experiments?
• RQ4 How does the testbed’s architecture enable scalability and resilience in long-term deployments across different indoor settings?

Key findings

• MakeSense enables non-intrusive, real-time monitoring of indoor activities in homes and offices with minimal disruption to participants’ daily routines.
• The IoTEgg sensor nodes are cost-effective, with a target cost of under £50 per unit, and support rapid, automated deployment via over-the-air updates.
• The system ensures high data reliability and security through automated recovery mechanisms, end-to-end encryption, and pseudonymisation of participant data.
• The testbed supports flexible integration of both commercial and custom sensor suites through extensible APIs and open-source software components.
• Two case studies demonstrated successful deployment in real homes and office environments, validating the platform’s adaptability and scalability for diverse social research applications.
• The use of Docker and shell scripts significantly reduced setup time and system administration overhead for server and device deployment.