Smart Desks to Promote Comfort, Health, and Productivity in Offices: A Vision for Future Workplaces

Abstract

People spend most of their day in buildings, and a large portion of the energy in buildings is used to control the indoor environment for creating acceptable conditions for occupants. However, the majority of the building systems are controlled based on a "one size fits all" scheme which cannot account for individual occupant preferences. This leads to discomfort, low satisfaction and negative impacts on occupants' productivity, health and well-being. In this paper, we describe our vision of how recent advances in Internet of Things (IoT) and machine learning can be used to add intelligence to an office desk to personalize the environment around the user. The smart desk can learn individual user preferences for the indoor environment, personalize the environment based on user preferences and act as an intelligent support system for improving user comfort, health and productivity. We briefly describe the recent advances made in different domains that can be leveraged to enhance occupant experience in buildings and describe the overall framework for the smart desk. We conclude the paper with a discussion of possible avenues for further research.

Worker Perspectives on Incorporating Artificial Intelligence into Office Workspaces: Implications for the Future of Office Work

“…The long-term goal of our research is to develop an AI-enabled office workstation that can support the health and well-being needs of office workers. We will do so by integrating sensors and feedback systems into the office environment that will enable the worker and AI to work synergistically [ 42 ]. At the outset of this broader project, we engaged with office workers to identify their perspectives so that we might design a system that could be easily translated into practice for maximum effects on the intended outcomes.…”

“…An interview guide facilitated these semi-structured interviews and ensured that each group interview covered the same topics ( Appendix A ). Specifically, instead of feedback on an existing AI system, we framed these discussions around the proposed development of a new AI-enabled, smart office workstation that could provide support for improving health and work performance through automated feedback and environmental modifications [ 42 ]. At the start of each focus group, the moderator provided the following prompt to set the foundation for group discussion: “We are looking at opportunities around making the work environment healthier for people.…”

“…There is a clear opportunity for integrating an AI system that can learn individual needs, improve the work environment, and support behavior change over time within office workspaces. We previously completed and published a comprehensive review of current evidence and gaps in knowledge relative to developing an AI system for this purpose [ 42 ], through which we determined that it is necessary to begin by understanding office workers’ perspectives, needs, and preferences. Specifically, there is limited knowledge of how the implementation of AI would alter the occupational context for workers in an office setting and how to develop an acceptable AI system that could become fully incorporated without being obtrusive.…”

Sensor commissioning detection in single-pixel thermopile sensing systems

“…Various smart building systems like lighting and HVAC (heating, ventilation and air conditioning) controls and space management applications rely on data from sensor systems [1], [2], [3]. For instance, temperature data and people count estimates from thermopile sensor systems may be used to improve user comfort by adaptively controlling HVAC systems.…”

Skin Temperature Extraction Using Facial Landmark Detection and Thermal Imaging for Comfort Assessment

“…Recent advancements in Internet of Things (IoT) and Machine Learning (ML) have opened the possibility of using distributed sensors integrated into everyday objects to collect data at a granular level and to develop individualized models [4]. To overcome the limitations of averaged comfort models, there has been a growing interest in creating comfort models that are personalized to each individual [21].…”