I love combining technologies and services because this is a great and inexpensive way for companies to expand their businesses and for users to have a better experience. Awair has developed a great B2B air quality monitor the OMNI (hardware) and Djinn has developed a great B2B service (software) that combined together may offer better AQ insights or in other words, they contextualize data.
So I took the liberty to use the API Awair provides to its users and integrate it into Djinn’s platform. The reason is simple, Awair measures a plethora of parameters (temperature, humidity, PM2.5, VOC, CO2, noise, and light), and Djinn provides better insights into the impact those various indoor environmental parameters have on our health, like cardiovascular health risk and allergy risk. However, they also provide the productivity index which estimates the quality of the indoor environment with regard to the influence on productivity.
In real-life situations (offices, classrooms, etc) low-quality indoor environments may result in productivity drop up to 10% and more. Often in such cases, indoor environment quality is not comprehended by a person during the work process. The productivity index is based on research by cognitive scientists from various Universities.
According to the researchers, Human Decision Making Performance may be divided into different cognitive functions. Djinn service is able not only to estimate a general level of productivity, called Integral Productivity Index (IPI) but specify it for 9 cognitive activity areas based on research. An IPI is calculated as the average of all 9 directions. Those different models allow you to tune indoor parameters for optimal productivity according to your needs.
There are four factors of the indoor environment influencing human productivity: CO2 level, Temperature, Humidity, Noise, and Light level. Awair OMNI measures all of them. The question is if we can trust the methodology. Djinn’s methodology is based on different researches (48 at the moment) and correlations between aspects of productivity and indoor parameters founded by researchers. A confirmation of productivity dependence from indoor factors may be carried out by experimental research. For example, evidence of the influence of carbon dioxide (CO2) concentrations on different aspects of productivity are possible to get from research here. Djinn collaborates closely with Usha Satish, Professor of Psychiatry and Behavioral Sciences, to adapt the Human Decision Making Performance model for specific professions and activities.
In the example below, we can see from the graphs (left) how worsened indoor conditions with increased levels of CO2 are enough for some “more simple tasks” cognitive activity (Information search) and not well suitable for another one (Information usage). Special diagrams (right) reveal the impacts of various factors on productivity at the moment with a specific indication of the magnitude of their influence as a percentage of the total impact.
The client can provide to the Djinn server raw data through API requests about the current and available indoor air quality, such as temperature, humidity, CO2, light, particulate matter, formaldehyde, and instead gets an array of data with health risks analytics, productivity, efficiency of HVAC systems. Data is not stored on Djinn AWS servers, all calculations are carried out in real time. Currently, the number of requests can reach 100K per day.
Nowadays, APIs are widely adopted because of the flexibility they offer in porting data into different platforms. Contextualizing air quality data is what is missing from the market, and I urge companies to adopt such services as a medium to help people understand the impact poor air quality has on human health and cognitive functions.