Description: In this project, I am a helper to help Izhar to finsh their research about using MEMS Multi-Sensors and formulas to replace machine learning on smart HVAC systems. Some of the HVAC Systems are using machine learning method to control the air conditioner in order to create a comfortable environment. However, sometimes, AI is not the best or makes things more complicated. We need build a system through our smartphones and Arduino board to control IOT devices in an effort to build a comfortable environment base on different condition (with some features, e,g, air velocity, PMV, room temperature). I help them build the system with bluetooth communication between smartphones and Arduino board. I use MIT app inventor to build a Android mobile app with simple UI, which can communicate with the Arduino board (arduino need C++ code to receive the data from the sensor on mobile phones). The mobile app will receive the data from the sensors of different IOT devices and do calculation. The IOT devices will base on the result to be controlled. We observe that our method has a quite good performance to create a comfortable environment and much simpler than train a machine learning model.

In this article, we report a predicted mean vote (PMV) index based micro Human Thermal Comfort Sensing (HTCS) system with multiple MEMS sensors. The system consists of a wireless multi-sensor (CMOS MEMS air velocity, MEMS relative humidity (RH) and MEMS air temperature) module to measure three environmental parameters and a smartphone App with a novel motion analytics algorithm (for estimation of metabolic rate) and personal factors (clothing insulation) input. While the majority of the reported HTCS systems are bulky and takes only environmental parameters into consideration, the developed system utilizes MEMS technology for sensors' fabrication and measures the essential environmental and human factors involved to compute human thermal comfort. Furthermore, the developed HTCS system shows much better accuracy (±0.13) than its commercial and reported counterparts (±0.17 to ±0.4). Moreover, the packaged HTCS system is placed in a testing room to monitor the PMV. The experimental results indicated that our micro PMV-based HTCS system is promising for smart HVAC system integration in the era of the Internet of Things.