Estimating wind speed and direction in outdoor areas with high precision and resolution requires a large number of anemometers distributed in different locations. Compared with others conventional sensors, the micro electro mechanical system (MEMS) sensors are lighter and smaller, therefore, they can be integrated in large numbers. Moreover, due to their batch production, MEMS sensors are relatively low cost. Their main drawbacks are the dependence on the air temperature and the inability of detecting the flow direction. This paper deals with the design of a cylindrical-shaped probe equipped with two dual MEMS hot-film sensor chips calibrated in a wind tunnel. With the obtained results, a model based on artificial neural network is developed and implemented on Arduino board. This model is assigned to calculate the corresponding values of wind speed and direction with correcting the effect of temperature drift. Finally, outdoor tests are carried out at wind monitoring points measured by an opto-electronic anemometer and an opto-electronic wind vane. The obtained results are accurate and agree well.
This paper describes a non-invasive system for respiratory monitoring using a Micro Electro Mechanical Systems (MEMS) flow sensor and an IMU (Inertial Measurement Unit) accelerometer. The designed system is intended to be wearable and used in a hospital or at home to assist people with respiratory disorders. To ensure the accuracy of our system, we proposed a calibration method based on ANN (Artificial Neural Network) to compensate the temperature drift of the silicon flow sensor. The sigmoid activation functions used in the ANN model were computed with the CORDIC (COordinate Rotation DIgital Computer) algorithm. This algorithm was also used to estimate the tilt angle in body position. The design was implemented on reconfigurable platform FPGA.