 Hello everyone and welcome to today's presentation. My name is Chris and I'm a field application engineer specializing in mem sensors. So I'm excited to demonstrate to you guys our latest inclinometer part called IIS2ICLX. This part is a high accuracy high stability inclinometer which can help enable stringent applications such as robotics structural monitoring and digital level. As you can see in our website the sensor is a high performance low power and highly configurable sensor with powerful embedded features. The IIS2ICLX notably has higher extended operating temperature range from negative 40 to 105 degrees C, has superior stability and repeatability performance over temperature, it has an ultra low noise performance of 15 micro g per square hertz, and it has advanced some better features such as finite state machine and machine learning core built into developed complex solutions at the sensor node level. The steps to running the tilt measurement library for two axis inclinometers done in five simple steps. First, visit our website and search for XQ MEMS 1. Next, download and unpack the XQ MEMS 1 package. Next, drag and drop the tilt sensing 2 underscore IIS2ICLX stop pin and lastly run the Uniqlo GUI. First demo is evaluating the uncalibrated IIS2ICLX using our nuclear expansion board with MotionTL2 library and we will compare its performance to a commercial digital level that has been calibrated to have accuracy of plus or minus 0.2 percent. I've mounted the IIS2ICLX on this truck along with the digital level together so we can look real time how the output looks on both device. Notice how as I incrementally change the tilt of the truck bed the uncalibrated IIS2ICLX provides accurate reading which is on par with the calibrated digital level. Next demonstration is leveraging our machine learning core capability in the IIS2ICLX to detect back of the open bed state. To demonstrate this I am using the Profi MEMS evaluation board with the STEVAL MKI 209 V1K adaptive board. With the second example I've pre-collected data in three different classes. First class is when the vehicle is stationary with the open box bed in the fully closed position. This class is labeled as 0. Next class is when the bed is moving up or down or when the bed is partially open. This class is labeled as 8. Last class is defined as when the bed is in a completely open position. This class is labeled as 4. The MLC configuration that I've generated will be able to accurately determine these three different classes. You'll notice that when the truck is stationary with open bed fully closed it accurately outputs zero. When the truck bed is moving or is partially open it is able to accurately output 8. You can also observe that there is no false positive cases occurring with different speeds as well as different tilt angles. Finally when the truck bed is fully open it provides the output of 4.