As the frequency and intensity of droughts around the world continues to increase, being able to reduce our water usage is vital for maintaining already strained freshwater resources. And according to the EPA, leaving a faucet running, whether intentionally or by accident for just five minutes can consume over ten gallons of water. However, Naveen has leveraged the power of machine learning to build a device that can automatically detect running faucets and send alerts over a cellular network in response. The hardware for this project is primarily centered around a Blues Wireless Notecard for cellular connectivity, a Blues Wireless Notecarrier-B as its breakout board, and a machine learning-capable microcontroller in the form of an Arduino Nano 33 BLE Sense. Beyond merely having a 32-bit Arm Cortex-M4 processor and 1MB of flash storage, its built-in microphone can be used to easily capture audio data.

We performed live classification of data using both our smartphones as well as the Arduino Nano 33 BLE Sense. Every Edge Impulse project has a test dataset in addition to its training data. The test dataset is immediately saved with the samples taken in Live classification, and the Model testing page displays all of the test data. To use the sample that was captured for testing, the expected outcome should be edited accordingly. Click the icon and select Edit expected outcome, then enter the relevant label, as shown below. Now, select the sample using the checkbox to the left of the table and click Classify selected. We can observe that the model's accuracy has been rated based on the test data. As expected, the performance of the model isn't always great on the first attempt, which can be so due to several factors.

TinyML reduces the complexity of adding AI to the edge, enabling new applications where streaming data back to the cloud is prohibitive. One common factor for all these applications is the low cost and power usage of the hardware they run on. Sure, we can detect audio and visual wake words or analyze sensor data for predictive maintenance on a desktop computer. But, for a lot of these applications to be viable, the hardware needs to be inexpensive and power efficient (so it can run on batteries for an extended time). Fortunately, the hardware is now getting to the point where running real-time analytics is possible.