Ultrasonic scans monitor noxious air bubbles via Arduino

The detailed project is highlighted on Hackser.io and features an Arduino Nano ESP32 connected to a 75KHz DFRobot URM15 Ultrasonic Sensor and an Adafruit Waterproof DS18B20 Digital temperature sensor, along with a USB webcam. It’s a serious piece of work.

The Gadget Master is one Kutluhan Aktar, and he’s using AI in the sense of multiple tank readings forming a classification model, and then taking readings to analyse the current state of health. He has created his own planted freshwater aquarium to do some serious water analysis…

Basically, the system aims to identify noxious air bubbles via ultrasonic scans and also assess water pollution based on chemical tests, writes Kutluhan.

“After completing constructing my ultrasonic scan data set, I built my artificial neural network model (ANN) with Edge Impulse to identify noxious air bubbles lurking in the underwater substrate. Considering the unique structure of ultrasonic imaging data, I employed the built-in Ridge classifier as the model classifier, provided by Edge Impulse Enterprise.”

“As a logistic regression method with L2 regularization, the Ridge classification combines conventional classification techniques and the Ridge regression for multi-class classification tasks. Since Edge Impulse is nearly compatible with all microcontrollers and development boards, even for complex Sklearn linear models, I have not encountered any issues while uploading and running my advanced model on Nano ESP32.”

The device, as you can see in the YouTube video below, can generate CSV data or capture an (ultrasonic) image, which is sent by social media to your phone.

Full details for the project – including code, schematics, parts list, and loads of images – can be found online.

[Via the Arduino blog]

See also: A Musical Variation of Arduino AI processing at the Edge