XIAO-Powered Detection Tools: Anomaly Detection & Motion Classification for Containers in Transit, AI-driven Yogurt Production, and Gas Leak Detection Robot

Detection tools play a crucial role in identifying specific conditions or events accurately and efficiently. We always expect detection tools to work accurately, reliably, cost-effective, and easily integrated with other systems. In order to meet these expectations, the hardware used in detection tools must be reliable, cost-effective, and easy to integrate with other systems. XIAO has been selected by several prototypes of detection tools. With its robust performance, user-friendly interface, and efficient integration capabilities, XIAO continually enlightens intelligent applications in this field.

Anomaly Detection & Motion Classification for Containers in Transportation by XIAO nRF52840 Sense 

Background: Cargo Damage is quite common in transit 

Cargo can be damaged due to dropping, rolling, breakages, or being knocked during transit. Careless movement of mechanical handling equipment and inattention to weight loads & lifting gear can be counted as two of the common causes of cargo damage.  

For these two issues, using correct pallet packing techniques and following proper truck loading techniques become important. 

Solution: A device quickly detects Anomalies and Trigger Relative Measures

A little anomaly detection tool powered by XIAO nRF52840 Sense can avoid unnecessary loss in transportation and can protect the interests of the cargo of the owners. Imagine a pallet or container that should be transported (and handled) worldwide in several ways, like by a forklift, truck, train, boat, etc. Our problem will be to identify the transportation history of a specific container, splitting its journey into typical situations such as a) Maritime (pallets in boats), Terrestrial (palettes in a Truck or Train), Lift (Palettes being handled by Fork-Lift) and Idle (Palettes in Storage houses).  Anomalies are detected if a container is in the not-typical situations listed above. Then measures can be taken by relative staff to check whether there any emergency happened. 

Why XIAO nRF52840 Sense: low-cost and intelligent powered with TinyML 

Marcelo Rovail chose TinyML and Microcontroller(XIAO nRF52840 Sense) to make a gadget. Microcontrollers (MCUs) are very cheap electronic components, usually with just a few kilobytes of RAM, designed to use tiny amounts of energy. They can be found in almost any consumer, medical, automotive, or industrial device. TinyML is a new technology that uses microcontrollers and machine learning algorithms to extract meaning from sensor data. With the rise of the Internet of Things (IoT), the data generated by microcontrollers is increasing. However, much is unused due to data transmission’s high cost and complexity. TinyML enables machine intelligence on these devices, using very little power, to interpret more of the sensor data. 

Seeed Studio XIAO nRF52840 Sense carries Bluetooth 5.0 wireless capability and can operate with low power consumption. Featuring onboard IMU and PDM, it can measure and report the specific gravity and angular rate of an object to which it is attached.

IoT AI-driven Yogurt Processing & Texture Prediction by XIAO ESP32C3

Background: Yogurt Texture Requires Careful Control

Even though yogurt production and manufacturing look like a simple task, achieving precise yogurt texture (consistency) can be arduous and strenuous since various factors affect the fermentation process. Ensuring the texture of yogurt in food production requires careful control of the ingredients, processing conditions, temperature, and monitoring of the product.


Even though the mentioned factors can provide insight into detecting yogurt consistency before fermentation, it is not possible to extrapolate and construe yogurt texture levels precisely by merely employing limited data without applying complex algorithms. Hence, Kutluhan decided to build and train an artificial neural network model by utilizing the empirically assigned yogurt consistency classes to predict yogurt texture levels before fermentation based on temperature, humidity, pressure, milk temperature, and culture weight measurements.

XIAO ESP32C3 is an ultra-small size IoT development board(also can be used as modules on PCBs in mass production) that can easily collect data and run my neural network model after being trained to predict yogurt consistency levels. To collect the required measurements to train my model, Kutluhan used a temperature & humidity sensor (Grove), an integrated pressure sensor kit (Grove), an I2C weight sensor kit (Gravity), and a DS18B20 waterproof temperature sensor. Since the XIAO expansion board provides various prototyping options and built-in peripherals, such as an SSD1306 OLED display and a MicroSD card module, I used the expansion board to make rigid connections between XIAO ESP32C3 and the sensors.

Web Browser-operated Robot for Gas Leak Detection using XIAO nRF52840 Sense:

Background: the importance of detecting green hydrogen

Green hydrogen has the potential to play a significant role in reducing greenhouse gas emissions and mitigating the impacts of climate change. However Green hydrogen is highly flammable. Here are some reasons to indicate how important it is to detect green hydrogen leaks:

  • Safety: it can displace oxygen and create a hazardous environment that could result in fire or explosion. Detecting leaks can help prevent these dangerous situations from occurring.
  • Environmental protection: Green hydrogen production is considered to be a clean and sustainable energy source, but leaks can release hydrogen into the environment, potentially contributing to air pollution. Detecting leaks can help minimize these emissions and protect the environment.
  • Economic losses: Leaks can result in the loss of valuable hydrogen, reducing the efficiency and profitability of green hydrogen production and use. Detecting leaks can help reduce these economic losses.
  • Reliability: Detecting leaks can help identify problems with the production or storage systems, allowing for repairs to be made and improving the reliability of the overall system.

Solution: a big remote-operated, budget-friendly robot to carry the required sensing equipment

The robot takes advantage of cellular connectivity and embedded Artificial Intelligence to detect air quality anomalies on its path. XIAO nRF52840 Sense plays the role of the main microcontroller that controls the robot, communicates with the gas sensor to detect gas leaks, and transmits the data to the web browser for visualization.

Why XIAO nRF52840 Sense?

The XIAO nRF52840 Sense is a powerful, low-power microcontroller with built-in Bluetooth Low Energy (BLE) connectivity, making it an ideal choice for a project that requires wireless communication between the robot and a web browser.

  • Elaborate Power Design: Provide ultra-low power consumption as 5 μA in deep sleep mode while supporting lithium battery charge management
  • Advanced onboard Functionality: Assemble additional digital microphone and 6-axis IMU in the tiny board for embedded Machine Learning applications
  • Thumb-sized Design: 21 x 17.5mm, Seeed Studio XIAO series classic form factor, suitable for wearable devices

Three-in-One Portable Electronic Sensory System Based on XIAO RP2040


A paper about a 3-in-1 portable sensory system for real-time monitoring of EEG, ECG, and EMG signals. Weighing only 22g and costing as little as $25! The embedded Machine Learning realizes the accurate and fast classification of EMG signals.

Bicycle Computer Adopting XIAO nRF52840 Sense

This project aims to build a bicycle computer, the main available features

  • Capture a low-resolution video stream and show it on a display with an option to take a high-resolution images for storage on an SD card
  • Track the location via GNSS and combine the location with weather data and points of interest (POI) data received from cloud services via the LTE connection.
  • Connect to bicycle sensors (currently heart rate) via Bluetooth Low Energy, show the data on the display, and record it.
  • Remote access to the camera and various data incl. location via MQTT

Why XIAO nRF52840 Sense?

  • XIAO’s BLE support makes it communicate with various sensors and peripherals
  • XIAO’s tiny size makes the whole design portable and lightweight

A Color Picker Powered by XIAO RP2040

It is pointed out that the LEDs cannot accurately show the full RGB colorspace (kinda impossible to show brown/black with just light). Guy designed a “color picker” called Dial Toner with the following features:

  • exceedingly clicky knobs/button
  • built-in conversation from hex to RGB, CMYK, HSV
  • that’s kinda it but w/e

About Author

1 thought on “XIAO-Powered Detection Tools: Anomaly Detection & Motion Classification for Containers in Transit, AI-driven Yogurt Production, and Gas Leak Detection Robot

Comments are closed.


February 2023