iTechGuides is reader-supported. When you buy through links on our site, we may earn an affiliate commission. As an Amazon Associate I earn from qualifying purchases. Learn more
Bunny Senses is a 2019 maker prototype that reads acceleration from an Azure Sphere board, sends the readings to a time-series anomaly detector, and uses the result to switch a relay connected to a remote-control plush bunny. It is a useful illustration of sensor-to-action IoT design—not a system that detects a rabbit’s senses, and not evidence of production-grade threat detection. Its original Azure services and MT3620 hardware are now at or past announced retirement milestones, so rebuilding it requires a current replacement plan.
What Bunny Senses does
Ron Dagdag’s Hackster.io project, published December 3, 2019, uses an Azure Sphere MT3620 Starter Kit, a MIKROE RELAY click board, and a remote-control plush pet. The board reads its LSM6DSO accelerometer; the program uses the y-axis acceleration value as its sensor input. The relay is wired to the bunny’s controller, giving the software a physical output to switch.
The bunny is a playful stand-in for an IoT device reacting to unusual activity. The project does not measure a rabbit’s biological senses or establish a method for detecting real-world security threats. It demonstrates a chain from motion data to a model result to a relay action.
How the sensor-to-relay chain works
- Read motion: The MT3620 board samples the LSM6DSO accelerometer and takes the y-acceleration reading.
- Build a time series: The program stores readings in a list capped at 200 entries.
- Request anomaly detection: The example submits a minutely time series to the last-point detection endpoint, with
MaxAnomalyRatioset to 0.25 andSensitivityset to 95. - Act on the response: If the returned
isAnomalyvalue is true, the program sets the relay; otherwise, it clears it.
The project author describes taking a sensor sample every second while advancing its timestamp by one minute, because the API’s minimum granularity was minutely. That means the timestamps represent compressed or artificial time, not the actual one-second sampling intervals. It is a workaround specific to the demo, not a sound general approach to time-series sampling: changing timestamps changes the time context the detector is asked to evaluate.
#1 Best Overall
- Dual-Core Performance Up to 240 MHz: Run sensor processing, wireless communication, automation logic and connected-device tasks on a 32-bit dual-core ESP32 platform designed for responsive embedded and IoT projects
- Built-in Wi-Fi and Bluetooth 4.2: Connect to 2.4 GHz Wi-Fi networks or use Bluetooth Classic and BLE for wireless sensors, smart devices, remote controls, home automation and other connected projects
- Flexible Power-Saving Modes: ESP32 power-management features support dynamic clock scaling and low-power operating modes, helping developers reduce energy use in compatible sensing, monitoring and connected-device applications, suitable for battery-powered Internet of Things (IoT) devices.
- USB-C Programming with CP2102: Connect through USB-C for power, sketch uploads and serial monitoring, while GPIO, UART, SPI and I2C interfaces support sensors, displays, motor drivers and other modules (USB-C cable not included)
- Over-the-Air Update Support: Configure OTA functionality through a compatible ESP-32 software framework to update deployed firmware over Wi-Fi without reconnecting the board by USB for every revision
The tutorial includes example request and response data, but it does not report a controlled accuracy test, benchmark, or independent evaluation. Its settings and sample output should not be read as proof that the detector reliably distinguishes threats from ordinary motion.
Local container or Azure endpoint?
The 2019 project presents two ways to run detection: use an Anomaly Detector container on a laptop or Raspberry Pi on the local network, or send data directly to an Azure endpoint. Dagdag’s stated rationale for the local option is that sensor readings can remain on the local network. That is the author’s design argument, not the result of a comparative security audit.
Rank #2
- Certified & Future-Ready: Espressif-certified ESP32-WROOM-32E ensures full hardware compatibility and lifetime firmware support. Upgraded 8MB Flash handles IoT data and OTA updates.
- Dual-Core Speed: 240MHz dual-core processor runs Wi-Fi/BLE and sensors 2x faster. 38 GPIO pins (10 RTC) support SPI/I2C/UART for LCDs, motors, and industrial sensors.
- Plug & Play Dev: USB-C driver pre-installed: upload code instantly on Windows/Mac/Linux. Works with Arduino IDE, MicroPython, and Espressif IDF.
- All-Environment Ready: Run Wi-Fi smart switches (Home Assistant) and BLE tracking on one board. Industrial-grade stability (-40°C~85°C) for outdoor/automated systems.
- Advantages: The ESP32 development board offers high performance, low power consumption, and rich wireless connectivity, making it suitable for developers of all levels, especially beginners.
| Consideration | Local container | Azure-hosted endpoint |
|---|---|---|
| Where detection runs | On a laptop or Raspberry Pi on the local network, as described by the project. | At an Azure endpoint, as described by the project. |
| Sensor-data path | Readings can be processed locally under the project’s proposed design; the author presents this as a way to keep sensor data local. | Readings are sent to the Azure endpoint for processing. |
| Connectivity and billing | The project says the container needs occasional internet access for billing. | Requires connectivity to the Azure endpoint; the project does not give a separate billing or availability comparison. |
| Maintenance and service lifecycle | Requires maintaining the host and a supported detector implementation. The managed service’s announced retirement means the original container path should not be assumed to remain supported. | The original managed Anomaly Detector service’s announced retirement date is October 1, 2026; check current Microsoft service guidance before designing around it. |
| Security evidence | No comparative security test is reported. | No comparative security test is reported. |
These are architectural trade-offs, not a tested ranking. Keeping data on a local network can reduce what is sent to a remote service, but it does not by itself establish that a system is secure; host updates, network controls, credentials, and the software’s ongoing support still matter.
The Tool Desk
Outbyte Driver Updater FREEFix the driver behind crashes, sound loss and screen glitchesFind Drivers →Outbyte PC Repair FREEClear out junk files and repair common Windows errorsFree Scan →What changes if you build it now?
Azure Anomaly Detector has reached its announced retirement date
Microsoft’s announced retirement date for Azure Anomaly Detector was October 1, 2026. Microsoft had also said that new resources could not be created starting September 20, 2023. For replacement direction, Microsoft points to the anomaly-detector open-source project through Microsoft Fabric integration or use of the open-source project directly. Do not assume that the original managed API shown in the 2019 tutorial is available for a new build; verify current service status and migration guidance in Microsoft’s Anomaly Detector service documentation and API guidance.
Rank #3
Azure Sphere and MT3620 are legacy-project dependencies
Microsoft announced Azure Sphere retirement on March 20, 2026. Its lifecycle notice gives July 31, 2026 as the MT3620 MCU end-of-life date and July 31, 2031 as the end of extended support for Azure Sphere OS and Security Service. Microsoft says MT3620-based hardware will need redesign for continued functionality beyond the retirement date. After July 31, 2031, devices will no longer receive application or OS updates, bug fixes, or security patches. The dates and implications are listed in Microsoft’s Azure Sphere retirement notice.
Those milestones make the named starter kit appropriate to discuss as part of maintaining or studying a legacy build, not as an unqualified choice for a new, long-lived device. A rebuild should assess replacement hardware and a supported anomaly-detection path together, rather than porting the old API call in isolation.
Rank #4
- 2.4GHz Dual Mode WiFi + Bluetooth Development Board
- Support LWIP protocol, Freertos
- SupportThree Modes: AP, STA, and AP+STA
- Ultra-Low power consumption, Compatible with Arduino IDE
- ESP32 is a safe, reliable, and scalable to a variety of applications
What the demo can—and cannot—show
- It can show: how an accelerometer reading can be assembled into a time series, evaluated for an anomaly, and translated into a relay state.
- It cannot establish: detection accuracy, false-alarm rates, resilience to deliberate attacks, or suitability for a production security system.
- It does not sense: a rabbit’s biological signals; the input described is the board’s y-axis acceleration.
- Its local-processing argument is limited: the author argues that local processing can keep sensor data local, but the project does not independently test privacy or security outcomes.
For learning, the project’s value is the end-to-end architecture and the memorable physical output. For a real deployment, timestamps must represent the actual sampling cadence, the detector must be validated against the intended data and failure costs, and both hardware and software dependencies must have a support path that extends through the device’s intended lifetime.
Quick Recap
Best Value
- D1 Mini NodeMCU Type-C ESP32 WLAN WiFi Bluetooth IoT Development Board 5V Compatible for Arduino
- Designed with ultra-low power technology, it offers the full range of performance and features of the ESP32 chip. The pin arrangement provides compatibility with the modules developed for the D1 Mini ESP8266 while also offering fast WLAN, enhanced GPIO, Bluetooth functionality, and with its higher performance, a wider range of applications.
- 100% compatible with Arudino IDE, Lua and Micropython, it shows robustness, versatility, and reliability in a wide variety of applications and power scenarios.
- All I/O pins have interrupt, PWM, I2C and one-wire capability, except the pin DO.
- Designed with ultra-low power technology, it offers the full range of performance and features of the ESP32 chip. The pin arrangement provides compatibility with the modules developed for the D1 Mini ESP8266 while also offering fast WLAN, enhanced GPIO, Bluetooth functionality, and with its higher performance, a wider range of applications.
Product prices and availability are accurate as of the date/time indicated and are subject to change. Any price and availability information displayed on Amazon at the time of purchase will apply.
