For Alejandro, helping to solve this problem really hit home as it’s a big issue in his native country of Mexico. In his words, “The environmental effects of illegal logging include deforestation, the loss of biodiversity and the emission of greenhouse gases. Illegal logging has contributed to conflicts with indigenous and local populations, violence, human rights abuses, corruption, funding of armed conflicts and the worsening of poverty.”
The Illegal Logging Detector starts with the QuickLogic QuickFeather board and its integrated EOS S3 platform SOC. The open-source QuickFeather board also includes an Infineon microphone which was used in the application to record audio samples of chainsaws and human conversations which were then captured and used as training models for the SensiML Analytics Toolkit. “Neutral silence” was also used to train the model in order to avoid false positives. The SensiML tool output was then tested to confirm that it was identifying the two key sounds correctly.
Results of the local SensiML-based AI were then fed into an STMicroelectronics LoRa long-range, low power radio network board. This approach created a straightforward way for the logging detector to communicate with the outside world without needing a lot of power.
The combination of the SensiML tools and QuickLogic EOS S3 / QuickFeather platform enabled the developer to create a highly accurate system without the need for cloud-based AI which would have been impractical in this case due to power and latency constraints. SensiML’s toolkit’s ability to run on the local Arm Cortex M4F MCU embedded in the EOS S3 SoC and the ultra-low power consumption of the EOS S3 platform itself helped Alejandro create a solution that was innovative, effective, and practical.
See Winning Hackster Batter Powered Project Details:
To check out the projects, please visit our Hackster page
* All product names, logos, and brands are property of their respective owners.