Table 1.

Overview on tree-cutting detection contributions in the literature and respective limitations.

Reference	Main Contribution	Main Limitations
[14]	Low-power microcontroller with sound/vibration sensors and Xbee	Effective only with chainsaw sounds, no long-range wireless transmission
[15]	Ultra-low-power device, sound/vibration sensors, Zigbee with fog computing	Effective only with chainsaw sounds, no long-range wireless transmission
[16]	Low-power microcontroller with sound/vibration sensors and GSM communication	Threshold-based approach, no low-power wireless transmission
[17]	Detection and location of chainsaws through air/soil sound TDOA	Effective only with chainsaw sounds, no wireless communication
[7]	Arduino/Raspberry Pi sound detector with LoRa communication	Effective only with chainsaw sounds, medium–low-power hardware (i.e., Raspberry Pi)
[28]	Chainsaw sound detection adopting spectrograms	Effective only with chainsaw sounds, no details are given on electronics and communication
[29]	92% accuracy on axe stroke sound detection through Gaussian mixture model, K-means Clustering, and Principal Component Analysis.	Effective only with axe stroke sounds, no details on electronics and communication
[18]	94.4% accuracy on chainsaw sound detection through neural networks, WiFi and ZigBee communication	Server-side classification and short-range wireless protocols
[30]	94% accuracy on chainsaw through Neural networks, chainsaw location through TDOA	Medium–low-power hardware (i.e., Raspberry Pi), no long-range communication (i.e., 802.15.4)