Optimizing IoT-Based Asset and Utilization Tracking: Efficient Activity Classification with MINIROCKET on Resource-Constrained Devices

This paper introduces an effective solution for retrofitting construction power tools with low-power Internet of Things (IoT) to enable accurate activity classification. We address the challenge of distinguishing between when a power tool is being moved and when it is actually being used. To achieve classification accuracy and power consumption preser-vation a newly released algorithm called MINImally RandOm Convolutional KErnel Transform (MINIROCKET) was employed. Known for its accuracy, scalability, and fast training for time-series classification, in this paper, it is proposed as a Tiny ML algorithm for inference on resource-constrained IoT devices. The paper demonstrates the portability and performance of MINIROCKET on a resource-constrained, ultra-low power sensor node for floating-point and fixed-point arithmetic, matching up to 1% of the floating-point accuracy. The hyperparameters of the algorithm have been optimized for the task at hand to find a Pareto point that balances memory usage, accuracy and energy consumption. For the classification problem, we rely on an accelerometer as the sole sensor source, and Bluetooth Low Energy(ble)for data transmission. Extensive real-world construction data, using 16 different power tools, were collected, labeled, and used to validate the algorithm's performance directly embedded in the IoT device. Experimental results demonstrate that the proposed solution achieves an accuracy of 96.9% in distinguishing between real usage status and other motion statuses while consuming only 7 kB of flash and 3 kB of RAM. The final application exhibits an average current consumption of less than 15 µW for the whole system, resulting in battery life performance ranging from 3 to 9 years depending on the battery capacity (250 - 500 mAh) and the number of power tool usage hours (100 - 1500 h).