SmartTag: An Ultra Low Power Asset Tracking and Usage Analysis IoT Device with Embedded ML Capabilities

Giordano, Marco; Fischer, Raphael; Crabolu, Michele; Bellusci, Giovanni; Magno, Michele

doi:10.1109/sas51076.2021.9530182

Cited by 7 publications

(5 citation statements)

References 10 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…An on-device detection of the activity of power tools has already been attempted in previous work by the same authors [18], [19]. In those works, the detection has first been done by thresholding the fast fourier transform (FFT) extracted from accelerometer data, and later also by employing deep learning on the edge with a convolutional neural network (CNN)-based approach.…”

Section: Related Workmentioning

confidence: 99%

“…The sensor node, named SMARTTAG and introduced in [18], [19], aims for ultra-low power consumption and energy efficiency. Fig.…”

Section: Hardwarementioning

confidence: 99%

“…With the goal of bringing intelligence in a compact and ultra-low power tag, in this work, the MiniRocket algorithm has been efficiently ported on a low-power MCU. A sensor node previously designed in [18], [19] has been used for an extensive evaluation of the embedded performance and power consumption, demonstrating the feasibility of advanced activity recognition in low-power processors. We decided to base our evaluation on accelerometer data only, as they are available at low cost and require very little power (e.g.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

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

Giordano,

Cortesi,

Crabolu

et al. 2023

2023 IEEE 9th World Forum on Internet of Things (WF-IoT)

Self Cite

View full text Add to dashboard Cite

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 preservation a newly released algorithm called MINImally RandOm Convolutional KErnel Transform (MINIROCKET) was employed. Known for its accuracy, scalability, and fast training for timeseries classification, in this paper, it is proposed as a TinyML 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).

show abstract

Section: Related Workmentioning

confidence: 99%

“…The sensor node, named SMARTTAG and introduced in [18], [19], aims for ultra-low power consumption and energy efficiency. Fig.…”

Section: Hardwarementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

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

Giordano,

Cortesi,

Crabolu

et al. 2023

2023 IEEE 9th World Forum on Internet of Things (WF-IoT)

Self Cite

View full text Add to dashboard Cite

show abstract

“…Rechargeable batteries and super-capacitors serve as storage elements to cope with such fluctuations, but are often limited in capacity by size and cost constraints, potentially leading to system failure. Therefore, meticulous energy resource management is required, and smart energy-aware algorithms are a very promising avenue [10,16].…”

Section: Introductionmentioning

confidence: 99%

Energy-Aware Adaptive Sampling for Self-Sustainability in Resource-Constrained IoT Devices

Giordano,

Cortesi,

Mekikis

et al. 2023

Proceedings of the 11th International Workshop on Energy Harvesting &Amp; Energy-Neutral Sensing Systems

View full text Add to dashboard Cite

In the ever-growing Internet of Things (IoT) landscape, smart power management algorithms combined with energy harvesting solutions are crucial to obtain self-sustainability. This paper presents an energy-aware adaptive sampling rate algorithm designed for embedded deployment in resource-constrained, battery-powered IoT devices. The algorithm, based on a finite state machine (FSM) and inspired by Transmission Control Protocol (TCP) Reno's additive increase and multiplicative decrease, maximizes sensor sampling rates, ensuring power self-sustainability without risking battery depletion. Moreover, we characterized our solar cell with data acquired over 48 days and used the model created to obtain energy data from an open-source world-wide dataset.To validate our approach, we introduce the EcoTrack device, a versatile device with global navigation satellite system (GNSS) capabilities and Long-Term Evolution Machine Type Communication (LTE-M) connectivity, supporting MQTT protocol for cloud data relay. This multi-purpose device can be used, for instance, as a health and safety wearable, remote hazard monitoring system, or as a global asset tracker.The results, validated on data from three different European cities, show that the proposed algorithm enables self-sustainability while maximizing sampled locations per day. In experiments conducted with a 3000 mAh battery capacity, the algorithm consistently maintained a minimum of 24 localizations per day and achieved peaks of up to 3000.

show abstract

“…Different quantities should thus be evaluated for each of the scenarios: temperature and humidity can be measured to monitor atmospheric conditions, while vibrations, and so accelerations, can be exploited for activity/operation/drop recognition. This work builds on top of [26]. In particular, this paper presents the design, implementation and experimental evaluation of a long-lasting SmartTag for remote power tools monitoring with embedded sensors and intelligence at the edge.…”

Section: Introductionmentioning

confidence: 99%

Design and Performance Evaluation of an Ultralow-Power Smart IoT Device With Embedded TinyML for Asset Activity Monitoring

Giordano¹,

Baumann²,

Crabolu

et al. 2022

IEEE Trans. Instrum. Meas.

Self Cite

View full text Add to dashboard Cite

SmartTag: An Ultra Low Power Asset Tracking and Usage Analysis IoT Device with Embedded ML Capabilities

Cited by 7 publications

References 10 publications

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

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

Energy-Aware Adaptive Sampling for Self-Sustainability in Resource-Constrained IoT Devices

Design and Performance Evaluation of an Ultralow-Power Smart IoT Device With Embedded TinyML for Asset Activity Monitoring

Contact Info

Product

Resources

About