Tiny cameras are ubiquitous in embedded devices like smart glasses and drones. On-device learning technique empowers these resource-constrained devices to adapt to changing environments locally. However, existing camera modules rely on diverse programming environments and APIs. This heterogeneity impedes the validation and deployment of practical on-device learning algorithms. In this work, we introduce CamOL, the first full-stack on-device learning scheme for heterogeneous tiny cameras. CamOL integrates a complete workflow encompassing preprocessing, learning, inference, and visualization. For learning, CamOL adopts a library-free code design for maximum portability and programmability, and incorporates a proposed staged training method for efficient full-parameter fine-tuning. For inferring, we have developed a suite of operators and achieved operator fusion for minimal latency. We demonstrate CamOL with a compact, low-cost (<$10) prototype that features an engaging and interactive visualization. This allows participants to intuitively experience the entire on-device learning pipeline for different applications in real-time. Moreover, CamOL can also serve as a handy testbed for embedded vision intelligence.

This paper presents Serafin, the first full-stack, sub-mW, and versatile Bluetooth-enabled RF sensor that brings transparent RF sensing to any mobile and IoT device: it independently conducts the whole RF sensing process from RF signal reception to sensing result computation in a wide variety of sensing tasks with only negligible power consumption. At the core of Serafin are our two designs that address the challenge posed by the stringent sub-mW power constraint to jointly achieving versatility and full stackness. Specifically, (i) we utilize the ambient Bluetooth advertising signal as the signal for sensing, and extract the phase difference of the sensing signals received by each antenna pair from the amplitude of their sum signal, which avoids power-hungry hardware components and intensive computation, and (ii) we employ low-power MCU as the computation hardware, and suppress its power consumption by activating it adaptively only when necessary and customizing a light-weight neural network model that still ensures satisfactory inference accuracy. Our extensive experiments on 6 representative sensing tasks show that Serafin achieves competitive sensing performance, but consumes only around 500–900μW power, which is 3–4 orders of magnitude lower than those of existing full-stack and versatile counterparts.

This paper demonstrates Serafin, the first full-stack, sub-mW, and versatile Bluetooth-enabled RF sensor that brings transparent RF sensing to mobile and IoT device: it independently conducts the whole RF sensing process from RF signal reception to sensing result computation in a wide variety of sensing tasks with only negligible power consumption. At the core of Serafin are our two designs that address the challenge posed by the stringent sub-mW power constraint to jointly achieving versatility and full stackness. Specifically, (i) we utilize the ambient Bluetooth advertising signal as the signal for sensing, and extract the phase difference of the sensing signals received by each antenna pair from the amplitude of their sum signal, which avoids power-hungry hardware components and intensive computation, and (ii) we employ low-power MCU as the computation hardware, and suppress its power consumption by activating it only when necessary and customizing a light-weight yet versatile neural network model.

With the rapid advance of the Internet of Things (IoT), more and more wearable devices are being developed for real-time monitoring. Most of these existing monitors are powered by chemical batteries. Replacing and disposing batteries for an exponentially increasing number of IoT nodes prohibitively results in labor-intensive maintenance. It is also environmentally unfriendly. Gls EH, reclaiming the wasted ambient energy, is a promising technology for battery-free IoT. This article presents a novel motion-powered real-time human activity recognition (HAR) system called motion-powered HAR system (MP-HAR), where the harvester works as both an energy source and sensor. MP-HAR emphasizes low-power as well as low-cost characteristics, encompassing four necessary units: 1) energy transduction unit (ETU); 2) energy management unit (EMU); 3) energy user unit (EUU); and 4) edge computing unit (ECU). In particular, the unique intermittent operation based on the reconfigurable on/off threshold voltages given by the well-rounded energy-aware circuit has been discussed in detail. The balance between energy supply and information demand in MP-HAR has been achieved by using a handy design. Utilizing the unique correspondence between human arm swing frequency and harvested energy, the information flows with energy inside the system. By knowing the interval between transmitted packets, MP-HAR has realized HAR in real time. Moreover, an all-in-one prototype has been fabricated to validate the performance of the proposed system. Lab and field tests have demonstrated that MP-HAR can reliably recognize different human activities, such as standing, walking, jogging, and running. As a cyber-electro-mechanical co-design, MP-HAR has brought a promising solution for pervasive HAR and ubiquitous IoT.

Nowadays, the Industrial Internet of Things (IIoT) plays a more and more significant role in smart manufacturing. Predictive Maintenance (PdM) is one of the essential applications, recognizing the current status of the machine and preventing disastrous breakdowns. End-point sensors for such monitoring systems are powered mainly by batteries. As IIoT grows, constantly replacing batteries across thousands of devices is cost-prohibitive. In addition, tremendous original sensing data are wirelessly transmitted to the server for data analysis, causing colossal energy consumption. In this paper, we propose the first self-powered on-device PdM system based on piezoelectric energy harvesting and tiny machine learning (Tiny ML). A trained TinyML model is deployed on the low-cost microcontroller (MCU) for on-device inferring; only the diagnosis result is transmitted. With an emphasis on ultra-low-power demands, a piezoelectric energy harvester is utilized as an energy source and self-powered sensor (SPS) simultaneously. The energy-aware circuit provides reconfigurable on/off threshold voltages for efficient and robust intermittent operation. The balance between energy supply and demand in the battery-free system has been achieved by a handy design. A rich SPS dataset has been collected in a simulated vibration environment and analyzed by five well-known machine-learning models. Random forest stands out given ultra-small data length and sampling rate with accuracy up to 99% for four-class similar vibration diagnosis. Lab test validates the feasibility and performance. As a cyber-electro-mechanical co-design, the system provides a promising solution to the ubiquitous artificial intelligence of things (AIoT).