TinyBird-ML: An ultra-low Power Smart Sensor Node for Bird Vocalization Analysis and Syllable Classification

Animal vocalisations serve a wide range of vital functions. Although it is possible to record animal vocalisations with external microphones, more insights are gained from miniature sensors mounted directly on animals' backs. We present TinyBird-ML; a wearable sensor node weighing only 1.4 g for acquiring, processing, and wirelessly transmitting acoustic signals to a host system using Bluetooth Low Energy. TinyBird-ML embeds low-latency tiny machine learning algorithms for song syllable classification. To optimize battery lifetime of TinyBird-ML during fault-tolerant continuous recordings, we present an efficient firmware and hardware design. We make use of standard lossy compression schemes to reduce the amount of data sent over the Bluetooth antenna, which increases battery lifetime by 70% without negative impact on offline sound analysis. Furthermore, by not transmitting signals during silent periods, we further increase battery lifetime. One advantage of our sensor is that it allows for closed-loop experiments in the microsecond range by processing sounds directly on the device instead of streaming them to a computer. We demonstrate this capability by detecting and classifying song syllables with minimal latency and a syllable error rate of 7%, using a light-weight neural network that runs directly on the sensor node itself. Thanks to our power-saving hardware and software design, during continuous operation at a sampling rate of 16 kHz, the sensor node achieves a lifetime of 25 hours on a single size 13 zinc-air battery.

Investigation of mmWave Radar Technology For Non-contact Vital Sign Monitoring

Non-contact vital sign monitoring has many advantages over conventional methods in being comfortable, unobtrusive and without any risk of spreading infection. The use of millimeter-wave (mmWave) radars is one of the most promising approaches that enable contact-less monitoring of vital signs. Novel low-power implementations of this technology promise to enable vital sign sensing in embedded, battery-operated devices. The nature of these new low-power sensors exacerbates the challenges of accurate and robust vital sign monitoring and especially the problem of heart-rate tracking. This work focuses on the investigation and characterization of three Frequency Modulated Continuous Wave (FMCW) low-power radars with different carrier frequencies of 24 GHz, 60 GHz and 120 GHz. The evaluation platforms were first tested on phantom models that emulated human bodies to accurately evaluate the baseline noise, error in range estimation, and error in displacement estimation. Additionally, the systems were also used to collect data from three human subjects to gauge the feasibility of identifying heartbeat peaks and breathing peaks with simple and lightweight algorithms that could potentially run in low-power embedded processors. The investigation revealed that the 24 GHz radar has the highest baseline noise level, 0.04mm at 0{\deg} angle of incidence, and an error in range estimation of 3.45 +- 1.88 cm at a distance of 60 cm. At the same distance, the 60 GHz and the 120 GHz radar system shows the least noise level, 0.0lmm at 0{\deg} angle of incidence, and error in range estimation 0.64 +- 0.01 cm and 0.04 +- 0.0 cm respectively. Additionally, tests on humans showed that all three radar systems were able to identify heart and breathing activity but the 120 GHz radar system outperformed the other two.

AIM 2020 Challenge on Efficient Super-Resolution: Methods and Results

This paper reviews the AIM 2020 challenge on efficient single image super-resolution with focus on the proposed solutions and results. The challenge task was to super-resolve an input image with a magnification factor x4 based on a set of prior examples of low and corresponding high resolution images. The goal is to devise a network that reduces one or several aspects such as runtime, parameter count, FLOPs, activations, and memory consumption while at least maintaining PSNR of MSRResNet. The track had 150 registered participants, and 25 teams submitted the final results. They gauge the state-of-the-art in efficient single image super-resolution.