GWQ: Gradient-Aware Weight Quantization for Large Language Models

Large language models (LLMs) show impressive performance in solving complex languagetasks. However, its large number of parameterspresent significant challenges for the deployment and application of the model on edge devices. Compressing large language models to low bits can enable them to run on resource-constrained devices, often leading to performance degradation. To address this problem, we propose gradient-aware weight quantization (GWQ), the first quantization approach for low-bit weight quantization that leverages gradients to localize outliers, requiring only a minimal amount of calibration data for outlier detection. GWQ retains the weights corresponding to the top 1% outliers preferentially at FP16 precision, while the remaining non-outlier weights are stored in a low-bit format. GWQ found experimentally that utilizing the sensitive weights in the gradient localization model is more scientific compared to utilizing the sensitive weights in the Hessian matrix localization model. Compared to current quantization methods, GWQ can be applied to multiple language models and achieves lower PPL on the WikiText2 and C4 dataset. In the zero-shot task, GWQ quantized models have higher accuracy compared to other quantization methods.GWQ is also suitable for multimodal model quantization, and the quantized Qwen-VL family model is more accurate than other methods. zero-shot target detection task dataset RefCOCO outperforms the current stat-of-the-arts method SPQR. GWQ achieves 1.2x inference speedup in comparison to the original model, and effectively reduces the inference memory.

DSORT-MCU: Detecting Small Objects in Real-Time on Microcontroller Units

Advances in lightweight neural networks have revolutionized computer vision in a broad range of IoT applications, encompassing remote monitoring and process automation. However, the detection of small objects, which is crucial for many of these applications, remains an underexplored area in current computer vision research, particularly for low-power embedded devices that host resource-constrained processors. To address said gap, this paper proposes an adaptive tiling method for lightweight and energy-efficient object detection networks, including YOLO-based models and the popular FOMO network. The proposed tiling enables object detection on low-power MCUs with no compromise on accuracy compared to large-scale detection models. The benefit of the proposed method is demonstrated by applying it to FOMO and TinyissimoYOLO networks on a novel RISC-V-based MCU with built-in ML accelerators. Extensive experimental results show that the proposed tiling method boosts the F1-score by up to 225% for both FOMO and TinyissimoYOLO networks while reducing the average object count error by up to 76% with FOMO and up to 89% for TinyissimoYOLO. Furthermore, the findings of this work indicate that using a soft F1 loss over the popular binary cross-entropy loss can serve as an implicit non-maximum suppression for the FOMO network. To evaluate the real-world performance, the networks are deployed on the RISC-V based GAP9 microcontroller from GreenWaves Technologies, showcasing the proposed method's ability to strike a balance between detection performance ($58% - 95%$ F1 score), low latency (0.6 ms/Inference - 16.2 ms/Inference}), and energy efficiency (31 uJ/Inference} - 1.27 mJ/Inference) while performing multiple predictions using high-resolution images on a MCU.

PuLsE: Accurate and Robust Ultrasound-based Continuous Heart-Rate Monitoring on a Wrist-Worn IoT Device

This work explores the feasibility of employing ultrasound (US) US technology in a wrist-worn IoT device for low-power, high-fidelity heart-rate (HR) extraction. US offers deep tissue penetration and can monitor pulsatile arterial blood flow in large vessels and the surrounding tissue, potentially improving robustness and accuracy compared to PPG. We present an IoT wearable system prototype utilizing a commercial microcontroller MCU employing the onboard ADC to capture high frequency US signals and an innovative low-power US pulser. An envelope filter lowers the bandwidth of the US signal by a factor of >5x, reducing the system's acquisition requirements without compromising accuracy (correlation coefficient between HR extracted from enveloped and raw signals, r(92)=0.99, p<0.001). The full signal processing pipeline is ported to fixed point arithmetic for increased energy efficiency and runs entirely onboard. The system has an average power consumption of 5.8mW, competitive with PPG based systems, and the HR extraction algorithm requires only 68kB of RAM and 71ms of processing time on an ARM Cortex-M4 MCU. The system is estimated to run continuously for more than 7 days on a smartwatch battery. To accurately evaluate the proposed circuit and algorithm and identify the anatomical location on the wrist with the highest accuracy for HR extraction, we collected a dataset from 10 healthy adults at three different wrist positions. The dataset comprises roughly 5 hours of HR data with an average of 80.6+-16.3 bpm. During recording, we synchronized the established ECG gold standard with our US-based method. The comparisons yields a Pearson correlation coefficient of r(92)=0.99, p<0.001 and a mean error of 0.69+-1.99 bpm in the lateral wrist position near the radial artery. The dataset and code have been open-sourced at https://github.com/mgiordy/Ultrasound-Heart-Rate

Predictive Spliner: Data-Driven Overtaking in Autonomous Racing Using Opponent Trajectory Prediction

Head-to-head racing against opponents is a challenging and emerging topic in the domain of autonomous racing. We propose Predictive Spliner, a data-driven overtaking planner that learns the behavior of opponents through Gaussian Process (GP) regression, which is then leveraged to compute viable overtaking maneuvers in future sections of the racing track. Experimentally validated on a 1:10 scale autonomous racing platform using Light Detection and Ranging (LiDAR) information to perceive the opponent, Predictive Spliner outperforms State-of-the-Art (SotA) algorithms by overtaking opponents at up to 83.1% of its own speed, being on average 8.4% faster than the previous best-performing method. Additionally, it achieves an average success rate of 84.5%, which is 47.6% higher than the previous best-performing method. The method maintains computational efficiency with a Central Processing Unit (CPU) load of 22.79% and a computation time of 8.4 ms, evaluated on a Commercial off-the-Shelf (CotS) Intel i7-1165G7, making it suitable for real-time robotic applications. These results highlight the potential of Predictive Spliner to enhance the performance and safety of autonomous racing vehicles. The code for Predictive Spliner is available at: https://github.com/ForzaETH/predictive-spliner.

A Survey of Low-bit Large Language Models: Basics, Systems, and Algorithms

Large language models (LLMs) have achieved remarkable advancements in natural language processing, showcasing exceptional performance across various tasks. However, the expensive memory and computational requirements present significant challenges for their practical deployment. Low-bit quantization has emerged as a critical approach to mitigate these challenges by reducing the bit-width of model parameters, activations, and gradients, thus decreasing memory usage and computational demands. This paper presents a comprehensive survey of low-bit quantization methods tailored for LLMs, covering the fundamental principles, system implementations, and algorithmic strategies. An overview of basic concepts and new data formats specific to low-bit LLMs is first introduced, followed by a review of frameworks and systems that facilitate low-bit LLMs across various hardware platforms. Then, we categorize and analyze techniques and toolkits for efficient low-bit training and inference of LLMs. Finally, we conclude with a discussion of future trends and potential advancements of low-bit LLMs. Our systematic overview from basic, system, and algorithm perspectives can offer valuable insights and guidelines for future works to enhance the efficiency and applicability of LLMs through low-bit quantization.

Aerodynamic Performance and Impact Analysis of a MEMS-Based Non-Invasive Monitoring System for Wind Turbine Blades

Wind power generation plays a crucial role in transitioning away from fossil fuel-dependent energy sources, contributing significantly to the mitigation of climate change. Monitoring and evaluating the aerodynamics of large wind turbine rotors is crucial to enable more wind energy deployment. This is necessary to achieve the European climate goal of a reduction in net greenhouse gas emissions by at least 55% by 2030, compared to 1990 levels. This paper presents a comparison between two measurement systems for evaluating the aerodynamic performance of wind turbine rotor blades on a full-scale wind tunnel test. One system uses an array of ten commercial compact ultra-low power micro-electromechanical systems (MEMS) pressure sensors placed on the blade surface, while the other employs high-accuracy lab-based pressure scanners embedded in the airfoil. The tests are conducted at a Reynolds number of 3.5 x 10^6, which represents typical operating conditions for wind turbines. MEMS sensors are of particular interest, as they can enable real-time monitoring which would be impossible with the ground truth system. This work provides an accurate quantification of the impact of the MEMS system on the blade aerodynamics and its measurement accuracy. Our results indicate that MEMS sensors, with a total sensing power below 1.6 mW, can measure key aerodynamic parameters like Angle of Attack (AoA) and flow separation with a precision of 1{\deg}. Although there are minor differences in measurements due to sensor encapsulation, the MEMS system does not significantly compromise blade aerodynamics, with a maximum shift in the angle of attack for flow separation of only 1{\deg}. These findings indicate that surface and low-power MEMS sensor systems are a promising approach for efficient and sustainable wind turbine monitoring using self-sustaining Internet of Things devices and wireless sensor networks.

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.

RF Power Transmission for Self-sustaining Miniaturized IoT Devices

Radio Frequency (RF) wireless power transfer is a promising technology that has the potential to constantly power small Internet of Things (IoT) devices, enabling even battery-less systems and reducing their maintenance requirements. However, to achieve this ambitious goal, carefully designed RF energy harvesting (EH) systems are needed to minimize the conversion losses and the conversion efficiency of the limited power. For intelligent internet of things sensors and devices, which often have non-constant power requirements, an additional power management stage with energy storage is needed to temporarily provide a higher power output than the power being harvested. This paper proposes an RF wireless power energy conversion system for miniaturized IoT composed of an impedance matching network, a rectifier, and power management with energy storage. The proposed sub-system has been experimentally validated and achieved an overall power conversion efficiency (PCE) of over 30 % for an input power of -10 dBm and a peak efficiency of 57 % at 3 dBm.

i-CardiAx: Wearable IoT-Driven System for Early Sepsis Detection Through Long-Term Vital Sign Monitoring

Sepsis is a significant cause of early mortality, high healthcare costs, and disability-adjusted life years. Digital interventions like continuous cardiac monitoring can help detect early warning signs and facilitate effective interventions. This paper introduces i-CardiAx, a wearable sensor utilizing low-power high-sensitivity accelerometers to measure vital signs crucial for cardiovascular health: heart rate (HR), blood pressure (BP), and respiratory rate (RR). Data collected from 10 healthy subjects using the i-CardiAx chest patch were used to develop and evaluate lightweight vital sign measurement algorithms. The algorithms demonstrated high performance: RR (-0.11 $\pm$ 0.77 breaths\min), HR (0.82 $\pm$ 2.85 beats\min), and systolic BP (-0.08 $\pm$ 6.245 mmHg). These algorithms are embedded in an ARM Cortex-M33 processor with Bluetooth Low Energy (BLE) support, achieving inference times of 4.2 ms for HR and RR, and 8.5 ms for BP. Additionally, a multi-channel quantized Temporal Convolutional Neural (TCN) Network, trained on the open-source HiRID dataset, was developed to detect sepsis onset using digitally acquired vital signs from i-CardiAx. The quantized TCN, deployed on i-CardiAx, predicted sepsis with a median time of 8.2 hours and an energy per inference of 1.29 mJ. The i-CardiAx wearable boasts a sleep power of 0.152 mW and an average power consumption of 0.77 mW, enabling a 100 mAh battery to last approximately two weeks (432 hours) with continuous monitoring of HR, BP, and RR at 30 measurements per hour and running inference every 30 minutes. In conclusion, i-CardiAx offers an energy-efficient, high-sensitivity method for long-term cardiovascular monitoring, providing predictive alerts for sepsis and other life-threatening events.

Machine Learning In-Sensors: Computation-enabled Intelligent Sensors For Next Generation of IoT

Smart sensors are an emerging technology that allows combining the data acquisition with the elaboration directly on the Edge device, very close to the sensors. To push this concept to the extreme, technology companies are proposing a new generation of sensors allowing to move the intelligence from the edge host device, typically a microcontroller, directly to the ultra-low-power sensor itself, in order to further reduce the miniaturization, cost and energy efficiency. This paper evaluates the capabilities of a novel and promising solution from STMicroelectronics. The presence of a floating point unit and an accelerator for binary neural networks provide capabilities for in-sensor feature extraction and machine learning. We propose a comparison of full-precision and binary neural networks for activity recognition with accelerometer data generated by the sensor itself. Experimental results have demonstrated that the sensor can achieve an inference performance of 10.7 cycles/MAC, comparable to a Cortex-M4-based microcontroller, with full-precision networks, and up to 1.5 cycles/MAC with large binary models for low latency inference, with an average energy consumption of only 90 $\mu$J/inference with the core running at 5 MHz.