Search

Abstract Electroencephalography (EEG) is widely used to monitor epileptic seizures, and standard clinical practice consists of monitoring patients in dedicated epilepsy monitoring units via video surveillance and cumbersome EEG caps. Such a setting is not compatible with long-term tracking under typical living conditions, thereby motivating the development of unobtrusive wearable solutions. However, wearable EEG devices present the challenges of fewer channels, restricted computational capabilities, and lower signal-to-noise ratio. Moreover, artifacts presenting morphological similarities to seizures act as major noise sources and can be misinterpreted as seizures. This paper presents a combined seizure and artifacts detection framework targeting wearable EEG devices based on Gradient Boosted Trees. The seizure detector achieves nearly zero false alarms with average sensitivity values of $$65.27\%$$ 65.27 % for 182 seizures from the CHB-MIT dataset and $$57.26\%$$ 57.26 % for 25 seizures from the private dataset with no preliminary artifact detection or removal. The artifact detector achieves a state-of-the-art accuracy of $$93.95\%$$ 93.95 % (on the TUH-EEG Artifact Corpus dataset). Integrating artifact and seizure detection significantly reduces false alarms—up to $$96\%$$ 96 % compared to standalone seizure detection. Optimized for a Parallel Ultra-Low Power platform, these algorithms enable extended monitoring with a battery lifespan reaching 300 h. These findings highlight the benefits of integrating artifact detection in wearable epilepsy monitoring devices to limit the number of false positives.

This paper deploys and explores variants of TinyissimoYOLO, a highly flexible and fully quantized ultra-lightweight object detection network designed for edge systems with a power envelope of a few milliwatts. With experimental measurements, we present a comprehensive characterization of the network’s detection performance, exploring the impact of various parameters, including input resolution, number of object classes, and hidden layer adjustments. We deploy variants of TinyissimoYOLO on state-of-the-art ultra-low-power extreme edge platforms, presenting a detailed comparison on latency, energy efficiency, and their ability to efficiently parallelize the workload. In particular, the paper presents a comparison between a RISC-V-based parallel processor (GAP9 from GreenWaves Technologies) with and without use of its on-chip hardware accelerator, an ARM Cortex-M7 core (STM32H7 from ST Microelectronics), two ARM Cortex-M4 cores (STM32L4 from ST Microelectronics and Apollo4b from Ambiq), and a multi-core platform aimed at edge AI applications with a CNN hardware accelerator (MAX78000 from Analog Devices). Experimental results show that the GAP9’s hardware accelerator achieves the lowest inference latency and energy at $\mathrm {2.12ms }$ and $\mathrm {150~\mu \text {J} }$ respectively, which is around 2x faster and 20% more energy efficient than the next best platform, the MAX78000. The hardware accelerator of GAP9 can even run an increased resolution version of TinyissimoYOLO with $112\times 112$ pixels and 10 detection classes within 3.2 ms, consuming $\mathrm {245~\mu \text {J} }$ . We also deployed and profiled a multi-core implementation on GAP9 at different core voltages and frequencies, achieving $\mathrm {11.3ms }$ with the lowest-latency and $\mathrm {490~\mu \text {J} }$ with the most energy-efficient configuration. With this paper, we demonstrate the flexibility of TinyissimoYOLO and prove its detection accuracy on a widely used detection dataset. Furthermore, we demonstrate its suitability for real-time ultra-low-power edge inference.

Modern manufacturing industry relies on complex machinery that requires skills, attention, and precise safety certifications. Protecting operators in the machine’s surroundings while at the same time reducing the impact on the normal workflow is a major challenge. In particular, safety systems based on proximity sensing of humans or obstacles require that the detection is accurate, low-latency, and robust against variations in environmental conditions. This work proposes a functional safety solution for collision avoidance relying on Ultrasounds (US) and a Temporal Convolutional Network (TCN) suitable for deployment directly at the edge on a low-power Microcontroller Unit (MCU). The setup allowed to acquire a sensor-fusion dataset with 9 US sensors mounted on a real industrial woodworking machine. Applying incremental training, the proposed TCN achieved sensitivity 90.5%, specificity 95.2%, and AUROC 0.972 on data affected by the typical acoustic noise of an industrial facility, an accuracy comparable with the State-of-the-Art (SoA). Deployment on an STM32H7 MCU yielded a memory footprint of 560 B (3× less than SoA), with an extremely low latency of 5.0 ms and an energy consumption of 8.2 mJ per inference (both >2.3× less than SoA). The proposed solution increases its robustness against acoustic noise by leveraging new data, and it fits the resource budget of real-time operation execution on resource-constrained embedded devices. It is thus promising for generalization to different industrial settings and for scale-up to wider monitored spaces.

Introduction Professional sports are fiercely competitive. In ski jumping, for example, even small changes in take-off and flight can make a decisive difference between victory and defeat (Elfmark et al., 2022). Within the short time of a jump, athletes must learn to solve complex motor control problems while being exposed to harsh environmental conditions, e.g., wind, snow, and low temperatures. The actual take-off occurs within the blink of an eye (~300 ms) and an aerodynamically favourable and stable flight position should be attained immediately. Fine control of the centre of gravity in the in-run favours high speeds to generate optimum momentum during take-off (Müller, 2008). In flight, athletes can voluntarily influence aerodynamics by changing their body position. However, non-optimal flight positions occur unintentionally or due to incorrect behaviour. Furthermore, as a non-cyclical sport, ski jumping suffers from low repetition rates, which impairs the effectiveness of training. Thus, increasing the learning rate for each jump is a key success factor. Biofeedback methods have been shown to accelerate motor learning in athletes (Mulder & Hulstijn, 1985). Current sensor technologies in ski jumping do not meet the requirements for a truly wearable system, which must be energy-efficient, unobtrusive and barely noticeable (so as not to interfere with natural movement behaviour and jumping technique) and, in particular, must be equipped with a wireless link (for real-time data analysis, e.g. on the trainer tower; Schulthess et al., 2023). Methods The proposed system consists of two multi-sensor nodes: One node is hidden in a modified ski jumping boot, integrating three force-sensing resistor sensors to measure the pressure distribution on the foot soles of ski jumpers. The second sensor node is located in the ski goggles and contains RGB LEDs that provide visual biofeedback in the peripheral vision. Results We have calculated the total power consumption of our systems to be 2.52 mW, meeting requirements for multi-day operation between battery recharges. Our on-device body position classification model achieves an accuracy of 92.7% in recognising body positions from data recorded in the laboratory. Discussion/Conclusion This is the first truly wearable training system in ski jumping, offering professional athletes a new augmented experience, aimed at accelerating motor learning. In addition, the real-time data transmission of biomechanically relevant characteristics facilitates the work of the training team and could in the future enable more informative and entertaining television broadcasts. References Elfmark, O., Ettema, G., & Gilgien, M. (2022). Assessment of the steady glide phase in ski jumping. Journal of Biomechanics, 139, 111139. https://doi.org/10.1016/j.jbiomech.2022.111139 Mulder, T., & Hulstijn, W. (1985). Sensory feedback in the learning of a novel motor task. Journal of Motor Behavior, 17(1), 110–128. https://doi.org/10.1080/00222895.1985.10735340 Müller, W. (2008). Performance factors in ski jumping. In H. Nørstrud (Ed.), Sport Aerodynamics (pp. 139– 160). Springer. https://doi.org/10.1007/978-3-211-89297-8_8 Schulthess, L., Ingolfsson, T. M., Nölke, M., Magno, M., Benini, L., & Leitner, C. (2023). Skilog: A smart sensor system for performance analysis and biofeedback in ski jumping. https://doi.org/10.48550/arXiv.2309.14455

Abstract Supercomputers are the most powerful computing machines available to society. They play a central role in economic, industrial, and societal development. While they are used by scientists, engineers, decision-makers, and data-analyst to computationally solve complex problems, supercomputers and their hosting datacenters are themselves complex power-hungry systems. Improving their efficiency, availability, and resiliency is vital and the subject of many research and engineering efforts. Still, a major roadblock hinders researchers: dearth of reliable data describing the behavior of production supercomputers. In this paper, we present the result of a ten-year-long project to design a monitoring framework (EXAMON) deployed at the Italian supercomputers at CINECA datacenter. We disclose the first holistic dataset of a tier-0 Top10 supercomputer. It includes the management, workload, facility, and infrastructure data of the Marconi100 supercomputer for two and half years of operation. The dataset (published via Zenodo) is the largest ever made public, with a size of 49.9TB before compression. We also provide open-source software modules to simplify access to the data and provide direct usage examples.

Wind energy generation plays a vital role in transitioning from fossil fuel-based energy sources and in alleviating the impacts of global warming. However, global wind energy coverage still needs to rise, while requiring a significant step up in conversion efficiency: monitoring wind flow and operational parameters of wind turbines is an essential prerequisite for coverage and conversion efficiency optimization. This paper presents a low-power, self-sustainable, and time-synchronised system for aerodynamic and acoustic measurements on operating wind turbines. It includes 40 high-accuracy barometers, 10 microphones, 5 differential pressure sensors, and implements a coarse time synchronisation on top of a Bluetooth Low Energy 5.1 protocol tuned for long-range communications. Moreover, we field-assessed the node capability to collect precise and accurate aerodynamic data with a multi-node setup. Outdoor experimental tests revealed that the system can acquire heterogeneous data with a time synchronisation error below $\mathrm {100~ \mu \text {s} }$ and sustain a data rate of 600 kbps over 400 m with up to 5 sensor nodes, enough to fully instrument a wind turbine. The proposed method does not add any traffic overhead on the Bluetooth Low Energy 5.1 protocol, fully relying only on connection events and withstands transmission discontinuity often present in long range wireless communications.

On-chip deep neural network (DNN) inference and training at the Extreme-Edge (TinyML) impose strict latency, throughput, accuracy, and flexibility requirements. Heterogeneous clusters are promising solutions to meet the challenge, combining the flexibility of DSP-enhanced cores with the performance and energy boost of dedicated accelerators. We present DARKSIDE, a System-on-Chip with a heterogeneous cluster of eight RISC-V cores enhanced with 2-b to 32-b mixed-precision integer arithmetic. To boost the performance and efficiency on key compute-intensive DNN kernels, the cluster is enriched with three digital accelerators: 1) a specialized engine for low-data-reuse depthwise convolution kernels (up to 30 MAC/cycle); 2) a minimal overhead datamover to marshal 1–32-b data on-the-fly; and 3) a 16-b floating-point tensor product engine (TPE) for tiled matrix-multiplication acceleration. DARKSIDE is implemented in 65-nm CMOS technology. The cluster achieves a peak integer performance of 65 GOPS and a peak efficiency of 835 GOPS/W when working on 2-b integer DNN kernels. When targeting floating-point tensor operations, the TPE provides up to 18.2 GFLOPS of performance or 300 GFLOPS/W of efficiency—enough to enable on-chip floating-point training at competitive speed coupled with ultralow power quantized inference.

The awareness of rock shape dependence in rockfall hazard assessment is growing, but experimental and field studies are scarce. This study presents a large data set of induced single block rockfall events quantifying the influence of rock shape and mass on its complex kinematic behaviour.

Abstract Brain-inspired high-dimensional (HD) computing represents and manipulates data using very long, random vectors with dimensionality in the thousands. This representation provides great robustness for various classification tasks where classifiers operate at low signal-to-noise ratio (SNR) conditions. Similarly, hyperdimensional modulation (HDM) leverages the robustness of complex-valued HD representations to reliably transmit information over a wireless channel, achieving a similar SNR gain compared to state-of-the-art codes. Here, we first propose methods to improve HDM in two ways: (1) reducing the complexity of encoding and decoding operations by generating, manipulating, and transmitting bipolar or integer vectors instead of complex vectors; (2) increasing the SNR gain by 0.2 dB using a new soft-feedback decoder; it can also increase the additive superposition capacity of HD vectors up to 1.7 $$\times$$ × in noise-free cases. Secondly, we propose to combine encoding/decoding aspects of communication with classification into a single framework by relying on multifaceted HD representations. This leads to a near-channel classification (NCC) approach that avoids transformations between different representations and the overhead of multiple layers of encoding/decoding, hence reducing latency and complexity of a wireless smart distributed system while providing robustness against noise and interference from other nodes. We provide a use-case for wearable hand gesture recognition with 5 classes from 64 EMG sensors, where the encoded vectors are transmitted to a remote node for either performing NCC, or reconstruction of the encoded data. In NCC mode, the original classification accuracy of 94% is maintained, even in the channel at SNR of 0 dB, by transmitting 10,000-bit vectors. We remove the redundancy by reducing the vector dimensionality to 2048-bit that still exhibits a graceful degradation: less than 6% accuracy loss is occurred in the channel at − 5 dB, and with the interference from 6 nodes that simultaneously transmit their encoded vectors. In the reconstruction mode, it improves the mean-squared error by up to 20 dB, compared to standard decoding, when transmitting 2048-dimensional vectors.

The implementation of memory-augmented neural networks using conventional computer architectures is challenging due to a large number of read and write operations. Here, Karunaratne, Schmuck et al. propose an architecture that enables analog in-memory computing on high-dimensional vectors at accuracy matching 32-bit software equivalent.

This article presents the design and characterisation of a new low-power hardware platform to integrate unmanned aerial vehicle and wireless sensor technologies. In combination, these technologies can overcome data collection and maintenance problems of in situ monitoring in remote and extreme environments. Precision localisation in support of maximum efficiency mid-range inductive power transfer when recharging devices and increased throughput between drone and device are needed for data intensive monitoring applications, and to balance proximity time for devices powered by supercapacitors that recharge in seconds. The platform described in this article incorporates ultra-wideband technology to achieve high-performance ranging and high data throughput. It enables the development of a new localisation system that is experimentally shown to improve accuracy by around two orders of magnitude to 10 cm with respect to GNSS and achieves almost 6 Mbps throughput in both lab and field conditions. These results are supported by extensive modelling and analysis. The platform is designed for application flexibility, and therefore includes a wide range of sensors and expansion possibilities, with source code for two applications made immediately available as part of a open source project to support research and development in this new area.

Hand gesture recognition applications based on surface electromiographic (sEMG) signals can benefit from on-device execution to achieve faster and more predictable response times and higher energy efficiency. However, deploying state-of-the-art deep learning (DL) models for this task on memory-constrained and battery-operated edge devices, such as wearables, requires a careful optimization process, both at design time, with an appropriate tuning of the DL models’ architectures, and at execution time, where the execution of large and computationally complex models should be avoided unless strictly needed. In this work, we pursue both optimization targets, proposing a novel gesture recognition system that improves upon the state-of-the-art models both in terms of accuracy and efficiency. At the level of DL model architecture, we apply for the first time tiny transformer models (which we call bioformers) to sEMG-based gesture recognition. Through an extensive architecture exploration, we show that our most accurate bioformer achieves a higher classification accuracy on the popular Non-Invasive Adaptive hand Prosthetics Database 6 (Ninapro DB6) dataset compared to the state-of-the-art convolutional neural network (CNN) TEMPONet (+3.1%). When deployed on the RISC-V-based low-power system-on-chip (SoC) GAP8, bioformers that outperform TEMPONet in accuracy consume 7.8×–44.5× less energy per inference. At runtime, we propose a three-level dynamic inference approach that combines a shallow classifier, i.e., a random forest (RF) implementing a simple “rest detector” with two bioformers of different accuracy and complexity, which are sequentially applied to each new input, stopping the classification early for “easy” data. With this mechanism, we obtain a flexible inference system, capable of working in many different operating points in terms of accuracy and average energy consumption. On GAP8, we obtain a further 1.03×–1.35× energy reduction compared to static bioformers at iso-accuracy.

Recent studies show that the integrity of core perceptual and cognitive functions may be tested in a short time with Steady-State Visual Evoked Potentials (SSVEP) with low stimulation frequencies, between 1 and 10 Hz. Wearable EEG systems provide unique opportunities to test these brain functions on diverse populations in out-of-the-lab conditions. However, they also pose significant challenges as the number of EEG channels is typically limited, and the recording conditions might induce high noise levels, particularly for low frequencies. Here we tested the performance of Normalized Canonical Correlation Analysis (NCCA), a frequency-normalized version of CCA, to quantify SSVEP from wearable EEG data with stimulation frequencies ranging from 1 to 10 Hz. We validated NCCA on data collected with an 8-channel wearable wireless EEG system based on BioWolf, a compact, ultra-light, ultra-low-power recording platform. The results show that NCCA correctly and rapidly detects SSVEP at the stimulation frequency within a few cycles of stimulation, even at the lowest frequency (4 s recordings are sufficient for a stimulation frequency of 1 Hz), outperforming a state-of-the-art normalized power spectral measure. Importantly, no preliminary artifact correction or channel selection was required. Potential applications of these results to research and clinical studies are discussed.

In-memory computing (IMC) is a non-von Neumann paradigm that has recently established itself as a promising approach for energy-efficient, high throughput hardware for deep learning applications. One prominent application of IMC is that of performing matrix-vector multiplication in O(1) time complexity by mapping the synaptic weights of a neural-network layer to the devices of an IMC core. However, because of the significantly different pattern of execution compared to previous computational paradigms, IMC requires a rethinking of the architectural design choices made when designing deep-learning hardware. In this work, we focus on application-specific, IMC hardware for inference of Convolution Neural Networks (CNNs), and provide methodologies for implementing the various architectural components of the IMC core. Specifically, we present methods for mapping synaptic weights and activations on the memory structures and give evidence of the various trade-offs therein, such as the one between on-chip memory requirements and execution latency. Lastly, we show how to employ these methods to implement a pipelined dataflow that offers throughput and latency beyond state-of-the-art for image classification tasks.

Medical devices measure vital parameters such as pulse, respiration rate, and blood oxygenation, over periods of days or weeks in a continuous manner. Traditional systems only support such requirements in stationary applications where a constant power supply is available. Trends toward remote healthcare and telemedicine require wearable devices, able to provide similar functionalities in wireless mode. Miniaturized and thin form factors, desirable in wearable applications, set stringent constraints on the available power, and consequently on the accuracy and lifetime. Energy harvesting combined with low-power design and energy efficient processing can significantly extend the lifetime of wearable devices. This paper presents a wearable pulse oximeter assembled in a 3D ring-like geometry that achieves self-sustainability by exploiting efficient power management, solar energy harvesting, and ultra-low power processing in a multi-core microcontroller. The design strategy of combining onboard processing to monitor blood oxygenation and the transmission of only relevant information via a Bluetooth low-energy (BLE) interface, significantly reduces the overall energy consumption. Experimental results on the designed and developed prototype demonstrate that measuring the blood oxygenation once every minute with a sampling rate of 100 samples/s achieve accurate results at the daily energy consumption of 28 J including hourly BLE transmissions. The low-power design allows the system to be self-sustainable with just 64 min of sunlight per day or 12 hrs. of indoor home light.

Standard-sized autonomous vehicles have rapidly improved thanks to the breakthroughs of deep learning. However, scaling autonomous driving to mini-vehicles poses several challenges due to their limited on-board storage and computing capabilities. Moreover, autonomous systems lack robustness when deployed in dynamic environments where the underlying distribution is different from the distribution learned during training. To address these challenges, we propose a closed-loop learning flow for autonomous driving mini-vehicles that includes the target deployment environment in-the-loop. We leverage a family of compact and high-throughput tinyCNNs to control the mini-vehicle that learn by imitating a computer vision algorithm, i.e., the expert, in the target environment. Thus, the tinyCNNs, having only access to an on-board fast-rate linear camera, gain robustness to lighting conditions and improve over time. Moreover, we introduce an online predictor that can choose between different tinyCNN models at runtime—trading accuracy and latency—which minimises the inference’s energy consumption by up to 3.2×. Finally, we leverage GAP8, a parallel ultra-low-power RISC-V-based micro-controller unit (MCU), to meet the real-time inference requirements. When running the family of tinyCNNs, our solution running on GAP8 outperforms any other implementation on the STM32L4 and NXP k64f (traditional single-core MCUs), reducing the latency by over 13× and the energy consumption by 92%.

This work describes the design, implementation, and validation of a wireless sensor network for predictive maintenance and remote monitoring in metal-rich, electromagnetically harsh environments. Energy is provided wirelessly at 2.45 GHz employing a system of three co-located active antennas designed with a conformal shape such that it can power, on-demand, sensor nodes located in non-line-of-sight (NLOS) and difficult-to-reach positions. This allows for eliminating the periodic battery replacement of the customized sensor nodes, which are designed to be compact, low-power, and robust. A measurement campaign has been conducted in a real scenario, i.e., the engine compartment of a car, assuming the exploitation of the system in the automotive field. Our work demonstrates that a one radio-frequency (RF) source (illuminator) with a maximum effective isotropic radiated power (EIRP) of 27 dBm is capable of transferring the energy of 4.8 mJ required to fully charge the sensor node in less than 170 s, in the worst case of 112-cm distance between illuminator and node (NLOS). We also show how, in the worst case, the transferred power allows the node to operate every 60 s, where operation includes sampling accelerometer data for 1 s, extracting statistical information, transmitting a 20-byte payload, and receiving a 3-byte acknowledgment using the extremely robust Long Range (LoRa) communication technology. The energy requirement for an active cycle is between 1.45 and 1.65 mJ, while sleep mode current consumption is less than 150 nA, allowing for achieving the targeted battery-free operation with duty cycles as high as 1.7%.

Power management is a crucial concern in micro-controller platforms for the Internet of Things (IoT) edge. Many applications present a variable and difficult to predict workload profile, usually driven by external inputs. The dynamic tuning of power consumption to the application requirements is indeed a viable approach to save energy. In this paper, we propose the implementation of a power management strategy for a novel low-cost low-power heterogeneous dual-core SoC for IoT edge fabricated in 28 nm FD-SOI technology. Ss with more complex power management policies implemented on high-end application processors, we propose a power management strategy where the power mode is dynamically selected to ensure user-specified target idleness. We demonstrate that the dynamic power mode selection introduced by our power manager allows achieving more than 43% power consumption reduction with respect to static worst-case power mode selection, without any significant penalty in the performance of a running application.

A key design challenge for successful wireless sensor network (WSN) deployment is a good balance between the collected data resolution and the overall energy consumption. In this paper, we present a WSN solution developed to efficiently satisfy the requirements for long-term monitoring of a historical building. The hardware of the sensor nodes and the network deployment are described and used to collect the data. To improve the network’s energy efficiency, we developed and compared two approaches, sharing similar sub-sampling strategies and data reconstruction assumptions: one is based on compressive sensing (CS) and the second is a custom data-driven latent variable-based statistical model (LV). Both approaches take advantage of the multivariate nature of the data collected by a heterogeneous sensor network and reduce the sampling frequency at sub-Nyquist levels. Our comparative analysis highlights the advantages and limitations: signal reconstruction performance is assessed jointly with network-level energy reduction. The performed experiments include detailed performance and energy measurements on the deployed network and explore how the different parameters can affect the overall data accuracy and the energy consumption. The results show how the CS approach achieves better reconstruction accuracy and overall efficiency, with the exception of cases with really aggressive sub-sampling policies.

Movement science investigating muscle and tendon functions during locomotion utilizes commercial ultrasound imagers built for medical applications. These limit biomechanics research due to their form factor, range of view, and spatio-temporal resolution. This review systematically investigates the technical aspects of applying ultrasound as a research tool to investigate human and animal locomotion. It provides an overview on the ultrasound systems used and of their operating parameters. We present measured fascicle velocities and discuss the results with respect to operating frame rates during recording. Furthermore, we derive why muscle and tendon functions should be recorded with a frame rate of at least 150 Hz and a range of view of 250 mm. Moreover, we analyze why and how the development of better ultrasound observation devices at the hierarchical level of muscles and tendons can support biomechanics research. Additionally, we present recent technological advances and their possible application. We provide a list of recommendations for the development of a more advanced ultrasound sensor system class targeting biomechanical applications. Looking to the future, mobile, ultrafast ultrasound hardware technologies create immense opportunities to expand the existing knowledge of human and animal movement.

We report on a self-sustainable, wireless accelerometer-based system for wear detection in a band saw blade. Due to the combination of low power hardware design, thermal energy harvesting with a small thermoelectric generator (TEG), an ultra-low power wake-up radio, power management and the low complexity algorithm implemented, our solution works perpetually while also achieving high accuracy. The onboard algorithm processes sensor data, extracts features, performs the classification needed for the blade’s wear detection, and sends the report wirelessly. Experimental results in a real-world deployment scenario demonstrate that its accuracy is comparable to state-of-the-art algorithms executed on a PC and show the energy-neutrality of the solution using a small thermoelectric generator to harvest energy. The impact of various low-power techniques implemented on the node is analyzed, highlighting the benefits of onboard processing, the nano-power wake-up radio, and the combination of harvesting and low power design. Finally, accurate in-field energy intake measurements, coupled with simulations, demonstrate that the proposed approach is energy autonomous and can work perpetually.

LoRaWAN is one of the most promising standards for long-range sensing applications. However, the high number of end devices expected in at-scale deployment, combined with the absence of an effective synchronization scheme, challenge the scalability of this standard. In this paper, we present an approach to increase network throughput through a Slotted-ALOHA overlay on LoRaWAN networks. To increase the single channel capacity, we propose to regulate the communication of LoRaWAN networks using a Slotted-ALOHA variant on the top of the Pure-ALOHA approach used by the standard; thus, no modification in pre-existing libraries is necessary. Our method is based on an innovative synchronization service that is suitable for low-cost wireless sensor nodes. We modelled the LoRaWAN channel with extensive measurement on hardware platforms, and we quantified the impact of tuning parameters on physical and medium access control layers, as well as the packet collision rate. Results show that Slotted-ALOHA supported by our synchronization service significantly improves the performance of traditional LoRaWAN networks regarding packet loss rate and network throughput.

Energy efficiency is crucial in the design of battery-powered end devices, such as smart sensors for the Internet of Things applications. Wireless communication between these distributed smart devices consumes significant energy, and even more when data need to reach several kilometers in distance. Low-power and long-range communication technologies such as LoRaWAN are becoming popular in IoT applications. However, LoRaWAN has drawbacks in terms of (i) data latency; (ii) limited control over the end devices by the gateway; and (iii) high rate of packet collisions in a dense network. To overcome these drawbacks, we present an energy-efficient network architecture and a high-efficiency on-demand time-division multiple access (TDMA) communication protocol for IoT improving both the energy efficiency and the latency of standard LoRa networks. We combine the capabilities of short-range wake-up radios to achieve ultra-low power states and asynchronous communication together with the long-range connectivity of LoRa. The proposed approach still works with the standard LoRa protocol, but improves performance with an on-demand TDMA. Thanks to the proposed network and protocol, we achieve a packet delivery ratio of 100% by eliminating the possibility of packet collisions. The network also achieves a round-trip latency on the order of milliseconds with sensing devices dissipating less than 46 mJ when active and 1.83 μ W during periods of inactivity and can last up to three years on a 1200-mAh lithium polymer battery.