Despite decades of research on battery-free systems, their adoption in everyday electronics remains limited. Interactive Internet of Things devices such as wearables, personal trackers, and health monitors are increasingly widespread, yet almost all depend on batteries that are environmentally harmful, slow to charge, and have limited lifespans. Existing battery-free devices have seen use only in niche applications with minimal user interaction, primarily due to slow energy harvesting, frequent power interruptions, and restricted sensing capabilities under tight energy constraints. To address these limitations, we present Cheetah, a battery-free architecture that charges rapidly and reliably from ubiquitous wireless chargers, reduces power consumption, and enhances usability. We implement and evaluate Cheetah architecture as a smartwatch and a wearable patch, capable of operating for a full day after only six seconds of charging. Our results demonstrate that battery-free design can move beyond niche deployments to become a practical and sustainable alternative for mainstream interactive electronics.

The rapid adoption of ear-worn devices (earables) has shown significant potential for continuous health monitoring. Despite their close proximity to the human brain and diverse sensing capabilities, the exploration of earable sensing in relation to cognitive function remains underexplored. Building on theoretical and empirical foundations regarding the interplay between cognitive load, auditory complexity, and changes in hearing characteristics influenced by brain function, this study is the first to leverage earable acoustic sensing to assess cognitive load. We specifically designed auditory tasks to elicit four levels of cognitive load and used otoacoustic emissions (OAEs) to measure cochlear response changes in response to cognitive load. By utilizing both audio content indicating auditory complexity and OAEs reflecting hearing characteristic changes, we designed machine learning pipelines to automate the assessment in a four-class cognitive detection task, achieving an accuracy of 68.88%. This research opens a new pathway for using earable acoustic sensing in monitoring cognitive function and holds great potential for future cognitive augmentation.

In a world dominated by podcasts and audiobooks, maintaining auditory attention is essential, yet lapses in focus are common. Auditory attention is crucial for effective communication and comprehension in a distraction-filled environment, as it enables us to focus on important sounds while avoiding external distractions. This work introduces a novel, imperceptible method for detecting auditory attention using earbuds by monitoring muscle movement within the ear canal. We employ an ultrasound-based sensing technique to track phase changes in reflected signals, detecting muscle vibrations associated with shifts in attention. A preliminary user study reveals significant changes in in-ear signal characteristics when participants switch between auditory and cognitive tasks. We show that our system can classify periods of auditory attention and lack of it with an accuracy of 85.7% and a variance of 0.0033. Our findings pave the way for earables that continuously monitor and enhance auditory attention in real-time.

We present a real-time multimodal sensing and feedback system that enables closed-loop interaction using wearable devices. Our implementation leverages OmniBuds—a pair of true wireless stereo (TWS) earbuds equipped with dual 9-axis inertial measurement units (IMUs), optical heart rate sensors, and skin temperature sensors, one set in each ear. These sensors continuously stream motion and physiological data via Bluetooth Low Energy (BLE) to a mobile computing platform, where lightweight inference models classify user actions and assess physiological states. Based on this analysis, the system provides real-time auditory feedback through the same earbuds, enabling responsive, human-in-the-loop interaction. As a demonstration, we apply this system to an interactive control scenario based on the T-Rex Chrome Dino game, where users control the avatar using head and body motion captured by the earbuds. Jumping and ducking are recognized in real time through IMU signals, while heart rate and skin temperature dynamically modulates the game speed. The system delivers auditory guidance via the OmniBuds' speakers to help users adapt their actions during game-play. This framework demonstrates the potential of multimodal wearable sensing and closed-loop feedback for embodied interaction, real-time behavioral adaptation, and health-aware interactive systems.

Wearable technology is advancing health monitoring by enabling real-time, privacy-preserving physiological analysis. However, traditional devices often rely on cloud processing, restricting access to raw sensor data and limiting the progress of health-related research. To overcome these limitations, we introduce OmniBuds, a programmable earable research platform that enables multimodal bio-sensing and on-device learning while providing direct access to raw physiological data, fostering advancements in health perception and wearable intelligence. It integrates PPG, temperature, IMUs, and multiple microphones, leveraging an embedded ML accelerator for efficient real-time processing. This paper presents its design, architecture, and applications, demonstrating its potential to shape the future of health-aware wearables.

Distortion Product OtoAcoustic Emissions (DPOAEs) represents faint cochlear responses to dual-frequency stimuli, commonly employed in hearing screening. This paper introduces an innovative approach to trigger DPOAEs using single-speaker earbuds. Due to their compact size, the speakers used in the earbuds exhibit nonlinear behavior, leading to Inter-Modulation Distortions (IMDs) that interfere with DPOAE signals. Conventional medical devices employ dual speakers to mitigate this distortion, such a solution is impractical for space-constrained earbuds. To address this challenge, we propose a method that triggers DPOAEs while circumventing IMDs by designing a stimulus signal that alternates between the two frequencies necessary for triggering DPOAEs. The performance of our system was evaluated through a preliminary user study involving 8 participants, and it demonstrated a median correlation of 0.65 when compared to a medical-grade reference device.

This paper presents a novel cancellation method of Intermodulation Distortions (IMDs) for earbud speakers used to measure Distortion Product Otoacoustic Emissions (DPOAE). Speakers’ non-linear behaviour is a significant problem for earbuds with small loudspeakers due to limitations in cone movement. Linear and non-linear speaker modelling enables us to inject exact distortion inverse to cancel what is introduced by speakers’ non-linearities. Our proposed method is compared against state-of-the-art related works in terms of harmonic reduction ratio. Simulation results and evaluation on real hardware show a 77% to 95% reduction in the harmonic distortions of a focused frequency region at the output of the loudspeaker, outperforming existing works by 6% to 14%.

We present SensiX++, a multi-tenant runtime for adaptive model execution with integrated MLOps on edge devices, e.g., a camera, a microphone, or IoT sensors. SensiX++ operates on two fundamental principles: highly modular componentisation to externalise data operations with clear abstractions and document-centric manifestation for system-wide orchestration. First, a data coordinator manages the lifecycle of sensors and serves models with correct data through automated transformations. Next, a resource-aware model server executes multiple models in isolation through model abstraction, pipeline automation, and feature sharing. An adaptive scheduler then orchestrates the best-effort executions of multiple models across heterogeneous accelerators, balancing latency and throughput. Finally, microservices with REST APIs serve synthesised model predictions, system statistics, and continuous deployment. Collectively, these components enable SensiX++ to serve multiple models efficiently with fine-grained control on edge devices while minimising data operation redundancy, managing data and device heterogeneity, and reducing resource contention. We benchmark SensiX++ with 10 different vision and acoustics models across various multi-tenant configurations on different edge accelerators (Jetson AGX and Coral TPU) designed for sensory devices. We report on the overall throughput and quantified benefits of various automation components of SensiX++ and demonstrate its efficacy in significantly reducing operational complexity and lowering the effort to deploy, upgrade, reconfigure, and serve embedded models on edge devices.

Multiple sensory devices on and around us are on the rise and require us to redesign a system to make an inference of ML models accurate, robust, and efficient at the deployment time. While this multiplicity opens up an exciting opportunity to leverage sensor redundancy, it is still extremely challenging to benefit from such multiplicity and boost the runtime performance of deployed ML models without model retraining and engineering. From our experience, we uncovered two prime caveats, device and data variabilities, that affect the runtime performance of ML models. We develop an ML system that addresses these variabilities without modifying deployed models by building on prior algorithmic work. It decouples model execution from sensor data and employs two essential operations between them: a) device-to-device data translation for principled mapping of training and inference data and b) quality-aware dynamic selection of the execution pipeline as a function of runtime accuracy. We evaluate the system on wearable devices with motion and audio-based models. The results show that ML models achieve a 7-13% increase in runtime accuracy solely by running on our system, and the increase goes up to 30% in dynamic environments, at the expense of 3 mW on the host device.

Continuous blood pressure monitoring is the key to mitigate significant risks for stroke, heart failure and coronary artery disease. Current gold-standard blood pressure devices cause discomfort and interfere with users’ activities. This paper explores an earable system, which continuously monitors users’ blood pressure from the ear. We propose a measurement technique based on the vascular transit time which utilises the time difference between the S1 heart sound and the PPG upstroke in one pulse cycle. We develop a multi-modal sensing hardware and processing pipeline and we evaluate it with 10 participants showing average errors in line with the range recommended by the Association for the Advancement of Medical Instrumentation: 4.07 mmHg for systolic and 5.61 mmHg for diastolic blood pressure.

Tsetlin Machine (TM) is a new machine learning algorithm that encodes propositional logic into learning automata---a set of logical expressions composed of boolean input features---to recognise patterns. The simplicity, efficiency, and accuracy of this logic-based algorithm encourage rethinking the application of traditional arithmetic-based neural networks (NNs) in intelligent sensors design. Indeed, TM is a promising candidate for embedding intelligence into tiny batteryless sensors with the potential to address two critical challenges: (1) computing under resource constraints and (2) demand for dynamic adaptation to the unpredictable nature of harvested energy. However, its structural model complexity manifests in two conflicting issues: large memory footprint and long latency. This paper addresses these shortcomings by proposing adaptive compression techniques exploiting the inherent redundancies observed in trained models. Through dynamically scaling the computational complexity based on available energy, our techniques significantly reduce the memory footprint and speed up the runtime execution. We evaluate our techniques against standard TMs and binarized neural networks (BNNs) for vision and acoustic workloads deployed on a TI MSP430 MCU operating under intermittent power supply conditions. We show that our techniques can achieve up to 99% compression of TM models and offer 13.5× latency and energy reductions when compared with the most efficient neural network configuration without compromising accuracy.

The development of edge devices with dedicated hardware accelerators has pushed the deployment and inference of Deep Neural Network (DNN) models closer to users and real-world sensory systems than ever before (e.g., wearables, IoT). Recently, a further subset of these devices has emerged: ultra-low power DNN accelerators. These microcontrollers possess a dedicated hardware accelerator and are able to operate with only μJ's of energy in milliseconds of time. With their small form-factor, such devices could be used for battery-powered machine learning (ML) applications. In this work, we take a close look at one such device: the MAX78000 by Maxim Integrated. We characterize the device's performance by running five DNN models of various sizes and architectures, and analyze its operational latency, power consumption, and memory footprint. To better understand the performance characteristics, we take a step further and investigate how different layer types (operation type, kernel size, number of input and output channels) and the selection of accelerator processors affect the execution time.

Earables (in-ear wearables) are a new frontier in wearables. Acting both as leisure devices, providing personal audio, as well as sensing platforms, earables could collect sensor data for the upper part of the body, subject to fewer vibrations and random movement variations than the lower parts of the body, due to inherent damping in the musculoskeletal system. These data may enable application domains such as augmented/virtual reality, medical rehabilitation, and health condition screening. Unfortunately, earables have inherent size, shape, and weight constraints limiting the type and position of the sensors on such platforms. For instance, lacking a magnetometer in all earables reference platforms, earables lack reference points. Thus, it becomes harder to work with absolute orientations. Embedding magnetometers in earables is challenging, as these rely heavily on radio (mostly Bluetooth) communication (RF) and contain magnets for magnetic-driven speakers and docking. We explore the feasibility of adding a built-in magnetometer in an earbud, presenting the first comprehensive study of the magnetic interference impacting the magnetometer when placed in an earable: both that caused by the speaker and by RF (music streaming and voice calls) are considered. We find that appropriate calibration of the magnetometer removes the offsets induced by the magnets, the speaker, and the variable interference due to BT. Further, we present an automatic, user-transparent adaptive calibration that obviates the need for alternative, expensive, and error-prone manual, or robotics, calibration procedures. Our evaluation shows how our calibration approach performs under different conditions, achieving convincing results with errors below 3° for the majority of the experiments.

For long, we have studied tiny energy harvesters to liberate sensors from batteries. With remarkable progress in embedded deep learning, we are now re-imagining these sensors as intelligent compute nodes. Naturally, we are approaching a crossroad where sensor intelligence is meeting energy autonomy enabling maintenance-free swarm intelligence and unleashing a plethora of applications ranging from precision agriculture to ubiquitous asset tracking to infrastructure monitoring. One of the critical challenges, however, is to adapt intelligence fidelity in response to available energy to maximise the overall system availability. To this end, we present the design and implementation of ePerceptive: a novel framework for best-effort embedded intelligence, i.e., inference fidelity varies in proportion to the instantaneous energy supplied. ePerceptive operates on two core principles. First, it enables training a single deep neural network (DNN) to operate on multiple input resolutions without compromising accuracy or incurring memory overhead. Second, it modifies a DNN architecture by injecting multiple exits to guarantee valid, albeit lower-fidelity inferences in the event of energy interruption. The combination of these techniques offers a smooth adaptation between inference latency and recognition accuracy while matching the computational load to the available power budget. We report the manifestation of ePerceptive in designing batteryless cameras and microphones built with TI MSP430 MCU and off-the-shelf RF and solar energy harvesters. Our evaluation of these batteryless sensors with multiple vision and acoustic workloads suggest that the dynamic adaptation of ePerceptive can increase the inference throughput by up to 80% compared to a static baseline while ensuring a maximum accuracy drop of less than 6%.

We explore a new variability observed in motion signals acquired from modern wearables. Wearing variability refers to the variations of the device orientation and placement across wearing events. We collect the accelerometer data on a smartwatch and an earbud and analyse how motion signals change due to the wearing variability. Our analysis shows that the wearing variability can bring an unexpected change to motion signals, not only from different users but also from different wearing sessions of the same user. We also provide empirical ranges of changes in device orientations.

The increasing availability of multiple sensory devices on or near a human body has opened brand new opportunities to leverage redundant sensory signals for powerful sensing applications. For instance, personal-scale sensory inferences with motion and audio signals can be done individually on a smartphone, a smartwatch, and even an earbud - each offering unique sensor quality, model accuracy, and runtime behaviour. At execution time, however, it is incredibly challenging to assess these characteristics to select the best device for accurate and resource-efficient inferences. To this end, we look at a quality-aware collaborative sensing system that actively interplays across multiple devices and respective sensing models. It dynamically selects the best device as a function of model accuracy at any given context. We propose two complementary techniques for the runtime quality assessment. Borrowing principles from active learning, our first technique runs on three heuristic-based quality assessment functions that employ confidence, margin sampling, and entropy of models' output. Our second technique is built with a siamese neural network and acts on the premise that runtime sensing quality can be learned from historical data. Our evaluation across multiple motion and audio datasets shows that our techniques provide 12% increase in overall accuracy through dynamic device selection at the average expense of 13 mW power on each device as compared to traditional single-device approaches.

We present eSense - an open and multi-sensory in-ear wearable platform for personal-scale behaviour analytics. eSense is a true wireless stereo (TWS) earbud and supports dual-mode Bluetooth and Bluetooth Low Energy. It is also augmented with a 6-axis in-ertial measurement unit and a microphone. We demonstrate the eSense platform, the data exploration tool with the open APIs for the real-time visualisation of multi-modal sensory data, and its manifestation in a 360° workplace well-being application.

The ability to detect and distinguish interactions in the workplace can shed light over productivity, team work and on employees' use of space. Questionnaires and direct observations have often been used as mechanisms to identify office based interactions, however, these are either very time consuming, yield coarse grained information or do not scale to large numbers of people. Technology has been recently employed to cut costs and improve output, however precise interaction dynamics gathering often requires individuals to wear custom hardware. In this paper, we present an extensive evaluation of Bluetooth Low Energy (BLE) as a technology to monitor people proximity in the workplace. We examine the key parameters that affect the accuracy of the detected contacts and their impact on power consumption. We study how this system can be implemented on popular wearable devices (i.e., Android Wear and Tizen) and the resulting limitations. Through a real world deployment in a commercial organisation with 25 participants we evaluate the performances of a BLE-based proximity detection technique. Our results show the suitability of BLE for workplace interaction detection and give guidance to vendors and Operating System (OS) developers on the impact of the restrictions regarding the use of BLE on commodity wearables.

Automation and monitoring systems for industrial and commercial sites (short: Site Management Systems) often grow organically, hence they need to be able to integrate large numbers of heterogeneous devices, based on both legacy and novel tools and systems. Currently, many standards are used in the site management field for both control (e.g., KNX, BACNet, LON) and communication (e.g., WiFi, Ethernet). Different systems are responsible for different tasks and parts of the site. Since they are usually not designed to interoperate, the site manager is forced to choose one that suits most of her needs, forgoing features offered by alternative solutions. I.e, the flexibility of the site manager is limited. Moreover, site management systems often require technical personnel for installation, calibration and configuration, and are not designed to be modified frequently to adapt to changes. Because of this, the site manager is discouraged from changing the settings of the system or from adding or updating devices, by lack of technical knowledge and by high costs. In other words, a site management system that makes adding new devices, e.g., solar panels, as easy as plugging in and using a webcam is needed.