Related papers: NanoHydra: Energy-Efficient Time-Series Classifica…
This literature review explores continual learning methods for on-device training in the context of neural networks (NNs) and decision trees (DTs) for classification tasks on smart environments. We highlight key constraints, such as data…
The widespread deployment of power grid ad hoc sensor networks based on IEEE 802.15.4 raises reliability challenges when nodes selfishly adapt CSMA/CA parameters to maximize individual performance. Such behavior degrades reliability, energy…
In the context of industry 4.0, long-serving industrial machines can be retrofitted with process monitoring capabilities for future use in a smart factory. One possible approach is the deployment of wireless monitoring systems, which can…
The rapid deployment of machine learning across platforms from milliwatt-class TinyML devices to large language models has made energy efficiency a primary constraint for sustainable AI. Across these scales, performance and energy are…
On-device CNN inference for real-time computer vision applications can result in computational demands that far exceed the energy budgets of mobile devices. This paper proposes FixyNN, a co-designed hardware accelerator platform which…
Tiny Machine Learning (TinyML) applications impose uJ/Inference constraints, with a maximum power consumption of tens of mW. It is extremely challenging to meet these requirements at a reasonable accuracy level. This work addresses the…
Transition edge sensors (TES) have the highest reported efficiencies (>98%) for detection of single photons in the visible and near infrared. Experiments in quantum information and foundations of physics that rely critically on this…
Nanoscale devices with Terahertz (THz) communication capabilities are envisioned to be deployed within human bloodstreams. Such devices will enable fine-grained sensing-based applications for detecting early indications (i.e., biomarkers)…
In recent years, deep learning (DL) has contributed significantly to the improvement of motor-imagery brain-machine interfaces (MI-BMIs) based on electroencephalography(EEG). While achieving high classification accuracy, DL models have also…
Recurrent neural networks can be large and compute-intensive, yet many applications that benefit from RNNs run on small devices with very limited compute and storage capabilities while still having run-time constraints. As a result, there…
We demonstrate a simple connection between dictionary methods for time series classification, which involve extracting and counting symbolic patterns in time series, and methods based on transforming input time series using convolutional…
Recent advances in Tiny Machine Learning (TinyML) empower low-footprint embedded devices for real-time on-device Machine Learning. While many acknowledge the potential benefits of TinyML, its practical implementation presents unique…
Tiny machine learning (TinyML) in IoT systems exploits MCUs as edge devices for data processing. However, traditional TinyML methods can only perform inference, limited to static environments or classes. Real case scenarios usually work in…
We introduce a nanocalorimetric technique based on microsecond-pulsed heating (\mu s-PHnC) that enables high-sensitivity, quasi-isothermal heat capacity measurements on nanoscale samples. Such resolution is critical for exploring…
Gesture recognition on wearable devices is extensively applied in human-computer interaction. Electromyography (EMG) has been used in many gesture recognition systems for its rapid perception of muscle signals. However, analyzing EMG…
We study time-series classification (TSC), a fundamental task of time-series data mining. Prior work has approached TSC from two major directions: (1) similarity-based methods that classify time-series based on the nearest neighbors, and…
In the evolving landscape of cloud computing, optimizing energy efficiency across the edge-cloud continuum is crucial for sustainability and cost-effectiveness. We introduce GMB-ECC, a framework for measuring and benchmarking energy…
In microdosimetry, lineal energies y are calculated from energy depositions $\epsilon$ inside the microdosimeter divided by the mean chord length, whose value is based on geometrical assumptions on both the detector and the radiation field.…
Using smart wearable devices to monitor patients electrocardiogram (ECG) for real-time detection of arrhythmias can significantly improve healthcare outcomes. Convolutional neural network (CNN) based deep learning has been used successfully…
EMG-based gesture recognition shows promise for human-machine interaction. Systems are often afflicted by signal and electrode variability which degrades performance over time. We present an end-to-end system combating this variability…