Xiaying Wang

Last Name

Wang

First Name

Xiaying

ORCID

0000-0003-3467-5033

Show all metadata

Search Results

Publications 1 - 10 of 34

FANN-on-MCU: An Open-Source Toolkit for Energy-Efficient Neural Network Inference at the Edge of the Internet of Things
Wang, Xiaying; Magno, Michele; Cavigelli, Lukas Arno Jakob; et al. (2020)
IEEE Internet of Things Journal
Near-Sensor Analytics and Machine Learning for Long-Term Wearable Biomedical Systems
Wang, Xiaying (2022)
Wearable devices for biomedical applications have become increasingly pervasive. In a field where privacy is a major concern and latency is not well-tolerated, low-power and small-sized edge devices are of central importance. An emerging trend is to embed the processing algorithms near the sensors on the edge device to preserve privacy, reduce latency, and increase battery life. A new generation of wearable Internet of things and smart sensing systems should not only provide continuous data monitoring and acquisition but are also expected to process and make sense of the acquired data in similar ways as human experts do. Over the years, machine learning has achieved impressive results in many applications, including the biomedical field. However, the limited resources available on battery-operated devices pose enormous challenges in executing machine learning algorithms that are generally resource-demanding. In this thesis, we first evaluate and assess the ability of two representative and leading-edge ultra-low-power microcontrollers to execute machine learning models for wearable applications. We then focus on the challenging task of brain–machine interface based on the motor imagery paradigm, which allows direct communication between the human brain and external machines by merely thinking of a body part movement. We identify the state-of-the-art classification algorithms in this domain and introduce methods to reduce their computational complexity and model size allowing efficient implementation on edge devices. We further propose optimized and energy-efficient deployment techniques by exploiting hardware extensions and parallel computing. Finally, we design a new model architecture that requires significantly less memory footprint and fewer computations while at the same time keeping state-of-the-art accuracy. We additionally limit the resource requirements by proposing an effective method to reduce the dimensionality of the input data, significantly lowering the overall system’s power consumption without significantly degrading the model accuracy. With this thesis, we demonstrate for the first time that it is feasible to execute real-time inference at the edge for a brain–machine interface based on motor imagery and reach the state-of-the-art trade-off among accuracy, resource demands, and power consumption necessary for a next-generation smart wearable device.
Train-On-Request: An On-Device Continual Learning Workflow for Adaptive Real-World Brain Machine Interfaces
Mei, Lan; Cioflan, Cristian; Ingolfsson, Thorir Mar; et al. (2024)
2024 IEEE Biomedical Circuits and Systems Conference (BioCAS)
Brain-machine interfaces (BMIs) are expanding beyond clinical settings thanks to advances in hardware and algorithms. However, they still face challenges in user-friendliness and signal variability. Classification models need periodic adaptation for real-life use, making an optimal re-training strategy essential to maximize user acceptance and maintain high performance. We propose TOR, a train-on-request workflow that enables user-specific model adaptation to novel conditions, addressing signal variability over time. Using continual learning, TOR preserves knowledge across sessions and mitigates inter-session variability. With TOR, users can refine, on demand, the model through on-device learning (ODL) to enhance accuracy adapting to changing conditions. We evaluate the proposed methodology on a motor-movement dataset recorded with a non-stigmatizing wearable BMI headband, achieving up to 92% accuracy and a re-calibration time as low as 1.6 minutes, a 46% reduction compared to a naive transfer learning workflow. We additionally demonstrate that TOR is suitable for ODL in extreme edge settings by deploying the training procedure on a RISC-V ultra-low-power SoC (GAP9), resulting in 21.6 ms of latency and 1 mJ of energy consumption per training step. To the best of our knowledge, this work is the first demonstration of an online, energy-efficient, dynamic adaptation of a BMI model to the intrinsic variability of EEG signals in real-time settings.
Optimization and Deployment of Deep Neural Networks for PPG-based Blood Pressure Estimation Targeting Low-power Wearables
Burrello, Alessio; Carlucci, Francesco; Pollo, Giovanni; et al. (2024)
2024 IEEE Biomedical Circuits and Systems Conference (BioCAS)
PPG-based Blood Pressure (BP) estimation is a challenging biosignal processing task for low-power devices such as wearables. State-of-the-art Deep Neural Networks (DNNs) trained for this task implement either a PPG-to-BP signal-to-signal reconstruction or a scalar BP value regression and have been shown to outperform classic methods on the largest and most complex public datasets. However, these models often require excessive parameter storage or computational effort for wearable deployment, exceeding the available memory or incurring too high latency and energy consumption. In this work, we describe a fully-automated DNN design pipeline, encompassing HW-aware Neural Architecture Search (NAS) and Quantization, thanks to which we derive accurate yet lightweight models, that can be deployed on an ultra-low-power multicore System-on-Chip (SoC), GAP8. Starting from both regression and signal-to-signal state-of-the-art models on four public datasets, we obtain optimized versions that achieve up to 4.99% lower error or 73.36% lower size at iso-error. Noteworthy, while the most accurate SoA network on the largest dataset can not fit the GAP8 memory, all our optimized models can; our most accurate DNN consumes as little as 0.37 mJ while reaching the lowest MAE of 8.08 on Diastolic BP estimation.
SzCORE: Seizure Community Open-Source Research Evaluation framework for the validation of electroencephalography-based automated seizure detection algorithms
Dan, Jonathan; Pale, Una; Amirshahi, Alireza; et al. (2025)
Epilepsia
The need for high-quality automated seizure detection algorithms based on electroencephalography (EEG) becomes ever more pressing with the increasing use of ambulatory and long-term EEG monitoring. Heterogeneity in validation methods of these algorithms influences the reported results and makes comprehensive evaluation and comparison challenging. This heterogeneity concerns in particular the choice of datasets, evaluation methodologies, and performance metrics. In this paper, we propose a unified framework designed to establish standardization in the validation of EEG-based seizure detection algorithms. Based on existing guidelines and recommendations, the framework introduces a set of recommendations and standards related to datasets, file formats, EEG data input content, seizure annotation input and output, cross-validation strategies, and performance metrics. We also propose the EEG 10-20 seizure detection benchmark, a machine-learning benchmark based on public datasets converted to a standardized format. This benchmark defines the machine-learning task as well as reporting metrics. We illustrate the use of the benchmark by evaluating a set of existing seizure detection algorithms. The SzCORE (Seizure Community Open-Source Research Evaluation) framework and benchmark are made publicly available along with an open-source software library to facilitate research use, while enabling rigorous evaluation of the clinical significance of the algorithms, fostering a collective effort to more optimally detect seizures to improve the lives of people with epilepsy.
Towards Long-term Non-invasive Monitoring for Epilepsy via Wearable EEG Devices
Ingolfsson, Thorir Mar; Cossettini, Andrea; Wang, Xiaying; et al. (2021)
2021 IEEE Biomedical Circuits and Systems Conference (BioCAS)
We present the implementation of seizure detection algorithms based on a minimal number of EEG channels on a parallel ultra-low-power embedded platform. The analyses are based on the CHB-MIT dataset, and include explorations of different classification approaches (Support Vector Machines, Random Forest, Extra Trees, AdaBoost) and different pre/post-processing techniques to maximize sensitivity while guaranteeing no false alarms. We analyze global and subject-specific approaches, considering all 23-electrodes or only 4 temporal channels. For 8 s window size and subject-specific approach, we report zero false positives and 100% sensitivity. These algorithms are parallelized and optimized for a parallel ultra-low power (PULP) platform, enabling 300h of continuous monitoring on a 300 mAh battery, in a wearable form factor and power budget. These results pave the way for the implementation of affordable, wearable, long-term epilepsy monitoring solutions with low false-positive rates and high sensitivity, meeting both patient and caregiver requirements.
HR-SAR-Net: A Deep Neural Network for Urban Scene Segmentation from High-Resolution SAR Data
Wang, Xiaying; Cavigelli, Lukas Arno Jakob; Eggimann, Manuel; et al. (2020)
2020 IEEE Sensors Applications Symposium (SAS)
Synthetic aperture radar (SAR) data is becoming increasingly available to a wide range of users through commercial service providers with resolutions reaching 0.5 m/px. Segmenting SAR data still requires skilled personnel, limiting the potential for large-scale use. We show that it is possible to automatically and reliably perform urban scene segmentation from next-gen resolution SAR data (0.15 m/px) using deep neural networks (DNNs), achieving a pixel accuracy of 95.19% and a mean intersection-over-union (mIoU) of 74.67% with data collected over a region of merely 2.2km2. The presented DNN is not only effective, but is very small with only 63k parameters and computationally simple enough to achieve a throughput of around 500 Mpx/s using a single GPU. We further identify that additional SAR receive antennas and data from multiple flights massively improve the segmentation accuracy. We describe a procedure for generating a high-quality segmentation ground truth from multiple inaccurate building and road annotations, which has been crucial to achieving these segmentation results.
Mixed-Precision Quantization and Parallel Implementation of Multispectral Riemannian Classification for Brain-Machine Interfaces
Wang, Xiaying; Schneider, Tibor; Hersche, Michael; et al. (2021)
2021 IEEE International Symposium on Circuits and Systems (ISCAS)
With Motor-Imagery (MI) Brain-Machine Interfaces (BMIs) we may control machines by merely thinking of performing a motor action. Practical use cases require a wearable solution where the classification of the brain signals is done locally near the sensor using machine learning models embedded on energy-efficient microcontroller units (MCUs), for assured privacy, user comfort, and long-term usage. In this work, we provide practical insights on the accuracy-cost tradeoff for embedded BMI solutions. Our proposed Multispectral Riemannian Classifier reaches 75.1% accuracy on 4-class MI task. We further scale down the model by quantizing it to mixed-precision representations with a minimal accuracy loss of 1%, which is still 3.2% more accurate than the state-of-the- art embedded convolutional neural network. We implement the model on a low-power MCU with parallel processing units taking only 33.39 ms and consuming 1.304 mJ per classification. © 2021 IEEE
Nonlinear and machine learning analyses on high-density EEG data of math experts and novices
Poikonen, Hanna; Zaluska, Tomasz; Wang, Xiaying; et al. (2023)
Scientific Reports
Current trend in neurosciences is to use naturalistic stimuli, such as cinema, class-room biology or video gaming, aiming to understand the brain functions during ecologically valid conditions. Naturalistic stimuli recruit complex and overlapping cognitive, emotional and sensory brain processes. Brain oscillations form underlying mechanisms for such processes, and further, these processes can be modified by expertise. Human cortical functions are often analyzed with linear methods despite brain as a biological system is highly nonlinear. This study applies a relatively robust nonlinear method, Higuchi fractal dimension (HFD), to classify cortical functions of math experts and novices when they solve long and complex math demonstrations in an EEG laboratory. Brain imaging data, which is collected over a long time span during naturalistic stimuli, enables the application of data-driven analyses. Therefore, we also explore the neural signature of math expertise with machine learning algorithms. There is a need for novel methodologies in analyzing naturalistic data because formulation of theories of the brain functions in the real world based on reductionist and simplified study designs is both challenging and questionable. Data-driven intelligent approaches may be helpful in developing and testing new theories on complex brain functions. Our results clarify the different neural signature, analyzed by HFD, of math experts and novices during complex math and suggest machine learning as a promising data-driven approach to understand the brain processes in expertise and mathematical cognition.
Physically-Constrained Adversarial Attacks on Brain-Machine Interfaces
Wang, Xiaying; Siller, Octavio R.Q.; Hersche, Michael; et al. (2022)
Workshop on Trustworthy and Socially Responsible Machine Learning (TSRML 2022) - NeurIPS 2022
Deep learning (DL) has been widely employed in brain--machine interfaces (BMIs) to decode subjects' intentions based on recorded brain activities enabling direct interaction with machines. BMI systems play a crucial role in medical applications and have recently gained an increasing interest as consumer-grade products. Failures in such systems might cause medical misdiagnoses, physical harm, and financial loss. Especially with the current market boost of such devices, it is of utmost importance to analyze and understand in-depth, potential malicious attacks to develop countermeasures and avoid future damages. This work presents the first study that analyzes and models adversarial attacks based on physical domain constraints in DL-based BMIs. Specifically, we assess the robustness of EEGNet which is the current state-of-the-art network embedded in a real-world, wearable BMI. We propose new methods that incorporate domain-specific insights and constraints to design natural and imperceptible attacks and to realistically model signal propagation over the human scalp. Our results show that EEGNet is significantly vulnerable to adversarial attacks with an attack success rate of more than 50%.

Publications 1 - 10 of 34

Xiaying Wang

Last Name

First Name

ORCID

Organisational unit

Filters

Search Results