arXiv subjects

Erik Scheme

Publications and source records attributed to Erik Scheme.

14 recordsLinked to original sources

arXiv2026

The 2nd International StepUP Competition for Biometric Footstep Recognition: From Steps to Strides

The International StepUP Competition Series was launched to advance research in pressure-based footstep biometrics through a standardized and challenging evaluation framework. Using the large-scale StepUP-P150 dataset (with more than 200,000 high-resolution dynamic footsteps from 150 individuals) and a previously unreleased test set, the 2nd edition of the competition addressed three key challenges: (1) generalization to unseen users with limited enrollment data, (2) robustness to domain shift caused by variations in footwear and walking speed and (3) effective fusion of paired left-right footsteps. While the first two challenges built on the inaugural competition, this edition introduced more extreme cross-domain conditions and moved beyond isolated footsteps to stride-level verification, enabling new opportunities for representation learning and inter-step information fusion. The competition attracted 26 registrants from academia and industry, with a best equal error rate of 8.00% achieved by the ArogyaPandit Research Team using a spatiotemporal CNN combined with an ensemble-based scoring strategy. The top solutions showcase the value of harnessing temporal patterns and of incorporating inference-time normalization and calibration strategies to improve scoring. However, the results also reveal that recognizing users in unseen personal footwear remains a challenge, especially in the presence of distractors with similar characteristics.

cs.CV↗

arXiv2026

First International StepUP Competition for Biometric Footstep Recognition: Methods, Results and Remaining Challenges

Biometric footstep recognition, based on a person's unique pressure patterns under their feet during walking, is an emerging field with growing applications in security and safety. However, progress in this area has been limited by the lack of large, diverse datasets necessary to address critical challenges such as generalization to new users and robustness to shifts in factors like footwear or walking speed. The recent release of the UNB StepUP-P150 dataset, the largest and most comprehensive collection of high-resolution footstep pressure recordings to date, opens new opportunities for addressing these challenges through deep learning. To mark this milestone, the First International StepUP Competition for Biometric Footstep Recognition was launched. Competitors were tasked with developing robust recognition models using the StepUP-P150 dataset that were then evaluated on a separate, dedicated test set designed to assess verification performance under challenging variations, given limited and relatively homogeneous reference data. The competition attracted global participation, with 23 registered teams from academia and industry. The top-performing team, Saeid_UCC, achieved the best equal error rate (EER) of 10.77% using a generative reward machine (GRM) optimization strategy. Overall, the competition showcased strong solutions, but persistent challenges in generalizing to unfamiliar footwear highlight a critical area for future work.

cs.CV↗

arXiv2025

Context Informed Incremental Learning Improves Myoelectric Control Performance in Virtual Reality Object Manipulation Tasks

Electromyography (EMG)-based gesture recognition is a promising approach for designing intuitive human-computer interfaces. However, while these systems typically perform well in controlled laboratory settings, their usability in real-world applications is compromised by declining performance during real-time control. This decline is largely due to goal-directed behaviors that are not captured in static, offline scenarios. To address this issue, we use \textit{Context Informed Incremental Learning} (CIIL) - marking its first deployment in an object-manipulation scenario - to continuously adapt the classifier using contextual cues. Nine participants without upper limb differences completed a functional task in a virtual reality (VR) environment involving transporting objects with life-like grips. We compared two scenarios: one where the classifier was adapted in real-time using contextual information, and the other using a traditional open-loop approach without adaptation. The CIIL-based approach not only enhanced task success rates and efficiency, but also reduced the perceived workload by 7.1 %, despite causing a 5.8 % reduction in offline classification accuracy. This study highlights the potential of real-time contextualized adaptation to enhance user experience and usability of EMG-based systems for practical, goal-oriented applications, crucial elements towards their long-term adoption. The source code for this study is available at: https://github.com/BiomedicalITS/ciil-emg-vr.

cs.HC↗

arXiv2025

A dataset of high-resolution plantar pressures for gait analysis across varying footwear and walking speeds

Gait refers to the patterns of limb movement generated during walking, which are unique to each individual due to both physical and behavioral traits. Walking patterns have been widely studied in biometrics, biomechanics, sports, and rehabilitation. While traditional methods rely on video and motion capture, advances in plantar pressure sensing technology now offer deeper insights into gait. However, underfoot pressures during walking remain underexplored due to the lack of large, publicly accessible datasets. To address this, we introduce the UNB StepUP-P150 dataset: a footStep database for gait analysis and recognition using Underfoot Pressure, including data from 150 individuals. This dataset comprises high-resolution plantar pressure data (4 sensors per cm-squared) collected using a 1.2m by 3.6m pressure-sensing walkway. It contains over 200,000 footsteps from participants walking with various speeds (preferred, slow-to-stop, fast, and slow) and footwear conditions (barefoot, standard shoes, and two personal shoes), supporting advancements in biometric gait recognition and presenting new research opportunities in biomechanics and deep learning. UNB StepUP-P150 establishes a new benchmark for plantar pressure-based gait analysis and recognition.

cs.CV↗

arXiv2024

Self-Supervised Representation Learning with Augmentations of Continuous Training Data Improves the Feel and Performance of Myoelectric Control

Pattern recognition-based myoelectric control is traditionally trained with static or ramp contractions, but this fails to capture the dynamic nature of real-world movements. This study investigated the benefits of training classifiers with continuous dynamic data, encompassing transitions between various movement classes. We employed both conventional (LDA) and deep learning (LSTM) classifiers, comparing their performance when trained with ramp data, continuous dynamic data, and continuous dynamic data augmented with a self-supervised learning technique (VICReg). An online Fitts' Law test with $20$ participants evaluated the usability and effectiveness of each classifier. Results demonstrate that temporal models, particularly LSTMs trained with continuous dynamic data, significantly outperformed traditional approaches. Furthermore, VICReg pre-training led to additional improvements in online performance and user experience. Qualitative feedback highlighted the importance of smooth, jitter-free control and consistent performance across movement classes. These findings underscore the potential of continuous dynamic data and self-supervised learning for advancing sEMG-PR-based myoelectric control, paving the way for more intuitive and user-friendly prosthetic devices.

eess.SP↗

arXiv2024

Decision-change Informed Rejection Improves Robustness in Pattern Recognition-based Myoelectric Control

Post-processing techniques have been shown to improve the quality of the decision stream generated by classifiers used in pattern-recognition-based myoelectric control. However, these techniques have largely been tested individually and on well-behaved, stationary data, failing to fully evaluate their trade-offs between smoothing and latency during dynamic use. Correspondingly, in this work, we survey and compare 8 different post-processing and decision stream improvement schemes in the context of continuous and dynamic class transitions: majority vote, Bayesian fusion, onset locking, outlier detection, confidence-based rejection, confidence scaling, prior adjustment, and adaptive windowing. We then propose two new temporally aware post-processing schemes that use changes in the decision and confidence streams to better reject uncertain decisions. Our decision-change informed rejection (DCIR) approach outperforms existing schemes during both steady-state and transitions based on error rates and decision stream volatility whether using conventional or deep classifiers. These results suggest that added robustness can be gained by appropriately leveraging temporal context in myoelectric control.

eess.SP↗

arXiv2024

Towards Robust and Interpretable EMG-based Hand Gesture Recognition using Deep Metric Meta Learning

Current electromyography (EMG) pattern recognition (PR) models have been shown to generalize poorly in unconstrained environments, setting back their adoption in applications such as hand gesture control. This problem is often due to limited training data, exacerbated by the use of supervised classification frameworks that are known to be suboptimal in such settings. In this work, we propose a shift to deep metric-based meta-learning in EMG PR to supervise the creation of meaningful and interpretable representations. We use a Siamese Deep Convolutional Neural Network (SDCNN) and contrastive triplet loss to learn an EMG feature embedding space that captures the distribution of the different classes. A nearest-centroid approach is subsequently employed for inference, relying on how closely a test sample aligns with the established data distributions. We derive a robust class proximity-based confidence estimator that leads to a better rejection of incorrect decisions, i.e. false positives, especially when operating beyond the training data domain. We show our approach's efficacy by testing the trained SDCNN's predictions and confidence estimations on unseen data, both in and out of the training domain. The evaluation metrics include the accuracy-rejection curve and the Kullback-Leibler divergence between the confidence distributions of accurate and inaccurate predictions. Outperforming comparable models on both metrics, our results demonstrate that the proposed meta-learning approach improves the classifier's precision in active decisions (after rejection), thus leading to better generalization and applicability.

eess.SP↗

arXiv2024

On-Demand Myoelectric Control Using Wake Gestures to Eliminate False Activations During Activities of Daily Living

While myoelectric control has recently become a focus of increased research as a possible flexible hands-free input modality, current control approaches are prone to inadvertent false activations in real-world conditions. In this work, a novel myoelectric control paradigm -- on-demand myoelectric control -- is proposed, designed, and evaluated, to reduce the number of unrelated muscle movements that are incorrectly interpreted as input gestures . By leveraging the concept of wake gestures, users were able to switch between a dedicated control mode and a sleep mode, effectively eliminating inadvertent activations during activities of daily living (ADLs). The feasibility of wake gestures was demonstrated in this work through two online ubiquitous EMG control tasks with varying difficulty levels; dismissing an alarm and controlling a robot. The proposed control scheme was able to appropriately ignore almost all non-targeted muscular inputs during ADLs (>99.9%) while maintaining sufficient sensitivity for reliable mode switching during intentional wake gesture elicitation. These results highlight the potential of wake gestures as a critical step towards enabling ubiquitous myoelectric control-based on-demand input for a wide range of applications.

cs.HC↗

arXiv2023

A Framework and Call to Action for the Future Development of EMG-Based Input in HCI

Electromyography (EMG) has been explored as an HCI input modality following a long history of success for prosthesis control. While EMG has the potential to address a range of hands-free interaction needs, it has yet to be widely accepted outside of prosthetics due to a perceived lack of robustness and intuitiveness. To understand how EMG input systems can be better designed, we sampled the ACM digital library to identify limitations in the approaches taken. Leveraging these works in combination with our research group's extensive interdisciplinary experience in this field, four themes emerged (1) interaction design, (2) model design, (3) system evaluation, and (4) reproducibility. Using these themes, we provide a step-by-step framework for designing EMG-based input systems to strengthen the foundation on which EMG-based interactions are built. Additionally, we provide a call-to-action for researchers to unlock the hidden potential of EMG as a widely applicable and highly usable input modality.

cs.HC↗

arXiv2021

A Transferable Adaptive Domain Adversarial Neural Network for Virtual Reality Augmented EMG-Based Gesture Recognition

Within the field of electromyography-based (EMG) gesture recognition, disparities exist between the offline accuracy reported in the literature and the real-time usability of a classifier. This gap mainly stems from two factors: 1) The absence of a controller, making the data collected dissimilar to actual control. 2) The difficulty of including the four main dynamic factors (gesture intensity, limb position, electrode shift, and transient changes in the signal), as including their permutations drastically increases the amount of data to be recorded. Contrarily, online datasets are limited to the exact EMG-based controller used to record them, necessitating the recording of a new dataset for each control method or variant to be tested. Consequently, this paper proposes a new type of dataset to serve as an intermediate between offline and online datasets, by recording the data using a real-time experimental protocol. The protocol, performed in virtual reality, includes the four main dynamic factors and uses an EMG-independent controller to guide movements. This EMG-independent feedback ensures that the user is in-the-loop during recording, while enabling the resulting dynamic dataset to be used as an EMG-based benchmark. The dataset is comprised of 20 able-bodied participants completing three to four sessions over a period of 14 to 21 days. The ability of the dynamic dataset to serve as a benchmark is leveraged to evaluate the impact of different recalibration techniques for long-term (across-day) gesture recognition, including a novel algorithm, named TADANN. TADANN consistently and significantly (p<0.05) outperforms using fine-tuning as the recalibration technique.

cs.LG↗

arXiv2020

Unsupervised Domain Adversarial Self-Calibration for Electromyographic-based Gesture Recognition

Surface electromyography (sEMG) provides an intuitive and non-invasive interface from which to control machines. However, preserving the myoelectric control system's performance over multiple days is challenging, due to the transient nature of the signals obtained with this recording technique. In practice, if the system is to remain usable, a time-consuming and periodic recalibration is necessary. In the case where the sEMG interface is employed every few days, the user might need to do this recalibration before every use. Thus, severely limiting the practicality of such a control method. Consequently, this paper proposes tackling the especially challenging task of unsupervised adaptation of sEMG signals, when multiple days have elapsed between each recording, by introducing Self-Calibrating Asynchronous Domain Adversarial Neural Network (SCADANN). SCADANN is compared with two state-of-the-art self-calibrating algorithms developed specifically for deep learning within the context of EMG-based gesture recognition and three state-of-the-art domain adversarial algorithms. The comparison is made both on an offline and a dynamic dataset (20 participants per dataset), using two different deep network architectures with two different input modalities (temporal-spatial descriptors and spectrograms). Overall, SCADANN is shown to substantially and systematically improves classification performances over no recalibration and obtains the highest average accuracy for all tested cases across all methods.

cs.HC↗

arXiv2020

Interpreting Deep Learning Features for Myoelectric Control: A Comparison with Handcrafted Features

The research in myoelectric control systems primarily focuses on extracting discriminative representations from the electromyographic (EMG) signal by designing handcrafted features. Recently, deep learning techniques have been applied to the challenging task of EMG-based gesture recognition. The adoption of these techniques slowly shifts the focus from feature engineering to feature learning. However, the black-box nature of deep learning makes it hard to understand the type of information learned by the network and how it relates to handcrafted features. Additionally, due to the high variability in EMG recordings between participants, deep features tend to generalize poorly across subjects using standard training methods. Consequently, this work introduces a new multi-domain learning algorithm, named ADANN, which significantly enhances (p=0.00004) inter-subject classification accuracy by an average of 19.40% compared to standard training. Using ADANN-generated features, the main contribution of this work is to provide the first topological data analysis of EMG-based gesture recognition for the characterisation of the information encoded within a deep network, using handcrafted features as landmarks. This analysis reveals that handcrafted features and the learned features (in the earlier layers) both try to discriminate between all gestures, but do not encode the same information to do so. Furthermore, using convolutional network visualization techniques reveal that learned features tend to ignore the most activated channel during gesture contraction, which is in stark contrast with the prevalence of handcrafted features designed to capture amplitude information. Overall, this work paves the way for hybrid feature sets by providing a clear guideline of complementary information encoded within learned and handcrafted features.

eess.SP↗

arXiv2020

A Comparison of Amputee and Able-Bodied Inter-Subject Variability in Myoelectric Control

Despite decades of research and development of pattern recognition approaches, the clinical usability of myoelectriccontrolled prostheses is still limited. One of the main issues is the high inter-subject variability that necessitates long and frequent user-specific training. Cross-user models present an opportunity to improve clinical viability of myoelectric control systems by leveraging existing data to shorten training. However, due to the difficulty of obtaining large sets of data from amputee populations, data from intact-limbed subjects are often supplemented when building cross-user models; which may not translate well to clinical usability. In this preliminary study, the differences between intact-limbed and amputee cross-user electromyography (EMG) patterns were examined. Previously collected EMG data from 20 intact limbed and 10 amputee subjects for different wrist, finger, and grasping gestures were analysed. Results using unsupervised clustering showed that amputees were consistently grouped into a different cluster than intact-limbed subjects and that additional clustering into more subgroups found larger differences between amputees than able-bodied subjects. Furthermore, a simple linear classifier was able to discriminate between able-bodied and amputee subjects using EMG from multiple gestures with 90% accuracy. These results suggest that using able-bodied subject data alone may be insufficient to capture the necessary inter-subject variance when designing cross-user myoelectric control systems for prosthesis control.

eess.SP↗

arXiv2020

Differences in Perspective on Inertial Measurement Unit Sensor Integration in Myoelectric Control

Recent human computer-interaction (HCI) studies using electromyography (EMG) and inertial measurement units (IMUs) for upper-limb gesture recognition have claimed that inertial measurements alone result in higher classification accuracy than EMG. In biomedical research such as in prosthesis control, however, EMG remains the gold standard for providing gesture specific information, exceeding the performance of IMUs alone. This study, therefore, presents a preliminary investigation of these conflicting claims between these converging research fields. Previous claims from both fields were verified within this study using publicly available datasets. The conflicting claims were found to stem from differences in terminology and experimental design. Specifically, HCI studies were found to exploit positional variation to increase separation between similar hand gestures. Conversely, in clinical applications such as prosthetics, position invariant gestures are preferred.This work therefore suggests that future studies explicitly outline experimental approaches to better differentiate between gesture recognition approaches.

eess.SP↗