arXiv subjects

Freek Hens

Publications and source records attributed to Freek Hens.

3 recordsLinked to original sources

arXiv2026

TRIPROBE: Probing Task Separability Beyond Classification for XAI

Modern evaluation of learning pipelines often reduces to downstream accuracy, leaving open the question of why tasks succeed or fail. TriProbe addresses this gap with a multi-level probing framework for explainable diagnosis of task separability. Rather than treating models as black boxes, TriProbe traces how separability evolves across inputs, learned features, and final classifiers. It decomposes multi-task problems into binary subtasks and applies three complementary probes: a Foundational Probe on input spaces, a Latent Probe on feature representations, and a Final Probe on classifier outputs. Using Maximum Fisher's Discriminant Ratio as a principled separability metric, TriProbe identifies bottlenecks and affected task pairs. Experiments on the Roshambo sEMG benchmark show how TriProbe reveals hidden breakdowns, guiding data collection, validation, and architecture design.

cs.AI↗

arXiv2026

When One Sensor Fails: Tolerating Dysfunction in Multi-Sensor Prototypes

Surface electromyography (sEMG) sensors are widely used in human-computer interaction, yet the failure of a single sensor can compromise system usability. We propose a methodological framework for implementing a fail-safe mechanism in multi-sensor sEMG systems. Using arm sEMG recordings of rock-paper-scissors gestures, we extracted hand-crafted features and quantified class separability via the maximum Fisher discriminant ratio (FDR). A multi-layer perceptron validated our approach, consistent with prior findings and physiological evidence. Systematic sensor ablations and FDR analysis produced a ranking of crucial versus replaceable sensors. This ranking informs robust device design, sensor redundancy, and reliability in clinical and practical applications.

cs.HC↗

arXiv2024

STAL: Spike Threshold Adaptive Learning Encoder for Classification of Pain-Related Biosignal Data

This paper presents the first application of spiking neural networks (SNNs) for the classification of chronic lower back pain (CLBP) using the EmoPain dataset. Our work has two main contributions. We introduce Spike Threshold Adaptive Learning (STAL), a trainable encoder that effectively converts continuous biosignals into spike trains. Additionally, we propose an ensemble of Spiking Recurrent Neural Network (SRNN) classifiers for the multi-stream processing of sEMG and IMU data. To tackle the challenges of small sample size and class imbalance, we implement minority over-sampling with weighted sample replacement during batch creation. Our method achieves outstanding performance with an accuracy of 80.43%, AUC of 67.90%, F1 score of 52.60%, and Matthews Correlation Coefficient (MCC) of 0.437, surpassing traditional rate-based and latency-based encoding methods. The STAL encoder shows superior performance in preserving temporal dynamics and adapting to signal characteristics. Importantly, our approach (STAL-SRNN) outperforms the best deep learning method in terms of MCC, indicating better balanced class prediction. This research contributes to the development of neuromorphic computing for biosignal analysis. It holds promise for energy-efficient, wearable solutions in chronic pain management.

cs.LG↗