arXiv subjects

Kianoush Nazarpour

Publications and source records attributed to Kianoush Nazarpour.

8 recordsLinked to original sources

arXiv2026

ViMoWear: Visual Motion-Guided sEMG-IMU Representation Learning for Subject-Independent Thumb Gesture Recognition

Wearable sensing enables intuitive hand gesture recognition for human--computer interaction, augmented reality, and prosthetic control, yet subject--independent recognition remains challenging because wearable signals provide only indirect and highly subject-specific observations of hand motion. Although visual information can improve wearable gesture recognition, requiring it during inference increases sensing complexity and limits practical deployment. We propose ViMoWear, a visual-motion-guided framework that leverages synchronized 3D hand motion as training-only supervision while requiring only wearable sensing for gesture classification at inference. Specifically, Motion-Guided Cross-Subject Contrastive Learning (MGCL) promotes subject-robust representations, and Thumb-Aware Masked Motion Reconstruction (TMMR) preserves fine-grained motion information. The leave-one-subject-out experiments on a synchronized sEMG--IMU--pose dataset demonstrate consistent improvements over supervised baselines across multiple sensing configurations, while the learned representations also support classifier-free retrieval. The proposed training-only visual motion supervision improves the generalization of wearable representations to unseen subjects.

cs.HC↗

arXiv2026

KinEMbed: Decoding Kinematics from Electromyography via Cross-Modal Contrastive Learning

Decoding hand kinematics from surface electromyography (EMG) is a core challenge in wearable biosignal processing with clinical relevance for prosthetic control and motor rehabilitation. Most representation learning approaches for EMG focus on discrete gesture classification, and few focus on continuous regression. We present KinEMbed, a cross-modal contrastive learning framework for hand kinematics regression that jointly trains dual encoders -- one for windowed EMG features and one for kinematic (joint angle) targets. The resulting embeddings inherit the geometric structure of the kinematic space without requiring kinematic signals at inference time. Evaluating on the NinaPro DB8 dataset that includes both able-bodied users and subjects with limb difference (N=11), KinEMbed outperforms PCA, PLS, autoencoder and contrastive (CEBRA) baselines on held-out sessions, with largest gains on the most challenging thumb degrees of articulation. We position this work as a first step toward contrastive representation learning for regression of hand kinematics from structured wearable biosignals.

cs.LG↗

arXiv2026

On Optimizing Electrode Configuration for Wrist-Worn sEMG-Based Thumb Gesture Recognition

Thumb gestures provide an effective and unobtrusive input modality for wearable and always-available human-machine interaction. Wrist-worn surface electromyography (sEMG) has emerged as a promising approach for compact and wearable human-machine interfaces. However, compared to forearm sEMG, the impact of electrode configuration on wrist-based decoding performance remains understudied. We systematically investigated electrode configuration strategies for wrist-based thumb-movement recognition using high-density (HD) and low-density (LD) sEMG measurement systems. We considered factors such as muscle region, reference scheme, channel count, and spatial density of the electrode. Experimental results show that 1) extensor-side electrodes outperform flexor-side electrodes (HD: 0.871 vs. 0.821; LD: 0.769 vs. 0.705); 2) monopolar recordings consistently outperform bipolar configurations (15 channel with HD monopolar vs. LD bipolar: 0.885 vs. 0.823); and 3) increasing channel count enhances performance, but exhibits diminishing returns. We further show that electrode spatial distribution introduces a trade-off between spatial coverage and compactness. The findings suggest that the effectiveness of wrist-worn sEMG systems depends less on the deployment of a large number of electrodes in a broad sensing area and more on the optimization of electrode placement and the referencing scheme. This work provides practical guidelines for developing efficient wrist-worn sEMG-based gesture recognition systems.

cs.HC↗

arXiv2022

Using unsupervised machine learning to quantify physical activity from accelerometry in a diverse and rapidly changing population

Accelerometers are widely used to measure physical activity behaviour, including in children. The traditional method for processing acceleration data uses cut points to define physical activity intensity, relying on calibration studies that relate the magnitude of acceleration to energy expenditure. However, these relationships do not generalise across diverse populations and hence they must be parametrised for each subpopulation (e.g., age groups) which is costly and makes studies across diverse populations and over time difficult. A data driven approach that allows physical activity intensity states to emerge from the data, without relying on parameters derived from external populations, and offers a new perspective on this problem and potentially improved results. We applied an unsupervised machine learning approach, namely a hidden semi Markov model, to segment and cluster the accelerometer data recorded from 279 children (9 to 38 months old) with a diverse range of physical and social-cognitive abilities (measured using the Paediatric Evaluation of Disability Inventory). We benchmarked this analysis with the cut points approach calculated using the best available thresholds for the population. Time spent active as measured by this unsupervised approach correlated more strongly with measures of the childs mobility, social-cognitive capacity, independence, daily activity, and age than that measured using the cut points approach. Unsupervised machine learning offers the potential to provide a more sensitive, appropriate, and cost-effective approach to quantifying physical activity behaviour in diverse populations, compared to the current cut points approach. This, in turn, supports research that is more inclusive of diverse or rapidly changing populations.

q-bio.QM↗

arXiv2021

Modelling and Analysis of Magnetic Fields from Skeletal Muscle for Valuable Physiological Measurements

MagnetoMyoGraphy (MMG) is a method of studying muscle function via weak magnetic fields generated from human active organs and tissues. The correspondence between MMG and electromyography means directly derived from the Maxwell-Ampère law. Here, upon briefly describing the principles of voltage distribution inside skeletal muscles due to the electrical stimulation, we provide a protocol to determine the effects of the magnetic field generated from a time-changing action potential propagating in a group of skeletal muscle cells. The position-dependent and the magnetic field behaviour on account of the different currents in muscle fibres are performed in temporal, spectral and spatial domains. The procedure covers identification of the fibre subpopulations inside the fascicles of a given nerve section, characterization of soleus skeletal muscle currents, check of axial intracellular currents, calculation of the generated magnetic field ultimately. We expect this protocol to take approximately 2-3 hours to complete for the whole finite-element analysis.

eess.SY↗

arXiv2020

Classification of Chinese Handwritten Numbers with Labeled Projective Dictionary Pair Learning

Dictionary learning is a cornerstone of image classification. We set out to address a longstanding challenge in using dictionary learning for classification; that is to simultaneously maximise the discriminability and sparse-representability power of the learned dictionaries. Upon this premise, we designed class-specific dictionaries incorporating three factors: discriminability, sparsity and classification error. We integrated these metrics into a unified cost function and adopted a new feature space, i.e., histogram of oriented gradients (HOG), to generate the dictionary atoms. The rationale of using HOG features for designing the dictionaries is their strength in describing fine details of crowded images. The results of applying the proposed method in the classification of Chinese handwritten numbers demonstrated enhanced classification performance $(\sim98\%)$ compared to state-of-the-art deep learning techniques (i.e., SqueezeNet, GoogLeNet and MobileNetV2), but with a fraction of parameters. Furthermore, combination of the HOG features with dictionary learning enhances the accuracy by $11\%$ compared to the case where only pixel domain data are used. These results were supported when the proposed method was applied to both Arabic and English handwritten number databases.

cs.CV↗

arXiv2019

Grasp Type Estimation for Myoelectric Prostheses using Point Cloud Feature Learning

Prosthetic hands can help people with limb difference to return to their life routines. Commercial prostheses, however have several limitations in providing an acceptable dexterity. We approach these limitations by augmenting the prosthetic hands with an off-the-shelf depth sensor to enable the prosthesis to see the object's depth, record a single view (2.5-D) snapshot, and estimate an appropriate grasp type; using a deep network architecture based on 3D point clouds called PointNet. The human can act as the supervisor throughout the procedure by accepting or refusing the suggested grasp type. We achieved the grasp classification accuracy of up to 88%. Contrary to the case of the RGB data, the depth data provides all the necessary object shape information, which is required for grasp recognition. The PointNet not only enables using 3-D data in practice, but it also prevents excessive computations. Augmentation of the prosthetic hands with such a semi-autonomous system can lead to better differentiation of grasp types, less burden on user, and better performance.

cs.CV↗

arXiv2018

Dealing with Ambiguity in Robotic Grasping via Multiple Predictions

Humans excel in grasping and manipulating objects because of their life-long experience and knowledge about the 3D shape and weight distribution of objects. However, the lack of such intuition in robots makes robotic grasping an exceptionally challenging task. There are often several equally viable options of grasping an object. However, this ambiguity is not modeled in conventional systems that estimate a single, optimal grasp position. We propose to tackle this problem by simultaneously estimating multiple grasp poses from a single RGB image of the target object. Further, we reformulate the problem of robotic grasping by replacing conventional grasp rectangles with grasp belief maps, which hold more precise location information than a rectangle and account for the uncertainty inherent to the task. We augment a fully convolutional neural network with a multiple hypothesis prediction model that predicts a set of grasp hypotheses in under 60ms, which is critical for real-time robotic applications. The grasp detection accuracy reaches over 90% for unseen objects, outperforming the current state of the art on this task.

cs.CV↗