arXiv subjects

Saeid Sanei

Publications and source records attributed to Saeid Sanei.

12 recordsLinked to original sources

arXiv2026

QiVC-Net: Quantum-Inspired Variational Convolutional Network, with Application to Biosignal Classification

In this paper, a learning framework is introduced which incorporates principles of probabilistic inference, variational optimization, and geometry-preserving operations inspired by quantum transformations. The central innovation of this quantum-inspired variational convolution (QiVC) lies in its quantum-inspired rotated ensemble (QiRE) mechanism. QiRE performs differentiable low-dimensional subspace rotations of convolutional weights. By drawing a mathematical analogy from unitary evolution, this approach enables structured uncertainty modeling that respects the intrinsic geometry of the parameter space. To demonstrate its practical potential, the concept is instantiated in a QiVC-based convolutional network (QiVC-Net) and evaluated in the context of biosignal classification, focusing on phonocardiogram (PCG) recordings. The proposed QiVC-Net integrates an architecture in which the QiVC layer does not introduce additional parameters, instead performing an ensemble rotation of the convolutional weights through a structured mechanism ensuring robustness without added highly computational burden. Experiments on two benchmark datasets, PhysioNet CinC 2016 and PhysioNet CirCor DigiScope 2022, show that QiVC-Net achieves state-of-the-art performance, reaching accuracies of 97.84% and 97.89%, respectively. These findings highlight the versatility of the QiVC framework and its promise for advancing uncertainty-aware modeling in real-world biomedical signal analysis. The implementation of the QiVConv layer is available in GitHub for public use.

cs.LG↗

arXiv2026

Physiologically Grounded Driver Behavior Classification: SHAP-Driven Elite Feature Selection and Hybrid Gradient Boosting for Multimodal Physiological Signals

An interpretable and scalable framework for decoding driving behaviors from multimodal physiological signals is proposed in this study. We utilize multimodal physiological driving behavior large-scale dataset comprising synchronized electroencephalogram (EEG), electromyography (EMG), and galvanic skin response (GSR) signals. Our approach involves rigorous preprocessing followed by a domain-specific feature extraction pipeline targeting time-domain, frequency-domain, and derived physiological indices. To address high dimensionality, we employ SHAP-based elite feature selection, retaining the top 250 features to reduce computational overhead while preserving predictive power. Hyperparameter optimization for extreme gradient boosting (XGBoost) and light gradient boosting machine (LightGBM) models is conducted using Bayesian optimization via Optuna. Finally, a weighted soft-voting ensemble is constructed to leverage the complementary strengths of both gradient boosting frameworks. The results demonstrate that the proposed ensemble achieves a test accuracy of 80.91% and a macro-F1 score of 0.79, significantly outperforming single-modality baselines and traditional machine learning models. Ablation studies confirm an 8% performance gain over the best single modality (EEG), validating the necessity of multimodal fusion. SHAP analysis further validates the physiological plausibility of the model, revealing that the EEG contributes the majority of predictive weight, GSR and EMG features provide critical discriminatory signals for high-arousal and motor-intensive maneuvers.

cs.LG↗

arXiv2024

Clinical translation of machine learning algorithms for seizure detection in scalp electroencephalography: systematic review

Machine learning algorithms for seizure detection have shown considerable diagnostic potential, with recent reported accuracies reaching 100%. Yet, only few published algorithms have fully addressed the requirements for successful clinical translation. This is, for example, because the properties of training data may limit the generalisability of algorithms, algorithm performance may vary depending on which electroencephalogram (EEG) acquisition hardware was used, or run-time processing costs may be prohibitive to real-time clinical use cases. To address these issues in a critical manner, we systematically review machine learning algorithms for seizure detection with a focus on clinical translatability, assessed by criteria including generalisability, run-time costs, explainability, and clinically-relevant performance metrics. For non-specialists, the domain-specific knowledge necessary to contextualise model development and evaluation is provided. It is our hope that such critical evaluation of machine learning algorithms with respect to their potential real-world effectiveness can help accelerate clinical translation and identify gaps in the current seizure detection literature.

eess.SP↗

arXiv2024

Fidelitous Augmentation of Human Accelerometric Data for Deep Learning

Time series (TS) data have consistently been in short supply, yet their demand remains high for training systems in prediction, modeling, classification, and various other applications. Synthesis can serve to expand the sample population, yet it is crucial to maintain the statistical characteristics between the synthesized and the original TS : this ensures consistent sampling of data for both training and testing purposes. However the time domain features of the data may not be maintained. This motivates for our work, the objective which is to preserve the following features in a synthesized TS: its fundamental statistical characteristics and important time domain features like its general shape and prominent transients. In a novel way, we first isolate important TS features into various components using a spectrogram and singular spectrum analysis. The residual signal is then randomized in a way that preserves its statistical properties. These components are then recombined for the synthetic time series. Using accelerometer data in a clinical setting, we use statistical and shape measures to compare our method to others. We show it has higher fidelity to the original signal features, has good diversity and performs better data classification in a deep learning application.

eess.SP↗

arXiv2023

Crowd Modeling and Control via Cooperative Adaptive Filtering

This paper introduces a crowd modeling and motion control approach that employs diffusion adaptation within an adaptive network. In the network, nodes collaboratively address specific estimation problems while simultaneously moving as agents governed by certain motion control mechanisms. Our research delves into the behaviors of agents when they encounter spatial constraints. Within this framework, agents pursue several objectives, such as target tracking, coherent motion, and obstacle evasion. Throughout their navigation, they demonstrate a nature of self-organization and self-adjustment that drives them to maintain certain social distances with each other, and adaptively adjust their behaviors in response to the environmental changes. Our findings suggest a promising approach to mitigate the spread of viral pandemics and averting stampedes.

cs.MA↗

arXiv2023

Underdetermined Blind Identification via $k$-Sparse Component Analysis: RANSAC-driven Orthogonal Subspace Search

Two primary families of methods exist for underdetermined blind identification (UBI) based on the sparsity of the source matrix: sparse component analysis (SCA) and $k$-SCA. SCA assumes one active source at each time instant, while $k$-SCA allows for varying numbers of active sources represented by $k$. However, existing $k$-SCA methods, which claim to solve UBI problems by accommodating $k$-sparse sources, predominantly rely on $1$-sparse sources, limiting their effectiveness in real-world scenarios with high noise levels. In this paper, we propose an effective and computationally less complex approach for UBI, specifically focusing on the challenging case when the number of active sources is equal to the number of sensors minus one ($k=m-1$). Our approach overcomes limitations by using a two-step scenario: (1) estimating the orthogonal complement subspaces of the overall space and (2) identifying the mixing vectors. We present an integrated algorithm based on the Gram-Schmidt process and random sample consensus (RANSAC) method to solve both steps. Experimental results using simulated data demonstrate the superior effectiveness of our proposed method compared to existing algorithms.

eess.SP↗

arXiv2020

Vision-based techniques for gait recognition

Global security concerns have raised a proliferation of video surveillance devices. Intelligent surveillance systems seek to discover possible threats automatically and raise alerts. Being able to identify the surveyed object can help determine its threat level. The current generation of devices provide digital video data to be analysed for time varying features to assist in the identification process. Commonly, people queue up to access a facility and approach a video camera in full frontal view. In this environment, a variety of biometrics are available - for example, gait which includes temporal features like stride period. Gait can be measured unobtrusively at a distance. The video data will also include face features, which are short-range biometrics. In this way, one can combine biometrics naturally using one set of data. In this paper we survey current techniques of gait recognition and modelling with the environment in which the research was conducted. We also discuss in detail the issues arising from deriving gait data, such as perspective and occlusion effects, together with the associated computer vision challenges of reliable tracking of human movement. Then, after highlighting these issues and challenges related to gait processing, we proceed to discuss the frameworks combining gait with other biometrics. We then provide motivations for a novel paradigm in biometrics-based human recognition, i.e. the use of the fronto-normal view of gait as a far-range biometrics combined with biometrics operating at a near distance.

cs.CV↗

arXiv2019

Variants of Partial Update Augmented CLMS Algorithm and Their Performance Analysis

Naturally complex-valued information or those presented in complex domain are effectively processed by an augmented complex least-mean-square (ACLMS) algorithm. In some applications, the ACLMS algorithm may be too computationally- and memory-intensive to implement. In this paper, a new algorithm, termed partial-update ACLMS (PU-ACLMS) algorithm is proposed, where only a fraction of the coefficient set is selected to update at each iteration. Doing so, two types of partial-update schemes are presented referred to as the sequential and stochastic partial-updates, to reduce computational load and power consumption in the corresponding adaptive filter. The computational cost for full-update PU-ACLMS and its partial-update implementations are discussed. Next, the steady-state mean and mean-square performance of PU-ACLMS for non-circular complex signals are analyzed and closed-form expressions of the steady-state excess mean-square error (EMSE) and mean-square deviation (MSD) are given. Then, employing the weighted energy-conservation relation, the EMSE and MSD learning curves are derived. The simulation results are verified and compared with those of theoretical predictions through numerical examples.

eess.SY↗

arXiv2019

Multiscale Fluctuation-based Dispersion Entropy and its Applications to Neurological Diseases

Fluctuation-based dispersion entropy (FDispEn) is a new approach to estimate the dynamical variability of the fluctuations of signals. It is based on Shannon entropy and fluctuation-based dispersion patterns. To quantify the physiological dynamics over multiple time scales, multiscale FDispEn (MFDE) is developed in this article. MFDE is robust to the presence of baseline wanders, or trends, in the data. We evaluate MFDE, compared with popular multiscale sample entropy (MSE), and the recently introduced multiscale dispersion entropy (MDE), on selected synthetic data and five neurological diseases' datasets: 1) focal and non-focal electroencephalograms (EEGs); 2) walking stride interval signals for young, elderly, and Parkinson's subjects; 3) stride interval fluctuations for Huntington's disease and amyotrophic lateral sclerosis; 4) EEGs for controls and Alzheimer's disease patients; and 5) eye movement data for Parkinson's disease and ataxia. MFDE dealt with the problem of undefined MSE values and, compared with MDE, led to more stable entropy values over the scale factors for pink noise. Overall, MFDE was the fastest and most consistent method for the discrimination of different states of neurological data, especially where the mean value of a time series considerably changes along the signal (e.g., eye movement data). This study shows that MFDE is a relevant new metric to gain further insights into the dynamics of neurological diseases recordings.

q-bio.NC↗

arXiv2017

Partial Diffusion Kalman Filtering

In conventional distributed Kalman filtering, employing diffusion strategies, each node transmits its state estimate to all its direct neighbors in each iteration. In this paper we propose a partial diffusion Kalman filter (PDKF) for state estimation of linear dynamic systems. In the PDKF algorithm every node (agent) is allowed to share only a subset of its intermediate estimate vectors at each iteration among its neighbors, which reduces the amount of internode communications. We study the stability of the PDKF algorithm where our analysis reveals that the algorithm is stable and convergent in both mean and mean-square senses. We also investigate the steady-state mean-square deviation (MSD) of the PDKF algorithm and derive a closed-form expression that describes how the algorithm performs at the steady-state. Experimental results validate the effectiveness of PDKF algorithm and demonstrate that the proposed algorithm provides a trade-off between communication cost and estimation performance that is extremely profitable.

eess.SY↗

arXiv2016

Partial Diffusion Recursive Least-Squares for Distributed Estimation under Noisy Links Condition

Partial diffusion-based recursive least squares (PDRLS) is an effective method for reducing computational load and power consumption in adaptive network implementation. In this method, each node shares a part of its intermediate estimate vector with its neighbors at each iteration. PDRLS algorithm reduces the internode communications relative to the full-diffusion RLS algorithm. This selection of estimate entries becomes more appealing when the information fuse over noisy links. In this paper, we study the steady-state performance of PDRLS algorithm in presence of noisy links and investigate its convergence in both mean and mean-square senses. We also derive a theoretical expression for its steady-state meansquare deviation (MSD). The simulation results illustrate that the stability conditions for PDRLS under noisy links are not sufficient to guarantee its convergence. Strictly speaking, considering nonideal links condition adds a new complexity to the estimation problem for which the PDRLS algorithm becomes unstable and do not converge for any value of the forgetting factor.

cs.DC↗

arXiv2015

Partial-Diffusion Least Mean-Square Estimation Over Networks Under Noisy Information Exchange

Partial diffusion scheme is an effective method for reducing computational load and power consumption in adaptive network implementation. The Information is exchanged among the nodes, usually over noisy links. In this paper, we consider a general version of partial-diffusion least-mean-square (PDLMS) algorithm in the presence of various sources of imperfect information exchanges. Like the established PDLMS, we consider two different schemes to select the entries, sequential and stochastic, for transmission at each iteration. Our objective is to analyze the aggregate effect of these perturbations on general PDLMS strategies. Simulation results demonstrate that considering noisy link assumption adds a new complexity to the related optimization problem and the trade-off between communication cost and estimation performance in comparison to ideal case becomes unbalanced.

eess.SY↗