arXiv subjects

Naimul Khan

Publications and source records attributed to Naimul Khan.

At least 19 recordsLinked to original sources

arXiv2026

FMMO: Detecting the Divergence Between Local Attribution and Global Drift

Post-deployment drift poses a critical risk to algorithmic accountability, particularly when ground truth labels are delayed and performance degradation becomes a "silent failure". While Explainable AI (XAI) is often relied upon to audit these shifts, we demonstrate that popular local attribution methods (e.g., TreeSHAP) can exhibit misleading stability even as model reliability collapses. In this paper, we propose a Framework for Model Monitoring and Observability (FMMO) designed to expose the divergence between local explanation stability and global distribution shifts. Using benchmark, synthetic, and real-world datasets, we show that local XAI methods fail to flag drift-induced disparate impact, specifically where False Positive Rates spike for protected groups while feature attributions remain unchanged. By integrating global surrogate models with model utilization measurements, FMMO mitigates this fairness blind spot, ensuring that stakeholders can detect discriminatory deterioration that standard local XAI tools overlook.

cs.LG↗

arXiv2026

An Enhanced Source-Free Unsupervised Domain Adaptation Framework for Cross-Dataset EEG Emotion Recognition via Predictive Coding and Test-Time Training

EEG-based emotion recognition is widely used in affective computing but suffers from poor generalization due to domain shifts caused by inter-subject variability, dataset differences, and recording conditions, especially in cross-dataset settings. Conventional unsupervised domain adaptation methods require source data, which is often unavailable due to privacy constraints. Although source-free UDA addresses this limitation, existing methods still struggle with large domain gaps, noisy pseudo-labels, and unstable adaptation. To address these challenges, we propose an enhanced source-free unsupervised domain adaptation (SF-UDA) framework for cross-dataset EEG emotion recognition. The framework introduces a non-contrastive predictive coding-based self-supervised pretraining strategy to learn robust and transferable EEG representations by modeling temporal dependencies in a reconstruction-based manner. During adaptation, we estimate target-domain structure through class-wise clustering and prediction disagreement, and optimize the model using a dual-stage strategy consisting of Multi-Loss Adaptive Regularization and Localized Consistency Learning, improving stability and neighborhood consistency under noisy pseudo-labels. We also propose a lightweight test-time training mechanism that enables selective online updates for uncertain samples using predictive reconstruction loss and entropy minimization. Experiments on DEAP, SEED, and DREAMER show consistent improvements over state-of-the-art SF-UDA methods, achieving 69.56% and 63.03% accuracy on SEED and DREAMER when trained on DEAP, and 61.38% and 68.90% when trained on SEED.

eess.SP↗

arXiv2026

Stress Classification from ECG Signals Using Vision Transformer

Vision Transformers have shown tremendous success in numerous computer vision applications; however, they have not been exploited for stress assessment using physiological signals such as Electrocardiogram (ECG). In order to get the maximum benefit from the vision transformer for multilevel stress assessment, in this paper, we transform the raw ECG data into 2D spectrograms using short time Fourier transform (STFT). These spectrograms are divided into patches for feeding to the transformer encoder. We also perform experiments with 1D CNN and ResNet-18 (CNN model). We perform leave-onesubject-out cross validation (LOSOCV) experiments on WESAD and Ryerson Multimedia Lab (RML) dataset. One of the biggest challenges of LOSOCV based experiments is to tackle the problem of intersubject variability. In this research, we address the issue of intersubject variability and show our success using 2D spectrograms and the attention mechanism of transformer. Experiments show that vision transformer handles the effect of intersubject variability much better than CNN-based models and beats all previous state-of-the-art methods by a considerable margin. Moreover, our method is end-to-end, does not require handcrafted features, and can learn robust representations. The proposed method achieved 71.01% and 76.7% accuracies with RML dataset and WESAD dataset respectively for three class classification and 88.3% for binary classification on WESAD.

eess.SP↗

arXiv2026

DynaGuide: A Generalizable Dynamic Guidance Framework for Unsupervised Semantic Segmentation

Unsupervised image segmentation is a critical task in computer vision. It enables dense scene understanding without human annotations, which is especially valuable in domains where labelled data is scarce. However, existing methods often struggle to reconcile global semantic structure with fine-grained boundary accuracy. This paper introduces DynaGuide, an adaptive segmentation framework that addresses these challenges through a novel dual-guidance strategy and dynamic loss optimization. Building on our previous work, DynaSeg, DynaGuide combines global pseudo-labels from zero-shot models such as DiffSeg or SegFormer with local boundary refinement using a lightweight CNN trained from scratch. This synergy allows the model to correct coarse or noisy global predictions and produce high-precision segmentations. At the heart of DynaGuide is a multi-component loss that dynamically balances feature similarity, Huber-smoothed spatial continuity, including diagonal relationships, and semantic alignment with the global pseudo-labels. Unlike prior approaches, DynaGuide trains entirely without ground-truth labels in the target domain and supports plug-and-play integration of diverse guidance sources. Extensive experiments on BSD500, PASCAL VOC2012, and COCO demonstrate that DynaGuide achieves state-of-the-art performance, improving mIoU by 17.5% on BSD500, 3.1% on PASCAL VOC2012, and 11.66% on COCO. With its modular design, strong generalization, and minimal computational footprint, DynaGuide offers a scalable and practical solution for unsupervised segmentation in real-world settings. Code available at: https://github.com/RyersonMultimediaLab/DynaGuide

cs.CV↗

arXiv2025

Beyond Identity: A Generalizable Approach for Deepfake Audio Detection

Deepfake audio presents a growing threat to digital security, due to its potential for social engineering, fraud, and identity misuse. However, existing detection models suffer from poor generalization across datasets, due to implicit identity leakage, where models inadvertently learn speaker-specific features instead of manipulation artifacts. To the best of our knowledge, this is the first study to explicitly analyze and address identity leakage in the audio deepfake detection domain. This work proposes an identity-independent audio deepfake detection framework that mitigates identity leakage by encouraging the model to focus on forgery-specific artifacts instead of overfitting to speaker traits. Our approach leverages Artifact Detection Modules (ADMs) to isolate synthetic artifacts in both time and frequency domains, enhancing cross-dataset generalization. We introduce novel dynamic artifact generation techniques, including frequency domain swaps, time domain manipulations, and background noise augmentation, to enforce learning of dataset-invariant features. Extensive experiments conducted on ASVspoof2019, ADD 2022, FoR, and In-The-Wild datasets demonstrate that the proposed ADM-enhanced models achieve F1 scores of 0.230 (ADD 2022), 0.604 (FoR), and 0.813 (In-The-Wild), consistently outperforming the baseline. Dynamic Frequency Swap proves to be the most effective strategy across diverse conditions. These findings emphasize the value of artifact-based learning in mitigating implicit identity leakage for more generalizable audio deepfake detection.

cs.SD↗

arXiv2025

Towards Practical Emotion Recognition: An Unsupervised Source-Free Approach for EEG Domain Adaptation

Emotion recognition is crucial for advancing mental health, healthcare, and technologies such as brain-computer interfaces. EEG-based models, however, struggle in cross-domain settings due to the high cost of labeled data and signal variability across individuals and recording conditions. Unsupervised domain adaptation typically requires access to source data, which is often infeasible because of privacy and computational constraints. Source-free unsupervised domain adaptation (SF-UDA) removes this requirement, but it has not yet been applied to emotion recognition. We propose an SF-UDA approach for cross-domain EEG emotion classification, built on a multi-stage framework that adapts to the target domain without source data. Dual-Loss Adaptive Regularization (DLAR) minimizes prediction discrepancies on confident samples and aligns predictions with expected pseudo-labels. Localized Consistency Learning (LCL) enforces local consistency by promoting similar predictions among reliable neighbors. Together, these components address domain shift and reduce the impact of noisy pseudo-labels, a key challenge in SF-UDA. Experiments on DEAP, SEED, and DREAMER show that our method significantly outperforms state-of-the-art approaches, reaching 65.84% and 58.87% accuracy on SEED and DREAMER when trained on DEAP, and 58.99% and 67.08% on DEAP and DREAMER when trained on SEED. It detects both positive and negative emotions well, making it suitable for practical emotion recognition applications. Code available at: https://github.com/RyersonMultimediaLab/EmotionRecognitionSF-UDA

eess.SP↗

arXiv2025

Temporal Feature Weaving for Neonatal Echocardiographic Viewpoint Video Classification

Automated viewpoint classification in echocardiograms can help under-resourced clinics and hospitals in providing faster diagnosis and screening when expert technicians may not be available. We propose a novel approach towards echocardiographic viewpoint classification. We show that treating viewpoint classification as video classification rather than image classification yields advantage. We propose a CNN-GRU architecture with a novel temporal feature weaving method, which leverages both spatial and temporal information to yield a 4.33\% increase in accuracy over baseline image classification while using only four consecutive frames. The proposed approach incurs minimal computational overhead. Additionally, we publish the Neonatal Echocardiogram Dataset (NED), a professionally-annotated dataset providing sixteen viewpoints and associated echocardipgraphy videos to encourage future work and development in this field. Code available at: https://github.com/satchelfrench/NED

cs.CV↗

arXiv2024

Enhanced Cross-Dataset Electroencephalogram-based Emotion Recognition using Unsupervised Domain Adaptation

Emotion recognition has significant potential in healthcare and affect-sensitive systems such as brain-computer interfaces (BCIs). However, challenges such as the high cost of labeled data and variability in electroencephalogram (EEG) signals across individuals limit the applicability of EEG-based emotion recognition models across domains. These challenges are exacerbated in cross-dataset scenarios due to differences in subject demographics, recording devices, and presented stimuli. To address these issues, we propose a novel approach to improve cross-domain EEG-based emotion classification. Our method, Gradual Proximity-guided Target Data Selection (GPTDS), incrementally selects reliable target domain samples for training. By evaluating their proximity to source clusters and the models confidence in predicting them, GPTDS minimizes negative transfer caused by noisy and diverse samples. Additionally, we introduce Prediction Confidence-aware Test-Time Augmentation (PC-TTA), a cost-effective augmentation technique. Unlike traditional TTA methods, which are computationally intensive, PC-TTA activates only when model confidence is low, improving inference performance while drastically reducing computational costs. Experiments on the DEAP and SEED datasets validate the effectiveness of our approach. When trained on DEAP and tested on SEED, our model achieves 67.44% accuracy, a 7.09% improvement over the baseline. Conversely, training on SEED and testing on DEAP yields 59.68% accuracy, a 6.07% improvement. Furthermore, PC-TTA reduces computational time by a factor of 15 compared to traditional TTA methods. Our method excels in detecting both positive and negative emotions, demonstrating its practical utility in healthcare applications. Code available at: https://github.com/RyersonMultimediaLab/EmotionRecognitionUDA

eess.SP↗

arXiv2024

DynaSeg: A Deep Dynamic Fusion Method for Unsupervised Image Segmentation Incorporating Feature Similarity and Spatial Continuity

Our work tackles the fundamental challenge of image segmentation in computer vision, which is crucial for diverse applications. While supervised methods demonstrate proficiency, their reliance on extensive pixel-level annotations limits scalability. We introduce DynaSeg, an innovative unsupervised image segmentation approach that overcomes the challenge of balancing feature similarity and spatial continuity without relying on extensive hyperparameter tuning. Unlike traditional methods, DynaSeg employs a dynamic weighting scheme that automates parameter tuning, adapts flexibly to image characteristics, and facilitates easy integration with other segmentation networks. By incorporating a Silhouette Score Phase, DynaSeg prevents undersegmentation failures where the number of predicted clusters might converge to one. DynaSeg uses CNN-based and pre-trained ResNet feature extraction, making it computationally efficient and more straightforward than other complex models. Experimental results showcase state-of-the-art performance, achieving a 12.2% and 14.12% mIOU improvement over current unsupervised segmentation approaches on COCO-All and COCO-Stuff datasets, respectively. We provide qualitative and quantitative results on five benchmark datasets, demonstrating the efficacy of the proposed approach. Code available at Code available at https://github.com/RyersonMultimediaLab/DynaSeg

cs.CV↗

arXiv2024

Navigating the Serious Game Design Landscape: A Comprehensive Reference Document

Within the evolving field of digital intervention, serious games emerge as promising tools for evidence-based interventions. Research indicates that gamified therapy, whether employed independently or in conjunction with online psychoeducation or traditional programs, proves more efficacious in delivering care to patients. As we navigate the intricate realm of serious game design, bridging the gap between therapeutic approaches and creative design proves complex. Professionals in clinical and research roles demonstrate innovative thinking yet face challenges in executing engaging therapeutic serious games due to the lack of specialized design skills and knowledge. Thus, a larger question remains: How might we aid and educate professionals in clinical and research roles the importance of game design to support their innovative therapeutic approaches? This study examines potential solutions aimed at facilitating the integration of gamification design principles into clinical study protocols, a pivotal aspect for aligning therapeutic practices with captivating narratives in the pursuit of innovative interventions. We propose two solutions, a flow chart framework for serious games or a comprehensive reference document encompassing gamification design principles and guidelines for best design practices. Through an examination of literature reviews, it was observed that selected design decisions varied across studies. Thus, we propose that the second solution, a comprehensive reference design guide, is more versatile and adaptable.

cs.HC↗

arXiv2024

A Dynamically Weighted Loss Function for Unsupervised Image Segmentation

Image segmentation is the foundation of several computer vision tasks, where pixel-wise knowledge is a prerequisite for achieving the desired target. Deep learning has shown promising performance in supervised image segmentation. However, supervised segmentation algorithms require a massive amount of data annotated at a pixel level, thus limiting their applicability and scalability. Therefore, there is a need to invest in unsupervised learning for segmentation. This work presents an improved version of an unsupervised Convolutional Neural Network (CNN) based algorithm that uses a constant weight factor to balance between the segmentation criteria of feature similarity and spatial continuity, and it requires continuous manual adjustment of parameters depending on the degree of detail in the image and the dataset. In contrast, we propose a novel dynamic weighting scheme that leads to a flexible update of the parameters and an automatic tuning of the balancing weight between the two criteria above to bring out the details in the images in a genuinely unsupervised manner. We present quantitative and qualitative results on four datasets, which show that the proposed scheme outperforms the current unsupervised segmentation approaches without requiring manual adjustment.

eess.IV↗

arXiv2023

Cross-Database and Cross-Channel ECG Arrhythmia Heartbeat Classification Based on Unsupervised Domain Adaptation

The classification of electrocardiogram (ECG) plays a crucial role in the development of an automatic cardiovascular diagnostic system. However, considerable variances in ECG signals between individuals is a significant challenge. Changes in data distribution limit cross-domain utilization of a model. In this study, we propose a solution to classify ECG in an unlabeled dataset by leveraging knowledge obtained from labeled source domain. We present a domain-adaptive deep network based on cross-domain feature discrepancy optimization. Our method comprises three stages: pre-training, cluster-centroid computing, and adaptation. In pre-training, we employ a Distributionally Robust Optimization (DRO) technique to deal with the vanishing worst-case training loss. To enhance the richness of the features, we concatenate three temporal features with the deep learning features. The cluster computing stage involves computing centroids of distinctly separable clusters for the source using true labels, and for the target using confident predictions. We propose a novel technique to select confident predictions in the target domain. In the adaptation stage, we minimize compacting loss within the same cluster, separating loss across different clusters, inter-domain cluster discrepancy loss, and running combined loss to produce a domain-robust model. Experiments conducted in both cross-domain and cross-channel paradigms show the efficacy of the proposed method. Our method achieves superior performance compared to other state-of-the-art approaches in detecting ventricular ectopic beats (V), supraventricular ectopic beats (S), and fusion beats (F). Our method achieves an average improvement of 11.78% in overall accuracy over the non-domain-adaptive baseline method on the three test datasets.

eess.SP↗

arXiv2023

Structure Preserving Cycle-GAN for Unsupervised Medical Image Domain Adaptation

The presence of domain shift in medical imaging is a common issue, which can greatly impact the performance of segmentation models when dealing with unseen image domains. Adversarial-based deep learning models, such as Cycle-GAN, have become a common model for approaching unsupervised domain adaptation of medical images. These models however, have no ability to enforce the preservation of structures of interest when translating medical scans, which can lead to potentially poor results for unsupervised domain adaptation within the context of segmentation. This work introduces the Structure Preserving Cycle-GAN (SP Cycle-GAN), which promotes medical structure preservation during image translation through the enforcement of a segmentation loss term in the overall Cycle-GAN training process. We demonstrate the structure preserving capability of the SP Cycle-GAN both visually and through comparison of Dice score segmentation performance for the unsupervised domain adaptation models. The SP Cycle-GAN is able to outperform baseline approaches and standard Cycle-GAN domain adaptation for binary blood vessel segmentation in the STARE and DRIVE datasets, and multi-class Left Ventricle and Myocardium segmentation in the multi-modal MM-WHS dataset. SP Cycle-GAN achieved a state of the art Myocardium segmentation Dice score (DSC) of 0.7435 for the MR to CT MM-WHS domain adaptation problem, and excelled in nearly all categories for the MM-WHS dataset. SP Cycle-GAN also demonstrated a strong ability to preserve blood vessel structure in the DRIVE to STARE domain adaptation problem, achieving a 4% DSC increase over a default Cycle-GAN implementation.

eess.IV↗

arXiv2023

Lightweight and Interpretable Left Ventricular Ejection Fraction Estimation using Mobile U-Net

Accurate LVEF measurement is important in clinical practice as it identifies patients who may be in need of life-prolonging treatments. This paper presents a deep learning based framework to automatically estimate left ventricular ejection fraction from an entire 4-chamber apical echocardiogram video. The aim of the proposed framework is to provide an interpretable and computationally effective ejection fraction prediction pipeline. A lightweight Mobile U-Net based network is developed to segment the left ventricle in each frame of an echocardiogram video. An unsupervised LVEF estimation algorithm is implemented based on Simpson's mono-plane method. Experimental results on a large public dataset show that our proposed approach achieves comparable accuracy to the state-of-the-art while being significantly more space and time efficient (with 5 times fewer parameters and 10 times fewer FLOPS).

eess.IV↗

arXiv2023

Classification of Lung Pathologies in Neonates using Dual Tree Complex Wavelet Transform

Annually 8500 neonatal deaths are reported in the US due to respiratory failure. Recently, Lung Ultrasound (LUS), due to its radiation free nature, portability, and being cheaper is gaining wide acceptability as a diagnostic tool for lung conditions. However, lack of highly trained medical professionals has limited its use especially in remote areas. To address this, an automated screening system that captures characteristics of the LUS patterns can be of significant assistance to clinicians who are not experts in lung ultrasound (LUS) images. In this paper, we propose a feature extraction method designed to quantify the spatially-localized line patterns and texture patterns found in LUS images. Using the dual-tree complex wavelet transform (DTCWT) and four types of common image features we propose a method to classify the LUS images into 6 common neonatal lung conditions. These conditions are normal lung, pneumothorax (PTX), transient tachypnea of the newborn (TTN), respiratory distress syndrome (RDS), chronic lung disease (CLD) and consolidation (CON) that could be pneumonia or atelectasis. The proposed method using DTCWT decomposition extracted global statistical, grey-level co-occurrence matrix (GLCM), grey-level run length matrix (GLRLM) and linear binary pattern (LBP) features to be fed to a linear discriminative analysis (LDA) based classifier. Using 15 best DTCWT features along with 3 clinical features the proposed approach achieved a per-image classification accuracy of 92.78% with a balanced dataset containing 720 images from 24 patients and 74.39% with the larger unbalanced dataset containing 1550 images from 42 patients. Likewise, the proposed method achieved a maximum per-subject classification accuracy of 81.53% with 43 DTCWT features and 3 clinical features using the balanced dataset and 64.97% with 13 DTCWT features and 3 clinical features using the unbalanced dataset.

eess.IV↗

arXiv2022

Pan-Tompkins++: A Robust Approach to Detect R-peaks in ECG Signals

R-peak detection is crucial in electrocardiogram (ECG) signal processing as it is the basis of heart rate variability analysis. The Pan-Tompkins algorithm is the most widely used QRS complex detector for the monitoring of many cardiac diseases including arrhythmia detection. However, the performance of the Pan-Tompkins algorithm in detecting the QRS complexes degrades in low-quality and noisy signals. This article introduces Pan-Tompkins++, an improved Pan-Tompkins algorithm. A bandpass filter with a passband of 5--18 Hz followed by an N-point moving average filter has been applied to remove the noise without discarding the significant signal components. Pan-Tompkins++ uses three thresholds to distinguish between R-peaks and noise peaks. Rather than using a generalized equation, different rules are applied to adjust the thresholds based on the pattern of the signal for the accurate detection of R-peaks under significant changes in signal pattern. The proposed algorithm reduces the False Positive and False Negative detections, and hence improves the robustness and performance of Pan-Tompkins algorithm. Pan-Tompkins++ has been tested on four open source datasets. The experimental results show noticeable improvement for both R-peak detection and execution time. We achieve 2.8% and 1.8% reduction in FP and FN, respectively, and 2.2% increase in F-score on average across four datasets, with 33% reduction in execution time. We show specific examples to demonstrate that in situations where the Pan-Tompkins algorithm fails to identify R-peaks, the proposed algorithm is found to be effective. The results have also been contrasted with other well-known R-peak detection algorithms. Code available at: https://github.com/Niaz-Imtiaz/Pan-Tompkins-Plus-Plus

eess.SP↗

arXiv2022

A Survey on Physiological Signal Based Emotion Recognition

Physiological Signals are the most reliable form of signals for emotion recognition, as they cannot be controlled deliberately by the subject. Existing review papers on emotion recognition based on physiological signals surveyed only the regular steps involved in the workflow of emotion recognition such as preprocessing, feature extraction, and classification. While these are important steps, such steps are required for any signal processing application. Emotion recognition poses its own set of challenges that are very important to address for a robust system. Thus, to bridge the gap in the existing literature, in this paper, we review the effect of inter-subject data variance on emotion recognition, important data annotation techniques for emotion recognition and their comparison, data preprocessing techniques for each physiological signal, data splitting techniques for improving the generalization of emotion recognition models and different multimodal fusion techniques and their comparison. Finally we discuss key challenges and future directions in this field.

cs.HC↗

arXiv2021

Interactive segmentation using U-Net with weight map and dynamic user interactions

Interactive segmentation has recently attracted attention for specialized tasks where expert input is required to further enhance the segmentation performance. In this work, we propose a novel interactive segmentation framework, where user clicks are dynamically adapted in size based on the current segmentation mask. The clicked regions form a weight map and are fed to a deep neural network as a novel weighted loss function. To evaluate our loss function, an interactive U-Net (IU-Net) model which applies both foreground and background user clicks as the main method of interaction is employed. We train and validate on the BCV dataset, while testing on spleen and colon cancer CT images from the MSD dataset to improve the overall segmentation accuracy in comparison to the standard U-Net using our weighted loss function. Applying dynamic user click sizes increases the overall accuracy by 5.60% and 10.39% respectively by utilizing only a single user interaction.

cs.CV↗