arXiv subjects

Siamak Mohammadi

Publications and source records attributed to Siamak Mohammadi.

7 recordsLinked to original sources

arXiv2026

Securing Deep Learning Hardware: A Survey of Side-Channel Vulnerabilities and Countermeasures

As deep learning models are increasingly deployed in critical sectors such as healthcare, finance, and security, ensuring their protection against emerging threats has become crucial. Among these threats, side-channel attacks (SCAs) represent a particular challenge since they can extract sensitive information such as model architectures, parameters, and even user inputs without requiring direct access to the model. By leveraging the physical and micro-architectural properties of the hardware, attackers can compromise systems. This survey begins by classifying leakage sources and attacker objectives, then analyzes representative studies that demonstrate practical side-channel exploits against deep-learning hardware. It also reviews existing defenses aimed at mitigating these vulnerabilities and concludes by outlining key open research challenges and potential future directions.

cs.CR↗

arXiv2026

Energy-Efficient Real-Time 4-Stage Sleep Classification at 10-Second Resolution

Sleep stage classification is critical for diagnosing and managing disorders like sleep apnea and insomnia. However, conventional methods like polysomnography are costly and impractical for long-term, home-based monitoring. This study presents an energy-efficient approach for detecting four sleep stages (wake, rapid eye movement (REM), light sleep, deep sleep) using a single-lead electrocardiogram (ECG) signal. We evaluate various machine learning and deep learning models, introducing two windowing strategies: (1) a 5-minute window with 30-second steps for machine learning and (2) a 30-second window with 10-second steps for deep learning, enabling 10-second temporal resolution for real-time predictions. While deep learning models like MobileNet-v1 achieve high accuracy (92%) and F1-score (91%), their energy demands make them unsuitable for wearables. To address this, we design SleepLiteCNN, optimized for ECG-based sleep staging, achieving 89\% accuracy and 89% F1-score while minimizing energy use. Applying 8-bit quantization further reduces energy consumption to 5.48 microJ per inference, with 90% accuracy and F1-score. Additionally, field-programmable gate array (FPGA) deployment shows significant reductions in resource usage. This approach provides a practical, energy-efficient solution for continuous ECG-based sleep monitoring in resource-constrained wearable devices.

eess.SP↗

arXiv2026

Domain-Adaptive Arrhythmia Classification Using a Hybrid Transformer on Wearable Heart Signals

Cardiovascular disease remains the leading cause of death globally, underscoring the need for effective, accessible monitoring solutions, particularly through wearable devices that enable continuous, real-time tracking of heart rhythms in home settings. However, deploying deep learning models trained on clinical electrocardiogram (ECG) datasets to wearable devices remains challenging, as differences in recording equipment, signal quality, and patient populations introduce domain shifts that degrade model performance. We propose a hybrid transformer model that processes continuous ECG signals alongside seven heart rate variability (HRV) features, where the raw signal path captures beat-level morphological patterns and the HRV path encodes rhythm regularity statistics, allowing the model to jointly leverage complementary information from both representations. To enhance the model's ability to generalize across domains, we employ representation learning techniques, including Maximum Mean Discrepancy (MMD), a non-parametric kernel-based metric that quantifies the distance between feature distributions of different domains, to align feature distributions between source and target domains, addressing the challenge of domain shifts between public datasets and wearable device data. By leveraging five public ECG datasets for training, the model learns robust, generalized representations that mitigate domain-specific biases. When tested on wearable device data with an unseen domain, the model achieved an F1-macro 95% and balanced accuracy of 96.15%. These results demonstrate minimal performance degradation, with only a 2% drop in F1-macro compared to seen-domain evaluation, highlighting the model's generalization capabilities and its potential for reliable, real-time heart monitoring applications in home and ambulatory settings.

eess.SP↗

arXiv2025

SleepLiteCNN: Energy-Efficient Sleep Apnea Subtype Classification with 1-Second Resolution Using Single-Lead ECG

Apnea is a common sleep disorder characterized by breathing interruptions lasting at least ten seconds and occurring more than five times per hour. Accurate, high-temporal-resolution detection of sleep apnea subtypes - Obstructive, Central, and Mixed - is crucial for effective treatment and management. This paper presents an energy-efficient method for classifying these subtypes using a single-lead electrocardiogram (ECG) with high temporal resolution to address the real-time needs of wearable devices. We evaluate a wide range of classical machine learning algorithms and deep learning architectures on 1-second ECG windows, comparing their accuracy, complexity, and energy consumption. Based on this analysis, we introduce SleepLiteCNN, a compact and energy-efficient convolutional neural network specifically designed for wearable platforms. SleepLiteCNN achieves over 95% accuracy and a 92% macro-F1 score, while requiring just 1.8 microjoules per inference after 8-bit quantization. Field Programmable Gate Array (FPGA) synthesis further demonstrates significant reductions in hardware resource usage, confirming its suitability for continuous, real-time monitoring in energy-constrained environments. These results establish SleepLiteCNN as a practical and effective solution for wearable device sleep apnea subtype detection.

eess.SP↗

arXiv2025

Using Test-Time Data Augmentation for Cross-Domain Atrial Fibrillation Detection from ECG Signals

Atrial fibrillation (AF) detection from electrocardiogram (ECG) signals is crucial for early diagnosis and management of cardiovascular diseases. However, deploying robust AF detection models across different datasets with significant domain variations remains a challenge. In this paper, we use test-time data augmentation (TTA) to address the cross-domain problem and enhance AF detection performance. We use a publicly available dataset for training - Physionet Computing in Cardiology Challenge 2017 -, while collecting a distinct test set, creating a cross-domain scenario. We employ a neural network architecture that integrates transformer-based encoding of ECG signals and convolutional layers for spectrogram feature extraction. The model combines the latent representations obtained from both encoders to classify the input signals. By incorporating TTA during inference, we enhance the model's performance, achieving an F1 score of 76.6\% on our test set. Furthermore, our experiments demonstrate that the model becomes more resilient to perturbations in the input signal, enhancing its robustness. We show that TTA can be effective in addressing the cross-domain problem, where training and test data originate from disparate sources. This work contributes to advancing the field of AF detection in real-world scenarios.

eess.SP↗

arXiv2024

MetaWearS: A Shortcut in Wearable Systems Lifecycle with Only a Few Shots

Wearable systems provide continuous health monitoring and can lead to early detection of potential health issues. However, the lifecycle of wearable systems faces several challenges. First, effective model training for new wearable devices requires substantial labeled data from various subjects collected directly by the wearable. Second, subsequent model updates require further extensive labeled data for retraining. Finally, frequent model updating on the wearable device can decrease the battery life in long-term data monitoring. Addressing these challenges, in this paper, we propose MetaWearS, a meta-learning method to reduce the amount of initial data collection required. Moreover, our approach incorporates a prototypical updating mechanism, simplifying the update process by modifying the class prototype rather than retraining the entire model. We explore the performance of MetaWearS in two case studies, namely, the detection of epileptic seizures and the detection of atrial fibrillation. We show that by fine-tuning with just a few samples, we achieve 70% and 82% AUC for the detection of epileptic seizures and the detection of atrial fibrillation, respectively. Compared to a conventional approach, our proposed method performs better with up to 45% AUC. Furthermore, updating the model with only 16 minutes of additional labeled data increases the AUC by up to 5.3%. Finally, MetaWearS reduces the energy consumption for model updates by 456x and 418x for epileptic seizure and AF detection, respectively.

cs.LG↗

arXiv2016

Application-aware Retiming of Accelerators: A High-level Data-driven Approach

Flexibility at hardware level is the main driving force behind adaptive systems whose aim is to realise microarhitecture deconfiguration 'online'. This feature allows the software/hardware stack to tolerate drastic changes of the workload in data centres. With emerge of FPGA reconfigurablity this technology is becoming a mainstream computing paradigm. Adaptivity is usually accompanied by the high-level tools to facilitate multi-dimensional space exploration. An essential aspect in this space is memory orchestration where on-chip and off-chip memory distribution significantly influences the architecture in coping with the critical spatial and timing constraints, e.g. Place and Route. This paper proposes a memory smart technique for a particular class of adaptive systems: Elastic Circuits which enjoy slack elasticity at fine level of granularity. We explore retiming of a set of popular benchmarks via investigating the memory distribution within and among accelerators. The area, performance and power patterns are adopted by our high-level synthesis framework, with respect to the behaviour of the input descriptions, to improve the quality of the synthesised elastic circuits.

cs.AR↗