arXiv subjects

Mohamad Sawan

Publications and source records attributed to Mohamad Sawan.

At least 37 records · Page 2Linked to original sources

arXiv2025

SynDCIM: A Performance-Aware Digital Computing-in-Memory Compiler with Multi-Spec-Oriented Subcircuit Synthesis

Digital Computing-in-Memory (DCIM) is an innovative technology that integrates multiply-accumulation (MAC) logic directly into memory arrays to enhance the performance of modern AI computing. However, the need for customized memory cells and logic components currently necessitates significant manual effort in DCIM design. Existing tools for facilitating DCIM macro designs struggle to optimize subcircuit synthesis to meet user-defined performance criteria, thereby limiting the potential system-level acceleration that DCIM can offer. To address these challenges and enable agile design of DCIM macros with optimal architectures, we present SynDCIM, a performance-aware DCIM compiler that employs multi-spec-oriented subcircuit synthesis. SynDCIM features an automated performance-to-layout generation process that aligns with user-defined performance expectations. This is supported by a scalable subcircuit library and a multi-spec-oriented searching algorithm for effective subcircuit synthesis. The effectiveness of SynDCIM is demonstrated through extensive experiments and validated with a test chip fabricated in a 40nm CMOS process. Testing results reveal that designs generated by SynDCIM exhibit competitive performance when compared to state-of-the-art manually designed DCIM macros.

cs.AR↗

arXiv2024

VSViG: Real-time Video-based Seizure Detection via Skeleton-based Spatiotemporal ViG

An accurate and efficient epileptic seizure onset detection can significantly benefit patients. Traditional diagnostic methods, primarily relying on electroencephalograms (EEGs), often result in cumbersome and non-portable solutions, making continuous patient monitoring challenging. The video-based seizure detection system is expected to free patients from the constraints of scalp or implanted EEG devices and enable remote monitoring in residential settings. Previous video-based methods neither enable all-day monitoring nor provide short detection latency due to insufficient resources and ineffective patient action recognition techniques. Additionally, skeleton-based action recognition approaches remain limitations in identifying subtle seizure-related actions. To address these challenges, we propose a novel Video-based Seizure detection model via a skeleton-based spatiotemporal Vision Graph neural network (VSViG) for its efficient, accurate and timely purpose in real-time scenarios. Our experimental results indicate VSViG outperforms previous state-of-the-art action recognition models on our collected patients' video data with higher accuracy (5.9% error), lower FLOPs (0.4G), and smaller model size (1.4M). Furthermore, by integrating a decision-making rule that combines output probabilities and an accumulative function, we achieve a 5.1 s detection latency after EEG onset, a 13.1 s detection advance before clinical onset, and a zero false detection rate. The project homepage is available at: https://github.com/xuyankun/VSViG/

cs.CV↗

arXiv2024

Neuro-BERT: Rethinking Masked Autoencoding for Self-supervised Neurological Pretraining

Deep learning associated with neurological signals is poised to drive major advancements in diverse fields such as medical diagnostics, neurorehabilitation, and brain-computer interfaces. The challenge in harnessing the full potential of these signals lies in the dependency on extensive, high-quality annotated data, which is often scarce and expensive to acquire, requiring specialized infrastructure and domain expertise. To address the appetite for data in deep learning, we present Neuro-BERT, a self-supervised pre-training framework of neurological signals based on masked autoencoding in the Fourier domain. The intuition behind our approach is simple: frequency and phase distribution of neurological signals can reveal intricate neurological activities. We propose a novel pre-training task dubbed Fourier Inversion Prediction (FIP), which randomly masks out a portion of the input signal and then predicts the missing information using the Fourier inversion theorem. Pre-trained models can be potentially used for various downstream tasks such as sleep stage classification and gesture recognition. Unlike contrastive-based methods, which strongly rely on carefully hand-crafted augmentations and siamese structure, our approach works reasonably well with a simple transformer encoder with no augmentation requirements. By evaluating our method on several benchmark datasets, we show that Neuro-BERT improves downstream neurological-related tasks by a large margin.

eess.SP↗

arXiv2024

CMISR: Circular Medical Image Super-Resolution

Classical methods of medical image super-resolution (MISR) utilize open-loop architecture with implicit under-resolution (UR) unit and explicit super-resolution (SR) unit. The UR unit can always be given, assumed, or estimated, while the SR unit is elaborately designed according to various SR algorithms. The closed-loop feedback mechanism is widely employed in current MISR approaches and can efficiently improve their performance. The feedback mechanism may be divided into two categories: local feedback and global feedback. Therefore, this paper proposes a global feedback-based closed-cycle framework, circular MISR (CMISR), with unambiguous UR and advanced SR elements. Mathematical model and closed-loop equation of CMISR are built. Mathematical proof with Taylor-series approximation indicates that CMISR has zero recovery error in steady-state. In addition, CMISR holds plug-and-play characteristic that fuses model-based and learning-based approaches and can be established on any existing MISR algorithms. Five CMISR algorithms are respectively proposed based on the state-of-the-art open-loop MISR algorithms. Experimental results with three scale factors and on three open medical image datasets show that CMISR is superior to MISR in reconstruction performance and is particularly suited to medical images with strong edges or intense contrast.

eess.IV↗

arXiv2023

A 137.5 TOPS/W SRAM Compute-in-Memory Macro with 9-b Memory Cell-Embedded ADCs and Signal Margin Enhancement Techniques for AI Edge Applications

In this paper, we propose a high-precision SRAM-based CIM macro that can perform 4x4-bit MAC operations and yield 9-bit signed output. The inherent discharge branches of SRAM cells are utilized to apply time-modulated MAC and 9-bit ADC readout operations on two bit-line capacitors. The same principle is used for both MAC and A-to-D conversion ensuring high linearity and thus supporting large number of analog MAC accumulations. The memory cell-embedded ADC eliminates the use of separate ADCs and enhances energy and area efficiency. Additionally, two signal margin enhancement techniques, namely the MAC-folding and boosted-clipping schemes, are proposed to further improve the CIM computation accuracy.

cs.AR↗

arXiv2023

Shorter Latency of Real-time Epileptic Seizure Detection via Probabilistic Prediction

Although recent studies have proposed seizure detection algorithms with good sensitivity performance, there is a remained challenge that they were hard to achieve significantly short detection latency in real-time scenarios. In this manuscript, we propose a novel deep learning framework intended for shortening epileptic seizure detection latency via probabilistic prediction. We are the first to convert the seizure detection task from traditional binary classification to probabilistic prediction by introducing a crossing period from seizure-oriented EEG recording and proposing a labeling rule using soft-label for crossing period samples. And, a novel multiscale STFT-based feature extraction method combined with 3D-CNN architecture is proposed to accurately capture predictive probabilities of samples. Furthermore, we also propose rectified weighting strategy to enhance predictive probabilities, and accumulative decision-making rule to achieve significantly shorter detection latency. We implement the proposed framework on two prevalent datasets -- CHB-MIT scalp EEG dataset and SWEC-ETHZ intracranial EEG dataset in patient-specific leave-one-seizure-out cross-validation scheme. Eventually, the proposed algorithm successfully detected 94 out of 99 seizures during crossing period and 100% seizures detected after EEG onset, averaged 14.84% rectified predictive ictal probability (RPIP) errors of crossing samples, 2.3 s detection latency, 0.08/h false detection rate (FDR) on CHB-MIT dataset. Meanwhile, 84 out of 89 detected seizures during crossing period, 100% detected seizures after EEG onset, 16.17% RPIP errors, 4.7 s detection latency, and 0.08/h FDR are achieved on SWEC-ETHZ dataset. The obtained detection latencies are at least 50% shorter than state-of-the-art results reported in previous studies.

eess.SP↗

arXiv2023

CSwin2SR: Circular Swin2SR for Compressed Image Super-Resolution

Closed-loop negative feedback mechanism is extensively utilized in automatic control systems and brings about extraordinary dynamic and static performance. In order to further improve the reconstruction capability of current methods of compressed image super-resolution, a circular Swin2SR (CSwin2SR) approach is proposed. The CSwin2SR contains a serial Swin2SR for initial super-resolution reestablishment and circular Swin2SR for enhanced super-resolution reestablishment. Simulated experimental results show that the proposed CSwin2SR dramatically outperforms the classical Swin2SR in the capacity of super-resolution recovery. On DIV2K test and valid datasets, the average increment of PSNR is greater than 0.18 dB and the related average increment of SSIM is greater than 0.01.

eess.IV↗

arXiv2022

A 97 fJ/Conversion Neuron-ADC with Reconfigurable Sampling and Static Power Reduction

A bio-inspired Neuron-ADC with reconfigurable sampling and static power reduction for biomedical applications is proposed in this work. The Neuron-ADC leverages level-crossing sampling and a bio-inspired refractory circuit to compressively converts bio-signal to digital spikes and information-of-interest. The proposed design can not only avoid dissipating ADC energy on unnecessary data but also achieve reconfigurable sampling, making it appropriate for either low power operation or high accuracy conversion when dealing with various kinds of bio-signals. Moreover, the proposed dynamic comparator can reduce static power up to 41.1% when tested with a 10 kHz sinusoidal input. Simulation results of 40 nm CMOS process show that the Neuron-ADC achieves a maximum ENOB of 6.9 bits with a corresponding FoM of 97 fJ/conversion under 0.6 V supply voltage.

eess.SP↗

arXiv2022

Transfer Learning on Electromyography (EMG) Tasks: Approaches and Beyond

Machine learning on electromyography (EMG) has recently achieved remarkable success on a variety of tasks, while such success relies heavily on the assumption that the training and future data must be of the same data distribution. However, this assumption may not hold in many real-world applications. Model calibration is required via data re-collection and label annotation, which is generally very expensive and time-consuming. To address this problem, transfer learning (TL), which aims to improve target learners' performance by transferring the knowledge from related source domains, is emerging as a new paradigm to reduce the amount of calibration effort. In this survey, we assess the eligibility of more than fifty published peer-reviewed representative transfer learning approaches for EMG applications. Unlike previous surveys on purely transfer learning or EMG-based machine learning, this survey aims to provide an insight into the biological foundations of existing transfer learning methods on EMG-related analysis. In specific, we first introduce the physiological structure of the muscles and the EMG generating mechanism, and the recording of EMG to provide biological insights behind existing transfer learning approaches. Further, we categorize existing research endeavors into data based, model based, training scheme based, and adversarial based. This survey systematically summarizes and categorizes existing transfer learning approaches for EMG related machine learning applications. In addition, we discuss possible drawbacks of existing works and point out the future direction of better EMG transfer learning algorithms to enhance practicality for real-world applications.

eess.SP↗

arXiv2022

A Compact Online-Learning Spiking Neuromorphic Biosignal Processor

Real-time biosignal processing on wearable devices has attracted worldwide attention for its potential in healthcare applications. However, the requirement of low-area, low-power and high adaptability to different patients challenge conventional algorithms and hardware platforms. In this design, a compact online learning neuromorphic hardware architecture with ultra-low power consumption designed explicitly for biosignal processing is proposed. A trace-based Spiking-Timing-Dependent-Plasticity (STDP) lgorithm is applied to realize hardware-friendly online learning of a single-layer excitatory-inhibitory spiking neural network. Several techniques, including event-driven architecture and a fully optimized iterative computation approach, are adopted to minimize the hardware utilization and power consumption for the hardware implementation of online learning. Experiment results show that the proposed design reaches the accuracy of 87.36% and 83% for the Mixed National Institute of Standards and Technology database (MNIST) and ECG classification. The hardware architecture is implemented on a Zynq-7020 FPGA. Implementation results show that the Look-Up Table (LUT) and Flip Flops (FF) utilization reduced by 14.87 and 7.34 times, respectively, and the power consumption reduced by 21.69% compared to state of the art.

eess.SP↗

arXiv2022

SpikeSEE: An Energy-Efficient Dynamic Scenes Processing Framework for Retinal Prostheses

Intelligent and low-power retinal prostheses are highly demanded in this era, where wearable and implantable devices are used for numerous healthcare applications. In this paper, we propose an energy-efficient dynamic scenes processing framework (SpikeSEE) that combines a spike representation encoding technique and a bio-inspired spiking recurrent neural network (SRNN) model to achieve intelligent processing and extreme low-power computation for retinal prostheses. The spike representation encoding technique could interpret dynamic scenes with sparse spike trains, decreasing the data volume. The SRNN model, inspired by the human retina special structure and spike processing method, is adopted to predict the response of ganglion cells to dynamic scenes. Experimental results show that the Pearson correlation coefficient of the proposed SRNN model achieves 0.93, which outperforms the state of the art processing framework for retinal prostheses. Thanks to the spike representation and SRNN processing, the model can extract visual features in a multiplication-free fashion. The framework achieves 12 times power reduction compared with the convolutional recurrent neural network (CRNN) processing-based framework. Our proposed SpikeSEE predicts the response of ganglion cells more accurately with lower energy consumption, which alleviates the precision and power issues of retinal prostheses and provides a potential solution for wearable or implantable prostheses.

cs.NE↗

arXiv2022

Cascade Decoders-Based Autoencoders for Image Reconstruction

Autoencoders are composed of coding and decoding units, hence they hold the inherent potential of high-performance data compression and signal compressed sensing. The main disadvantages of current autoencoders comprise the following several aspects: the research objective is not data reconstruction but feature representation; the performance evaluation of data recovery is neglected; it is hard to achieve lossless data reconstruction by pure autoencoders, even by pure deep learning. This paper aims for image reconstruction of autoencoders, employs cascade decoders-based autoencoders, perfects the performance of image reconstruction, approaches gradually lossless image recovery, and provides solid theory and application basis for autoencoders-based image compression and compressed sensing. The proposed serial decoders-based autoencoders include the architectures of multi-level decoders and the related optimization algorithms. The cascade decoders consist of general decoders, residual decoders, adversarial decoders and their combinations. It is evaluated by the experimental results that the proposed autoencoders outperform the classical autoencoders in the performance of image reconstruction.

cs.LG↗

arXiv2022

ICRICS: Iterative Compensation Recovery for Image Compressive Sensing

Closed-loop architecture is widely utilized in automatic control systems and attain distinguished performance. However, classical compressive sensing systems employ open-loop architecture with separated sampling and reconstruction units. Therefore, a method of iterative compensation recovery for image compressive sensing (ICRICS) is proposed by introducing closed-loop framework into traditional compresses sensing systems. The proposed method depends on any existing approaches and upgrades their reconstruction performance by adding negative feedback structure. Theory analysis on negative feedback of compressive sensing systems is performed. An approximate mathematical proof of the effectiveness of the proposed method is also provided. Simulation experiments on more than 3 image datasets show that the proposed method is superior to 10 competition approaches in reconstruction performance. The maximum increment of average peak signal-to-noise ratio is 4.36 dB and the maximum increment of average structural similarity is 0.034 on one dataset. The proposed method based on negative feedback mechanism can efficiently correct the recovery error in the existing systems of image compressive sensing.

cs.LG↗

arXiv2022

Bridging the Gap Between Patient-specific and Patient-independent Seizure Prediction via Knowledge Distillation

Objective. Deep neural networks (DNNs) have shown unprecedented success in various brain-machine interface applications such as epileptic seizure prediction. However, existing approaches typically train models in a patient-specific fashion due to the highly personalized characteristics of epileptic signals. Therefore, only a limited number of labeled recordings from each subject can be used for training. As a consequence, current DNN based methods demonstrate poor generalization ability to some extent due to the insufficiency of training data. On the other hand, patient-independent models attempt to utilize more patient data to train a universal model for all patients by pooling patient data together. Despite different techniques applied, results show that patient-independent models perform worse than patient-specific models due to high individual variation across patients. A substantial gap thus exists between patient-specific and patient-independent models. Approach. In this paper, we propose a novel training scheme based on knowledge distillation which makes use of a large amount of data from multiple subjects. It first distills informative features from signals of all available subjects with a pre-trained general model. A patient-specific model can then be obtained with the help of distilled knowledge and additional personalized data. Main results. Four state-of-the-art seizure prediction methods are trained on the Children's Hospital of Boston-MIT sEEG database with our proposed scheme. The resulting accuracy, sensitivity, and false prediction rate show that our proposed training scheme consistently improves the prediction performance of state-of-the-art methods by a large margin. Significance. The proposed training scheme significantly improves the performance of patient-specific seizure predictors and bridges the gap between patient-specific and patient-independent predictors.

cs.LG↗

arXiv2022

Binary Single-dimensional Convolutional Neural Network for Seizure Prediction

Nowadays, several deep learning methods are proposed to tackle the challenge of epileptic seizure prediction. However, these methods still cannot be implemented as part of implantable or efficient wearable devices due to their large hardware and corresponding high-power consumption. They usually require complex feature extraction process, large memory for storing high precision parameters and complex arithmetic computation, which greatly increases required hardware resources. Moreover, available yield poor prediction performance, because they adopt network architecture directly from image recognition applications fails to accurately consider the characteristics of EEG signals. We propose in this paper a hardware-friendly network called Binary Single-dimensional Convolutional Neural Network (BSDCNN) intended for epileptic seizure prediction. BSDCNN utilizes 1D convolutional kernels to improve prediction performance. All parameters are binarized to reduce the required computation and storage, except the first layer. Overall area under curve, sensitivity, and false prediction rate reaches 0.915, 89.26%, 0.117/h and 0.970, 94.69%, 0.095/h on American Epilepsy Society Seizure Prediction Challenge (AES) dataset and the CHB-MIT one respectively. The proposed architecture outperforms recent works while offering 7.2 and 25.5 times reductions on the size of parameter and computation, respectively.

eess.SP↗

arXiv2022

C$^2$SP-Net: Joint Compression and Classification Network for Epilepsy Seizure Prediction

Recent development in brain-machine interface technology has made seizure prediction possible. However, the communication of large volume of electrophysiological signals between sensors and processing apparatus and related computation become two major bottlenecks for seizure prediction systems due to the constrained bandwidth and limited computation resource, especially for wearable and implantable medical devices. Although compressive sensing (CS) can be adopted to compress the signals to reduce communication bandwidth requirement, it needs a complex reconstruction procedure before the signal can be used for seizure prediction. In this paper, we propose C$^2$SP-Net, to jointly solve compression, prediction, and reconstruction with a single neural network. A plug-and-play in-sensor compression matrix is constructed to reduce transmission bandwidth requirement. The compressed signal can be used for seizure prediction without additional reconstruction steps. Reconstruction of the original signal can also be carried out in high fidelity. Prediction accuracy, sensitivity, false prediction rate, and reconstruction quality of the proposed framework are evaluated under various compression ratios. The experimental results illustrate that our model outperforms the competitive state-of-the-art baselines by a large margin in prediction accuracy. In particular, our proposed method produces an average loss of 0.35 % in prediction accuracy with a compression ratio ranging from 1/2 to 1/16.

cs.LG↗

arXiv2022

Recent Trends and Future Prospects of Neural Recording Circuits and Systems: A Tutorial Brief

Recent years have seen fast advances in neural recording circuits and systems as they offer a promising way to investigate real-time brain monitoring and the closed-loop modulation of psychological disorders and neurodegenerative diseases. In this context, this tutorial brief presents a concise overview of concepts and design methodologies of neural recording, highlighting neural signal characteristics, system-level specifications and architectures, circuit-level implementation, and noise reduction techniques. Future trends and challenges of neural recording are finally discussed.

eess.SP↗

arXiv2022

An Event-Driven Compressive Neuromorphic System for Cardiac Arrhythmia Detection

Wearable electrocardiograph (ECG) recording and processing systems have been developed to detect cardiac arrhythmia to help prevent heart attacks. Conventional wearable systems, however, suffer from high energy consumption at both circuit and system levels. To overcome the design challenges, this paper proposes an event-driven compressive ECG recording and neuromorphic processing system for cardiac arrhythmia detection. The proposed system achieves low power consumption and high arrhythmia detection accuracy via system level co-design with spike-based information representation. Event-driven level-crossing ADC (LC-ADC) is exploited in the recording system, which utilizes the sparsity of ECG signal to enable compressive recording and save ADC energy during the silent signal period. Meanwhile, the proposed spiking convolutional neural network (SCNN) based neuromorphic arrhythmia detection method is inherently compatible with the spike-based output of LC-ADC, hence realizing accurate detection and low energy consumption at system level. Simulation results show that the proposed system with 5-bit LC-ADC achieves 88.6\% reduction of sampled data points compared with Nyquist sampling in the MIT-BIH dataset, and 93.59\% arrhythmia detection accuracy with SCNN, demonstrating the compression ability of LC-ADC and the effectiveness of system level co-design with SCNN.

eess.SP↗