ORCID Profile
0000-0002-2753-5553
Current Organisations
The University of Hong Kong
,
University of Sydney
Does something not look right? The information on this page has been harvested from data sources that may not be up to date. We continue to work with information providers to improve coverage and quality. To report an issue, use the Feedback Form.
In Research Link Australia (RLA), "Research Topics" refer to ANZSRC FOR and SEO codes. These topics are either sourced from ANZSRC FOR and SEO codes listed in researchers' related grants or generated by a large language model (LLM) based on their publications.
Microelectronics and Integrated Circuits | Electrical and Electronic Engineering | Medical Devices | Biomaterials | Biomedical Engineering | Wireless Communications | Biomedical engineering | Computational neuroscience (incl. mathematical neuroscience and theoretical neuroscience) | Microelectromechanical Systems (MEMS) | Neural networks | Microelectronics | Electronics sensors and digital hardware | Medical devices | Regenerative Medicine (incl. Stem Cells and Tissue Engineering)
Skeletal System and Disorders (incl. Arthritis) | National Security | Ceramics, Glass and Industrial Mineral Products not elsewhere classified | Expanding Knowledge in Technology | Medical Instruments | Integrated Circuits and Devices |
Publisher: IOP Publishing
Date: 25-02-2020
Publisher: Wiley
Date: 14-04-2015
Publisher: IEEE
Date: 2006
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2022
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2010
Publisher: SPIE
Date: 26-12-2008
DOI: 10.1117/12.813924
Publisher: Wiley
Date: 19-06-2012
Publisher: IEEE
Date: 03-2019
Publisher: IEEE
Date: 09-2017
Publisher: IEEE
Date: 06-2014
Publisher: Elsevier BV
Date: 09-2018
DOI: 10.1016/J.NEUNET.2018.04.018
Abstract: Seizure prediction has attracted growing attention as one of the most challenging predictive data analysis efforts to improve the life of patients with drug-resistant epilepsy and tonic seizures. Many outstanding studies have reported great results in providing sensible indirect (warning systems) or direct (interactive neural stimulation) control over refractory seizures, some of which achieved high performance. However, to achieve high sensitivity and a low false prediction rate, many of these studies relied on handcraft feature extraction and/or tailored feature extraction, which is performed for each patient independently. This approach, however, is not generalizable, and requires significant modifications for each new patient within a new dataset. In this article, we apply convolutional neural networks to different intracranial and scalp electroencephalogram (EEG) datasets and propose a generalized retrospective and patient-specific seizure prediction method. We use the short-time Fourier transform on 30-s EEG windows to extract information in both the frequency domain and the time domain. The algorithm automatically generates optimized features for each patient to best classify preictal and interictal segments. The method can be applied to any other patient from any dataset without the need for manual feature extraction. The proposed approach achieves sensitivity of 81.4%, 81.2%, and 75% and a false prediction rate of 0.06/h, 0.16/h, and 0.21/h on the Freiburg Hospital intracranial EEG dataset, the Boston Children's Hospital-MIT scalp EEG dataset, and the American Epilepsy Society Seizure Prediction Challenge dataset, respectively. Our prediction method is also statistically better than an unspecific random predictor for most of the patients in all three datasets.
Publisher: Elsevier BV
Date: 09-2009
Publisher: IEEE
Date: 07-2009
Publisher: IOP Publishing
Date: 22-05-2023
Abstract: Objective. This study presents a proof-of-concept optical telemetry module that leverages a single light-emitting diode (LED) to transmit data at a high bit rate while consuming low power and occupying a small area. Our experiments showed that we could achieve 108 Mbit s −1 and 54 Mbit s −1 back telemetry data rates for tissue thicknesses of 3 mm and 8 mm, respectively. Approach. The proposed module is designed to be powered by near-field coupling and achieve bidirectional communication by low-speed downlink from near-field communication. It aims to minimize the size of the implant while providing reliable transmission that meets the requirements of high-speed wireless communication from a multi-electrode array neurotechnology implant outside the body. Results. The power consumption of the module is 1.57 mW, including the power consumption of related circuits, resulting in an efficiency of 14.5 pJ bit −1 , at a tissue thickness of 3 mm and a data rate of 108 Mbit. The use of an optical lens, combined with tissue scattering effect and optimized emission angle, makes the module robust to misalignments of up to ±5 mm and ±15° between the implantable and external units. The LED in the implantable unit is only 0.98 × 0.98 × 0.6 mm 3 , and the testing module is composed of discrete components and laboratory instruments. Significance. This work aims to show how it is possible to strike a balance between a small, reliable, and high-bit-rate data uplink between a neural implant and its proximal, wirelessly connected external unit. This optical telemetry module has the potential to be integrated into a significantly miniaturized system through an application-specific integrated circuit and can support up to 1000 channels of neural recordings, each s led at 9 kSps with a 12-bit readout resolution.
Publisher: IEEE
Date: 2006
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 08-2011
Publisher: International Academy Publishing (IAP)
Date: 02-2008
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2012
Publisher: IEEE
Date: 07-2019
Publisher: Elsevier BV
Date: 07-2021
Publisher: Springer Science and Business Media LLC
Date: 04-08-2015
DOI: 10.1038/SREP12785
Abstract: Physical unclonable functions (PUFs) exploit the intrinsic complexity and irreproducibility of physical systems to generate secret information. The advantage is that PUFs have the potential to provide fundamentally higher security than traditional cryptographic methods by preventing the cloning of devices and the extraction of secret keys. Most PUF designs focus on exploiting process variations in Complementary Metal Oxide Semiconductor (CMOS) technology. In recent years, progress in nanoelectronic devices such as memristors has demonstrated the prevalence of process variations in scaling electronics down to the nano region. In this paper, we exploit the extremely large information density available in nanocrossbar architectures and the significant resistance variations of memristors to develop an on-chip memristive device based strong PUF (mrSPUF). Our novel architecture demonstrates desirable characteristics of PUFs, including uniqueness, reliability and large number of challenge-response pairs (CRPs) and desirable characteristics of strong PUFs. More significantly, in contrast to most existing PUFs, our PUF can act as a reconfigurable PUF (rPUF) without additional hardware and is of benefit to applications needing revocation or update of secure key information.
Publisher: IEEE
Date: 05-2007
Publisher: IEEE
Date: 06-0011
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2019
Publisher: Springer International Publishing
Date: 2014
Publisher: IEEE
Date: 11-2019
Publisher: IEEE
Date: 05-2009
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2012
Publisher: IEEE
Date: 10-2013
Publisher: IEEE
Date: 08-2011
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2018
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2019
Publisher: IEEE
Date: 12-2011
Publisher: Elsevier BV
Date: 06-2016
Publisher: IEEE
Date: 08-2012
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 05-2021
Publisher: MDPI AG
Date: 04-11-2020
DOI: 10.3390/S20216285
Abstract: There has been a growing interest in computational electroencephalogram (EEG) signal processing in a erse set of domains, such as cortical excitability analysis, event-related synchronization, or desynchronization analysis. In recent years, several inconsistencies were found across different EEG studies, which authors often attributed to methodological differences. However, the assessment of such discrepancies is deeply underexplored. It is currently unknown if methodological differences can fully explain emerging differences and the nature of these differences. This study aims to contrast widely used methodological approaches in EEG processing and compare their effects on the outcome variables. To this end, two publicly available datasets were collected, each having unique traits so as to validate the results in two different EEG territories. The first dataset included signals with event-related potentials (visual stimulation) from 45 subjects. The second dataset included resting state EEG signals from 16 subjects. Five EEG processing steps, involved in the computation of power and phase quantities of EEG frequency bands, were explored in this study: artifact removal choices (with and without artifact removal), EEG signal transformation choices (raw EEG channels, Hjorth transformed channels, and averaged channels across primary motor cortex), filtering algorithms (Butterworth filter and Blackman–Harris window), EEG time window choices (−750 ms to 0 ms and −250 ms to 0 ms), and power spectral density (PSD) estimation algorithms (Welch’s method, Fast Fourier Transform, and Burg’s method). Powers and phases estimated by carrying out variations of these five methods were analyzed statistically for all subjects. The results indicated that the choices in EEG transformation and time-window can strongly affect the PSD quantities in a variety of ways. Additionally, EEG transformation and filter choices can influence phase quantities significantly. These results raise the need for a consistent and standard EEG processing pipeline for computational EEG studies. Consistency of signal processing methods cannot only help produce comparable results and reproducible research, but also pave the way for federated machine learning methods, e.g., where model parameters rather than data are shared.
Publisher: Ovid Technologies (Wolters Kluwer Health)
Date: 02-2021
DOI: 10.1161/HYPERTENSIONAHA.120.16138
Abstract: This study aims to evaluate the causal association of blood pressure (BP) with cardiovascular diseases (CVDs). Two-s le Mendelian randomization was performed using a large genome-wide association study (n=299 024) and the UK Biobank cohort (n=375 256). We identified 327 and 364 single-nucleotide polymorphisms strongly and independently associated with systolic BP and diastolic BP, respectively, as genetic instruments to assess the causal association of BP with total CVD, CVD mortality, and 14 cardiovascular conditions. Nonlinearity was examined with nonlinear instrumental variable assumptions. Genetically predicted BP was significantly positively associated with total CVD (systolic BP, per 10 mm Hg: odds ratio [OR], 1.32 [95% CI, 1.25–1.40] diastolic BP, per 5 mm Hg: OR, 1.20 [95% CI, 1.15–1.26]). Similar positive causal associations were observed for 14 cardiovascular conditions including ischemic heart disease (systolic BP, per 10 mm Hg: OR, 1.33 [95% CI, 1.24–1.41] diastolic BP, per 5 mm Hg: OR, 1.20 [95% CI, 1.14–1.27]) and stroke (systolic BP, per 10 mm Hg: OR, 1.35 [95% CI, 1.24–1.48] diastolic BP, per 5 mm Hg: OR, 1.20 [95% CI, 1.12–1.28]). Nonlinearity Mendelian randomization test demonstrated linear causal association of BP with these outcomes. Consistent estimates were observed in sensitivity analyses, suggesting robustness of the associations and minimal horizontal pleiotropy. The linear positive causal association of BP and CVD was consistent with previous findings that lower BP is better, thus consolidating clinical knowledge on hypertension management in CVD risk reduction.
Publisher: MDPI AG
Date: 18-10-2022
DOI: 10.3390/APP122010487
Abstract: The implications of combining structural and functional connectivity to quantify the most active brain regions in seizure onset remain unclear. This study tested a new model that may facilitate the incorporation of diffusion MRI (dMRI) in clinical practice. We obtained structural connectomes from dMRI and functional connectomes from electroencephalography (EEG) to assess whether high structure-function coupling corresponded with the seizure onset region. We mapped in idual electrodes to their nearest cortical region to allow for a one-to-one comparison between the structural and functional connectomes. A seizure laterality score and expected onset zone were defined. The patients with well-lateralised seizures revealed high structure-function coupling consistent with the seizure onset zone. However, a lower seizure lateralisation score translated to reduced alignment between the high structure-function coupling regions and the seizure onset zone. We illustrate that dMRI, in combination with EEG, can improve the identification of the seizure onset zone. Our model may be valuable in enhancing ultra-long-term monitoring by indicating optimal, in idualised electrode placement.
Publisher: IOP Publishing
Date: 18-11-2016
DOI: 10.1088/0957-4484/27/50/505210
Abstract: Donor doping of perovskite oxides has emerged as an attractive technique to create high performance and low energy non-volatile analog memories. Here, we examine the origins of improved switching performance and stable multi-state resistive switching in Nb-doped oxygen-deficient amorphous SrTiO
Publisher: IEEE
Date: 2008
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2019
Publisher: Cold Spring Harbor Laboratory
Date: 10-02-2023
DOI: 10.1101/2023.02.09.23285681
Abstract: The application of deep learning models to evaluate connectome data is gaining interest in epilepsy research. Deep learning may be a useful initial tool to partition connectome data into network subsets for further analysis. Few prior works have used deep learning to examine structural connectomes from patients with focal epilepsy. We evaluated whether a deep learning model applied to whole-brain connectomes could classify 28 participants with focal epilepsy from 20 controls and identify nodal importance for each group. Participants with epilepsy were further grouped based on whether they had focal seizures that evolved into bilateral tonic-clonic seizures (17 with, 11 without). The trained neural network classified patients from controls with an accuracy of 72.92%, while the seizure subtype groups achieved a classification accuracy of 67.86%. In the patient subgroups, the nodes and edges deemed important for accurate classification were also clinically relevant, indicating the model’s interpretability. The current work expands the evidence for the potential of deep learning to extract relevant markers from clinical datasets. Our findings offer a rationale for further research interrogating structural connectomes to obtain features that can be biomarkers and aid the diagnosis of seizure subtypes.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 2016
Publisher: Cold Spring Harbor Laboratory
Date: 07-2023
DOI: 10.1101/2023.06.30.23292069
Abstract: An algorithm for processing raw 12-lead ECG data has been developed and validated in this study that is based on the S4D model. Among the notable features of this algorithm is its strong resilience to noise, enabling the algorithm to achieve an average F1-score of 81.2% and an AUROC of 95.5%. It is characterized by the elimination of pre-processing features as well as the availability of a low-complexity architecture that makes it suitable for implementation on numerous computing devices because it is easily implementable. Consequently, this algorithm exhibits considerable potential for practical applications in analyzing real-world ECG data.
Publisher: Elsevier BV
Date: 11-2017
Publisher: IEEE
Date: 05-2013
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2021
Publisher: Science Publications
Date: 02-2008
Publisher: Institution of Engineering and Technology (IET)
Date: 11-2020
Publisher: Science Alert
Date: 11-2007
Publisher: Elsevier BV
Date: 10-2019
DOI: 10.1016/J.TIPS.2019.08.001
Abstract: Epilepsy is a neurological disorder that affects ∼1% of the world population. Nearly 30% of epilepsy patients suffer from pharmacoresistant epilepsy that cannot be treated with antiepileptic drugs. Depending on seizure type, a erse range of therapies are available, including surgery, vagus nerve stimulation, and deep brain stimulation. We review the sensing and stimulation technologies most used in neurological disorders, and provide a vision of minimally invasive electroceuticals to enable accurate forecasting of epileptic seizures and therapy. The use of such systems could potentially help patients to prevent injuries and, in combination with an intervention mechanism, could provide a method of suppressing seizures in epileptic patients.
Publisher: IEEE
Date: 05-2012
Publisher: Cold Spring Harbor Laboratory
Date: 04-07-2021
DOI: 10.1101/2021.07.02.450974
Abstract: Epilepsy is one of the most common severe neurological disorders worldwide. The International League Against Epilepsy (ILAE) define epilepsy as a brain disorder that generates (1) two unprovoked seizures more than 24 hrs apart, or (2) one unprovoked seizure with at least 60% risk of recurrence over the next ten years. Complete remission has been defined as ten years seizure free with the last five years medication free. This requires a cost-effective ambulatory ultra-long term out-patient monitoring solution. The common practice of self-reporting is inaccurate. Applying artificial intelligence (AI) to scalp electroencephalogram (EEG) interpretation is becoming increasingly common, but other data modalities such as electrocardiograms (ECGs) are simpler to collect and often recorded simultaneously with EEG. Both recordings contain biomarkers in the detection of seizures. Here, we propose a state-of-the-art performing AI system that combines EEG and ECG for seizure detection, tested on clinical data with early evidence demonstrating generalization across hospitals. The model was trained and validated on the publicly available Temple University Hospital (TUH) dataset. To evaluate performance in a clinical setting, we conducted nonpatient-specific inference-only tests on three out-of-distribution datasets, including EPILEPSIAE (30 patients) and the Royal Prince Alfred Hospital (RPAH) in Sydney, Australia (31 patients shortlisted by neurologists and 30 randomly selected). Across all datasets, our multimodal approach improves the area under the receiver operating characteristic curve (AUC-ROC) by an average margin of 6.71% and 14.42% for prior state-of-the-art approaches using EEG and ECG alone, respectively. Our model’s state-of-the-art performance and robustness to out-ofdistribution datasets can improve the accuracy and efficiency of epilepsy diagnoses.
Publisher: MDPI AG
Date: 05-02-2018
DOI: 10.3390/BIOS8010014
Publisher: American Association for the Advancement of Science (AAAS)
Date: 20-10-2017
Abstract: Two-dimensional (2D) materials have a wide variety of potential applications in the electronics industry. However, certain compositions of 2D materials are difficult to obtain owing to the challenges in exfoliating thin sheets from bulk crystals. Zavabeti et al. exploited liquid metals to synthesize 2D Ga 2 O 3 , HfO 2 , Gd 2 O 3 , and Al 2 O 3 . The 2D sheets appear as a surface layer in gallium-based liquid metals after the Hf, Gd, or Al is dissolved into the bulk alloy. The 2D oxide that appears on the surface is the oxide with the lowest energy, suggesting that it should be possible to make other 2D oxides by using the same process. Science , this issue p. 332
Publisher: Springer Science and Business Media LLC
Date: 18-01-2021
Publisher: The Royal Society
Date: 08-2022
DOI: 10.1098/RSOS.220374
Abstract: This paper proposes an artificial intelligence system that continuously improves over time at event prediction using initially unlabelled data by using self-supervised learning. Time-series data are inherently autocorrelated. By using a detection model to generate weak labels on the fly, which are concurrently used as targets to train a prediction model on a time-shifted input data stream, this autocorrelation can effectively be harnessed to reduce the burden of manual labelling. This is critical in medical patient monitoring, as it enables the development of personalized forecasting models without demanding the annotation of long sequences of physiological signal recordings. We perform a feasibility study on seizure prediction, which is identified as an ideal test case, as pre-ictal brainwaves are patient-specific, and tailoring models to in idual patients is known to improve forecasting performance significantly. Our self-supervised approach is used to train in idualized forecasting models for 10 patients, showing an average relative improvement in sensitivity by 14.30% and a reduction in false alarms by 19.61% in early seizure forecasting. This proof-of-concept on the feasibility of using a continuous stream of time-series neurophysiological data paves the way towards a low-power neuromorphic neuromodulation system.
Publisher: Cold Spring Harbor Laboratory
Date: 06-07-2023
DOI: 10.1101/2023.06.28.23291916
Abstract: Recent advances in Large Language Models (LLMs) have shown great potential in various domains, particularly in processing text-based data. However, their applicability to biomedical time-series signals (e.g. electrograms) remains largely unexplored due to the lack of a signal-to-text (sequence) engine to harness the power of LLMs. The application of biosignals has been growing due to the improvements in the reliability, noise and performance of front-end sensing, and back-end signal processing, despite lowering the number of sensing components (e.g. electrodes) needed for effective and long-term use (e.g. in wearable or implantable devices). One of the most reliable techniques used in clinical settings is producing a technical/clinical report on the quality and features of collected data and using that alongside a set of auxiliary or complementary data (e.g. imaging, blood tests, medical records). This work addresses the missing puzzle in implementing conversational artificial intelligence (AI), a reliable, technical and clinically relevant signal-to-text (Sig2Txt) engine. While medical foundation models can be expected, reports of Sig2Txt engine in large scale can be utilised in years to come to develop foundational models for a unified purpose. In this work, we propose a system (SignalGPT or BioSignal Copilot) that reduces medical signals to a freestyle or formatted clinical, technical report close to a brief clinical report capturing key features and characterisation of input signal. In its ideal form, this system provides the tool necessary to produce the technical input sequence necessary for LLMs as a step toward using AI in the medical and clinical domains as an assistant to clinicians and patients. To the best of our knowledge, this is the first system for bioSig2Txt generation, and the idea can be used in other domains as well to produce technical reports to harness the power of LLMs. This method also improves the interpretability and tracking (history) of information into and out of the AI models. We did implement this aspect through a buffer in our system. As a preliminary step, we verify the feasibility of the BioSignal Copilot (SignalGPT) using a clinical ECG dataset to demonstrate the advantages of the proposed system. In this feasibility study, we used prompts and fine-tuning to prevent fluctuations in response. The combination of biosignal processing and natural language processing offers a promising solution that improves the interpretability of the results obtained from AI, which also leverages the rapid growth of LLMs.
Publisher: Royal Society of Chemistry (RSC)
Date: 2022
DOI: 10.1039/D2SD00033D
Abstract: We provide a perspective on monitoring the blood bilirubin concentration using simple methods, which are economical and can be adopted in point of care settings. These are a homecare test system, a miniature implant, and a neonatal wearable patch.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 03-2014
Publisher: Royal Society of Chemistry (RSC)
Date: 2013
DOI: 10.1039/C3NR00535F
Abstract: We report on the implementation of an Associative Capacitive Network (ACN) based on the nondestructive capacitive readout of two Complementary Resistive Switches (2-CRSs). ACNs are capable of performing a fully parallel search for Hamming distances (i.e. similarity) between input and stored templates. Unlike conventional associative memories where charge retention is a key function and hence, they require frequent refresh cycles, in ACNs, information is retained in a nonvolatile resistive state and normal tasks are carried out through capacitive coupling between input and output nodes. Each device consists of two CRS cells and no selective element is needed, therefore, CMOS circuitry is only required in the periphery, for addressing and read-out. Highly parallel processing, nonvolatility, wide interconnectivity and low-energy consumption are significant advantages of ACNs over conventional and emerging associative memories. These characteristics make ACNs one of the promising candidates for applications in memory-intensive and cognitive computing, switches and routers as binary and ternary Content Addressable Memories (CAMs) and intelligent data processing.
Publisher: Springer Science and Business Media LLC
Date: 22-03-2017
DOI: 10.1038/NCOMMS15116
Abstract: Nature Communications 8: Article number: 14482 published: 17 February 2017 Updated: 22 March 2017 The original version of this Article contained a typographical error in the spelling of the author Omid Kavehei, which was incorrectly given as Omid Kevehei. This has now been corrected in both the PDF and HTML versions of the Article.
Publisher: Cold Spring Harbor Laboratory
Date: 08-03-2021
DOI: 10.1101/2021.03.07.433990
Abstract: Electroencephalogram (EEG) monitoring and objective seizure identification is an essential clinical investigation for some patients with epilepsy. Accurate annotation is done through a time-consuming process by EEG specialists. Computer-assisted systems for seizure detection currently lack extensive clinical utility due to retrospective, patient-specific, and/or irreproducible studies that result in low sensitivity or high false positives in clinical tests. We aim to significantly reduce the time and resources on data annotation by demonstrating a continental generalization of seizure detection that balances sensitivity and specificity. This is a prospective inference test of artificial intelligence on nearly 14,590 hours of adult EEG data from patients with epilepsy between 2011 and 2019 in a hospital in Sydney, Australia. The inference set includes patients with different types and frequencies of seizures across a wide range of ages and EEG recording hours. The artificial intelligence (AI) is a convolutional long short-term memory network that is trained on a USA-based dataset. The Australian set is about 16 times larger than the US training dataset with very long interictal periods (between seizures), which is way more realistic than the training set and makes our false positives highly reliable. We validated our inference model in an AI-assisted mode with a human expert arbiter and a result review panel of expert neurologists and EEG specialists on 66 sessions to demonstrate achievement of the same performance with over an order-of-magnitude reduction in time. Our inference on 1,006 EEG recording sessions on the Australian dataset achieved 76.68% with nearly 56 [0, 115] false alarms per 24 hours on average, against legacy ground-truth annotations by human experts, conducted independently over nine years. Our pilot test of 66 sessions with a human arbiter, and reviewed ground truth by a panel of experts, confirmed an identical human performance of 92.19% with an AI-assisted system, while the time requirements reduce significantly from 90 to 7.62 minutes on average. Accurate and objective seizure counting is an important factor in epilepsy. An AI-assisted system can help improve efficiency and accuracy alongside human experts, particularly in low and middle-income countries with limited expert human resources. SOAR Fellowship from The University of Sydney, a Microsoft AI for Accessibility grant, and a Research Training Program (RTP) support provided by the Australian Government. During the development of our artificial intelligence (AI) system, we did a systematic review of the scientific literature with search via PubMed for research articles published on seizure detection with the following inclusion criteria: (1) Tests or inference evaluation is conducted on large-scale clinical EEG data (2) Generalization is attempted or potentials for generalization is considered, e.g., in commercialized tools (3) Seizure detection delay and real-time (aka. online) operation were not considered critical in this context as long as the test was conducted on raw EEG data. Note that ICU seizure detection or portable seizure alert systems are relying on detection delay and real-time needs. Our keywords include “prospective seizure detection”, “automated seizure detection”, “non-patient specific seizure detection”, “seizure detection on continuous EEG”, and “deep learning-based seizure detection” and “machine learning-based seizure detection”. We found that the only two categories of works meet our criteria: two research papers published in 2020 and works published by commercial tools developers. We cited a recent review of 89 deep learning-based seizure detection, all of which are retrospective. One work from Stanford reported seizure detection on all ages (pediatric to adult ages) using post-acquisition EEG recordings and provided an avenue for independent evaluation by providing a test on a publicly available Temple University Hospital (TUH) EEG dataset. The other work pivoted on algorithmic-assisted real-time seizure risk monitoring in continuous EEG in neonatal intensive care unit (NICU) with 128 neonates (32 with seizures) showing about 20% improvement in seizure identification over 130 neonates (38 with seizures) with no algorithmic assistance. Commercial tools we studied are Encevis (EpiScan), Besa, and Persyst. There is a recent comparative study on these tools on 81 patients. Encevis is reported as the best performing tool, and hence we provided a comparative study with Encevis ver. 1.9.2. Encevis is also the only tool that provided an avenue for comparative study on publicly available EEG data. The Stanford work, published in 2020, confirms many false positives with Persyst 13. We excluded our tests on Persyst 14 as it highly under-performed relative to Encevis. Only Stanford’s work provides code availability. We compared our results with Stanford’s work outcome and provided pilot test results with the Encevis (EpiScan) tool on the Australian dataset, which shows a considerably lower sensitivity. To the best of our knowledge, the current study is the first continental generalization that demonstrates the potential to achieve an expert human-level seizure recognition rate in a clinical setting and in just a fraction of time. The two datasets used in this study are recorded with different infrastructure, which adds to the independence of inference from hardware types and improves clinical utility. This is particularly important as 80% of patients with epilepsy live in low and middle-income countries with limited resources, particularly EEG specialists and neurologists. Our results support the potential benefits of deep learning AI in clinical settings for seizure recognition and its contribution to significant sensitivity over available solutions. Our AI-assisted system achieves more than a ten-fold increase in time efficiency and reports identical performance to human experts for EEG interpretation with access to great neurophysiology support and auxiliary data. Our findings, particularly our tests on an available commercial tool, recommend that the evaluation, test, or inference in AI systems be performed on different datasets, with erse infrastructures, and on large-scale and realistic sets with long interictal periods.
Publisher: IOP Publishing
Date: 24-02-2023
Abstract: The vast majority of studies that process and analyze neural signals are conducted on cloud computing resources, which is often necessary for the demanding requirements of deep neural network workloads. However, applications such as epileptic seizure detection stand to benefit from edge devices that can securely analyze sensitive medical data in a real-time and personalised manner. In this work, we propose a novel neuromorphic computing approach to seizure detection using a surrogate gradient-based deep spiking neural network (SNN), which consists of a novel spiking ConvLSTM unit. We have trained, validated, and rigorously tested the proposed SNN model across three publicly accessible datasets, including Boston Children’s Hospital–MIT (CHB-MIT) dataset from the U.S., and the Freiburg (FB) and EPILEPSIAE intracranial electroencephalogram datasets from Germany. The average leave-one-out cross-validation area under the curve score for FB, CHB-MIT and EPILEPSIAE datasets can reach 92.7 % , 89.0 % , and 81.1 % , respectively, while the computational overhead and energy consumption are significantly reduced when compared to alternative state-of-the-art models, showing the potential for building an accurate hardware-friendly, low-power neuromorphic system. This is the first feasibility study using a deep SNN for seizure detection on several reliable public datasets.
Publisher: Elsevier BV
Date: 10-2009
Publisher: Cold Spring Harbor Laboratory
Date: 06-07-2023
DOI: 10.1101/2023.07.05.23292238
Abstract: Diagnosing cardiac arrhythmia through interpreting electrocardiogram (ECG) recordings is a challenging and time-consuming task, frequently resulting in inconsistent outcomes and misdiagnosis due to signal noise, interference, and comorbidities. To overcome these challenges, machine learning algorithms have been explored as potential solutions, with promising initial results. However, their lack of generalizability and explainability has hindered their widespread use in clinical settings. This study focuses on evaluating and reproducing a popular Deep Neuron Network (DNN) model proposed by Ribeiro et al [19]. The performance of the model in classifying ECG recordings was found to be influenced by the characteristics of the training dataset, which was composed of different ECG recordings. Although the model exhibited strong generalizability with an F1 score of 0.87 when tested on the CPSC dataset, its performance was inconsistent when applied to the Shaoxing and Ningbo Hospital ECG dataset. To enhance the model’s interpretability and performance, an attention layer was incorporated into the network, which improved its focus and resulted in an F 1 score of 0.87 from 0.83 trained on the same dataset.
Publisher: IEEE
Date: 06-2014
Publisher: Cold Spring Harbor Laboratory
Date: 24-01-2023
DOI: 10.1101/2023.01.24.525308
Abstract: Epilepsy is a common neurological disorder that sub-stantially deteriorates patients’ safety and quality of life. Electroencephalogram (EEG) has been the golden-standard technique for diagnosing this brain disorder and has played an essential role in epilepsy monitoring and disease management. It is extremely laborious and challenging, if not practical, for physicians and expert humans to annotate all recorded signals, particularly in long-term monitoring. The annotation process often involves identifying signal segments with suspected epileptic seizure features or other abnormalities and/or known healthy features. Therefore, automated epilepsy detection becomes a key clinical need because it can greatly improve clinical practice’s efficiency and free up human expert time to attend to other important tasks. Current automated seizure detection algorithms generally face two challenges: (1) models trained for specific patients, but such models are patient-specific, hence fail to generalize to other patients and real-world situations (2) seizure detection models trained on large EEG datasets have low sensitivity and/or high false positive rates, often with an area under the receiver operating characteristic (AUROC) that is not high enough for potential clinical applicability. This paper proposes Transformers for Seizure Detection, which we refer to as TSD in this manuscript. A Transformer is a deep learning architecture based on an encoder-decoder structure and on attention mechanisms, which we apply to recorded brain signals. The AUROC of our proposed model has achieved 92.1%, tested with Temple University’s publically available electroencephalogram (EEG) seizure corpus dataset (TUH). Additionally, we highlight the impact of input domains on the model’s performance. Specifically, TSD performs best in identifying epileptic seizures when the input domain is a time-frequency. Finally, our proposed model for seizure detection in inference-only mode with EEG recordings shows outstanding performance in classifying seizure types and superior model initialization.
Publisher: Springer International Publishing
Date: 2015
Publisher: IEEE
Date: 07-2018
Publisher: Elsevier BV
Date: 11-2022
Publisher: IEEE
Date: 10-2019
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2014
Publisher: Springer Science and Business Media LLC
Date: 09-03-2018
Publisher: Royal Society of Chemistry (RSC)
Date: 2023
DOI: 10.1039/D2CS00830K
Abstract: Neural recording, stimulation, and biochemical sensing using semiconducting electrodes in both electrical and optical domains are discussed. Their differences from metallic electrodes from the application and characterization perspective are highlighted.
Publisher: American Scientific Publishers
Date: 05-2013
Abstract: This paper introduces an integrated sensor circuit based on an analog Memristor-MOS (M2) pattern matching building block that calculates the similarity/dissimilarity between two analog values. A new approach for a pulse-width modulation pixel image sensor compatible with the memristive-MOS matching structure is introduced allowing direct comparison between incoming and stored images. The pulsed-width encoded information from the pixels is forwarded to a matching circuitry that provides an anti-Gaussian-like comparison between the states of memristors. The non-volatile and multi-state memory characteristics of memristor, together with the related ability to be programmed at any one of the intermediate states between logic '1' and logic '0' brings us closer to the implementation of bio-machines that can eventually emulate human-like sensory functions.
Publisher: Cold Spring Harbor Laboratory
Date: 07-07-2023
DOI: 10.1101/2023.07.06.548044
Abstract: Flow cytometry is a widespread and high-throughput technology that can measure the features of cells and can be combined with fluorescence analysis for additional phenotypical characterisations but only provide low-dimensional output and spatial resolution. Imaging flow cytometry is another technology that offers rich spatial information, allowing more profound insight into single-cell analysis. However, offering such high-resolution, full-frame feedback can compromise speed and has become a significant trade-off challenge to tackle during development. In addition, the current dynamic range offered by conventional photosensors can only capture limited fluorescence signals, exacerbating the difficulties in elevating performance speed. Neuromorphic photo-sensing architecture focuses on the events of interest via in idual-firing pixels to reduce data redundancy and provide low latency in data processing. With the inherent high dynamic range, this architecture has the potential to drastically elevate the performance in throughput by incorporating motion-activated spatial resolution. Herein, we presented an early demonstration of neuromorphic cytometry with the implementation of object counting and size estimation to measure 8 μ m and 15 μ m polystyrene-based microparticles and human monocytic cell line (THP-1). In this work, our platform has achieved highly consistent outputs with a widely adopted flow cytometer (CytoFLEX) in detecting the total number and size of the microparticles. Although the current platform cannot deliver multiparametric measurements on cells, future endeavours will include further functionalities and increase the measurement parameters (granularity, cell condition, fluorescence analysis) to enrich cell interpretation.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 07-2022
Publisher: IEEE
Date: 03-2016
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2015
Publisher: Wiley
Date: 05-12-2017
Publisher: American Scientific Publishers
Date: 05-2013
Abstract: This paper proposes a programmable inhibitory interconnection network between pixels in an array of novel low-voltage Schmitt-trigger-based PFM sensors that will be of interest for future applications in memristor-based early vision processing. In addition, a new low-power inverter-based pulse-frequency modulation (PFM) design and its integration with the network is also presented. To ensure no change in the memristors conductance in the network, the CMOS imager was designed for low voltage operation. That has resulted in a significant power reduction, better than 60%, and a comparable linear dynamic range when compared to published designs in the literature. The design was performed using a 0.13 um Samsung Electronics standard CMOS process, using 0.75 V supply voltage.
Publisher: Elsevier BV
Date: 07-2017
Publisher: Wiley
Date: 02-2017
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 12-2018
Publisher: Royal Society of Chemistry (RSC)
Date: 2022
DOI: 10.1039/D1SD00020A
Abstract: Minimally invasive subcutaneous electroencephalography provides an emerging opportunity to address the need for continuous and chronic monitoring, where conventional technologies fail.
Publisher: The Royal Society
Date: 17-03-2010
Abstract: In 2008, researchers at the Hewlett–Packard (HP) laboratories published a paper in Nature reporting the development of a new basic circuit element that completes the missing link between charge and flux linkage, which was postulated by Chua in 1971 (Chua 1971 IEEE Trans. Circuit Theory 18 , 507–519 ( doi:10.1109/TCT.1971.1083337 )). The HP memristor is based on a nanometre scale TiO 2 thin film, containing a— doped region and an undoped region. Further to proposed applications of memristors in artificial biological systems and non-volatile RAM, they also enable reconfigurable nanoelectronics. Moreover, memristors provide new paradigms in application-specific integrated circuits and field programmable gate arrays. A significant reduction in area with an unprecedented memory capacity and device density are the potential advantages of memristors for integrated circuits. This work reviews the memristor and provides mathematical and SPICE models for memristors. Insight into the memristor device is given via recalling the quasi-static expansion of Maxwell’s equations. We also review Chua’s arguments based on electromagnetic theory.
Publisher: Royal Society of Chemistry (RSC)
Date: 2017
DOI: 10.1039/C7NR04372D
Abstract: Highly transparent SrTiO 3 resistive memories with transient response to optical excitations are demonstrated and the evolution of oxygen vacancies with the location of a conductive filament is optically mapped.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 04-2010
Publisher: Springer Science and Business Media LLC
Date: 07-11-2017
DOI: 10.1038/S41598-017-15395-5
Abstract: Today’s electronic devices are fabricated using highly toxic materials and processes which limits their applications in environmental sensing applications and mandates complex encapsulation methods in biological and medical applications. This paper proposes a fully resorbable high density bio-compatible and environmentally friendly solution processable memristive crossbar arrays using silk fibroin protein which demonstrated bipolar resistive switching ratio of 10 4 and possesses programmable device lifetime characteristics before the device gracefully bio-degrades, minimizing impact to environment or to the implanted host. Lactate dehydrogenase assays revealed no cytotoxicity on direct exposure to the fabricated device and support their environmentally friendly and biocompatible claims. Moreover, the correlation between the oxidation state of the cations and their tendency in forming conductive filaments with respect to different active electrode materials has been investigated. The experimental results and the numerical model based on electro-thermal effect shows a tight correspondence in predicting the memristive switching process with various combinations of electrodes which provides insight into the morphological changes of conductive filaments in the silk fibroin films.
Publisher: Springer Science and Business Media LLC
Date: 17-02-2017
DOI: 10.1038/NCOMMS14482
Abstract: A variety of deposition methods for two-dimensional crystals have been demonstrated however, their wafer-scale deposition remains a challenge. Here we introduce a technique for depositing and patterning of wafer-scale two-dimensional metal chalcogenide compounds by transforming the native interfacial metal oxide layer of low melting point metal precursors (group III and IV) in liquid form. In an oxygen-containing atmosphere, these metals establish an atomically thin oxide layer in a self-limiting reaction. The layer increases the wettability of the liquid metal placed on oxygen-terminated substrates, leaving the thin oxide layer behind. In the case of liquid gallium, the oxide skin attaches exclusively to a substrate and is then sulfurized via a relatively low temperature process. By controlling the surface chemistry of the substrate, we produce large area two-dimensional semiconducting GaS of unit cell thickness (∼1.5 nm). The presented deposition and patterning method offers great commercial potential for wafer-scale processes.
Publisher: IEEE
Date: 06-2014
Publisher: IEEE
Date: 2006
Publisher: Elsevier BV
Date: 06-2011
Publisher: Informa UK Limited
Date: 06-2010
Publisher: Cold Spring Harbor Laboratory
Date: 28-08-2021
DOI: 10.1101/2021.08.25.21262594
Abstract: Electroencephalography (EEG) has been widely used to understand the nervous system and as a clinical diagnostic tool. In the case of neurological conditions with intermittent episodes, such as epilepsy, long-term EEG monitoring outside the clinics and in the community setting is vital. Subgaleal EEG (sgEEG) has emerged as an essential tool for long-term monitoring over several years. Current sgEEG solutions share a need for at least a 10 cm long lead wire, resulting in a bulky and invasive device. This work introduces a novel electrode architecture for subgaleal EEG recording, which forgoes the need for lead wires. A back-to-back electrode configuration with an electrode spacing of less than 1 mm is proposed. Compared to the current side-by-side approaches with an electrode spacing of several cm, our proposed approach results in at least one order of magnitude reduction in volume. The efficacy of the proposed electrode architecture is investigated through finite element modeling, phantom measurements, and cadaver studies. Our results suggest that compared to the conventional side-by-side electrode configuration, the source signal can be recorded reliably. Lead wires have posed a significant challenge from a device reliability and measurement quality perspective. Moreover, lead wires and the associated feedthrough connectors are bulky. Our proposed lead-free EEG recording solution may lead to a less invasive surgical placement through volume reduction and improve EEG recording quality.
Publisher: Springer Science and Business Media LLC
Date: 28-10-2019
DOI: 10.1038/S41598-019-51700-0
Abstract: Memristors have demonstrated immense potential as building blocks in future adaptive neuromorphic architectures. Recently, there has been focus on emulating specific synaptic functions of the mammalian nervous system by either tailoring the functional oxides or engineering the external programming hardware. However, high device-to-device variability in memristors induced by the electroforming process and complicated programming hardware are among the key challenges that hinder achieving biomimetic neuromorphic networks. Here, a simple hybrid complementary metal oxide semiconductor (CMOS)-memristor approach is reported to implement different synaptic learning rules by utilizing a CMOS-compatible memristor based on oxygen-deficient SrTiO 3 -x (STO x ). The potential of such hybrid CMOS-memristor approach is demonstrated by successfully imitating time-dependent (pair and triplet spike-time-dependent-plasticity) and rate-dependent (Bienenstosk-Cooper-Munro) synaptic learning rules. Experimental results are benchmarked against in-vitro measurements from hippoc al and visual cortices with good agreement. The scalability of synaptic devices and their programming through a CMOS drive circuitry elaborates the potential of such an approach in realizing adaptive neuromorphic computation and networks.
Publisher: IEEE
Date: 2006
Publisher: IEEE
Date: 08-2012
Publisher: IEEE
Date: 12-2011
Publisher: Wiley
Date: 03-2018
Publisher: The Royal Society
Date: 05-2023
DOI: 10.1098/RSOS.230022
Abstract: Epilepsy is a prevalent condition characterized by recurrent, unpredictable seizures. Monitoring with surface electroencephalography (EEG) is the gold standard for diagnosing epilepsy, but a time-consuming, uncomfortable and sometimes ineffective process for patients. Further, using EEG over a brief monitoring period has variable success, dependent on patient tolerance and seizure frequency. The availability of hospital resources and hardware and software specifications inherently restrict the options for comfortable, long-term data collection, resulting in limited data for training machine-learning models. This mini-review examines the current patient journey, providing an overview of the current state of EEG monitoring with reduced electrodes and automated channel reduction methods. Opportunities for improving data reliability through multi-modal data fusion are suggested. We assert the need for further research in electrode reduction to advance brain monitoring solutions towards portable, reliable devices that simultaneously offer patient comfort, perform ultra-long-term monitoring and expedite the diagnosis process.
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 06-2023
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 02-2020
Publisher: Elsevier BV
Date: 09-2023
Publisher: IOP Publishing
Date: 20-10-0020
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Date: 10-2020
Publisher: IEEE
Date: 03-2017
Publisher: Royal Society of Chemistry (RSC)
Date: 2014
DOI: 10.1039/C4NR03405H
Abstract: A bipolar-switch-based synaptic circuit realizes multiprotocol-induced plasticity in both excitatory and inhibitory synaptic transmission.
Location: United States of America
Start Date: 12-2023
End Date: 12-2026
Amount: $372,150.00
Funder: Australian Research Council
View Funded ActivityStart Date: 07-2014
End Date: 10-2020
Amount: $312,591.00
Funder: Australian Research Council
View Funded ActivityStart Date: 03-2018
End Date: 06-2022
Amount: $4,420,408.00
Funder: Australian Research Council
View Funded ActivityStart Date: 2016
End Date: 12-2017
Amount: $400,000.00
Funder: Australian Research Council
View Funded ActivityStart Date: 2023
End Date: 12-2023
Amount: $1,465,519.00
Funder: Australian Research Council
View Funded Activity