Publications
164 results found
Abdulsadig R, Rodriguez-Villegas E, 2023, Sleep posture monitoring using a single neck-situated accelerometer: a proof-of-concept, IEEE Access, Vol: 11, Pages: 17693-17706, ISSN: 2169-3536
Sleep position identification and monitoring is important in the context of certain healthcare conditions, such as obstructive sleep apnoea and epilepsy. Many studies have thoroughly investigated automatic sleep detection using various sensing channels located in optimum body locations. However, this has not been the case for detection using physiological data acquired from a single sensing channel on the neck. In certain healthcare contexts the neck can, however, be an attractive location despite being suboptimal for position monitoring; the reason being that it enables better extraction of more critical biomarkers from other sensing modalities, making possible multimodal monitoring using just one wearable. This work focuses on investigating methods of automatic sleep position detection using one wearable channel of accelerometry data sensed on the neck. Three different models are explored. These are based on: decision trees (DT), extra-trees classifier (ET) and long-short term memory neural networks (LSTM-NN). The paper also investigates for the first time what would be optimum design choices when considering that wearables are power and memory-constrained, but performance in the type of healthcare applications where a single location multimodal sensing is important must not be compromised. This includes looking into how changing the sampling rate and window sizes would affect the performance of the different models. It is demonstrated that a sampling rate as low as 5 Hz, and a window size as short as 1 second, still lead to high classification performance (around 0.945, 0.975 and 0.965 mean f1-score when using the DT, ET and LSTM-NN models, respectively, and at least 98% average accuracy in all three models); and that the DT model occupies the least memory space (1.765 KB) and takes the least mean prediction time across all window sizes (around 0.8 ms).
Kozłowski M, Singh S, Ramage G, et al., 2021, Effects of denoising strategies on R-wave detection in ECG analysis, IEEE EMBC 2021, Publisher: IEEE, Pages: 373-376
The use of ECG in cardiovascular health monitor-ing is well established. The signal is collected using specialisedequipment, capturing the electrical discharge properties of thehuman heart. This produces a well-structured signal tracewhich can be characterised through its peaks and troughs.The signal can then be used by clinicians to diagnose cardiacdisorders. However, as with any measuring equipment, theECG output signal can experience deterioration resulting fromnoise. This can happen due to environmental interference,human issues or measuring equipment failure necessitatingthe development of various denoising strategies to reduce, orremove the noise entirely. In this paper, we study typicallyoccurring types of noise and implement popular strategies usedto rectify them. We also show, that the given strategy’s denoisingpotential is directly related to R-wave detection, and providebest strategies to apply when faced with specific noise type.
Iranmanesh S, Raikos G, Imtiaz S, et al., 2019, A seizure based power reduction SoC for wearable EEG In epilepsy, IEEE Access, Vol: 7, Pages: 151682-151691, ISSN: 2169-3536
Epilepsy is one of the most common serious braindisorders affecting 1% of the world population. Epileptic seizureevents are caused by abnormal excessive neuronal activity in thebrain, which may be associated with behavioural changes thatseverely affect the patients’ quality of life. These events are manifested as abnormal activity in electroencephalography (EEG)recordings of individuals with epilepsy. This paper presents theon-chip implementation of an algorithm that, operating on theprinciple of data selection applied to seizures, would be able toreduce the power consumption of EEG devices, and consequentlytheir size, thereby significantly increasing their usability. In orderto reduce the power consumed by the on-chip implementation ofthe algorithm, mathematical approximations have been carriedout to allow for an analog implementation, resulting in the powerconsumed by the system to be negligible in comparison to otherblocks in an EEG device. The system has been fabricated in a0.18 µm CMOS process, consumes 1.14 µW from a 1.25 V supplyand achieves a sensitivity of 98.5% while only selecting 52.5%of the EEG data for transmission.
Imtiaz S, Iranmanesh S, Rodriguez Villegas E, 2019, A low power system with EEG data reduction for long-term epileptic seizures monitoring, IEEE Access, Vol: 7, Pages: 71195-71208, ISSN: 2169-3536
Long-term monitoring of epilepsy patients requires low-power systems that can record and transmit electroencephalogram data over extended periods of time. Since seizure events are rare, long-term monitoring inherently results in large amounts of data that are recorded and hence need to be reduced. This paper presents an ultra-low power integrated circuit implementation of a data reduction algorithm for epilepsy monitoring, specific to seizure events. The algorithm uses line length of the electroencephalogram signals as the key discriminating feature to classify epochs of data as seizure or non-seizure events. It is implemented in AMS 0.18- $\mu \text{m}$ CMOS technology and its output is connected to a Bluetooth low energy transceiver to wirelessly transmit potential seizure events. All the modules of the algorithm have been implemented on chip to use a small number of clock cycles and remain mostly in an idle mode. The algorithm, on the chip, achieves 50% of data reduction with a sensitivity of 80% for capturing seizure events. The overall power consumption of the chip is measured to be 23 $\mu \text{W}$ , while the full system with wireless transmission consumes 743 $\mu \text{W}$ . The results in this paper demonstrate the feasibility of a long-term seizure monitoring system capable of running autonomously for over two weeks.
Pramono RXA, Imtiaz SA, Rodriguez-Villegas E, 2019, Evaluation of features for classification of wheezes and normal respiratory sounds, PLoS ONE, Vol: 14, Pages: e0213659-e0213659, ISSN: 1932-6203
Chronic Respiratory Diseases (CRDs), such as Asthma and Chronic Obstructive Pulmonary Disease (COPD), are leading causes of deaths worldwide. Although both Asthma and COPD are not curable, they can be managed by close monitoring of symptoms to prevent worsening of the condition. One key symptom that needs to be monitored is the occurrence of wheezing sounds during breathing since its early identification could prevent serious exacerbations. Since wheezing can happen randomly without warning, a long-term monitoring system with automatic wheeze detection could be extremely helpful to manage these respiratory diseases. This study evaluates the discriminatory ability of different types of feature used in previous related studies, with a total size of 105 individual features, for automatic identification of wheezing sound during breathing. A linear classifier is used to determine the best features for classification by evaluating several performance metrics, including ranksum statistical test, area under the sensitivity--specificity curve (AUC), F1 score, Matthews Correlation Coefficient (MCC), and relative computation time. Tonality index attained the highest effect size, at 87.95%, and was found to be the feature with the lowest p-value when ranksum significance test was performed. Third MFCC coefficient achieved the highest AUC and average optimum F1 score at 0.8919 and 82.67% respectively, while the highest average optimum MCC was obtained by the first coefficient of a 6th order LPC. The best possible combination of two and three features for wheeze detection is also studied. The study concludes with an analysis of the different trade-offs between accuracy, reliability, and computation requirements of the different features since these will be highly useful for researchers when designing algorithms for automatic wheeze identification.
Sharma P, Imtiaz SA, Rodriguez Villegas E, 2019, An algorithm for heart rate extraction from acoustic recordings at the neck, IEEE Transactions on Biomedical Engineering, Vol: 66, Pages: 246-256, ISSN: 0018-9294
Heart rate is an important physiological parameter to assess the cardiac condition of an individual and is traditionally determined by attaching multiple electrodes on the chest of a subject to record the electrical activity of the heart. The installation and handling complexities of such systems does not prove feasible for a user to undergo a long-term monitoring in the home settings. A small-sized, battery-operated wearable monitoring device is placed on the suprasternal notch at neck to record acoustic signals containing information about breathing and cardiac sounds. The heart sounds obtained are heavily corrupted by the respiratory cycles and other external artifacts. This paper presents a novel algorithm for reliably extracting the heart rate from such acoustic recordings, keeping in mind the constraints posed by the wearable technology. The methodology constructs the Hilbert energy envelope of the signal by calculating its instantaneous characteristics to segment and classify a cardiac cycle into S1 and S2 sounds using their timing characteristics. The algorithm is tested on a dataset consisting of 13 subjects with an approximate data length of 75 hours and achieves an accuracy of 94.34%, an RMS error of 3.96 bpm and a correlation coefficient of 0.93 with reference to a commercial device in use.
Dwivedi AK, Imtiaz SA, Rodriguez Villegas E, 2018, Algorithms for automatic analysis and classification of heart sounds – a systematic review, IEEE Access, Vol: 7, Pages: 8316-8345, ISSN: 2169-3536
Cardiovascular diseases currently pose the highest threat to human health around the world. Proper investigation of the abnormalities in heart sounds is known to provide vital clinical information that can assist in the diagnosis and management of cardiac conditions. However, despite significant advances in the development of algorithms for automated classification and analysis of heart sounds, the validity of different approaches has not been systematically reviewed. This paper provides an in-depth systematic review and critical analysis of all the existing approaches for automatic identification and classification of the heart sounds. All statements on the Preferred Reporting Items for Systematic Reviews and Meta-Analyses 2009 Checklist were followed and addressed thoroughly to maintain the quality of the accounted systematic review. Out of 1347 research articles available in the academic databases from 1963 to 2018, 117 peer-reviewed articles were found to fall under the search and selection criteria of this paper. Amongst them: 53 articles are focused on segmentation, 72 of the studies are related to the feature extraction approaches and 88 to classification, and 56 reported on the databases and heart sounds acquisition. From this review, it is clear that, although a lot of research has been done in the field of automated analysis, there is still some work to be done to develop robust methods for identification and classification of various events in the cardiac cycle so that this could be effectively used to improve the diagnosis and management of cardiovascular diseases in combination with the wearable mobile technologies.
Rodriguez Villegas E, Iranmanesh S, Imtiaz SA, 2018, Wearable medical devices: high level system design considerations and trade-offs, IEEE Solid State Circuits Magazine, Vol: 10, Pages: 43-52, ISSN: 1943-0582
Wearable devices have seen tremendous growth over the last 10 years. This has been madepossible with the ever-shrinking electronics, reduction in costs as well as the rise in mobilecomputing making it possible to share significant computational workload. Recent estimatesshow an annual growth of 17% in wearable devices in the year 2017 with over 300 milliondevices being sold. It is also projected that over 500 million devices will be sold by the year2021 [1]. While these figures show some staggering growth and potential for wearable devices,a detailed look at the numbers reveal that the application areas where wearable devices havebeen a success are quite limited. Most of these devices whichare consideredwearable, takethe form of smartwatches, fitness trackers, body worn cameras and headphones. It should beemphasized that the mentioned numbers are for devices that are made for consumers and usedmostly for entertainment, wellness and general health purposes. The benefits provided by mostof these health-related wearable devices are insufficient for medical usage mainly because oflow quality data and insufficient accuracy in classificationtasks.While wearables for consumer use will continue to grow, it is important to keep in mindthe distinction between consumer and medical-grade devices. In the sphere of medical devices,wearables for monitoring, diagnosing and real-time management of illnesses is still at a veryearly stage. One of the main reasons for this slow growth, as well as adoption, is the designof such devices, which is inherently very challenging. In this paper, we will first look at theneed for wearable devices to improve healthcare in order to understand and define a set of requirements for the design of such devices. Subsequently,based on these requirements, we willlook at the challenges that exist in the development of wearable medical devices particularlyfrom the perspective of their system and circuit level implementations.
Garcia-Lopez I, Imtiaz SA, Rodriguez-Villegas E, 2018, Characterization study of neck photoplethysmography, EMBC 2018, Publisher: IEEE, Pages: 4355-4358
This paper presents a comparison between finger and neck photoplethysmography (PPG) in order to assess the potential and limitations of this, non-conventionally used, body site for application in pulse oximetry. PPG signals were recorded at both sites from healthy subjects to inspect the differences in average waveforms, as well as in oxygen saturation (SpO2) and heart rate (HR) estimation. The results show significant differences in the average PPG pulse waveforms for different contour features such as diastolic or dicrotic notch amplitude, among others. The results show that the HR estimated from signals obtained with the neck sensor are strongly correlated to the output of the reference finger (R=0.862, MAE=1.27 BPM), whereas SpO2 measurements are not that accurately predicted (R=0.129, MAE=11.7%). Spectrograms under different breathing conditions revealed that the respiratory frequency is more predominant in neck PPG than in finger, which has a great potential for respiratory rate (RR) extraction. These are very promising results for the suitability of the neck as an alternative location for monitoring of respiratory diseases, and specifically for sleep apnea.
Peng M, Imtiaz SA, Rodriguez-Villegas E, 2017, Pulse oximetry in the neck - a proof of concept, Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Publisher: IEEE, Pages: 877-880, ISSN: 1558-4615
Oxygen saturation levels are routinely monitoredin clinical settings. Pulse oximetry, in transmittance operationmode, is the most common method of estimating oxygen satu-ration (SpO2). This is inexpensive and non-invasive and thusallows for long-term monitoring. However, it suffers from issuessuch as signal integrity, reliability and patient comfortability.As a result, there is an interest in exploring other locations onthe body where oxygen saturation can be measured reliably. Inthis paper, a wearable device has been designed to study thefeasibility of extracting photoplethysmogram (PPG) signals atthe neck in reflectance pulse oximetry mode. It explores thesignal integrity and strength compared to other locations aswell as the presence of motion artefacts in that location. Theresults demonstrate that the PPG signals acquired at the neckshow a very strong correlation (r=0.82) with the SpO2valuesobtained using a commercial device. Further, the SpO2valuesare calculated with an accuracy of 98.6%.
Torres I, Echebarria U, Imtiaz SA, et al., 2017, Monitoring smoking behaviour using a wearable acoustic sensor, Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Publisher: IEEE, Pages: 4459-4462, ISSN: 1558-4615
Smoking is a cause of multiple health problemsresulting in diseases which can also be fatal. It is well knownthat smoking has long-term impact on the health of anindividual as well. While a number of studies have looked atthe impact of smoking on health and its economic impacts,most of these rely on input from smokers in the form ofquestionnaires and surveys. Long-term monitoring of smokinghabits and behaviour is thus not possible because of the lackof means to do so. This paper proposes the use of a wearabledevice to monitor breathing signals of subjects. It is shown thatthe acoustic properties of a smoking breath are different froma non-smoking breath. To encapsulate these differences, severalfeatures from a breath segment are extracted and used with asimple classifier to automatically identify smoking breaths. Theproposed algorithm detected smoking and non-smoking breathswith average accuracy of 66% and 99% respectively.
Rodriguez Villegas E, Iranmanesh S, 2017, A 950 nW analog-based data reduction chip for wearable EEG systems in epilepsy, IEEE Journal of Solid State Circuits, Vol: 52, Pages: 2362-2373, ISSN: 0018-9200
Long-term electroencephalogram (EEG) monitoring is an important tool used for the diagnosis of epilepsy. Truly Wearable EEG can be considered as the future of ambulatory EEG units, which are the current standard for long-term EEG monitoring. Replacing these short lifetime, bulky units with long-lasting miniature and wearable devices which can be easily worn by patients will result in more EEG data being acquired for longer monitoring periods. This paper presents an analog-based data reduction integrated circuit that would reduce the amount of power required to transmit EEG data by identifying the sections of data that are interesting for diagnostic purposes while discarding the background activity. Using the data reduction system as part of a miniature wireless, EEG monitoring unit would yield significant reductions in power consumption since the transmitter will only be switched ON based on the data reduction system output. A system prototype chip has been fabricated in a 0.35 μm CMOS process. The system consumes 760 nA from a 1.25 V supply and is able to achieve a sensitivity of 87%, while transmitting 45% of the overall EEG data.
Eid MH, Rodriguez-Villegas E, 2017, Analysis of reversion losses in charge pumps and its impact on efficiency for low power design, 15th IEEE International New Circuits and Systems Conference (NEWCAS), Publisher: IEEE, Pages: 9-12, ISSN: 2472-467X
Jiang Z, Huxter JR, Bowyer S, et al., 2017, TaiNi: maximizing research output whilst improving animals' welfare in neurophysiology experiments, Scientific Reports, Vol: 7, ISSN: 2045-2322
Understanding brain function at the cell and circuit level requires representation of neuronal activity through multiple recording sites and at high sampling rates. Traditional tethered recording systems restrict movement and limit the environments suitable for testing, while existing wireless technology is still too heavy for extended recording in mice. Here we tested TaiNi, a novel ultra-lightweight (<2 g) low power wireless system allowing 72-hours of recording from 16 channels sampled at ~19.5 KHz (9.7 KHz bandwidth). We captured local field potentials and action-potentials while mice engaged in unrestricted behaviour in a variety of environments and while performing tasks. Data was synchronized to behaviour with sub-second precision. Comparisons with a state-of-the-art wireless system demonstrated a significant improvement in behaviour owing to reduced weight. Parallel recordings with a tethered system revealed similar spike detection and clustering. TaiNi represents a significant advance in both animal welfare in electrophysiological experiments, and the scope for continuously recording large amounts of data from small animals.
Eid MH, Rodriguez-Villegas E, 2017, Analysis and design of cross-coupled charge pump for low power on chip applications, MICROELECTRONICS JOURNAL, Vol: 66, Pages: 9-17, ISSN: 0026-2692
Pramono R, Bowyer S, Rodriguez Villegas E, 2017, Automatic adventitious respiratory sound analysis: A systematic review, PLOS One, Vol: 12, ISSN: 1932-6203
BackgroundAutomatic detection or classification of adventitious sounds is useful to assist physicians in diagnosing or monitoring diseases such as asthma, Chronic Obstructive Pulmonary Disease (COPD), and pneumonia. While computerised respiratory sound analysis, specifically for the detection or classification of adventitious sounds, has recently been the focus of an increasing number of studies, a standardised approach and comparison has not been well established.ObjectiveTo provide a review of existing algorithms for the detection or classification of adventitious respiratory sounds. This systematic review provides a complete summary of methods used in the literature to give a baseline for future works.Data sourcesA systematic review of English articles published between 1938 and 2016, searched using the Scopus (1938-2016) and IEEExplore (1984-2016) databases. Additional articles were further obtained by references listed in the articles found. Search terms included adventitious sound detection, adventitious sound classification, abnormal respiratory sound detection, abnormal respiratory sound classification, wheeze detection, wheeze classification, crackle detection, crackle classification, rhonchi detection, rhonchi classification, stridor detection, stridor classification, pleural rub detection, pleural rub classification, squawk detection, and squawk classification.Study selectionOnly articles were included that focused on adventitious sound detection or classification, based on respiratory sounds, with performance reported and sufficient information provided to be approximately repeated.Data extractionInvestigators extracted data about the adventitious sound type analysed, approach and level of analysis, instrumentation or data source, location of sensor, amount of data obtained, data management, features, methods, and performance achieved.Data synthesisA total of 77 reports from the literature were included in this review. 55 (71.43%) of the studies focused
Iranmanesh S, Rodriguez Villegas E, 2017, An ultra-low power sleep spindle detection system on chip, IEEE Transactions on Biomedical Circuits and Systems, Vol: 11, Pages: 858-866, ISSN: 1940-9990
This paper describes a full system-on-chip to automatically detect sleep spindle events from scalp EEG signals. These events, which are known to play an important role on memory consolidation during sleep, are also characteristic of a number of neurological diseases. The operation of the system is based on a previously reported algorithm, which used the Teager energy operator, together with the Spectral Edge Frequency (SEF50) achieving more than 70% sensitivity and 98% specificity. The algorithm is now converted into a hardware analog based customized implementation in order to achieve extremely low levels of power. Experimental results prove that the system, which is fabricated in a 0.18 μm CMOS technology, is able to operate from a 1.25 V power supply consuming only 515 nW, with an accuracy that is comparable to its software counterpart.
Imtiaz SA, Jiang Z, Rodriguez Villegas E, 2017, An ultra-low power system-on-chip for automatic sleep staging, IEEE Journal of Solid State Circuits, Vol: 52, Pages: 822-833, ISSN: 1558-173X
This paper presents an ultra-low power SoC for automatic sleep staging using a single electroen-cephalography (EEG) channel. The system integrates an analog front-end for EEG data acquisition and adigital processor to extract spectral features from this data and classify them into one of the sleep stages.The digital processor consists of multiple blocks implementing an automatic sleep staging algorithmthat uses a set of contextual decision trees controlled by a state machine. The processor is designedto stay in idle mode at most times waking up only when computations are required. In addition, themathematical operations are implemented in a way such that the number of datapath components neededis very small. The SoC is implemented in AMS 0.18μm CMOS technology and is powered using asingle 1.25V supply. Its power consumption is measured to be575μW while its classification accuracyusing real EEG data is 98.7%.
Patrick KCA, Imtiaz SA, Bowyer S, et al., 2016, An Algorithm for Automatic Detection of Drowsiness for Use inWearable EEG Systems, IEEE EMBC 2016, Publisher: IEEE, ISSN: 1557-170X
Lack of proper restorative sleep can induce sleepinessat odd hours making a person drowsy. This onset of drowsinesscan be detrimental for the individual in a number of waysif it happens at an unwanted time. For example, drowsinesswhile driving a vehicle or operating heavy machinery poses athreat to the safety and wellbeing of individuals as well as thosearound them. Timely detection of drowsiness can prevent theoccurrence of unfortunate accidents thereby improving roadand work environment safety. In this paper, by analyzing theelectroencephalographic (EEG) signals of human subjects inthe frequency domain, several features across different EEGchannels are explored. Of these, three features are identified tohave a strong correlation with drowsiness. A weighted sum ofthese defining features, extracted from a single EEG channel,is then used with a simple classifier to automatically separatethe state of wakefulness from drowsiness. The proposed algorithmresulted in drowsiness detection sensitivity of 85% andspecificity of 93%.
Imtiaz SA, Mardell JAMES, Saremi-Yarahmadi SIAVASH, et al., 2016, ECG Artefact Identification and Removal in mHealth Systems for Continuous Patient Monitoring, Healthcare Technology Letters, Vol: 3, Pages: 171-176, ISSN: 2053-3713
Continuous patient monitoring systems acquire enormous amounts of data that is either manually analysed by doctors or automaticallyprocessed using intelligent algorithms. Sections of data acquired over long period of time can be corrupted with artefacts due to patientmovement, sensor placement and interference from other sources. Because of the large volume of data these artefacts need to be automaticallyidentified so that the analysis systems and doctors are aware of them while making medical diagnosis. This paper explores three importantfactors that must be considered and quantified for the design and evaluation of automatic artefact identification algorithms: signal quality,interpretation quality and computational complexity. The first two are useful to determine the effectiveness of an algorithm while the third isparticularly vital in mHealth systems where computational resources are heavily constrained. A series of artefact identification and filteringalgorithms are then presented focusing on the electrocardiography data. These algorithms are quantified using the three metrics to demonstratehow different algorithms can be evaluated and compared to select the best ones for a given wireless sensor network.
Pramono R, Imtiaz SA, Rodriguez Villegas ESTHER, 2016, A Cough-Based Algorithm for Automatic Diagnosis of Pertussis, PLOS One, Vol: 11, ISSN: 1932-6203
Pertussis is a contagious respiratory disease which mainly affects young children and can be fatal if left untreated. The World Health Organization estimates 16 million pertussis cases annually worldwide resulting in over 200,000 deaths. It is prevalent mainly in developing countries where it is difficult to diagnose due to the lack of healthcare facilities and medical professionals. Hence, a low-cost, quick and easily accessible solution is needed to provide pertussis diagnosis in such areas to contain an outbreak. In this paper we present an algorithm for automated diagnosis of pertussis using audio signals by analyzing cough and whoop sounds. The algorithm consists of three main blocks to perform automatic cough detection, cough classification and whooping sound detection. Each of these extract relevant features from the audio signal and subsequently classify them using a logistic regression model. The output from these blocks is collated to provide a pertussis likelihood diagnosis. The performance of the proposed algorithm is evaluated using audio recordings from 38 patients. The algorithm is able to diagnose all pertussis successfully from all audio recordings without any false diagnosis. It can also automatically detect individual cough sounds with 92% accuracy and PPV of 97%. The low complexity of the proposed algorithm coupled with its high accuracy demonstrates that it can be readily deployed using smartphones and can be extremely useful for quick identification or early screening of pertussis and for infection outbreaks control.
Logesparan L, Casson AJ, Rodriguez-Villegas E, 2016, Erratum to: Optimal features for online seizure detection., Medical & Biological Engineering & Computing, Vol: 54, Pages: 1295-1295, ISSN: 1741-0444
Chen G, Bowyer S, Rodriguez Villegas E, 2016, Low-complexity prediction of frequency-rich biosignals for lossless compression in wearable technologies, IEEE Engineering in Medicine and Biology Society (EMBC) Annual International Conference
Iranmanesh S, Raikos G, Jiang Z, et al., 2016, CMOS implementation of a low power absolute value comparator circuit, 14th IEEE International New Circuits and Systems Conference (NEWCAS), Publisher: IEEE, ISSN: 2472-467X
- Author Web Link
- Cite
- Citations: 1
Saraswat R, Rodriguez-Villegas E, Jiang Z, 2016, Low Emission, Open Loop MAC Protocol Compliant Implantable FSK Modulator, 14th IEEE International New Circuits and Systems Conference (NEWCAS), Publisher: IEEE, ISSN: 2472-467X
Iranmanesh S, Eid M, Rodriguez-Villegas E, 2016, Optimizing simulation times in biomedical systems containing Quasi-Infinite Resistors, 2nd IEEE Nordic Circuits and Systems Conference (NORCAS), Publisher: IEEE
Logesparan L, Rodriguez-Villegas E, Casson AJ, 2015, The impact of signal normalization on seizure detection using line length features, MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING, Vol: 53, Pages: 929-942, ISSN: 0140-0118
- Author Web Link
- Cite
- Citations: 21
Imtiaz SA, Rodriguez-Villegas E, 2015, Automatic sleep staging using state machine-controlled decision trees., 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC), Publisher: IEEE, Pages: 378-381, ISSN: 1557-170X
Automatic sleep staging from a reduced number of channels is desirable to save time, reduce costs and make sleep monitoring more accessible by providing home-based polysomnography. This paper introduces a novel algorithm for automatic scoring of sleep stages using a combination of small decision trees driven by a state machine. The algorithm uses two channels of EEG for feature extraction and has a state machine that selects a suitable decision tree for classification based on the prevailing sleep stage. Its performance has been evaluated using the complete dataset of 61 recordings from PhysioNet Sleep EDF Expanded database achieving an overall accuracy of 82% and 79% on training and test sets respectively. The algorithm has been developed with a very small number of decision tree nodes that are active at any given time making it suitable for use in resource-constrained wearable systems.
Imtiaz SA, Rodriguez-Villegas E, 2015, An open-source toolbox for standardized use of PhysioNet Sleep EDF Expanded Database., 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC, Publisher: IEEE, Pages: 6014-6017, ISSN: 1557-170X
PhysioNet Sleep EDF database has been the most popular source of data used for developing and testing many automatic sleep staging algorithms. However, the recordings from this database has been used in an inconsistent fashion. For example, arbitrary selection of start and end times from long term recordings, data-hypnogram mismatches, different performance metrics and hypnogram conversion from R&K to AASM. All these differences result in different data sections and performance metrics being used by researchers thereby making any direct comparison between algorithms very difficult. Recently, a superset of this database has been made available on PhysioNet, known as the Sleep EDF Expanded Database which includes 61 recordings. This provides an opportunity to standardize the way in which signals from this database should be used. With this goal in mind, we present in this paper a toolbox for automatically downloading and extracting recordings from the Sleep EDF Expanded database and converting them to a suitable format for use in MATLAB. This toolbox contains functions for selecting appropriate data for sleep analysis (based on our previous recommendations for sleep staging), hypnogram conversion and computation of performance metrics. Its use makes it simpler to start using the new sleep database and also provides a foundation for much-needed standardization in this research field.
Imtiaz SA, Logesparan L, Rodriguez-Villegas E, 2015, Performance-Power Consumption Tradeoff in Wearable Epilepsy Monitoring Systems, IEEE Journal of Biomedical and Health Informatics, Vol: 19, Pages: 1019-1028, ISSN: 2168-2208
Automated seizure detection methods can be used to reduce time and costs associated with analyzing large volumes of ambulatory EEG recordings. These methods however have to rely on very complex, power hungry algorithms, implemented on the system backend, in order to achieve acceptable levels of accuracy. In size, and therefore power-constrained EEG systems, an alternative approach to the problem of data reduction is online data selection, in which simpler algorithms select potential epileptiform activity for discontinuous recording but accurate analysis is still left to a medical practitioner. Such a diagnostic decision support system would still provide doctors with information relevant for diagnosis while reducing the time taken to analyze the EEG. For wearable systems with limited power budgets, data selection algorithm must be of sufficiently low complexity in order to reduce the amount of data transmitted and the overall power consumption. In this paper, we present a low-power hardware implementation of an online epileptic seizure data selection algorithm with encryption and data transmission and demonstrate the tradeoffs between its accuracy and the overall system power consumption. We demonstrate that overall power savings by data selection can be achieved by transmitting less than 40% of the data. We also show a 29% power reduction when selecting and transmitting 94% of all seizure events and only 10% of background EEG.
This data is extracted from the Web of Science and reproduced under a licence from Thomson Reuters. You may not copy or re-distribute this data in whole or in part without the written consent of the Science business of Thomson Reuters.