2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)最新文献

{"title":"Neural Interface System for Virtual High-Density Microelectrode Array Adaptive Neuromodulation","authors":"Gerard O’Leary, Adam Gierlach, R. Genov, T. Valiante","doi":"10.1109/BIOCAS.2019.8918739","DOIUrl":"https://doi.org/10.1109/BIOCAS.2019.8918739","url":null,"abstract":"The ultimate tool in neuroscience would offer the ability to record from every cell and adaptively stimulate each neuron based on inferred states. Microelectrode arrays (MEAs) have been developed to observe and probe neural populations with subcellular resolution, however, processing the large volumes of generated data streams is a critical bottleneck. Presented here is a microelectrode neural interface system (µNIT) which relaxes the physical electrode density requirement by combining lowdensity MEA technology with the generation of virtual electrodes. This increases the effective electrode density while minimizing the required processing overhead. µNIT integrates hardware accelerators for the real-time analysis of neuron-level activity, and for the adaptive generation of responsive electrical stimuli. Spike clustering is performed using an exponentially decaying memory-based autoencoder (EDM-AE) at a rate of up to 2676 spikes/second across all channels. Inferred states are used to adaptively control programmable waveform generators which create per-electrode stimuli at a 22.3 KHz sample rate. The processing system is demonstrated in vitro with clinically resected human brain tissue using a 60-channel microelectrode array.","PeriodicalId":222264,"journal":{"name":"2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121467444","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Deep Recurrent Neural Network for Extracting Pulse Rate Variability from Photoplethysmography During Strenuous Physical Exercise","authors":"Ke Xu, Xinyu Jiang, Haoran Ren, Xiangyu Liu, Wei Chen","doi":"10.1109/BIOCAS.2019.8918711","DOIUrl":"https://doi.org/10.1109/BIOCAS.2019.8918711","url":null,"abstract":"Pulse rate variability (PRV) extracted from photoplethysmography (PPG) signal is a promising surrogate for heart rate variability (HRV) and has shown its great potential in diagnosing cardiac dysfunctions and autonomic nervous system diseases. However, the accurate extraction of PRV during strenuous physical exercise faces enormous challenges due to PPG’s extreme vulnerability to motion artifacts. In this work, we introduce a deep recurrent neural network (RNN) based on bidirectional Long-Short Term Memory Network (biLSTM) for accurate PPG cardiac period segmentation. After that, three important indexes for PRV are calculated, which are peak intervals, pulse intervals, and instantaneous heart rates (IHR). Comparison results with state-of-the-art methods on a dataset including 48 subjects show the promising performance of the proposed algorithm in PRV indexes estimation and recovery. To our best knowledge, this is the first time a deep learning-based algorithm been involved for extraction of PRV from seriously corrupted PPG signals.","PeriodicalId":222264,"journal":{"name":"2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"206 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132233689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Continuous wave laser excitation based portable optoacoustic imaging system for melanoma detection","authors":"Siyu Liu, Kai Tang, Haoran Jin, Ruochong Zhang, T. T. Kim, Yuanjin Zheng","doi":"10.1109/BIOCAS.2019.8919157","DOIUrl":"https://doi.org/10.1109/BIOCAS.2019.8919157","url":null,"abstract":"Optoacoustic imaging has been demonstrated successfully in detecting cutaneous melanoma in its early stage. In this work, we develop a handheld optoacoustic based portable medical imaging system for early melanoma diagnosis. In the portable optoacoustic system, laser excitation is provided by a compact continuous wave laser diode, which is driven by an FPGA controlled Howland circuit driver board. Optoacoustic detection is performed using a 2D square ultrasound transducer array and a portable multichannel data acquisition system. To pursue the optimized imaging SNR and resolution, chirp modulated laser excitation and matched filtering based acoustic pulse compression are further incorporated. To evaluate the feasibility of imaging melanoma, multisite 3D imaging on a human breast phantom is handheld performed. The prospect of using low-cost continuous wave laser diode and matrix array ultrasound transducers for volumetric optoacoustic imaging would be a real breakthrough towards commercialization of the optoacoustic technique.","PeriodicalId":222264,"journal":{"name":"2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"178 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132407905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Evaluation of the Effects of Mozart Music on Cerebral Hemodynamics in Preterm Infants","authors":"Haoran Ren, Xinyu Jiang, Ke Xu, L. Zou, Laishuan Wang, Chunmei Lu, Xiangyu Liu, Wei Chen","doi":"10.1109/BIOCAS.2019.8919100","DOIUrl":"https://doi.org/10.1109/BIOCAS.2019.8919100","url":null,"abstract":"Preterm infants, as a special population, exposed to the stimulus of medical procedures, need efficient integrated care. Music, a non-invasive positive stimulus, has the ability to improve infants well-being. In this study, a randomized controlled trial was conducted to evaluate the effect of Mozart music on cerebral hemodynamics detected by functional near-infrared spectroscopy (fNIRS). The statistical analysis results showed that the sample entropy of the experimental group was significantly lower than that of the control group in resting state after music intervention. It suggested that Mozart music could achieve the effect of calmness and relaxed state correlated with lower brain activities. This study will provide evidence to support the wide application of music intervention in clinical practice.","PeriodicalId":222264,"journal":{"name":"2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"20 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133068668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"A Novel Hybrid BCI Web Browser Based on SSVEP and Eye-Tracking","authors":"Xinyuan Lin, Wasim Q. Malik, Shaomin Zhang","doi":"10.1109/BIOCAS.2019.8919087","DOIUrl":"https://doi.org/10.1109/BIOCAS.2019.8919087","url":null,"abstract":"In this study, we developed and tested assistive technology for neuro-rehabilitation consisting of a novel hybrid web browser following \"true web access\" principles. We combined Steady-State Visual Evoked Potentials (SSVEP) derived from electroencephalography (EEG) together with gaze-point data from an eye-tracker to provide a natural method for people with severe motor impairment to access the internet without using a computer mouse. This system was tested by three healthy subjects. All subjects completed the online experiment successfully. The results showed an average overall accuracy of 88.5 ± 1.72%, whereas the copy-spelling accuracy of 100% was achieved by every subject. The average overall ITR value was 32.2 ± 1.14 bits/min. Thanks to the joining of eye-tracking technology, our system outperformed other BCI web browsers in command detection time and information transfer rate. And the user interface is much more friendly while the control panel and webpages are highly fused together.","PeriodicalId":222264,"journal":{"name":"2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"45 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133396213","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Neural Networks for Pathological Gait Classification Using Wearable Motion Sensors","authors":"Shubao Yin, Chen Chen, Hangyu Zhu, Xinping Wang, Wei Chen","doi":"10.1109/BIOCAS.2019.8919096","DOIUrl":"https://doi.org/10.1109/BIOCAS.2019.8919096","url":null,"abstract":"Gait, as an essential feature reflecting human health status, has attracted extensive attention in research. Automatic pathological gait identification can contribute to diseases diagnosis and intervention. In this paper, an unobtrusive sensing technology with deep learning methods to discriminate healthy and pathological gaits is proposed. Two accelerometers are mounted on the left and right lower limbs to acquire the motion signals. Based on these signals, three Neural Networks, namely, BPNN (Back Propagation Neural Network), LSTM (Long Short Term Memory) and CNN (Convolutional Neural Networks) are proposed for classifying the gaits. Experimental results exhibit that the accuracy of the proposed method can reach 86%, 81%, and 93% on a database of 15 participants while using BPNN, LSTM, CNN, respectively. With the strong ability of spatial-temporal signal analysis, CNN outperforms the other two neural networks and provides a favorable result. The proposed method can be extended to an automated gait classification tool, which can be used in the diagnosis and identification of pathological gaits.","PeriodicalId":222264,"journal":{"name":"2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"44 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133594246","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Balanced Laser Transmission Spectroscopy Based on a Tunable Gain Double Channel LIA for Nanoparticles Detection in Biomedical Applications","authors":"A. Marcellis, A. Sarra, Guido Di Patrizio Stanchieri, F. Bruni, F. Bordi, E. Palange, P. Postorino","doi":"10.1109/BIOCAS.2019.8918741","DOIUrl":"https://doi.org/10.1109/BIOCAS.2019.8918741","url":null,"abstract":"This paper reports on the design, fabrication and characterization of a double channel, tunable gain Lock-in Amplifier (LIA) operating with voltage input pulses provided by two Si photodiodes that measure the power variations of 10ns laser pulses of a 10Hz repetition rate Q-Switched Nd:YAG tunable laser equipped with an optical parametric oscillator and second and third harmonic generation crystals. This laser is used to perform laser transmission spectroscopy measurement to evaluate both the concentration and dimension of nanoparticles for biomedical and biophysics applications. Nowadays, the challenge is to investigate the role of nanoparticles in activating biological processes when their concentrations are less than 109 particles/ml and/or their size ranges from few tens to few hundreds of nanometers. The laser transmission spectroscopy is a powerful technique to investigate these topics of research and is based on the measurement of the transmittance through the sample containing the nanoparticles (i.e., the signal channel) against that one through a sample with no nanoparticles (i.e., the reference channel). When the nanoparticles size and/or concentration are small, also the light scattering process that influences the transmittance is small: the value of the signal channel approaches that one of the reference channel. Thus, in this case, it is of paramount importance to develop methods to perform measurements with very low indetermination. The proposed double channel, tunable gain LIA is a solution to this problem since it allows to implement a new balanced laser transmission spectroscopy method. Before performing the laser transmission spectroscopy of the samples of interest, a calibration curve is accomplished for each wavelength of the laser beam passing through the signal and reference channels both in absence of nanoparticles. Under these conditions, the LIA gain is varied to achieve a ratio between the light power passing through the two channels close to 1. This avoids any experimental artifact due to the optical components that drive the laser beam along the two channels. Once verified that the calibration curve remains unaltered in time, the balanced laser transmission spectroscopy method was used to determine the wavelength dependent extinction coefficient of NIST standard polystyrene particles suspension. Respect to the method of the double ratio conventionally used for these measurements, the proposed balanced technique decreases the extinction coefficient relative error up to a factor 8. Moreover, the calculated particle size and concentration was found equal to 510±10nm and (1.18±0.08)×109 particles/ml, respectively. The indetermination of the particle size value respect to the nominal one is equal to 0.78% that is 4 times lower than the corresponding value calculated by the laser transmission spectroscopy using the double ratio method.","PeriodicalId":222264,"journal":{"name":"2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127243726","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"An ECG Processor for the Detection of Eight Cardiac Arrhythmias with Minimum False Alarms","authors":"Muhammad Sohail, Zain Taufique, S. Abubakar, Wala Saadeh, Muhammad Awais Bin Altaf","doi":"10.1109/BIOCAS.2019.8919053","DOIUrl":"https://doi.org/10.1109/BIOCAS.2019.8919053","url":null,"abstract":"An Electrocardiography (ECG) based processor for eight Cardiac arrhythmias (CA) detection with smart priority logic is presented to minimize the false alarms. The processor utilizes a Multi-Level Linear Support Vector Machine (ML-LSVM) classifiers with one-vs-all approach to distinguish the different CAs. The classification is solely based on 5 features including R-wave, S-wave, T-wave, R-R interval and Q-S interval. The processor employs a priority logic to prioritize the detected conditions if more than one condition are detected. The system is implemented using CMOS 180nm with an area of 0.18mm2 and validated using 83 patient’s recordings from Physionet Arrhythmia Database and Creighton University Database. The proposed processor consumes 0.91uW with an average classification accuracy of 98.5% while reducing the false alarms by 99%, which is 30% superior performance compared to conventional systems.","PeriodicalId":222264,"journal":{"name":"2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115544917","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"New Channel Merging Methods for Multi-DoF Force Prediction of Finger Contractions","authors":"Yuyang Chen, Xinyu Jiang, C. Dai, Wei Chen","doi":"10.1109/BIOCAS.2019.8919012","DOIUrl":"https://doi.org/10.1109/BIOCAS.2019.8919012","url":null,"abstract":"Surface electromyography (sEMG) signal is one of the widely applied biological signals in the research field of the force intention prediction. However, due to the severe crosstalk issue of sEMG signals during fine hand contractions, few studies have related sEMG to multiple degree-of-freedom (DoF) force prediction of individual fingers. Accordingly, this pilot study proposed two methodsCommon Spatial Pattern (CSP) and Softmax function to solve the cross-talk issues for the estimation of EMG-force during multiple finger contractions through weighting the significance of each selected channel. High-density sEMG signals of forearm extensor muscles were obtained, and experimental data from two able-bodied subjects were analyzed. Subjects produced 1-DoF and 3-DoF forces up to 30% maximum voluntary contraction (MVC). Then, the root-mean-square values of sEMG were related to joint force. Linear EMG-force models were trained using 1-DoF trials, then tested on 3-DoF trials. Our results showed that the proposed two novel methods had lower RMS errors than the traditional methods for index, and ring with little fingers. The results suggest that 3-DoF control for individual fingers with minimal training procedure (1-DoF trials) may be feasible for practical use.","PeriodicalId":222264,"journal":{"name":"2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"96 12 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115688200","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Entropy and Complexity Assisted EEG-based Mental Workload Assessment System","authors":"Po-Kang Liu, Win-Ken Beh, Ching-Yen Shih, Yi-Ta Chen, A. Wu","doi":"10.1109/BIOCAS.2019.8919019","DOIUrl":"https://doi.org/10.1109/BIOCAS.2019.8919019","url":null,"abstract":"As the era of Brain-Computer Interfacing (BCI) arrives, computationally measuring human mental workload via Electroencephalography (EEG) signal has become a crucial research field. Conventionally, mental workload assessment studies are mainly based on time-statistics, frequency, and wavelet domain features. In this paper, we present a mental workload assessment system in discriminating high and low mental workload by extracting EEG features from two new domains: time-complexity and entropy domains features. According to statistical analysis, the result demonstrates that the Frontal and Frontal-Central are two dominating regions. In addition, by fusing the traditional and new features, we boosted the classification performance from 69% to 88%. It indicates time-complexity and entropy domain features are able to extract some non-linear characteristics of EEG, which could not be achieved by traditional approaches. We conclude that the new features are feasible to assess human mental workload, and could provide complementary information to traditional features.","PeriodicalId":222264,"journal":{"name":"2019 IEEE Biomedical Circuits and Systems Conference (BioCAS)","volume":"216 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124264579","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}