Showing papers in "IEEE Transactions on Biomedical Engineering in 2006"
TL;DR: Improvements in the accuracy of orientation estimates are demonstrated for the proposed quaternion based extended Kalman filter, as compared with filter implementations where either the in-line calibration procedure, the adaptive mechanism for weighting the measurements of the aiding system sensors, or both are not implemented.
Abstract: In this paper, a quaternion based extended Kalman filter (EKF) is developed for determining the orientation of a rigid body from the outputs of a sensor which is configured as the integration of a tri-axis gyro and an aiding system mechanized using a tri-axis accelerometer and a tri-axis magnetometer. The suggested applications are for studies in the field of human movement. In the proposed EKF, the quaternion associated with the body rotation is included in the state vector together with the bias of the aiding system sensors. Moreover, in addition to the in-line procedure of sensor bias compensation, the measurement noise covariance matrix is adapted, to guard against the effects which body motion and temporary magnetic disturbance may have on the reliability of measurements of gravity and earth's magnetic field, respectively. By computer simulations and experimental validation with human hand orientation motion signals, improvements in the accuracy of orientation estimates are demonstrated for the proposed EKF, as compared with filter implementations where either the in-line calibration procedure, the adaptive mechanism for weighting the measurements of the aiding system sensors, or both are not implemented.
852 citations
TL;DR: A recognition approach is proposed based on the extracted frequency features for an SSVEP-based brain computer interface (BCI) that were higher than those using a widely used fast Fourier transform (FFT)-based spectrum estimation method.
Abstract: Canonical correlation analysis (CCA) is applied to analyze the frequency components of steady-state visual evoked potentials (SSVEP) in electroencephalogram (EEG). The essence of this method is to extract a narrowband frequency component of SSVEP in EEG. A recognition approach is proposed based on the extracted frequency features for an SSVEP-based brain computer interface (BCI). Recognition Results of the approach were higher than those using a widely used fast Fourier transform (FFT)-based spectrum estimation method
826 citations
TL;DR: Experimental and simulation results suggest that the main sources of gaze estimation errors are the discrepancy between the shape of real corneas and the spherical corneal shape assumed in the general theory, and the noise in the estimation of the centers of the pupil and corNEal reflections.
Abstract: This paper presents a general theory for the remote estimation of the point-of-gaze (POG) from the coordinates of the centers of the pupil and corneal reflections. Corneal reflections are produced by light sources that illuminate the eye and the centers of the pupil and corneal reflections are estimated in video images from one or more cameras. The general theory covers the full range of possible system configurations. Using one camera and one light source, the POG can be estimated only if the head is completely stationary. Using one camera and multiple light sources, the POG can be estimated with free head movements, following the completion of a multiple-point calibration procedure. When multiple cameras and multiple light sources are used, the POG can be estimated following a simple one-point calibration procedure. Experimental and simulation results suggest that the main sources of gaze estimation errors are the discrepancy between the shape of real corneas and the spherical corneal shape assumed in the general theory, and the noise in the estimation of the centers of the pupil and corneal reflections. A detailed example of a system that uses the general theory to estimate the POG on a computer screen is presented.
646 citations
TL;DR: Results of in vivo experiments that confirm the feasibility of a new minimally invasive method for tissue ablation, irreversible electroporation (IRE), and demonstrates that IRE can become an effective method for nonthermal tissueAblation requiring no drugs.
Abstract: This paper reports results of in vivo experiments that confirm the feasibility of a new minimally invasive method for tissue ablation, irreversible electroporation (IRE). Electroporation is the generation of a destabilizing electric potential across biological membranes that causes the formation of nanoscale defects in the lipid bilayer. In IRE, these defects are permanent and lead to cell death. This paper builds on our earlier theoretical work and demonstrates that IRE can become an effective method for nonthermal tissue ablation requiring no drugs. To test the capability of IRE pulses to ablate tissue in a controlled fashion, we subjected the livers of male Sprague-Dawley rats to a single 20-ms-long square pulse of 1000 V/cm, which calculations had predicted would cause nonthermal IRE. Three hours after the pulse, treated areas in perfusion-fixed livers exhibited microvascular occlusion, endothelial cell necrosis, and diapedeses, resulting in ischemic damage to parenchyma and massive pooling of erythrocytes in sinusoids. However, large blood vessel architecture was preserved. Hepatocytes displayed blurred cell borders, pale eosinophilic cytoplasm, variable pyknosis and vacuolar degeneration. Mathematical analysis indicates that this damage was primarily nonthermal in nature and that sharp borders between affected and unaffected regions corresponded to electric fields of 300-500 V/cm.
530 citations
TL;DR: The results of this study show that the performance of a patient adaptable classifier increases with the amount of training of the system on the local record and the performance can be significantly boosted with a small amount of adaptation.
Abstract: An adaptive system for the automatic processing of the electrocardiogram (ECG) for the classification of heartbeats into one of the five beat classes recommended by ANSI/AAMI EC57:1998 standard is presented. The heartbeat classification system processes an incoming recording with a global-classifier to produce the first set of beat annotations. An expert then validates and if necessary corrects a fraction of the beats of the recording. The system then adapts by first training a local-classifier using the newly annotated beats and combines this with the global-classifier to produce an adapted classification system. The adapted system is then used to update beat annotations. The results of this study show that the performance of a patient adaptable classifier increases with the amount of training of the system on the local record. Crucially, the performance of the system can be significantly boosted with a small amount of adaptation even when all beats used for adaptation are from a single class. This study illustrates the ability to provide highly beneficial automatic arrhythmia monitoring and is an improvement on previously reported results for automated heartbeat classification systems
472 citations
TL;DR: A new method for muscle artifact removal in EEG is presented, based on canonical correlation analysis (CCA) as a blind source separation (BSS) technique, which outperformed a low-pass filter with different cutoff frequencies and an independent component analysis (ICA)-based technique for muscle artifacts removal.
Abstract: The electroencephalogram (EEG) is often contaminated by muscle artifacts. In this paper, a new method for muscle artifact removal in EEG is presented, based on canonical correlation analysis (CCA) as a blind source separation (BSS) technique. This method is demonstrated on a synthetic data set. The method outperformed a low-pass filter with different cutoff frequencies and an independent component analysis (ICA)-based technique for muscle artifact removal. In addition, the method is applied on a real ictal EEG recording contaminated with muscle artifacts. The proposed method removed successfully the muscle artifact without altering the recorded underlying ictal activity
465 citations
TL;DR: It is concluded that, in the absence of applied currents, propagating action potentials on the scale of a human heart can be studied with a monodomain model.
Abstract: A bidomain reaction-diffusion model of the human heart was developed, and potentials resulting from normal depolarization and repolarization were compared with results from a compatible monodomain model. Comparisons were made for an empty isolated heart and for a heart with fluid-filled ventricles. Both sinus rhythm and ectopic activation were simulated. The bidomain model took 2 days on 32 processors to simulate a complete cardiac cycle. Differences between monodomain and bidomain results were extremely small, even for the extracellular potentials, which in case of the monodomain model were computed with a high-resolution forward model. Propagation of activation was 2% faster in the bidomain model than in the monodomain model. Electrograms computed with monodomain and bidomain models were visually indistinguishable. We conclude that, in the absence of applied currents, propagating action potentials on the scale of a human heart can be studied with a monodomain model
440 citations
TL;DR: An automated system that integrates a series of advanced analysis methods that can be used to segment, classify, and track individual cells in a living cell population over a few days is presented.
Abstract: Quantitative measurement of cell cycle progression in individual cells over time is important in understanding drug treatment effects on cancer cells. Recent advances in time-lapse fluorescence microscopy imaging have provided an important tool to study the cell cycle process under different conditions of perturbation. However, existing computational imaging methods are rather limited in analyzing and tracking such time-lapse datasets, and manual analysis is unreasonably time-consuming and subject to observer variances. This paper presents an automated system that integrates a series of advanced analysis methods to fill this gap. The cellular image analysis methods can be used to segment, classify, and track individual cells in a living cell population over a few days. Experimental results show that the proposed method is efficient and effective in cell tracking and phase identification.
403 citations
TL;DR: The motion artifacts were reduced by exploiting the quasi-periodicity of the PPG signal and the independence between the P PG and the motion artifact signals by the combination of independent component analysis and block interleaving with low-pass filtering.
Abstract: Removing the motion artifacts from measured photoplethysmography (PPG) signals is one of the important issues to be tackled for the accurate measurement of arterial oxygen saturation during movement. In this paper, the motion artifacts were reduced by exploiting the quasi-periodicity of the PPG signal and the independence between the PPG and the motion artifact signals. The combination of independent component analysis and block interleaving with low-pass filtering can reduce the motion artifacts under the condition of general dual-wavelength measurement. Experiments with synthetic and real data were performed to demonstrate the efficacy of the proposed algorithm.
393 citations
TL;DR: This approach combined wavelet-transformed ECG waves with timing information as a feature set for classification, and used select waveforms of 18 files of the MIT/BIH arrhythmia database for training the neural-network classifier.
Abstract: Automatic electrocardiogram (ECG) beat classification is essential to timely diagnosis of dangerous heart conditions. Specifically, accurate detection of premature ventricular contractions (PVCs) is imperative to prepare for the possible onset of life-threatening arrhythmias. Although many groups have developed highly accurate algorithms for detecting PVC beats, results have generally been limited to relatively small data sets. Additionally, many of the highest classification accuracies (>90%) have been achieved in experiments where training and testing sets overlapped significantly. Expanding the overall data set greatly reduces overall accuracy due to significant variation in ECG morphology among different patients. As a result, we believe that morphological information must be coupled with timing information, which is more constant among patients, in order to achieve high classification accuracy for larger data sets. With this approach, we combined wavelet-transformed ECG waves with timing information as our feature set for classification. We used select waveforms of 18 files of the MIT/BIH arrhythmia database, which provides an annotated collection of normal and arrhythmic beats, for training our neural-network classifier. We then tested the classifier on these 18 training files as well as 22 other files from the database. The accuracy was 95.16% over 93,281 beats from all 40 files, and 96.82% over the 22 files outside the training set in differentiating normal, PVC, and other beats
383 citations
TL;DR: A novel technique that allows the simultaneous optimization of a spatial and a spectral filter enhancing discriminability rates of multichannel EEG single-trials is presented.
Abstract: Brain-computer interface (BCI) systems create a novel communication channel from the brain to an output device by bypassing conventional motor output pathways of nerves and muscles. Therefore they could provide a new communication and control option for paralyzed patients. Modern BCI technology is essentially based on techniques for the classification of single-trial brain signals. Here we present a novel technique that allows the simultaneous optimization of a spatial and a spectral filter enhancing discriminability rates of multichannel EEG single-trials. The evaluation of 60 experiments involving 22 different subjects demonstrates the significant superiority of the proposed algorithm over to its classical counterpart: the median classification error rate was decreased by 11%. Apart from the enhanced classification, the spatial and/or the spectral filter that are determined by the algorithm can also be used for further analysis of the data, e.g., for source localization of the respective brain rhythms
TL;DR: An investigation aimed at gaining a better understanding of the LZ complexity itself and its interpretability as a biomedical signal analysis technique indicates that LZ is particularly useful as a scalar metric to estimate the bandwidth of random processes and the harmonic variability in quasi-periodic signals.
Abstract: Lempel-Ziv complexity (LZ) and derived LZ algorithms have been extensively used to solve information theoretic problems such as coding and lossless data compression. In recent years, LZ has been widely used in biomedical applications to estimate the complexity of discrete-time signals. Despite its popularity as a complexity measure for biosignal analysis, the question of LZ interpretability and its relationship to other signal parameters and to other metrics has not been previously addressed. We have carried out an investigation aimed at gaining a better understanding of the LZ complexity itself, especially regarding its interpretability as a biomedical signal analysis technique. Our results indicate that LZ is particularly useful as a scalar metric to estimate the bandwidth of random processes and the harmonic variability in quasi-periodic signals
TL;DR: A novel real-time electromyogram (EMG) pattern recognition for the control of a multifunction myoelectric hand from four channel EMG signals using a wavelet packet transform and a linear-nonlinear feature projection composed of principal components analysis (PCA) and a self-organizing feature map (SOFM).
Abstract: This paper proposes a novel real-time electromyogram (EMG) pattern recognition for the control of a multifunction myoelectric hand from four channel EMG signals. To extract a feature vector from the EMG signal, we use a wavelet packet transform that is a generalized version of wavelet transform. For dimensionality reduction and nonlinear mapping of the features, we also propose a linear-nonlinear feature projection composed of principal components analysis (PCA) and a self-organizing feature map (SOFM). The dimensionality reduction by PCA simplifies the structure of the classifier and reduces processing time for the pattern recognition. The nonlinear mapping by SOFM transforms the PCA-reduced features into a new feature space with high class separability. Finally, a multilayer perceptron (MLP) is used as the classifier. Using an analysis of class separability by feature projections, we show that the recognition accuracy depends more on the class separability of the projected features than on the MLP's class separation ability. Consequently, the proposed linear-nonlinear projection method improves class separability and recognition accuracy. We implement a real-time control system for a multifunction virtual hand. Our experimental results show that all processes, including virtual hand control, are completed within 125 ms, and the proposed method is applicable to real-time myoelectric hand control without an operational time delay
TL;DR: Using the F-Ratio and Fisher's discriminant ratio, it will be demonstrated that the detection of voice impairments can be performed using both mel cepstral vectors and their first derivative, ignoring the second derivative.
Abstract: Voice diseases have been increasing dramatically in recent times due mainly to unhealthy social habits and voice abuse. These diseases must be diagnosed and treated at an early stage, especially in the case of larynx cancer. It is widely recognized that vocal and voice diseases do not necessarily cause changes in voice quality as perceived by a listener. Acoustic analysis could be a useful tool to diagnose this type of disease. Preliminary research has shown that the detection of voice alterations can be carried out by means of Gaussian mixture models and short-term mel cepstral parameters complemented by frame energy together with first and second derivatives. This paper, using the F-Ratio and Fisher's discriminant ratio, will demonstrate that the detection of voice impairments can be performed using both mel cepstral vectors and their first derivative, ignoring the second derivative
TL;DR: These tests demonstrated the feasibility of SMP actuation by inductive heating and rapid and uniform heating was achieved in complex device geometries and particle loading up to 10% volume content did not interfere with the shape recovery of the SMP.
Abstract: Presently, there is interest in making medical devices such as expandable stents and intravascular microactuators from shape memory polymer (SMP). One of the key challenges in realizing SMP medical devices is the implementation of a safe and effective method of thermally actuating various device geometries in vivo. A novel scheme of actuation by Curie-thermoregulated inductive heating is presented. Prototype medical devices made from SMP loaded with nickel zinc ferrite ferromagnetic particles were actuated in air by applying an alternating magnetic field to induce heating. Dynamic mechanical thermal analysis was performed on both the particle-loaded and neat SMP materials to assess the impact of the ferrite particles on the mechanical properties of the samples. Calorimetry was used to quantify the rate of heat generation as a function of particle size and volumetric loading of ferrite particles in the SMP. These tests demonstrated the feasibility of SMP actuation by inductive heating. Rapid and uniform heating was achieved in complex device geometries and particle loading up to 10% volume content did not interfere with the shape recovery of the SMP
TL;DR: This paper presents an original hidden Markov model (HMM) approach for online beat segmentation and classification of electrocardiograms, and the results obtained validate the approach for real world application.
Abstract: This paper presents an original hidden Markov model (HMM) approach for online beat segmentation and classification of electrocardiograms. The HMM framework has been visited because of its ability of beat detection, segmentation and classification, highly suitable to the electrocardiogram (ECG) problem. Our approach addresses a large panel of topics some of them never studied before in other HMM related works: waveforms modeling, multichannel beat segmentation and classification, and unsupervised adaptation to the patient's ECG. The performance was evaluated on the two-channel QT database in terms of waveform segmentation precision, beat detection and classification. Our waveform segmentation results compare favorably to other systems in the literature. We also obtained high beat detection performance with sensitivity of 99.79% and a positive predictivity of 99.96%, using a test set of 59 recordings. Moreover, premature ventricular contraction beats were detected using an original classification strategy. The results obtained validate our approach for real world application
TL;DR: The recent availability of Ra data is utilized, estimated with a model-independent multiple tracer technique, to formulate a system model of intestinal glucose absorption, which has important potential both in simulation contexts and in clinical studies to quantitatively characterize possible impairment of glucose absorption in particular populations such as elderly and diabetic individuals.
Abstract: A reliable model of glucose absorption after oral ingestion may facilitate simulation as well as pathophysiological studies. One of the difficulties for the development and quality assessment of such models has been the lack of gold standard data for their validation. Thus, while data on plasma concentrations of glucose are available, the rates of appearance in plasma of ingested glucose (Ra) were not available to develop such models. Here we utilize the recent availability of Ra data, estimated with a model-independent multiple tracer technique, to formulate a system model of intestinal glucose absorption. Two published and two new models are tested on this new data set. One of the two new models performed best: it is nonlinear, describes the Ra data well and its parameters are estimated with good precision. This model has important potential both in simulation contexts, e.g., it can be incorporated in whole-body models of the glucose regulatory system, as well as in physiological and clinical studies to quantitatively characterize possible impairment of glucose absorption in particular populations such as elderly and diabetic individuals
TL;DR: MAMI exhibits higher resolution, lower sidelobes, and better noise and interference rejection capabilities than the existing approaches, and is demonstrated via a simulated 3-D breast model and several numerical examples.
Abstract: We propose a new multistatic adaptive microwave imaging (MAMI) method for early breast cancer detection. MAMI is a two-stage robust Capon beamforming (RCB) based image formation algorithm. MAMI exhibits higher resolution, lower sidelobes, and better noise and interference rejection capabilities than the existing approaches. The effectiveness of using MAMI for breast cancer detection is demonstrated via a simulated 3-D breast model and several numerical examples
TL;DR: It is shown that the various algorithms used for the calculation of entropy and complexity actually measure different properties of the signal, and ShEn tends to increase while the other tested measures decrease with deepening sedation.
Abstract: Entropy and complexity of the electroencephalogram (EEG) have recently been proposed as measures of depth of anesthesia and sedation. Using surrogate data of predefined spectrum and probability distribution we show that the various algorithms used for the calculation of entropy and complexity actually measure different properties of the signal. The tested methods, Shannon entropy (ShEn), spectral entropy, approximate entropy (ApEn), Lempel-Ziv complexity (LZC), and Higuchi fractal dimension (HFD) are then applied to the EEG signal recorded during sedation in the intensive care unit (ICU). It is shown that the applied measures behave in a different manner when compared to clinical depth of sedation score the Ramsay score. ShEn tends to increase while the other tested measures decrease with deepening sedation. ApEn, LZC, and HFD are highly sensitive to the presence of high-frequency components in the EEG signal.
TL;DR: This study shows the feasibility of the method for long-term, convenient, everyday use of ECG measurement without direct conductive contact with the skin while subjects sat on a chair wearing normal clothes.
Abstract: For the purpose of long-term, everyday electrocardiogram (ECG) monitoring, we present a convenient method of ECG measurement without direct conductive contact with the skin while subjects sat on a chair wearing normal clothes. Measurements were made using electrodes attached to the back of a chair, high-input-impedance amplifiers mounted on the electrodes, and a large ground-plane placed on the chair seat. ECGs were obtained by the presented method for several types of clothing and compared to ECGs obtained from conventional measurement using Ag-AgCl electrodes. Motion artifacts caused by usual desk works were investigated. This study shows the feasibility of the method for long-term, convenient, everyday use
TL;DR: The MM proved to be a powerful and compact mathematical model for decomposing a complex task such as laparoscopic suturing and an objective learning curve was defined based on measuring quantitative statistical distance between MM of experts and residents at different levels of training.
Abstract: Minimally invasive surgery (MIS) involves a multidimensional series of tasks requiring a synthesis between visual information and the kinematics and dynamics of the surgical tools. Analysis of these sources of information is a key step in defining objective criteria for characterizing surgical performance. The Blue DRAGON is a new system for acquiring the kinematics and the dynamics of two endoscopic tools synchronized with the endoscopic view of the surgical scene. Modeling the process of MIS using a finite state model [Markov model (MM)] reveals the internal structure of the surgical task and is utilized as one of the key steps in objectively assessing surgical performance. The experimental protocol includes tying an intracorporeal knot in a MIS setup performed on an animal model (pig) by 30 surgeons at different levels of training including expert surgeons. An objective learning curve was defined based on measuring quantitative statistical distance (similarity) between MM of experts and MM of residents at different levels of training. The objective learning curve was similar to that of the subjective performance analysis. The MM proved to be a powerful and compact mathematical model for decomposing a complex task such as laparoscopic suturing. Systems like surgical robots or virtual reality simulators in which the kinematics and the dynamics of the surgical tool are inherently measured may benefit from incorporation of the proposed methodology.
TL;DR: Results show that in the larger blood vessels where the diameter of the microdevices could be as large as a couple a millimeters, the few tens of mT/m of gradients required for displacement against the relatively high blood flow rate is well within the limits of clinical MRI systems.
Abstract: This paper reports the use of a magnetic resonance imaging (MRI) system to propel a ferromagnetic core. The concept was studied for future development of microdevices designed to perform minimally invasive interventions in remote sites accessible through the human cardiovascular system. A mathematical model is described taking into account various parameters such as the size of blood vessels, the velocities and viscous properties of blood, the magnetic properties of the materials, the characteristics of MRI gradient coils, as well as the ratio between the diameter of a spherical core and the diameter of the blood vessels. The concept of magnetic propulsion by MRI is validated experimentally by measuring the flow velocities that magnetized spheres (carbon steel 1010/1020) can withstand inside cylindrical tubes under the different magnetic forces created with a Siemens Magnetom Vision 1.5 T MRI system. The differences between the velocities predicted by the theoretical model and the experiments are approximately 10%. The results indicate that with the technology available today for gradient coils used in clinical MRI systems, it is possible to generate sufficient gradients to propel a ferromagnetic sphere in the larger sections of the arterial system. In other words, the results show that in the larger blood vessels where the diameter of the microdevices could be as large as a couple a millimeters, the few tens of mT/m of gradients required for displacement against the relatively high blood flow rate is well within the limits of clinical MRI systems. On the other hand, although propulsion of a ferromagnetic core with diameter of /spl sim/600 /spl mu/m may be possible with existing clinical MRI systems, gradient amplitudes of several T/m would be required to propel a much smaller ferromagnetic core in small vessels such as capillaries and additional gradient coils would be required to upgrade existing MRI systems for operations at such a scale.
TL;DR: The proposed technique provides a solution to fusing the data of gyroscopes and accelerometers that yields stable and drift-free estimates of segment orientation and is portable, easily mountable, and can be used for long term monitoring without hindrance to natural activities.
Abstract: A new method of estimating lower limbs orientations using a combination of accelerometers and gyroscopes is presented. The model is based on estimating the accelerations of ankle and knee joints by placing virtual sensors at the centers of rotation. The proposed technique considers human locomotion and biomechanical constraints, and provides a solution to fusing the data of gyroscopes and accelerometers that yields stable and drift-free estimates of segment orientation. The method was validated by measuring lower limb motions of eight subjects, walking at three different speeds, and comparing the results with a reference motion measurement system. The results are very close to those of the reference system presenting very small errors (Shank: rms=1.0, Thigh: rms=1.6/spl deg/) and excellent correlation coefficients (Shank: r=0.999, Thigh: r=0.998). Technically, the proposed ambulatory system is portable, easily mountable, and can be used for long term monitoring without hindrance to natural activities. Finally, a gait analysis tool was designed to visualize the motion data as synthetic skeletons performing the same actions as the subjects.
TL;DR: Simulations, as well as experiments with phantoms and tissue, indicate that TDPE is capable of reliably estimating tissue displacement and strain over a large range of displacements in real time.
Abstract: In this paper we introduce a new speckle tracking method that is based on the standard time-domain cross correlation strain estimation (TDE). We call this method time-domain cross-correlation with prior estimates (TDPE), because it uses prior displacement estimates of neighboring windows to speed up computation. TDPE has all the advantages of TDE, but is much faster. Simulations, as well as experiments with phantoms and tissue, indicate that TDPE is capable of reliably estimating tissue displacement and strain over a large range of displacements in real time. The computational efficiency of TDPE is compared with current time-efficient methods that have been used in real time strain imaging systems. The results show that TDPE is the most time efficient algorithm to date, and is roughly 10 times faster than the TDE. The implementation of TDPE on an Ultrasonix RP500 ultrasound machine runs at 30 fps for strain images of 16 000 pixels
TL;DR: The myoprocessor seems an adequate model, sufficiently robust for further integration into the exoskeleton control system, and high correlation between joint moment predictions of the model and the measured data is indicated.
Abstract: Exoskeleton robots are promising assistive/rehabilitative devices that can help people with force deficits or allow the recovery of patients who have suffered from pathologies such as stroke. The key component that allows the user to control the exoskeleton is the human machine interface (HMI). Setting the HMI at the neuro-muscular level may lead to seamless integration and intuitive control of the exoskeleton arm as a natural extension of the human body. At the core of the exoskeleton HMI there is a model of the human muscle, the "myoprocessor," running in real-time and in parallel to the physiological muscle, that predicts joint torques as a function of the joint kinematics and neural activation levels. This paper presents the development of myoprocessors for the upper limb based on the Hill phenomenological muscle model. Genetic algorithms are used to optimize the internal parameters of the myoprocessors utilizing an experimental database that provides inputs to the model and allows for performance assessment. The results indicate high correlation between joint moment predictions of the model and the measured data. Consequently, the myoprocessor seems an adequate model, sufficiently robust for further integration into the exoskeleton control system
TL;DR: It is concluded that the cardiorespiratory signals provide moderate sleep-staging accuracy, however, features exhibit significant subject dependence which presents potential limits to the use of these signals in a general subject-independent sleep staging system.
Abstract: A cardiorespiratory-based automatic sleep staging system for subjects with sleep-disordered breathing is described. A simplified three-state system is used: Wakefulness (W), rapid eye movement (REM) sleep (R), and non-REM sleep (S). The system scores the sleep stages in standard 30-s epochs. A number of features associated with the epoch RR-intervals, an inductance plethysmography estimate of rib cage respiratory effort, and an electrocardiogram-derived respiration (EDR) signal were investigated. A subject-specific quadratic discriminant classifier was trained, randomly choosing 20% of the subject's epochs (in appropriate proportions of W, S and R) as the training data. The remaining 80% of epochs were presented to the classifier for testing. An estimated classification accuracy of 79% (Cohen's /spl kappa/ value of 0.56) was achieved. When a similar subject-independent classifier was trained, using epochs from all other subjects as the training data, a drop in classification accuracy to 67% (/spl kappa/=0.32) was observed. The subjects were further broken in groups of low apnoea-hypopnea index (AHI) and high AHI and the experiments repeated. The subject-specific classifier performed better on subjects with low AHI than high AHI; the performance of the subject-independent classifier is not correlated with AHI. For comparison an electroencephalograms (EEGs)-based classifier was trained utilizing several standard EEG features. The subject-specific classifier yielded an accuracy of 87% (/spl kappa/=0.75), and an accuracy of 84% (/spl kappa/=0.68) was obtained for the subject-independent classifier, indicating that EEG features are quite robust across subjects. We conclude that the cardiorespiratory signals provide moderate sleep-staging accuracy, however, features exhibit significant subject dependence which presents potential limits to the use of these signals in a general subject-independent sleep staging system.
TL;DR: An advanced model-based control technique for regulating the blood glucose for patients with Type 1 diabetes is presented and is expected to simplify the insulin delivery mechanism, thereby enhancing the quality of life of the patient.
Abstract: An advanced model-based control technique for regulating the blood glucose for patients with Type 1 diabetes is presented. The optimal insulin delivery rate is obtained off-line as an explicit function of the current blood glucose concentration of the patient by using novel parametric programming algorithms, developed at Imperial College London. The implementation of the optimal insulin delivery rate, therefore, requires simple function evaluation and minimal on-line computations. The proposed framework also addresses the uncertainty in the model due to interpatient and intrapatient variability by identifying the model parameters which ensure that a feasible control law can be obtained. The developments reported in this paper are expected to simplify the insulin delivery mechanism, thereby enhancing the quality of life of the patient
TL;DR: The use of hidden Markov models (HMMs) to automatically detect cough sounds from continuous ambulatory recordings and the results suggest that HMMs can be applied to the detection of coughSounds from ambulatory patients.
Abstract: Cough is a common symptom of many respiratory diseases. The evaluation of its intensity and frequency of occurrence could provide valuable clinical information in the assessment of patients with chronic cough. In this paper we propose the use of hidden Markov models (HMMs) to automatically detect cough sounds from continuous ambulatory recordings. The recording system consists of a digital sound recorder and a microphone attached to the patient's chest. The recognition algorithm follows a keyword-spotting approach, with cough sounds representing the keywords. It was trained on 821 min selected from 10 ambulatory recordings, including 2473 manually labeled cough events, and tested on a database of nine recordings from separate patients with a total recording time of 3060 min and comprising 2155 cough events. The average detection rate was 82% at a false alarm rate of seven events/h, when considering only events above an energy threshold relative to each recording's average energy. These results suggest that HMMs can be applied to the detection of cough sounds from ambulatory patients. A postprocessing stage to perform a more detailed analysis on the detected events is under development, and could allow the rejection of some of the incorrectly detected events.
TL;DR: A viable fully on-line adaptive brain computer interface (BCI) is introduced that was based on motor imagery, the feature extraction was performed with an adaptive autoregressive model and the classifier was an adaptive quadratic discriminant analysis.
Abstract: A viable fully on-line adaptive brain computer interface (BCI) is introduced. On-line experiments with nine naive and able-bodied subjects were carried out using a continuously adaptive BCI system. The data were analyzed and the viability of the system was studied. The BCI was based on motor imagery, the feature extraction was performed with an adaptive autoregressive model and the classifier used was an adaptive quadratic discriminant analysis. The classifier was on-line updated by an adaptive estimation of the information matrix (ADIM). The system was also able to provide continuous feedback to the subject. The success of the feedback was studied analyzing the error rate and mutual information of each session and this analysis showed a clear improvement of the subject's control of the BCI from session to session.