Christoph Dinh

A new real-time fall detection approach using fuzzy logic and a neural network

A real-time fall detection system monitors the daily activity of especially elderly people to enlist someones help as fast as possible in case of emergency. This paper presents a new real-time fall detection algorithm using a single commercial accelerometer. After transforming the acceleration data from Cartesian coordinates to spherical coordinates, the main part of the algorithm is based on a fuzzy logic inference system and a neural network. These methods allow both the integration of specific expert knowledge about typical falls as well as generalization ability. In order to compare the achieved performance of the method to those of literature, four fall scenarios (forward, backward, sideward and collapse) were performed and evaluated in a laboratory trial with, in the first instance, 5 test subjects. The average sensitivity of those four fall scenarios reached 94% and the false positive rate was about 0.35%. These results show that one single accelerometer is completely sufficient to implement a reliable fall detection system and, furthermore, that knowledge based methods are a suitable alternative to standard pattern recognition methods.

Real-Time MEG Source Localization Using Regional Clustering

With its millisecond temporal resolution, Magnetoencephalography (MEG) is well suited for real-time monitoring of brain activity. Real-time feedback allows the adaption of the experiment to the subject’s reaction and increases time efficiency by shortening acquisition and off-line analysis. Two formidable challenges exist in real-time analysis: the low signal-to-noise ratio (SNR) and the limited time available for computations. Since the low SNR reduces the number of distinguishable sources, we propose an approach which downsizes the source space based on a cortical atlas and allows to discern the sources in the presence of noise. Each cortical region is represented by a small set of dipoles, which is obtained by a clustering algorithm. Using this approach, we adapted dynamic statistical parametric mapping for real-time source localization. In terms of point spread and crosstalk between regions the proposed clustering technique performs better than selecting spatially evenly distributed dipoles. We conducted real-time source localization on MEG data from an auditory experiment. The results demonstrate that the proposed real-time method localizes sources reliably in the superior temporal gyrus. We conclude that real-time source estimation based on MEG is a feasible, useful addition to the standard on-line processing methods, and enables feedback based on neural activity during the measurements.

Mne-X: MEG/EEG Real-Time Acquisition, Real-Time Processing, and Real-Time Source Localization Framework

Providing millisecond-temporal resolution for non-invasive mapping of human brain functions, Magneto/Electroencephalography (MEG/EEG) is predestined to monitor brain activity in real-time. While data analysis to date is mostly done subsequent to the acquistion process we introduce here an acquisition and real-time analysis application. Online feedback allows the adaption of the experiment to the subject’s reaction creating a whole set of new options and increasing time efficiency by shortening acquisition and offline analysis. To build a standalone application, we first designed MNE-CPP a cross-platform open source Qt5 C++ library, which implements the validated parts of our scripting toolboxes MNE-Python/MATLAB. Based on MNE-CPP we built MNE-X, which allows realtime acquisition, processing, and source localization.

Brain Atlas based Region of Interest Selection for Real-Time Source Localization using K-Means Lead Field Clustering and RAP-MUSIC.

C. Dinh, Institute of Biomedical Engineering and Informatics, Ilmenau University of Technology, Ilmenau, Germany, christoph.dinh@tu-ilmenau.de D. Strohmeier, Institute of Biomedical Engineering and Informatics, Ilmenau University of Technology, Germany, daniel.strohmeier@tu-ilmenau.de J. Haueisen, Institute of Biomedical Engineering and Informatics, Ilmenau University of Technology, Germany, jens.haueisen@tu-ilmenau.de D. Güllmar, Department of Radiology, Jena University Hospital, Jena, Germany, daniel.guellmar@med.uni-jena.de

A GPU-accelerated Performance Optimized RAP-MUSIC Algorithm for Real-Time Source Localization

C. Dinh, Institute of Biomedical Engineering and Informatics, Ilmenau University of Technology, Ilmenau, Germany, christoph.dinh@tu-ilmenau.de J. Rühle, Department of Mathematics and Computer Sciences, Friedrich Schiller University Jena, Jena, Germany, johannes.ruehle@tu-ilmenau.de S. Bollmann, Zentrum für MR-Forschung, Kinderspital Zürich, Zurich, Switzerland, steffen.bollmann@kispi.uzh.ch J. Haueisen, Institute of Biomedical Engineering and Informatics, Ilmenau University of Technology, Germany, jens.haueisen@tu-ilmenau.de D. Güllmar, Department of Radiology, Jena University Hospital, Jena, Germany, daniel.guellmar@med.uni-jena.de

MNE Scan: Software for real-time processing of electrophysiological data

BACKGROUND Magnetoencephalography (MEG) and Electroencephalography (EEG) are noninvasive techniques to study the electrophysiological activity of the human brain. Thus, they are well suited for real-time monitoring and analysis of neuronal activity. Real-time MEG/EEG data processing allows adjustment of the stimuli to the subjects responses for optimizing the acquired information especially by providing dynamically changing displays to enable neurofeedback. NEW METHOD We introduce MNE Scan, an acquisition and real-time analysis software based on the multipurpose software library MNE-CPP. MNE Scan allows the development and application of acquisition and novel real-time processing methods in both research and clinical studies. The MNE Scan development follows a strict software engineering process to enable approvals required for clinical software. RESULTS We tested the performance of MNE Scan in several device-independent use cases, including, a clinical epilepsy study, real-time source estimation, and Brain Computer Interface (BCI) application. COMPARISON WITH EXISTING METHOD(S) Compared to existing tools we propose a modular software considering clinical software requirements expected by certification authorities. At the same time the software is extendable and freely accessible. CONCLUSION We conclude that MNE Scan is the first step in creating a device-independent open-source software to facilitate the transition from basic neuroscience research to both applied sciences and clinical applications.

Real-Time Clustered Multiple Signal Classification (RTC-MUSIC)

Magnetoencephalography (MEG) and electroencephalography provide a high temporal resolution, which allows estimation of the detailed time courses of neuronal activity. However, in real-time analysis of these data two major challenges must be handled: the low signal-to-noise ratio (SNR) and the limited time available for computations. In this work, we present real-time clustered multiple signal classification (RTC-MUSIC) a real-time source localization algorithm, which can handle low SNRs and can reduce the computational effort. It provides correlation information together with sparse source estimation results, which can, e.g., be used to identify evoked responses with high sensitivity. RTC-MUSIC clusters the forward solution based on an anatomical brain atlas and optimizes the scanning process inherent to MUSIC approaches. We evaluated RTC-MUSIC by analyzing MEG auditory and somatosensory data. The results demonstrate that the proposed method localizes sources reliably. For the auditory experiment the most dominant correlated source pair was located bilaterally in the superior temporal gyri. The highest activation in the somatosensory experiment was found in the contra-lateral primary somatosensory cortex.

Versatile synchronized real-time MEG hardware controller for large-scale fast data acquisition

Versatile controllers for accurate, fast, and real-time synchronized acquisition of large-scale data are useful in many areas of science, engineering, and technology. Here, we describe the development of a controller software based on a technique called queued state machine for controlling the data acquisition (DAQ) hardware, continuously acquiring a large amount of data synchronized across a large number of channels (>400) at a fast rate (up to 20 kHz/channel) in real time, and interfacing with applications for real-time data analysis and display of electrophysiological data. This DAQ controller was developed specifically for a 384-channel pediatric whole-head magnetoencephalography (MEG) system, but its architecture is useful for wide applications. This controller running in a LabVIEW environment interfaces with microprocessors in the MEG sensor electronics to control their real-time operation. It also interfaces with a real-time MEG analysis software via transmission control protocol/internet protocol, to control the synchronous acquisition and transfer of the data in real time from >400 channels to acquisition and analysis workstations. The successful implementation of this controller for an MEG system with a large number of channels demonstrates the feasibility of employing the present architecture in several other applications.

Online monitoring of brain activity

A general problem in the design of an EEG-BCI system is the poor quality and low robustness of the extracted features, affecting overall performance. However, BCI systems that are applicable in real-time and outside clinical settings require high performance. Therefore, we have to improve the current methods for feature extraction. In this work, we investigated EEG source reconstruction techniques to enhance the extracted features based on a linearly constrained minimum variance (LCMV) beamformer. Beamformers allow for easy incorporation of anatomical data and are applicable in real-time. A 32-channel EEG-BCI system was designed for a two-class motor imagery (MI) paradigm. We optimized a synchronous system for two untrained subjects and investigated two aspects. First, we investigated the effect of using beamformers calculated on the basis of three different head models: a template 3-layered boundary element method (BEM) head model, a 3-layered personalized BEM head model and a personalized 5-layered finite difference method (FDM) head model including white and gray matter, CSF, scalp and skull tissue. Second, we investigated the influence of how the regions of interest, areas of expected MI activity, were constructed. On the one hand, they were chosen around electrodes C3 and C4, as hand MI activity theoretically is expected here. On the other hand, they were constructed based on the actual activated regions identified by an fMRI scan. Subsequently, an asynchronous system was derived for one of the subjects and an optimal balance between speed and accuracy was found. Lastly, a real-time application was made. These systems were evaluated by their accuracy, defined as the percentage of correct left and right classifications. From the real-time application, the information transfer rate (ITR) was also determined. An accuracy of 86.60 ± 4.40% was achieved for subject 1 and 78.71 ± 0.73% for subject 2. This gives an average accuracy of 82.66 ± 2.57%. We found that the use of a personalized FDM model improved the accuracy of the system, on average 24.22% with respect to the template BEM model and on average 5.15% with respect to the personalized BEM model. Including fMRI spatial priors did not improve accuracy. Personal fine- tuning largely resolved the robustness problems arising due to the differences in head geometry and neurophysiology between subjects. A real-time average accuracy of 64.26% was reached and the maximum ITR was 6.71 bits/min. We conclude that beamformers calculated with a personalized FDM model have great potential to ameliorate feature extraction and, as a consequence, to improve the performance of real-time BCI systems.Observability of electrical potentials from deep brain sources to surface EEG remains unclear and debated among the neuroscience community. This question is particularly crucial in the temporal lobe epilepsies investigations because they involve complex (mesial and/or lateral) epileptogenic networks (Maillard et al., 2004; Bartolomei et al, 2008). At present, when mesial structures are supposed to be epileptogenic only clinical indirect evidences are used to diagnose mesial temporal lobe (MTL) epilepsy. Based on this methodology and on drug resistance evidence, surgical treatment can be proposed without the need of invasive intracerebral investigation. Reported results of this surgery demonstrate an incomplete success (70-80%; McIntosh et al. 2012) which indicate that indirect evidences of the contribution of mesial sources are not sufficient. Seven patients undergoing pre-surgical evaluation of drug resistant epilepsy were selected from a prospective series of twenty eight patients in whom simultaneous depth and surface EEG recordings had been performed since 2009. Above these patients, three had right temporal lobe (TLE) epilepsy and four left TLE. Simultaneous SEEG-EEG signals were recorded using 128 channels placed on the same acquisition system that avoids the need to synchronize both signals. Intracerebral interictal spikes (IIS) were selected on depth EEG signals blinded to EEG signals. These IIS were triggered as temporally known (T0) brain sources due to their specific waveform and the high signal to noise ratio. Then, after IIS characterization and classification, EEG signals were automatically averaged according to the T0 markers. Averaged EEG signals were finally characterized (3D mapping, duration, amplitude and statistics) and clustered using hierarchical clustering method. Overview of the data collection and analysis process is presented in figure 1. In mean in our population, 9 depth EEG electrodes and 16 surface EEG electrodes were simultaneously used. 684±186 IIS were selected by patient for a total number of spikes in our population of 4787. According to the anatomical distribution of the IIS, 21 foci were defined and classified according to three categories: mesial (limbic structures plus collateral fissure; M, 9 foci), mesial and neocortical (M+NC, 5 foci) and neocortical part of the temporal lobe (NC, 7 foci). Comparison between SEEG spikes and averaged EEG spikes on the most activated electrode at T0 was presented in table 1. Concerning 3D Map amplitude, negative pole were always seen in the temporo-basal region for both M, M+NC and NC foci and positive pole were only observed for M+NC and NC foci. Using Walsh statistical test, 8 EEG channels in mean was presented averaged amplitude at t0 statistically different of the averaged background activity. Three different clusters were fund using the hierarchical clustering method on averaged EEG signals: 1) all patients included in the M foci class and 2) all patients included in the M+NC and NC foci class and 3) one patient with an atypical brain source. Observability of deep sources with surface EEG recordings is possible. Electrical sources from mesial temporal lobe cannot be considered as closed electrical field structures. The main problem to observe signals from these deep structures concern the signal to noise ratio. Indeed, spontaneous surface spikes originated from mesial structures cannot be seen without averaging. Hierarchical clustering method and 3D map amplitude of average EEG signals at t0 seems to indicate that M contributions was different to M+NC and NC contributions. So ICA method associated with a predetermined topography constraint should detect (without the need of simultaneous depth EEG) the mesial contribution in raw EEG signals.