Objective
Support Vector Machines (SVM) have developed into a gold standard for accurate classification in Brain-Computer-Interfaces (BCI). The choice of the most appropriate classifier for a particular application depends on several characteristics in addition to decoding accuracy. Here we investigate the implementation of Hidden Markov Models (HMM)for online BCIs and discuss strategies to improve their performance.
Approach
We compare the SVM, serving as a reference, and HMMs for classifying discrete finger movements obtained from the Electrocorticograms of four subjects doing a finger tapping experiment. The classifier decisions are based on a subset of low-frequency time domain and high gamma oscillation features.
Main results
We show that decoding optimization between the two approaches is due to the way features are extracted and selected and less dependent on the classifier. An additional gain in HMM performance of up to 6% was obtained by introducing model constraints. Comparable accuracies of up to 90% were achieved with both SVM and HMM with the high gamma cortical response providing the most important decoding information for both techniques.
Significance
We discuss technical HMM characteristics and adaptations in the context of the presented data as well as for general BCI applications. Our findings suggest that HMMs and their characteristics are promising for efficient online brain-computer interfaces.
State-of-the-art calibration very often constructs models motivated by a real-world device. Recently, artificial neural networks (ANNs) have been proposed as a more universal, accurate, and practical black-box approach. For a galvanometric triangulation device based on two mirrors, we embrace this proposal and set it into context with other supervised data-driven approaches: 1) ridge regression; 2) support vector regression; and 3) Gaussian processes. We show that they outperform available model-based approaches and yield similar performance compared with a memorizing lookup table calibration. The results demonstrate that an off-the-shelf usage of ANNs may run into generalization problems. Restricting the space of functions using kernel-based learning has proven to be advantageous. Finally, all approaches and distinct properties are discussed in a broader context, since each application entails differently relevant requirements for its calibration. This also holds for any calibration other than the considered triangulation device.
In modern robotic radiotherapy, precise radiation of moving tumors is possible by tracking external optical surrogates. The surrogates are used to compensate for time delays and to predict internal landmarks using a correlation model. The correlation depends significantly on the surrogate position and breathing characteristics of the patient. In this context, we aim to increase the accuracy and robustness of prediction and correlation models by using a multi-modal sensor setup. Here, we evaluate the correlation coefficient of a strain belt, an acceleration and temperature sensor (air flow) with respect to external optical sensors and one internal landmark in the liver, measured by 3D ultrasound. The focus of this study is the influence of breathing artefacts, like coughing and harrumphing. Evaluating seven subjects, we found a strong decrease of the correlation for all modalities in case of artefacts. The results indicate that no precise motion compensation during these times is possible. Overall, we found that apart from the optical markers, the strain belt and temperature sensor data show the best correlation to external and internal motion.
Immobilization and marker-based motion tracking in radiation therapy often cause decreased patient comfort. However, the more comfortable alternative of optical surface tracking is highly inaccurate due to missing point-to-point correspondences between subsequent point clouds as well as elastic deformation of soft tissue. In this study, we present a proof of concept for measuring subcutaneous features with a laser scanner setup focusing on the skin thickness as additional input for high accuracy optical surface tracking. Using Monte-Carlo simulations for multi-layered tissue, we show that informative features can be extracted from the simulated tissue reflection by integrating intensities within concentric ROIs around the laser spot center. Training a regression model with a simulated data set identifies patterns that allow for predicting skin thickness with a root mean square error of down to 18 µm. Different approaches to compensate for varying observation angles were shown to yield errors still below 90 µm. Finally, this initial study provides a very promising proof of concept and encourages research towards a practical prototype.
Abstract. In modern robotic radiation therapy, tumor movements due to respiration can be compensated. The accuracy of these methods can be increased by time series prediction of external optical surrogates. An algorithm based on relevance vector machines (RVM) is introduced. We evaluate RVM with linear and nonlinear basis functions on a real patient data set containing 304 motion traces and compare it with a wavelet based least mean square algorithm (wLMS), the best algorithm for this data set so far. Linear RVM outperforms wLMS significantly and increases the prediction accuracy for 80.3 % of the data. We show that real time prediction is possible in case of linear RVM and discuss how the predicted variance can be used to construct promising hybrid algorithms, which further reduce the prediction error.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.