Bryan Matthews

Brain-computer interfaces for 1-D and 2-D cursor control: designs using volitional control of the EEG spectrum or steady-state visual evoked potentials

We have developed and tested two electroencephalogram (EEG)-based brain-computer interfaces (BCI) for users to control a cursor on a computer display. Our system uses an adaptive algorithm, based on kernel partial least squares classification (KPLS), to associate patterns in multichannel EEG frequency spectra with cursor controls. Our first BCI, Target Practice, is a system for one-dimensional device control, in which participants use biofeedback to learn voluntary control of their EEG spectra. Target Practice uses a KPLS classifier to map power spectra of 62-electrode EEG signals to rightward or leftward position of a moving cursor on a computer display. Three subjects learned to control motion of a cursor on a video display in multiple blocks of 60 trials over periods of up to six weeks. The best subjects average skill in correct selection of the cursor direction grew from 58% to 88% after 13 training sessions. Target Practice also implements online control of two artifact sources: 1) removal of ocular artifact by linear subtraction of wavelet-smoothed vertical and horizontal electrooculograms (EOG) signals, 2) control of muscle artifact by inhibition of BCI training during periods of relatively high power in the 40-64 Hz band. The second BCI, Think Pointer, is a system for two-dimensional cursor control. Steady-state visual evoked potentials (SSVEP) are triggered by four flickering checkerboard stimuli located in narrow strips at each edge of the display. The user attends to one of the four beacons to initiate motion in the desired direction. The SSVEP signals are recorded from 12 electrodes located over the occipital region. A KPLS classifier is individually calibrated to map multichannel frequency bands of the SSVEP signals to right-left or up-down motion of a cursor on a computer display. The display stops moving when the user attends to a central fixation point. As for Target Practice, Think Pointer also implements wavelet-based online removal of ocular artifact; however, in Think Pointer muscle artifact is controlled via adaptive normalization of the SSVEP. Training of the classifier requires about 3 min. We have tested our system in real-time operation in three human subjects. Across subjects and sessions, control accuracy ranged from 80% to 100% correct with lags of 1-5 s for movement initiation and turning. We have also developed a realistic demonstration of our system for control of a moving map display (http://ti.arc.nasa.gov/).

Multiple kernel learning for heterogeneous anomaly detection: algorithm and aviation safety case study

The world-wide aviation system is one of the most complex dynamical systems ever developed and is generating data at an extremely rapid rate. Most modern commercial aircraft record several hundred flight parameters including information from the guidance, navigation, and control systems, the avionics and propulsion systems, and the pilot inputs into the aircraft. These parameters may be continuous measurements or binary or categorical measurements recorded in one second intervals for the duration of the flight. Currently, most approaches to aviation safety are reactive, meaning that they are designed to react to an aviation safety incident or accident. In this paper, we discuss a novel approach based on the theory of multiple kernel learning to detect potential safety anomalies in very large data bases of discrete and continuous data from world-wide operations of commercial fleets. We pose a general anomaly detection problem which includes both discrete and continuous data streams, where we assume that the discrete streams have a causal influence on the continuous streams. We also assume that atypical sequences of events in the discrete streams can lead to off-nominal system performance. We discuss the application domain, novel algorithms, and also discuss results on real-world data sets. Our algorithm uncovers operationally significant events in high dimensional data streams in the aviation industry which are not detectable using state of the art methods.

Algorithms for speeding up distance-based outlier detection

The problem of distance-based outlier detection is difficult to solve efficiently in very large datasets because of potential quadratic time complexity. We address this problem and develop sequential and distributed algorithms that are significantly more efficient than state-of-the-art methods while still guaranteeing the same outliers. By combining simple but effective indexing and disk block accessing techniques, we have developed a sequential algorithm iOrca that is up to an order-of-magnitude faster than the state-of-the-art. The indexing scheme is based on sorting the data points in order of increasing distance from a fixed reference point and then accessing those points based on this sorted order. To speed up the basic outlier detection technique, we develop two distributed algorithms (DOoR and iDOoR) for modern distributed multi-core clusters of machines, connected on a ring topology. The first algorithm passes data blocks from each machine around the ring, incrementally updating the nearest neighbors of the points passed. By maintaining a cutoff threshold, it is able to prune a large number of points in a distributed fashion. The second distributed algorithm extends this basic idea with the indexing scheme discussed earlier. In our experiments, both distributed algorithms exhibit significant improvements compared to the state-of-the-art distributed method [13].

EEG-based estimation of mental fatigue: convergent evidence for a three-state model

Two new computational models show that the EEG distinguishes three distinct mental states ranging from alert to fatigue. State 1 indicates heightened alertness and is frequently present during the first few minutes of time on task. State 2 indicates normal alertness, often following and lasting longer than State 1. State 3 indicates fatigue, usually following State 2, but sometimes alternating with State 1 and State 2. Thirty-channel EEGs were recorded from 16 subjects who performed up to 180 min of nonstop computer-based mental arithmetic. Alert or fatigued states were independently confirmed with measures of subjects performance and pre- or post-task mood. We found convergent evidence for a three-state model of fatigue using Bayesian analysis of two different types of EEG features, both computed for single 13-s EEG epochs: 1) kernel partial least squares scores representing composite multichannel power spectra; 2) amplitude and frequency parameters of multiple single-channel autoregressive models.

Discovering Anomalous Aviation Safety Events Using Scalable Data Mining Algorithms

The worldwide civilian aviation system is one of the most complex dynamical systems created. Most modern commercial aircraft have onboard flight data recorders that record several hundred discrete ...

Detecting Abnormal Machine Characteristics in Cloud Infrastructures

In the cloud computing environment resources are accessed as services rather than as a product. Monitoring this system for performance is crucial because of typical pay-per-use packages bought by the users for their jobs. With the huge number of machines currently in the cloud system, it is often extremely difficult for system administrators to keep track of all machines using distributed monitoring programs such as Ganglia\footnote{\url{ganglia.sourceforge.net/}} which lacks system health assessment and summarization capabilities. To overcome this problem, we propose a technique for automated anomaly detection using machine performance data in the cloud. Our algorithm is entirely distributed and runs locally on each computing machine on the cloud in order to rank the machines in order of their anomalous behavior for given jobs. There is no need to centralize any of the performance data for the analysis and at the end of the analysis, our algorithm generates error reports, thereby allowing the system administrators to take corrective actions. Experiments performed on real data sets collected for different jobs validate the fact that our algorithm has a low overhead for tracking anomalous machines in a cloud infrastructure.

Measures and Models for Predicting Cognitive Fatigue

We measured multichannel EEG spectra during a continuous mental arithmetic task and created statistical learning models of cognitive fatigue for single subjects. Sixteen subjects (4 F, 18-38 y) viewed 4-digit problems on a computer, solved the problems, and pressed keys to respond (inter-trial interval = 1 s). Subjects performed until either they felt exhausted or three hours had elapsed. Pre- and post-task measures of mood (Activation Deactivation Adjective Checklist, Visual Analogue Mood Scale) confirmed that fatigue increased and energy decreased over time. We examined response times (RT); amplitudes of ERP components N1, P2, and P300, readiness potentials; and power of frontal theta and parietal alpha rhythms for change as a function of time. Mean RT rose from 6.7 s to 7.9 s over time. After controlling for or rejecting sources of artifact such as EOG, EMG, motion, bad electrodes, and electrical interference, we found that frontal theta power rose by 29% and alpha power rose by 44% over the course of the task. We used 30-channel EEG frequency spectra to model the effects of time in single subjects using a kernel partial least squares (KPLS) classifier. We classified 13-s long EEG segments as being from the first or last 15 minutes of the task, using random sub-samples of each class. Test set accuracies ranged from 91% to 100% correct. We conclude that a KPLS classifier of multichannel spectral measures provides a highly accurate model of EEG-fatigue relationships and is suitable for on-line applications to neurological monitoring.

Aircraft anomaly detection using performance models trained on fleet data

This paper describes an application of data mining technology called Distributed Fleet Monitoring (DFM) to Flight Operational Quality Assurance (FOQA) data collected from a fleet of commercial aircraft. DFM transforms the data into a list of abnormaly performing aircraft, abnormal flight-to-flight trends, and individual flight anomalies by fitting a large scale multi-level regression model to the entire data set. The model takes into account fixed effects: flight-to-flight and vehicle-to-vehicle variability. The regression parameters include aerodynamic coefficients and other aircraft performance parameters that are usually identified by aircraft manufacturers in flight tests. Using DFM, a multi-terabyte airline data set with a half million flights was processed in a few hours. The anomalies found include wrong values of computed variables such as aircraft weight and angle of attack as well as failures, biases, and trends in flight sensors and actuators. These anomalies were missed by the FOQA data exceedance monitoring currently used by the airline.

Space shuttle main propulsion system anomaly detection: A case study

The space shuttle main engine (SSME) is part of the Main Propulsion System (MPS) which is an extremely complex system containing several sub-systems and components, each of which must work precisely in order to achieve a successful mission. A critical component under study is the flow control valve (FCY) which controls the pressure of the gaseous hydrogen between the SSME and the external fuel tank. The FCV has received added attention since a Space Shuttle Mission in November 2008, where it was discovered during the mission that an anomaly had occurred in one of the three FCVs. Subsequent inspection revealed that one FCV cracked during ascent. This type of fault is of high criticality because it can lead to potentially catastrophic gaseous hydrogen leakage. A supervised learning method known as Virtual Sensors (VS), and an unsupervised learning method known as the Inductive Monitoring System (IMS) were used to detect anomalies related to the FCV in the MPS. Both algorithms identify the time of the anomaly in a multi-dimensional time series of temperatures, pressures, and control signals related to the FCV. This discovery corroborates the results of the inspection and also reveals the time at which the anomaly likely occurred. The methods were applied to data obtained from the March 2009 launch of Space Shuttle Discovery to determine whether an anomaly occurred in the same sub-system. According to our models, the FCV sub-system showed nominal behavior during ascent.

Discovery of Precursors to Adverse Events using Time Series Data.

We develop an algorithm for automatic discovery of precursors in time series data (ADOPT). In a time series setting, a precursor may be considered as any event that precedes and increases the likelihood of an adverse event. In a multivariate time series data, there are exponential number of events which makes a brute force search intractable. ADOPT works by breaking down the problem into two steps (1) inferring a model of the nominal time series (data without adverse event) by considering the nominal data to be generated by a hidden expert and (2) using the expert’s model as a benchmark to evaluate the adverse time series to identify suboptimal events as precursors. For step (1), we use a Markov Decision Process (MDP) framework where value functions and Bellman’s optimality are used to infer the expert’s actions. For step (2), we define a precursor score to evaluate a given instant of a time series by comparing its utility with that of the expert. Thus, the search for precursors is transformed to a search for sub-optimal action sequences in ADOPT. As an application case study, we use ADOPT to discover precursors to go-around events in commercial flights using real