Rudolph L. Mappus

Applications for Brain-Computer Interfaces

Brain-computer Interfaces (BCIs) have been studied for nearly thirty years, with the primary motivation of providing assistive technologies for people with very severe motor disabilities. The slow speeds, high error rate, susceptibility to artifact, and complexity of BCI systems have been challenges for implementing workable real-world systems. However, recent advances in computing and bio-sensing technologies have improved the outlook for BCI applications, making them promising not only as assistive technologies but also for mainstream applications. This chapter presents a survey of applications for BCI systems, both historical and recent, in order to characterize the broad range of possibilities for neural control.

An fNIR based BMI for letter construction using continuous control

A long term goal of assistive technology research is to build creative expression applications where subjects can extemporaneously express themselves. Sketch drawing is one form of creative expression. In this work, we demonstrate the usability of a brain-machine interface (BMI) for expression using a letter drawing task. We describe empirical results that represent a first step toward assistive applications for creative expression.

Continuous Control Paradigms for Direct Brain Interfaces

Direct Brain Interfaces (DBIs) offer great possibilities for people with severe disabilities to communicate and control their environments. However, many DBI systems implement discrete selection, such as choosing a letter from an alphabet, which offers limited control over certain tasks. Continuous control is important for applications such as driving a wheelchair or drawing for creative expression. This paper describes two projects currently underway at the Georgia Tech BrainLab exploring continuous control interface paradigms for an EEG-based approach centered on responses from visual cortex, and functional near Infrared (fNIR) imaging of the language center of the brain.

Neural Control Interfaces

The control interface is the primary component of a Brain-Computer Interface (BCI) system that provides user interaction. The control interface supplies cues for performing mental tasks, reports system status and task feedback, and often displays representations of the user’s brain signals. Control interfaces play a significant role in determining the usability of a BCI, and some of the traditional human-computer interaction design methods apply. However, the very specialized input methods and display paradigms of a BCI require consideration to create optimal usability for a BCI system. This chapter outlines some of the issues and challenges that make designing control interfaces for BCIs unique.

Using neural networks to assess flight deck human–automation interaction

Abstract The increased complexity and interconnectivity of flight deck automation has made the prediction of human–automation interaction (HAI) difficult and has resulted in a number of accidents and incidents. There is a need to develop objective and robust methods by which the changes in HAI brought about by the introduction of new automation into the flight deck could be predicted and assessed prior to implementation and without use of extensive simulation. This paper presents a method to model a parametrization of flight deck automation known as HART and link it to HAI consequences using a backpropagation neural network approach. The transformation of the HART into a computational model suitable for modeling as a neural network is described. To test and train the network data were collected from 40 airline pilots for six HAI consequences based on one scenario family consisting of a baseline and four variants. For a binary classification of HAI consequences, the neural network successfully classified 62–78.5% depending on the consequence. The results were verified using a decision tree analysis.

Maintaining Spatial Relations in an Incremental Diagrammatic Reasoner

This paper describes an architecture for dynamically handling spatial relations in an incremental, nonmonotonic diagrammatic reasoning system. The architecture represents jointly exhaustive and pairwise disjoint (JEPD) spatial relation sets as nodes in a dependency network. These spatial relation sets include interval relations, relative orientation relations, and connectivity relations, but in theory could include any JEPD spatial relation sets. This network then caches dependencies between low-level spatial relations, allowing those relations to be easily assumed or retracted as visual elements are added or removed from a diagram. For example, in the architecture’s Undo mechanism, the dependency network can quickly reactivate cached spatial relations when a previously-deleted element is restored. As part of this work, we describe how the system supports higher-level reasoning, including support for creating default assumptions. We also describe how this system was integrated with an existing drawing program and discuss its possible use in diagrammatic and geographic reasoning.

Bruise chromophore concentrations over time

During investigations of potential child and elder abuse, clinicians and forensic practitioners are often asked to offer opinions about the age of a bruise. A commonality between existing methods of bruise aging is analysis of bruise color or estimation of chromophore concentration. Relative chromophore concentration is an underlying factor that determines bruise color. We investigate a method of chromophore concentration estimation that can be employed in a handheld imaging spectrometer with a small number of wavelengths. The method, based on absorbance properties defined by Beer-Lamberts law, allows estimation of differential chromophore concentration between bruised and normal skin. Absorption coefficient data for each chromophore are required to make the estimation. Two different sources of this data are used in the analysis- generated using Independent Component Analysis and taken from published values. Differential concentration values over time, generated using both sources, show correlation to published models of bruise color change over time and total chromophore concentration over time.

Enhancing brain-machine interface throughput using simultaneous activation detection

In this work, we investigate the viability of a novel combination of evoked responses as input signals for a general-purpose brain machine interface (BMI). We demonstrate response accuracy to alphanumeric stimuli in valid and mirror-reversed orientations, and show task-related activity differences correlated with rotation degree and character validity in superior parietal and inferior frontal gyrus regions of the brain. By observing simultaneous task-related activation in spatially dissociated regions, we increase the amount of information used for inferring user intent in control interfaces.