SEARCH · Engineering Papers

Results for “Seizure Detection”

Search indexed NASA NTRS and DOE OSTI research on propulsion, heat transfer, battery materials and energy systems. Follow report and document links to the original sources.

SourceResearch connectionFrom yearThrough year

Quote a phrase for an exact phrase match. Source license links do not imply unrestricted reuse.

13 records

All sources NASA NTRS DOE OSTI

DOE OSTI2021

Seizure detection device

Example aspects of a collector for a seizure detection device, a seizure detection device, and a method of detecting a seizure are disclosed. The collector for a seizure detection device can comprise a collector material configured to collect volatile organic compounds given off from a patient's skin; a wrapping configured to isolate the collector material from an external environment; a heater comprising a heating element, the heating element configured to emit a thermal pulse to desorb the volatile organic compounds from the collector material; and a mesh layer configured to prevent the collector material from contacting the patient's skin, wherein the collector material is received between the wrapping and the mesh layer.

Arnold, Gary Stephen↗

DOE OSTI2023

Seizure detection device

A method of detecting a seizure includes collecting volatile organic compounds with a collector material of a collector; separating a mixture of the volatile organic compounds into its constituent chemicals with a gas chromatography column; ionizing the constituent chemicals to create ionized chemicals and detecting the ionized chemicals; and analyzing the ionized chemicals to identify seizure-indicative volatile organic compounds.

Arnold, Gary Stephen↗

NASA NTRS1993

Automatic Detection of Seizures with Applications

There are an estimated two million people with epilepsy in the United States. Many of these people do not respond to anti-epileptic drug therapy. Two devices can be developed to assist in the treatment of epilepsy. The first is a microcomputer-based system designed to process massive amounts of electroencephalogram (EEG) data collected during long-term monitoring of patients for the purpose of diagnosing seizures, assessing the effectiveness of medical therapy, or selecting patients for epilepsy surgery. Such a device would select and display important EEG events. Currently many such events are missed. A second device could be implanted and would detect seizures and initiate therapy. Both of these devices require a reliable seizure detection algorithm. A new algorithm is described. It is believed to represent an improvement over existing seizure detection algorithms because better signal features were selected and better standardization methods were used.

Olsen, Dale E.↗

DOE OSTI2020

DEEP CELLULAR RECURRENT NEURAL ARCHITECTURE FOR EFFICIENT MULTIDIMENSIONAL TIME-SERIES DATA PROCESSING

Efficient processing of time series data is a fundamental yet challenging problem in pattern recognition. Though recent developments in machine learning and deep learning have enabled remarkable improvements in processing large scale datasets in many application domains, most are designed and regulated to handle inputs that are static in time. Many real-world data, such as in biomedical, surveillance and security, financial, manufacturing and engineering applications, are rarely static in time, and demand models able to recognize patterns in both space and time. Current machine learning (ML) and deep learning (DL) models adapted for time series processing tend to grow in complexity and size to accommodate the additional dimensionality of time. Specifically, the biologically inspired learning based models known as artificial neural networks that have shown extraordinary success in pattern recognition, tend to grow prohibitively large and cumbersome in the presence of large scale multi-dimensional time series biomedical data such as EEG. Consequently, this work aims to develop representative ML and DL models for robust and efficient large scale time series processing. First, we design a novel ML pipeline with efficient feature engineering to process a large scale multi-channel scalp EEG dataset for automated detection of epileptic seizures. With the use of a sophisticated yet computationally efficient time-frequency analysis technique known as harmonic wavelet packet transform and an efficient self-similarity computation based on fractal dimension, we achieve state-of-the-art performance for automated seizure detection in EEG data. Subsequently, we investigate the development of a novel efficient deep recurrent learning model for large scale time series processing. For this, we first study the functionality and training of a biologically inspired neural network architecture known as cellular simultaneous recurrent neural network (CSRN). We obtain a generalization of this network for multiple topological image processing tasks and investigate the learning efficacy of the complex cellular architecture using several state-of-the?art training methods. Finally, we develop a novel deep cellular recurrent neural network (CDRNN) architecture based on the biologically inspired distributed processing used in CSRN for processing time series data. The proposed DCRNN leverages the cellular recurrent architecture to promote extensive weight sharing and efficient, individualized, synchronous processing of multi-source time series data. Experiments on a large scale multi-channel scalp EEG, and a machine fault detection dataset show that the proposed DCRNN offers state-of-the-art recognition performance while using substantially fewer trainable recurrent units.

Vidyaratne, Lasitha S.↗

DOE OSTI2021

Deep Cellular Recurrent Network for Efficient Analysis of Time-Series Data With Spatial Information

Efficient processing of large-scale time series data is an intricate problem in machine learning. Conventional sensor signal processing pipelines with hand engineered feature extraction often involve huge computational cost with high dimensional data. Deep recurrent neural networks have shown promise in automated feature learning for improved time-series processing. However, generic deep recurrent models grow in scale and depth with increased complexity of the data. This is particularly challenging in presence of high dimensional data with temporal and spatial characteristics. Consequently, this work proposes a novel deep cellular recurrent neural network (DCRNN) architecture to efficiently process complex multi-dimensional time series data with spatial information. Here, the cellular recurrent architecture in the proposed model allows for location-aware synchronous processing of time series data from spatially distributed sensor signal sources. Extensive trainable parameter sharing due to cellularity in the proposed architecture ensures efficiency in the use of recurrent processing units with high-dimensional inputs. This study also investigates the versatility of the proposed DCRNN model for classification of multi-class time series data from different application domains. Consequently, the proposed DCRNN architecture is evaluated using two time-series datasets: a multichannel scalp EEG dataset for seizure detection, and a machine fault detection dataset obtained in-house. The results suggest that the proposed architecture achieves state-of-the-art performance while utilizing substantially less trainable parameters when compared to comparable methods in the literature.

60 APPLIED LIFE SCIENCES↗

NASA NTRS2000

Oxygen desaturations triggered by partial seizures: implications for cardiopulmonary instability in epilepsy

PURPOSE: The occurrence of hypoxemia in adults with partial seizures has not been systematically explored. Our aim was to study in detail the temporal dynamics of this specific type of ictal-associated hypoxemia. METHODS: During long-term video/EEG monitoring (LTM), patients underwent monitoring of oxygen saturation using a digital Spo2 (pulse oximeter) transducer. Six patients (nine seizures) were identified with oxygen desaturations after the onset of partial seizure activity. RESULTS: Complex partial seizures originated from both left and right temporal lobes. Mean seizure duration (+/-SD) was 73 +/- 18 s. Mean Spo2 desaturation duration was 76 +/- 19 s. The onset of oxygen desaturation followed seizure onset with a mean delay of 43 +/- 16 s. Mean (+/-SD) Spo2 nadir was 83 +/- 5% (range, 77-91%), occurring an average of 35 +/- 12 s after the onset of the desaturation. One seizure was associated with prolonged and recurrent Spo2 desaturations. CONCLUSIONS: Partial seizures may be associated with prominent oxygen desaturations. The comparable duration of each seizure and its subsequent desaturation suggests a close mechanistic (possibly causal) relation. Spo2 monitoring provides an added means for seizure detection that may increase LTM yield. These observations also raise the possibility that ictal ventilatory dysfunction could play a role in certain cases of sudden unexpected death in epilepsy in adults with partial seizures.

NASA Program Biomedical Research and Countermeasur↗

DOE OSTI2026

Protonic nickelate device networks for spatiotemporal neuromorphic computing

Computation in biological neural circuits arises from the interplay of nonlinear temporal responses and spatially distributed dynamic network interactions. Replicating this richness in hardware has remained challenging, as most neuromorphic devices emulate only isolated neuron- or synapse-like functions. Here we introduce an integrated neuromorphic computing platform in which both nonlinear spatiotemporal processing and programmable memory are realized within a single perovskite nickelate material system. By engineering symmetric and asymmetric hydrogenated NdNiO 3 junction devices on the same wafer, we combine ultrafast, proton-mediated transient dynamics with stable multilevel resistance states. Networks of symmetric NdNiO 3 junctions exhibit emergent spatial interactions mediated by proton redistribution, while each node simultaneously provides short-term temporal memory, enabling nanosecond-scale operation with an energy cost of ~0.2 nJ per input. When interfaced with asymmetric output units serving as reconfigurable long-term weights, these networks allow both feature transformation and linear classification in the same material system. Leveraging these emergent interactions, the platform enables real-time pattern recognition and achieves high accuracy in spoken digit classification and early seizure detection, outperforming temporal-only or uncoupled architectures. These results position protonic nickelates as a compact, energy-efficient, CMOS-compatible platform that integrates processing and memory for scalable intelligent hardware.

Electrical and electronic engineering↗

NASA NTRS1994

Monitor for status epilepticus seizures

This paper describes the sensor technology and associated electronics of a monitor designed to detect the onset of a seizure disorder called status epilepticus. It is a condition that affects approximately 3-5 percent of those individuals suffering from epilepsy. This form of epilepsy does not follow the typical cycle of start-peak-end. The convulsions continue until medically interrupted and are life threatening. The mortality rate is high without prompt medical treatment at a suitable facility. The paper describes the details of a monitor design that provides an inexpensive solution to the needs of those responsible for the care of individuals afflicted with this disorder. The monitor has been designed as a cooperative research and development effort involving the United States Army Armament Research, Development, and Engineering Center's Benet Laboratories (Benet) and the Cerebral Palsy Center for the Disabled (Center), in association with the Department of Neurology at Albany Medical College (AMC). Benet has delivered a working prototype of the device for field testing, in collaboration with Albany Medical College. The Center has identified several children in need of special monitoring and has agreed to pursue commercialization of the device.

Johnson, Mark↗

NASA NTRS2003

Computer Program Recognizes Patterns in Time-Series Data

A computer program recognizes selected patterns in time-series data like digitized samples of seismic or electrophysiological signals. The program implements an artificial neural network (ANN) and a set of N clocks for the purpose of determining whether N or more instances of a certain waveform, W, occur within a given time interval, T. The ANN must be trained to recognize W in the incoming stream of data. The first time the ANN recognizes W, it sets clock 1 to count down from T to zero; the second time it recognizes W, it sets clock 2 to count down from T to zero, and so forth through the Nth instance. On the N + 1st instance, the cycle is repeated, starting with clock 1. If any clock has not reached zero when it is reset, then N instances of W have been detected within time T, and the program so indicates. The program can readily be encoded in a field-programmable gate array or an application-specific integrated circuit that could be used, for example, to detect electroencephalographic or electrocardiographic waveforms indicative of epileptic seizures or heart attacks, respectively.

Hand, Charles↗

NASA NTRS2001

Screening EEG in Aircrew Selection: Clinical Aerospace Neurology Perspective

As clinical aerospace neurologists we do not favor using screening EEG in pilot selection on unselected and otherwise asymptomatic individuals. The role of EEG in aviation screening should be as an adjunct to diagnosis, and the decision to disqualify a pilot should never be based solely on the EEG. Although a policy of using a screening EEG in an unselected population might detect an individual with a potentially increased relative risk, it would needlessly exclude many applicants who would probably never have a seizure. A diagnostic test performed on an asymptomatic individual without clinical indications, in a population with a low prevalence of disease (seizure) may be of limited or possibly detrimental value. We feel that rather than do EEGs on all candidates, a better approach would be to perform an EEG for a specific indication, such as family history of seizure, single convulsion (seizure) , history of unexplained loss of consciousness or head injury. Routine screening EEGs in unselected aviation applications are not done without clinical indication in the U.S. Air Force, Navy, or NASA. The USAF discontinued routine screening EEGs for selection in 1978, the U.S. Navy discontinued it in 1981 , and NASA discontinued it in 1995. EEG as an aeromedical screening tool in the US Navy dates back to 1939. The US Navy routinely used EEGs to screen all aeromedical personnel from 1961 to 1981. The incidence of epileptiform activity on EEG in asymptomatic flight candidates ranges from 0.11 to 2.5%. In 3 studies of asymptomatic flight candidates with epileptiform activity on EEG followed for 2 to 15 years, 1 of 31 (3.2%), 1 of 30 (3.3%), and 0 of 14 (0%) developed a seizure, for a cumulative risk of an individual with an epileptiform EEG developing a seizure of 2.67% (2 in 75). Of 28,658 student naval aviation personnel screened 31 had spikes and/or slow waves on EEG, and only 1 later developed a seizure. Of the 28,627 who had a normal EEG, 4 later developed seizures, or .0139% (4/28627). After review of the value of the EEG as a screening tool, the US Navy now uses EEG only for certain clinical indications (head injury, unexplained loss of consciousness, family history of epilepsy, and abnormal neurological exam). Currently the US Navy does not use EEG for screening for any flight applicant without a neurologic indication. In the US Navy, an electroencephalographic pattern is determined to be epileptiform by a neurologist.

Clark, Jonathan B.↗

NASA NTRS1979

Portable device for detection of petit mal epilepsy

A portable device that analyzes the electroencephalogram to determine if petit mal epilepsy waveforms are present is developed and tested. Clinicians should find it useful in diagnosing seizure activity of their patients. The micropower, battery-operated, portable device indicates a seizure has occurred if three criteria are satisfied: (1) frequencies of 2.5-7 Hz, (2) large-amplitude waves, and (3) minimum number of waves per second. Levels and counts are adjustable, thus insuring high reliability against noise artifacts and permitting each subject to be individually fitted. The device has shown promise in giving the patient a possible mechanism of seizure control or suppression.

Smith, R. G.↗

DOE OSTI2020

Long-term persistence of infectious Zika virus: Inflammation and behavioral sequela in mice

The neurodevelopmental defects associated with ZIKV infections early in pregnancy are well documented, however the potential defects and long-term consequences associated with milder infections in late pregnancy and perinatal period are less well understood. To model these, we challenged 1 day old (P1) immunocompetent C57BL/6 mice with ZIKV. The animals developed a transient neurological syndrome including unsteady gait, kinetic tremors, severe ataxia and seizures 10–15 days post-infection (dpi) but symptoms subsided after a week, and most animals survived. Despite apparent recovery, MRI of convalescent mice show reduced cerebellar volume that correlates with altered coordination and motor function as well as hyperactivity and impulsivity. Persistent mRNA levels of pro-inflammatory genes including Cd80 , Il-1α , and Ifn-γ together with Cd3 , Cd8 and perforin ( PrfA) , suggested persistence of low-grade inflammation. Surprisingly, the brain parenchyma of convalescent mice harbor multiple small discrete foci with viral antigen, active apoptotic processes in neurons, and cellular infiltrates, surrounded by activated astrocytes and microglia as late as 1-year post-infection. Detection of negative-sense strand viral RNA and isolation of infectious virus derived from these convalescent mice by blinded passage in Vero cells confirmed long-term persistence of replicating ZIKV in CNS of convalescent mice. Although the infection appears to persist in defined reservoirs within CNS, the resulting inflammation could increase the risk of neurodegenerative disorders. This raises concern regarding possible long-term effects in asymptomatic children exposed to the virus and suggests that long-term neurological and behavioral monitoring as well as anti-viral treatment to clear virus from the CNS may be useful in patients exposed to ZIKV at an early age.

59 BASIC BIOLOGICAL SCIENCES↗

NASA NTRS1991

Measurement and modification of the EEG and related behavior

Electrophysiological changes in the sensorimotor pathways were found to accompany the effect of rhythmic EEG patterns in the sensorimotor cortex. Additionally, several striking behavioral changes were seen, including in particular an enhancement of sleep and an elevation of seizure threshold to epileptogenic agents. This raised the possibility that human seizure disorders might be influenced therapeutically by similar training. Our objective in human EEG feedback training became not only the facilitation of normal rhythmic patterns, but also the suppression of abnormal activity, thus requiring complex contingencies directed to the normalization of the sensorimotor EEG. To achieve this, a multicomponent frequency analysis was developed to extract and separate normal and abnormal elements of the EEG signal. Each of these elements was transduced to a specific component of a visual display system, and these were combined through logic circuits to present the subject with a symbolic display. Variable criteria provided for the gradual shaping of EEG elements towards the desired normal pattern. Some 50-70% of patients with poorly controlled seizure disorders experienced therapeutic benefits from this approach in our laboratory, and subsequently in many others. A more recent application of this approach to the modification of human brain function in our lab has been directed to the dichotomous problems of task overload and underload in the contemporary aviation environment. At least 70% of all aviation accidents have been attributed to the impact of these kinds of problems on crew performance. The use of EEG in this context has required many technical innovations and the application of the latest advances in EEG signal analysis. Our first goal has been the identification of relevant EEG characteristics. Additionally, we have developed a portable recording and analysis system for application in this context. Findings from laboratory and in-flight studies suggest that we will be able to detect appropriate changes in brain function, and feed this information to on-board computers for modification of mission requirements and/or crew status.

Sterman, M. B.↗