Engineering Papers⌕ Search

SEARCH · Engineering Papers

Results for “Recognition”

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.

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

At least 1,657 records · Page 92

Computer identification of ground pattern from aerial photographs.

Two statistical models are comapared in the classification of crops recorded on color aerial photographs. A theory of error ellipses is applied to the pattern recognition problem. An elliptical boundary condition classification model (EBC), useful for recognition of candidate patterns, evolves out of error ellipse theory. The EBC model is compared with the minimum distance to the mean (MDM) classification model in terms of pattern recognition ability. The pattern recognition results of both models are interpreted graphically using scatter diagrams to represent measurement space. Measurement space, for this report, is determined by optical density measurements collected from Kodak Ektachrome Infrared Aero Film 8443 (EIR). The EBC model is shown to be a significant improvement over the MDM model.

Richardson, A. J.↗

Finding the earth in ERTS

Itek's Optical System Division recently completed an investigation funded by NASA to develop interpretation methods and algorithms suitable for recognition of earth resources by machines using multispectral data from ERTS. Through the algorithms developed (and described here) it is now possible to automatically recognize terrain types. The clustering algorithm guarantees high accuracy in the recognition process with almost complete automation. Interestingly, the machine recognition seems to be more accurate than a human photointerpreter who has been restricted to using only ERTS-1 color composites. That is, machine recognition appears to be more sensitive, it can operate much closer, to the resolution limit of the ERTS-1 imagery than the human photointerpreter.

Gramenopoulos, N.↗

A multidisciplinary study of earth resources imagery of Australia, Antarctica and Papua, New Guinea

The author has identified the following significant results. A thirteen category recognition map was prepared, showing forest, water, grassland, and exposed rock types. Preliminary assessment of classification accuracies showed that water, forest, meadow, and Niobrara shale were the most accurately mapped classes. Unsatisfactory results, were obtained in an attempt to discrimate sparse forest cover over different substrates. As base elevation varied from 7,000 to 13,000 ft, with an atmospheric visibility of 48 km, no changes in water and forest recognition were observed. Granodiorite recognition accuracy decreased monotonically as base elevation increased, even though the training set location was at 10,000 ft elevation. For snow varying in base elevation from 9400 to 8420 ft, recognition decreases from 99% at the 9400 ft training set elevation to 88% at 8420 ft. Calculations of expected radiance at the ERTS sensor from snow reflectance measured at the site and from Turner model calculations of irradiance, transmission and path radiance, reveal that snow signals should not be clipped, assuming that calculations and ERTS calibration constants were correct.

Fisher, N. H.↗

Fidelity of Satellite Soundings

Two pattern recognition procedures to provide improvements to first guess fields for satellite temperature retrievals were developed. The first technique where a radiometer measurement is used to select one or more historical radiosonde temperature profiles as analog estimates of ambient thermal structure. Radiosondes are the vertical scales of the analogs. The vertical resolving power of the satellite radiometer is relevant only to a decision process. The analog selection process is much more effective if implemented in an orthogonalized space of measurement information. The second procedure partitions a priori dependent data into shape coherent pattern libraries using structure information inherent in the data itself. It is shown that the pattern recognition techniques are able to reduce first guess profile errors by nearly 50%. The impact of pattern recognition on temperature retrieval error is assessed by regression and physical iterative retrieval algorithms. The influence of improved first guess fields is markedly different on these two types of algorithm. Pattern recognition was a strong positive impact on the physical iterative method.

Thompson, O.↗

Map learning with indistinguishable locations

Nearly all spatial reasoning problems involve uncertainty of one sort or another. Uncertainty arises due to the inaccuracies of sensors used in measuring distances and angels. This is inferred as directional uncertainty. Uncertainty also arises in combining spatial information when one location is mistakenly identified with another. This is referred to as recognition uncertainty. Most problems in constructing spatial representations (maps) for the purpose of navigation involve both directional and recognition uncertainty. It is shown that a particular class of spatial reasoning problems involving the construction of representations of large-scale space can be solved efficiently even in the presence of directional and recognition uncertainty. Particular attention is paid to the problems that arise due to recognition uncertainty. The results described are applicable to the construction of global maps from satellite data as well as the construction of local navigation maps from measurements made by a rover in exploring a planetary surface.

Basye, Kenneth↗

Autonomous star referenced attitude determination

A general star pattern recognition algorithm has been used to develop JPL's redundant, microcomputer-equipped ASTROS II CCD star tracker into a full-sky autonomous star tracker (FAST), capable of determining its attitude about all three axes without requiring any a priori attitude knowledge. A large field of view allows the number of guide stars in the all-sky data-base of the tracker to be limited to a manageable number, while high accuracy ensures that the pattern formed by the observed guide stars is unique. The recognition algorithm can also be used for automating the acquisition of celestial targets by astronomy telescopes, for autonomously updating the attitude of gyro-based attitude control systems, and for automating ground-based attitude recognition. Using both Monte Carlo simulations and a quasi-analytical method, it is shown that the general recognition algorithm and a less software-intensive special algorithm can be used to reliably automate the acquisition of celestial targets by astronomy telescopes.

Van Bezooijen, R. W. H.↗

Analysis of objects in binary images

Digital image processing techniques are typically used to produce improved digital images through the application of successive enhancement techniques to a given image or to generate quantitative data about the objects within that image. In support of and to assist researchers in a wide range of disciplines, e.g., interferometry, heavy rain effects on aerodynamics, and structure recognition research, it is often desirable to count objects in an image and compute their geometric properties. Therefore, an image analysis application package, focusing on a subset of image analysis techniques used for object recognition in binary images, was developed. This report describes the techniques and algorithms utilized in three main phases of the application and are categorized as: image segmentation, object recognition, and quantitative analysis. Appendices provide supplemental formulas for the algorithms employed as well as examples and results from the various image segmentation techniques and the object recognition algorithm implemented.

Leonard, Desiree M.↗

Voice integrated systems

The program at Naval Air Development Center was initiated to determine the desirability of interactive voice systems for use in airborne weapon systems crew stations. A voice recognition and synthesis system (VRAS) was developed and incorporated into a human centrifuge. The speech recognition aspect of VRAS was developed using a voice command system (VCS) developed by Scope Electronics. The speech synthesis capability was supplied by a Votrax, VS-5, speech synthesis unit built by Vocal Interface. The effects of simulated flight on automatic speech recognition were determined by repeated trials in the VRAS-equipped centrifuge. The relationship of vibration, G, O2 mask, mission duration, and cockpit temperature and voice quality was determined. The results showed that: (1) voice quality degrades after 0.5 hours with an O2 mask; (2) voice quality degrades under high vibration; and (3) voice quality degrades under high levels of G. The voice quality studies are summarized. These results were obtained with a baseline of 80 percent recognition accuracy with VCS.

Curran, P. Mike↗

Neuroelectric Virtual Devices

This paper presents recent results in neuroelectric pattern recognition of electromyographic (EMG) signals used to control virtual computer input devices. The devices are designed to substitute for the functions of both a traditional joystick and keyboard entry method. We demonstrate recognition accuracy through neuroelectric control of a 757 class simulation aircraft landing at San Francisco International Airport using a virtual joystick as shown. This is accomplished by a pilot closing his fist in empty air and performing control movements that are captured by a dry electrode array on the arm which are then analyzed and routed through a flight director permitting full pilot outer loop control of the simulation. We then demonstrate finer grain motor pattern recognition through a virtual keyboard by having a typist tap his traders on a typical desk in a touch typist position. The EMG signals are then translated to keyboard presses and displayed. The paper describes the bioelectric pattern recognition methodology common to both examples. Figure 2 depicts raw EMG data from typing, the numeral '8' and the numeral '9'. These two gestures are very close in appearance and statistical properties yet are distinguishable by our hidden Kharkov model algorithms. Extensions of this work to NASA emissions and robotic control are considered.

Wheeler, Kevin↗

Spoken Language Processing in the Clarissa Procedure Browser

Clarissa, an experimental voice enabled procedure browser that has recently been deployed on the International Space Station, is as far as we know the first spoken dialog system in space. We describe the objectives of the Clarissa project and the system's architecture. In particular, we focus on three key problems: grammar-based speech recognition using the Regulus toolkit; methods for open mic speech recognition; and robust side-effect free dialogue management for handling undos, corrections and confirmations. We first describe the grammar-based recogniser we have build using Regulus, and report experiments where we compare it against a class N-gram recogniser trained off the same 3297 utterance dataset. We obtained a 15% relative improvement in WER and a 37% improvement in semantic error rate. The grammar-based recogniser moreover outperforms the class N-gram version for utterances of all lengths from 1 to 9 words inclusive. The central problem in building an open-mic speech recognition system is being able to distinguish between commands directed at the system, and other material (cross-talk), which should be rejected. Most spoken dialogue systems make the accept/reject decision by applying a threshold to the recognition confidence score. NASA shows how a simple and general method, based on standard approaches to document classification using Support Vector Machines, can give substantially better performance, and report experiments showing a relative reduction in the task-level error rate by about 25% compared to the baseline confidence threshold method. Finally, we describe a general side-effect free dialogue management architecture that we have implemented in Clarissa, which extends the "update semantics'' framework by including task as well as dialogue information in the information state. We show that this enables elegant treatments of several dialogue management problems, including corrections, confirmations, querying of the environment, and regression testing.

Rayner, M.↗

Gesture-controlled interfaces for self-service machines and other applications

A gesture recognition interface for use in controlling self-service machines and other devices is disclosed. A gesture is defined as motions and kinematic poses generated by humans, animals, or machines. Specific body features are tracked, and static and motion gestures are interpreted. Motion gestures are defined as a family of parametrically delimited oscillatory motions, modeled as a linear-in-parameters dynamic system with added geometric constraints to allow for real-time recognition using a small amount of memory and processing time. A linear least squares method is preferably used to determine the parameters which represent each gesture. Feature position measure is used in conjunction with a bank of predictor bins seeded with the gesture parameters, and the system determines which bin best fits the observed motion. Recognizing static pose gestures is preferably performed by localizing the body/object from the rest of the image, describing that object, and identifying that description. The disclosure details methods for gesture recognition, as well as the overall architecture for using gesture recognition to control of devices, including self-service machines.

Cohen, Charles J.↗

Thin membrane sensor with biochemical switch

A modular biosensor system for chemical or biological agent detection utilizes electrochemical measurement of an ion current across a gate membrane triggered by the reaction of the target agent with a recognition protein conjugated to a channel blocker. The sensor system includes a bioresponse simulator or biochemical switch module which contains the recognition protein-channel blocker conjugate, and in which the detection reactions occur, and a transducer module which contains a gate membrane and a measuring electrode, and in which the presence of agent is sensed electrically. In the poised state, ion channels in the gate membrane are blocked by the recognition protein-channel blocker conjugate. Detection reactions remove the recognition protein-channel blocker conjugate from the ion channels, thus eliciting an ion current surge in the gate membrane which subsequently triggers an output alarm. Sufficiently large currents are generated that simple direct current electronics are adequate for the measurements. The biosensor has applications for environmental, medical, and industrial use.

Case, George D.↗

Biomimetic/Optical Sensors for Detecting Bacterial Species

Biomimetic/optical sensors have been proposed as means of real-time detection of bacteria in liquid samples through real-time detection of compounds secreted by the bacteria. Bacterial species of interest would be identified through detection of signaling compounds unique to those species. The best-characterized examples of quorum-signaling compounds are acyl-homoserine lactones and peptides. Each compound, secreted by each bacterium of an affected species, serves as a signal to other bacteria of the same species to engage in a collective behavior when the population density of that species reaches a threshold level analogous to a quorum. A sensor according to the proposal would include a specially formulated biomimetic film, made of a molecularly imprinted polymer (MIP), that would respond optically to the signaling compound of interest. The MIP film would be integrated directly onto an opticalwaveguide- based ring resonator for optical readout. Optically, the sensor would resemble the one described in Chemical Sensors Based on Optical Ring Resonators (NPO-40601), NASA Tech Briefs, Vol. 29, No. 10 (October 2005), page 32. MIPs have been used before as molecular- recognition compounds, though not in the manner of the present proposal. Molecular imprinting is an approach to making molecularly selective cavities in a polymer matrix. These cavities function much as enzyme receptor sites: the chemical functionality and shape of a cavity in the polymer matrix cause the cavity to bind to specific molecules. An MIP matrix is made by polymerizing monomers in the presence of the compound of interest (template molecule). The polymer forms around the template. After the polymer solidifies, the template molecules are removed from the polymer matrix by decomplexing them from their binding sites and then dissolving them, leaving cavities that are matched to the template molecules in size, shape, and chemical functionality. The cavities thus become molecular-recognition sites that bind only to molecules matched to the sites; other molecules are excluded. In a sensor according to the proposal, the MIP would feature molecular recognition sites that would bind the specific signaling molecules selectively according to their size, shape, and chemical functionality (see figure). As the film took up the signaling molecules in the molecular recognition sites, the index of refraction and thickness of the film would change, causing a wavelength shift of the peak of the resonance spectrum. It has been estimated that by measuring this wavelength shift, it should be possible to detect as little as 10 picomoles of a peptide signaling compound.

Homer, Margie↗

Natural Language Understanding and Extraction of Flight Constraints Recorded in Letters of Agreement

This paper presents an automated information extraction and inference technique using natural language processing for extracting flight operational procedures and constraints embedded in heritage air traffic management documents. The extracted flight constraints can be digitized and fit into existing airspace information exchange models such as the Aeronautical Information Exchange Model (AIXM). This approach offers a digitized solution to disseminate airspace operating conditions to diverse air users and stakeholders in the National Airspace System (NAS). Furthermore, the digitized flight procedures can provide operational flexibility for emerging advanced air mobility providers and reduce traffic controller workload while maintaining current safety standards. To demonstrate this process, 1,972 Letters of Agreement (LOAs) have been selected for processing, named entity extraction, constraint identification and extraction. This dataset is derived from a subset of documents related to Air Route Traffic Control Centers (ARTCC) operations. We experimented with various traditional information extraction techniques, state-of-the-art machine learning and deep learning models to perform named entity recognition and pattern recognition on our dataset. We present the results from our experiments and demonstrate 99.0% F-1 score for named entity recognition, and a 96.6% accuracy for our entire workflow up to named entity recognition. We also discuss constraint definitions using generic patterned templates and extensions to this work in applying entity linking to digitally extracting relevant constraints.

Natural Language Processing↗

Natural Language Understanding and Extraction of Flight Constraints Recorded in Letters of Agreement

This paper presents an automated information extraction and inference technique using natural language processing for extracting flight operational procedures and constraints embedded in heritage air traffic management documents. The extracted flight constraints can be digitized and fit into existing airspace information exchange models such as the Aeronautical Information Exchange Model (AIXM). This approach offers a digitized solution to disseminate airspace operating conditions to diverse air users and stakeholders in the National Airspace System (NAS). Furthermore, the digitized flight procedures can provide operational flexibility for emerging advanced air mobility providers and reduce traffic controller workload while maintaining current safety standards. To demonstrate this process, 1,972 Letters of Agreement (LOAs) have been selected for processing, named entity extraction, constraint identification and extraction. This dataset is derived from a subset of documents related to Air Route Traffic Control Centers (ARTCC) operations. We experimented with various traditional information extraction techniques, state-of-the-art machine learning and deep learning models to perform named entity recognition and pattern recognition on our dataset. We present the results from our experiments and demonstrate 99.0% F-1 score for named entity recognition, and a 96.6% accuracy for our entire workflow up to named entity recognition. We also discuss constraint definitions using generic patterned templates and extensions to this work in applying entity linking to digitally extracting relevant constraints.

Natural Language Processing↗

Neurosymbolic Hybrid Approach to Driver Collision Warning

There are two main algorithmic approaches to autonomous driving systems: (1) An end-to-end system in which a single deep neural network learns to map sensory input directly into appropriate warning and driving responses. (2) A mediated hybrid recognition system in which a system is created by combining independent modules that detect each semantic feature. While some researchers believe that deep learning can solve any problem, others believe that a more engineered and symbolic approach is needed to cope with complex environments with less data. Deep learning alone has achieved state-of-the-art results in many areas, from complex gameplay to predicting protein structures. In particular, in image classification and recognition, deep learning models have achieved accuracies as high as humans. But sometimes it can be very difficult to debug if the deep learning model doesn't work. Deep learning models can be vulnerable and are very sensitive to changes in data distribution. Generalization can be problematic. It's usually hard to prove why it works or doesn't. Deep learning models can also be vulnerable to adversarial attacks. Here, we combine deep learning-based object recognition and tracking with an adaptive neurosymbolic network agent, called the Non-Axiomatic Reasoning System (NARS), that can adapt to its environment by building concepts based on perceptual sequences. We achieved an improved intersection-over-union (IOU) object recognition performance of 0.65 in the adaptive retraining model compared to IOU 0.31 in the COCO data pre-trained model. We improved the object detection limits using RADAR sensors in a simulated environment, and demonstrated the weaving car detection capability by combining deep learning-based object detection and tracking with a neurosymbolic model.

Wang, Pei↗

Limbus Impact on Off-angle Iris Degradation

The accuracy of iris recognition depends on the quality of data capture and is negatively affected by several factors such as angle, occlusion, and dilation. Off-angle iris recognition is a new research focus in biometrics that tries to address several issues including corneal refraction, complex 3D iris texture, and blur. In this paper, we present an additional significant challenge that degrades the performance of the off-angle iris recognition systems, called the limbus effect . The limbus is the region at the border of the cornea where the cornea joins the sclera. The limbus is a semitransparent tissue that occludes a side portion of the iris plane. The amount of occluded iris texture on the side nearest the camera increases as the image acquisition angle increases. Without considering the role of the limbus effect, it is difficult to design an accurate off-angle iris recognition system. To the best of our knowledge, this is the first work that investigates the limbus effect in detail from a biometrics perspective. Based on results from real images and simulated experiments with real iris texture, the limbus effect increases the hamming distance score between frontal and off-angle iris images ranging from 0.05 to 0.2 depending upon the limbus height.

Karakaya, Mahmut↗

Personal glucose meters for detection and quantification of a broad range of analytes

A general methodology for the development of highly sensitive and selective sensors that can achieve portable, low-cost and quantitative detection of a broad range of targets using only a personal glucose meter (PGM) is disclosed. The method uses recognition molecules that are specific for a target agent, enzymes that can convert an enzyme substrate into glucose, and PGM. Also provided are sensors, which can include a solid support to which is attached a recognition molecule that permits detection of a target agent, wherein the recognition molecule specifically binds to the target agent in the presence of the target agent but not significantly to other agents as well as an enzyme that can catalyze the conversion of a substance into glucose, wherein the enzyme is attached directly or indirectly to the recognition molecule, and wherein in the presence of the target agent the enzyme can convert the substance into glucose. The disclosed sensors can be part of a lateral flow device. Methods of using such sensors for detecting target agents are also provided.

59 BASIC BIOLOGICAL SCIENCES↗