Search PubMed⌕ Search

SEARCH · Search PubMed

Results for “artificial intelligence”

Search indexed PubMed citations on genomics, clinical trials, systematic reviews and public health. Explore titles, authors and supplied subject terms, then open the PubMed record.

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

At least 1,387 records · Page 77Linked to original sources
PubMedDate not supplied

Predictive haptic guidance: intelligent user assistance for the control of dynamic tasks.

Intelligent systems are increasingly able to offer real-time information relevant to a user's manual control of an interactive system, such as dynamic system control space constraints for animation control and driving. However, it is difficult to present this information in a usable manner and other approaches which have employed haptic cues for manual control in "slow" systems often lead to instabilities in highly dynamic tasks. We present a predictive haptic guidance method based on a look-ahead algorithm, along with a user evaluation which compares it with other approaches (no guidance and a standard potential-field method) in a 1-DoF steered path-following scenario. Look-ahead guidance outperformed the other methods in both quantitative performance and subjective preference across a range of path complexity and visibility and a force analysis demonstrated that it applied smaller and fewer forces to users. These results (which appear to derive from the predictive guidance's supporting users in taking earlier and more subtle corrective action) suggest the potential of predictive methods in aiding manual control of dynamic interactive tasks where intelligent support is available.

Algorithms↗
PubMed2002

A methodology for missile countermeasures optimization under uncertainty.

The missile countermeasures optimization problem is a complex strategy optimization problem that combines aircraft maneuvers with additional countermeasures in an attempt to survive attack from a single surface-launched, anti-aircraft missile. Classic solutions require the evading aircraft to execute specific sequences of maneuvers at precise distances from the pursuing missile and do not effectively account for uncertainty about the type and/or current state of the missile. This paper defines a new methodology for solving the missile countermeasures optimization problem under conditions of uncertainty. The resulting genetic programming system evolves programs that combine maneuvers with such countermeasures as chaff, flares, and jamming to optimize aircraft survivability. This methodology may be generalized to solve strategy optimization problems for intelligent, autonomous agents operating under conditions of uncertainty.

Aircraft↗
PubMed2006

[Comparison of SmartCare and spontaneous breathing trials for weaning old patients with chronic obstructive pulmonary diseases].

OBJECTIVE: To compare the outcome of the SmartCare and spontaneous breathing trials (SBT) for weaning old patients with chronic obstructive pulmonary diseases (COPD). METHODS: Thirty-eight COPD patients were enrolled in Department of Respiratory Medicine on the South Building, General Hospital of People's Liberation Army from January, 2003 to April, 2005. They mechanically ventilated for at least 3 d (age: 70 - 91 year, average: 83.3 +/- 4.3), randomly assigned to receive SmartCare (SC group, n = 13) or SBT (SBT group, n = 25). All patients were considered clinically and biologically stable, and therefore ready to be weaned from mechanical ventilation. In SC group, patients were ventilated with an inspiratory pressure (IPAP) support adjusted to achieve pH value > or = 7.35, saturation of oxygen in arterial blood (SaO2) > or = 90%, respiratory frequency (RR) > or = 10 and < or = 30 breaths/min, and fraction of inspired oxygen (FiO2) < or = 45%. In SBT group, the patients were placed in a weaning protocol utilizing increasing duration of spontaneous breathing. The following data were recorded at weaning: the acute physiology and chronic health evaluation II (APACHE II) score, arterial blood gases under mechanical ventilation, serum calcium, magnesium, and phosphorus, the days of ventilation before weaning and the duration of weaning. The patients of both groups were considered as successfully weaned when they were able to tolerate at least 48 consecutive hours of spontaneous breathing. Failure was defined in a patient who died during the weaning process or who still needed mechanical ventilation after at least 40 consecutive days of weaning. RESULTS: No significant differences were found between the groups at the onset of weaning from mechanical ventilation regarding APACHE II, serum albumin, calcium, magnesium, phosphorus, partial pressure of carbon dioxide in arterial blood (PaCO2), and the days of mechanical ventilation (t = 0.834, 0.696, 1.384, 0.682, 0.467, 0.816, 0.384, all P > 0.05). The pH value of the SBT group (7.45 +/- 0.05) was higher than the SC group (7.40 +/- 0.04, t = 3.263, P < 0.05). Although patients in the SC group spent less time in weaning than those in the SBT group, the difference was not significant [(8.54 +/- 2.09), (13.32 +/- 2.19) d for the SC and SBT groups, respectively, t = 1.320, P = 0.251]. The 7-d weaning success rate was greater in the SC group than the SBT group (77%, 40%, chi(2) = 4.677, P = 0.031). No significant difference was found in 14-d weaning success rate (77%, 64% in the SC and SBT groups, chi(2) = 0.661, P = 0.416). Fewer arterial blood analyses were performed in the SC group (3.5 +/- 3.1, 6.6 +/- 3.7, t = 2.710, P = 0.011). CONCLUSION: The SmartCare is better than SBT in weaning patients with COPD within 7 days.

Aged↗
PubMed1991

A multimedia Anatomy Browser incorporating a knowledge base and 3D images.

We describe a multimedia program for teaching anatomy. The program, called the Anatomy Browser, displays cross-sectional and topographical images, with outlines around structures and regions of interest. The user may point to these structures and retrieve text descriptions, view symbolic relationships between structures, or view spatial relationships by accessing 3-D graphics animations from videodiscs produced specifically for this program. The software also helps students exercise what they have learned by asking them to identify structures by name and location. The program is implemented in a client-server architecture, with the user interface residing on a Macintosh, while images, data, and a growing symbolic knowledge base of anatomy are stored on a fileserver. This architecture allows us to develop practical tutorial modules that are in current use, while at the same time developing the knowledge base that will lead to more intelligent tutorial systems.

Anatomy↗
PubMed2003

Neural architectures for robot intelligence.

We argue that direct experimental approaches to elucidate the architecture of higher brains may benefit from insights gained from exploring the possibilities and limits of artificial control architectures for robot systems. We present some of our recent work that has been motivated by that view and that is centered around the study of various aspects of hand actions since these are intimately linked with many higher cognitive abilities. As examples, we report on the development of a modular system for the recognition of continuous hand postures based on neural nets, the use of vision and tactile sensing for guiding prehensile movements of a multifingered hand, and the recognition and use of hand gestures for robot teaching. Regarding the issue of learning, we propose to view real-world learning from the perspective of data-mining and to focus more strongly on the imitation of observed actions instead of purely reinforcement-based exploration. As a concrete example of such an effort we report on the status of an ongoing project in our laboratory in which a robot equipped with an attention system with a neurally inspired architecture is taught actions by using hand gestures in conjunction with speech commands. We point out some of the lessons learnt from this system, and discuss how systems of this kind can contribute to the study of issues at the junction between natural and artificial cognitive systems.

Action Potentials↗
PubMed2000

Modeling of an intelligent pressure sensor using functional link artificial neural networks.

A capacitor pressure sensor (CPS) is modeled for accurate readout of applied pressure using a novel artificial neural network (ANN). The proposed functional link ANN (FLANN) is a computationally efficient nonlinear network and is capable of complex nonlinear mapping between its input and output pattern space. The nonlinearity is introduced into the FLANN by passing the input pattern through a functional expansion unit. Three different polynomials such as, Chebyschev, Legendre and power series have been employed in the FLANN. The FLANN offers computational advantage over a multilayer perceptron (MLP) for similar performance in modeling of the CPS. The prime aim of the present paper is to develop an intelligent model of the CPS involving less computational complexity, so that its implementation can be economical and robust. It is shown that, over a wide temperature variation ranging from -50 to 150 degrees C, the maximum error of estimation of pressure remains within +/- 3%. With the help of computer simulation, the performance of the three types of FLANN models has been compared to that of an MLP based model.

Algorithms↗
PubMed2002

[Actuator design and control exemplified by a urologic implant].

The state of the art concerning the use of actuators and sensors and the intelligent microprocessor-based control will be discussed on the basis of a novel urological implant, a fine tuned, sensor controlled artificial sphincter. A set of powerful actuators with a reaction time lower than 10 ms have been realised due to an appropriate design of components. This has been achieved at a supply voltage of 4.2 V and a power input lower than 0.1 mW. An optimal reliability as well as the comfort in operating the implant by the physician and the patient was gained by the use of different data technologies being adapted to the implanted system.

Artificial Intelligence↗
PubMed1988

Intelligent systems for human resources.

An intelligent system contains knowledge about some domain; it has sophisticated decision-making processes and the ability to explain its actions. The most important aspect of an intelligent system is its ability to effectively interact with humans to teach or assist complex information processing. Two intelligent systems are Intelligent Tutoring Systems (ITs) and Expert Systems. The ITSs provide instruction to a student similar to a human tutor. The ITSs capture individual performance and tutor deficiencies. These systems consist of an expert module, which contains the knowledge or material to be taught; the student module, which contains a representation of the knowledge the student knows and does not know about the domain; and the instructional or teaching module, which selects specific knowledge to teach, the instructional strategy, and provides assistance to the student to tutor deficiencies. Expert systems contain an expert's knowledge about some domain and perform specialized tasks or aid a novice in the performance of certain tasks. The most important part of an expert system is the knowledge base. This knowledge base contains all the specialized and technical knowledge an expert possesses. For an expert system to interact effectively with humans, it must have the ability to explain its actions. Use of intelligent systems can have a profound effect on human resources. The ITSs can provide better training by tutoring on an individual basis, and the expert systems can make better use of human resources through job aiding and performing complex tasks. With increasing training requirements and "doing more with less," intelligent systems can have a positive effect on human resources.

Artificial Intelligence↗
PubMedDate not supplied

Automatic monitoring system for artificial hearts using self organizing map.

This study presents an automatic monitoring system for artificial hearts. The self organizing map (SOM) was applied to monitoring and analysis of an aortic pressure (AoP) signal measured from an adult goat equipped with a total artificial heart. In the proposed system, two different SOMs were used to detect and classify abnormalities in the measured AoP signal. In the first stage, an ordinary SOM, taught with only normal AoP data, was used for detection of abnormalities on the basis of the quantization error in the real-time monitoring task. In the second stage, a supervised SOM was used for classification of abnormalities. The supervised SOM can be regarded as an ordinary SOM with an extra class vector for solving the classification problem. The class vector is assigned to every node in the second SOM as an output weight learned according to Kohonen's learning rule. The effectiveness of detection and classification of abnormalities using these two SOMs was confirmed.

Animals↗
PubMed1998

VM-in-Protégé: a study of software reuse.

Protégé is a system that encompasses a suite of graphical tools and a methodology for applying them to the task of creating and maintaining knowledge-based systems. One of our key goals for Protégé is to facilitate reuse on new problems of components of previously developed solutions. We investigated this reusability by applying preexisting library components in the Protégé system to a reconstruction of VM, a well-known rule-based system for ventilator management. The formal steps of the Protégé methodology-ontology creation, problem-solving method selection, knowledge engineering, and mapping-relation instantiation-were followed, and a working system with much of the reasoning capability of the original VM was created. The work illuminated important lessons regarding aspects of component reusability.

Algorithms↗
PubMed1989

Creation of realistic appearing simulated patient cases using the INTERNIST-1/QMR knowledge base and interrelationship properties of manifestations.

The Internist-1/Quick Medical Reference (QMR) knowledge base (KB) describes the clinical manifestations of some 600 diseases in the domain of internal medicine. This KB, while not representing deep causal modelling of disease processes, is nonetheless effective in providing medical diagnostic assistance through the QMR medical decision support system. One potential application of this extensive KB is the generation of simulated patient cases for use in educating health professionals. However, the "flat" KB is not adequate for this because the clinical manifestations used in the disease descriptions are not mutually independent. While it is theoretically possible to construct disease descriptions which embody pathophysiologic mechanisms of disease causality, it is not practical from the standpoint of resource utilization. Short of constructing a causal knowledge base, the authors herein describe the generation of realistic appearing simulated patient case data using existing information in the knowledge base. This existing information in the KB is in the form of properties which represent a shallow form of interrelationships of the manifestations. The authors conclude that this ability to generate simulated cases represents another view in which to look at an extensive knowledge base, as well as having application to constructing intelligent tutoring systems for health professionals in training.

Artificial Intelligence↗
PubMedDate not supplied

The intelligent systems in biomedicine laboratory in the Department of Automatic Control and Systems Engineering at the University of Sheffield, UK.

The group has been engaged in research into modelling and control in biomedicine for many years. Initially, this used quantitative approaches but increasingly this has moved towards qualitative techniques, in particular that of fuzzy logic. The current emphasis is on hybrid models (quantitative/qualitative) and hybrid intelligent algorithms (fuzzy logic, neural networks, evolutionary computing) applied into anaesthesia.

Algorithms↗