This paper proposes a word segmentation method for machine-printed text lines. It utilizes gaps and special symbols as delimiters between words. A gap clustering technique is used to identify the gaps between words re...
详细信息
This paper proposes a word segmentation method for machine-printed text lines. It utilizes gaps and special symbols as delimiters between words. A gap clustering technique is used to identify the gaps between words regardless of the gap-size variations among different document images. Next a special symbol detection technique is applied to find two types of special symbols lying between words. An experiment with 1,675 text lines in 100 different English and Korean documents shows that the proposed method achieves a high accuracy of word segmentation.
A class of artificial neural networks with a two-layer feedback topology to solve nonlinear discrete dynamic optimization problems is developed. Generalized recurrent neuron models are introduced. A direct method to a...
详细信息
A class of artificial neural networks with a two-layer feedback topology to solve nonlinear discrete dynamic optimization problems is developed. Generalized recurrent neuron models are introduced. A direct method to assign the weights of neural networks is presented. The method is based on Bellmann's Optimality Principle and on the interchange of information which occurs during the synaptic chemical processing among neurons. A comparative analysis of the computational requirements is made. The analysis shows advantages of this approach as compared to the standard dynamic programming algorithm. The technique has been applied to several important optimization problems, such as shortest path and control optimal problems.
We present a novel approach to classification, based on a tight coupling of instance-based learning and a genetic algorithm. In contrast to the usual instance-based learning setting, we do not rely on (parts of) the g...
详细信息
This paper describes BR-4, a discovery system that integrates several research tasks in modeling the discovery of certain quantum properties and conservation laws by physicists in this century. The program is directed...
详细信息
As technology advances and our dependency on software increases, the requirement to develop the correct means to improve quality in both the deveiopment phase and the maintenance phase of software life cycle support b...
As technology advances and our dependency on software increases, the requirement to develop the correct means to improve quality in both the deveiopment phase and the maintenance phase of software life cycle support becomes increasingly significant. The focus of this paper is on the dilemma facing software engineering in maintaining quality within the constraints of the maintenance phase. The paper further proposes that the software maintenance process can also be analvzed and improved using statistical process control (SPC) techniques. The methods discussed in this paper have been proposed for use in the Software Maintenance project at NUWC Detachment Norfolk. Upon successful testing at NUWC Detachment Norfolk, they will be forwarded to the AN/SQQ-89(V) (interagencv) Software Quality Evaluation Committee for use by other agencies which are developing and maintaining AN/SQQ-89(V) software.
This paper describes a modularized AI system being built to help improve electromagnetic compatibility (EMC) among shipboard topside equipment and their associated systems. CLEER is intended to act as an easy to use i...
详细信息
This paper describes a modularized AI system being built to help improve electromagnetic compatibility (EMC) among shipboard topside equipment and their associated systems. CLEER is intended to act as an easy to use integrator of existing expert knowledge and pre-existing data bases and large scale analytical models. Due to these interfaces; to the need for portability of the software; and to artificialintelligence related design requirements (such as the need for spatial reasoning, expert data base management, model base management, track-based reasoning, and analogical (similar ship) reasoning) it was realized that traditional expert system shells would be inappropriate, although relatively off-the-shelf AI technology could be incorporated. In the same vein, the rapid prototyping approach to expert system design and knowledge engineering was not pursued in favor of a rigorous systems engineering methodology. The critical design decisions affecting CLEER's development are summarized in this paper along with lessons learned to date all in terms of “how,” “why,” and “when” specific features are being developed.
作者：
MALKOFF, DBMOY, MCWILLIAMS, HLDr. Donald B. Malkoff majored in physics as an undergraduate at Harvard University. He received an M.D. degree from the University of Pittsburgh School of Medicine in 1960. This was followed by an internship and residency in neurology at University Hospital in Ann Arbor
Michigan. He spent several years at the National Institutes of Health engaged in gerontology research has practiced and taught clinical neurology and in 1983 received an M.S. degree in computer science at the University of California San Diego. Currently Dr. Malkoff is employed by the Navy Personnel Research and Development Center in San Diego California where he is senior investigator in a human factor/computer display-and-control project involving the DDG-51 gas turbine propulsion unit. He is a member of the American Academy of Neurology the Society for Neuroscience the American Association for Artificial Intelligence and the Association for Computing Machinery. Dr. Malkoff is certified by the American Board of Psychiatry and Neurology has taught computer science at UCSD and published in several research areas including magnetoencephalography and electron microscopy. His basic interests are in the areas of artificial intelligence and learning expert systems particularly as they apply to the problems of fault-detection and control. Dr. Melvyn C. Moy received his undergraduate training in mathematics and chemistry at the University of Texas
Austin. He studied experimental psychology at the University of Wisconsin Madison receiving his M.S. in 1970 and Ph.D. in 1972. He served as an assistant professor at the University of South Dakota where he taught experimental design and methodology for a year before joining the Navy Personnel Research and Development Center in 1973. His work and research since then spans across many application areas such as the development of manpower planning models for the Navy the design of operational decision aids the human engineering of interactive large-scale war gaming systems and the evaluation o
The ship fire main has undergone considerable development throughout the past 2,000 years, resulting in a system that is critical both for normal ship function and for ship survivability in emergencies. Because of its...
详细信息
The ship fire main has undergone considerable development throughout the past 2,000 years, resulting in a system that is critical both for normal ship function and for ship survivability in emergencies. Because of its complexity, the modern firemain system is highly vulnerable to malfunction and to damage during combat. Firemain fault detection and fault recovery are currently conducted manually by damage control teams. The advantages and disadvantages of this method are discussed, and alternative methods of fault detection and recovery are explored. An interactive computer program is introduced which uses central control over remotely situated valves to facilitate fault detection and recovery, significantly reducing recovery-time and manpower requirements. These reductions may result in savings of lives, ship systems, and ships themselves. The computer program is based upon an algorithm which is, in effect, a prescription that can be followed manually by the operator or be completely automated. The color graphic display which is used for monitoring can also be utilized for the training of damage control operators or for the evaluation of other algorithms for firemain control. Alternative firemain hardware and configurations could lead to even more efficient methods of fault detection and recovery as well as improved firemain water supply management in general.
暂无评论