The seeds of artificial intelligence : SUMEX-AIM /

"March 1980."

Environmental scan report on artificial intelligence : strategy considerations for the U.S. Department of the Treasury.

"December 1983."

A system monitor for programs in artificial intelligence /

Bibliography: p. 84-85.

Report on Workshop on High Performance Computing and Communications for Grand Challenge Applications : computer vision, speech and natural language processing, and artificial intelligence /

Cover title.

An association scheme for artificial intelligence.

Cover title.

Navy Center for Applied Research in Artificial Intelligence.

Cover title.

Successful artificial insemination (AI) in the koala using neat and extended semen collected by electroejaculation (EE)

Presently AI in the koala has been based on the insemination of fresh undiluted semen collected with an artificial vagina (1). While this approach has been extremely successful, further refinement and implementation of AI for use with cryopreserved semen will require protocols that incorporate diluted semen collected by EE. Recent studies have shown that koala semen is likely to have an "ovulation factor" such that over-dilution may result in ovulation failure (2). The current study determined whether AI of EEed neat and/or diluted semen was capable of inducing a luteal phase and/or resulted in the production of pouch young. All koalas were inseminated in the breeding season between day 2 and 5 of oestrus and subsequently monitored for evidence of parturition (day 35) and return of oestrus. Successful induction of a luteal phase was based on evidence of an elevated progesterone concentration 28 days after insemination (2). All semen samples were collected by EE and seminal characteristics recorded (3). The diluent used for semen extension was Tris-citrate glucose (TCG) which contained antibiotics but no egg yolk (4). AI was conducted on conscious koalas using a "Cook koala insemination catheter" and a glass rod used to mimic penile thrusting (1). Three insemination treatments were used; (A) 1mL of undiluted semen (n = 9); (B) 2mL of 1:1 diluted semen (n = 9); and (C) 1 mL of 1:1 diluted semen (n = 9). The results of the AI trial are shown in Table 1. This study has shown that it is possible to use both neat and diluted semen (1:1; 1 or 2 mL) to successfully produce koala offspring at conception rates similar to those achieved following natural mating. Interestingly, dilution of semen had no apparent detrimental effect on induction of a luteal phase following AI.

Modelling and improving maintenance decisions:Having foresight with simulation and artificial intelligence

Machine breakdowns are one of the main sources of disruption and throughput fluctuation in highly automated production facilities. One element in reducing this disruption is ensuring that the maintenance team responds correctly to machine failures. It is, however, difficult to determine the current practice employed by the maintenance team, let alone suggest improvements to it. 'Knowledge based improvement' is a methodology that aims to address this issue, by (a) eliciting knowledge on current practice, (b) evaluating that practice and (c) looking for improvements. The methodology, based on visual interactive simulation and artificial intelligence methods, and its application to a Ford engine assembly facility are described. Copyright © 2002 Society of Automotive Engineers, Inc.

Evaluating the performance of a EuroDivisia index using artificial intelligence techniques

We compare two methods in order to predict inflation rates in Europe. One method uses a standard back propagation neural network and the other uses an evolutionary approach, where the network weights and the network architecture is evolved. Results indicate that back propagation produces superior results. However, the evolving network still produces reasonable results with the advantage that the experimental set-up is minimal. Also of interest is the fact that the Divisia measure of money is superior as a predictive tool over simple sum.

Evaluating the performance of a EuroDivisia index using artificial intelligence techniques

This paper compares two methods to predict in°ation rates in Europe. One method uses a standard back propagation neural network and the other uses an evolutionary approach, where the network weights and the network architecture are evolved. Results indicate that back propagation produces superior results. However, the evolving network still produces reasonable results with the advantage that the experimental set-up is minimal. Also of interest is the fact that the Divisia measure of money is superior as a predictive tool over simple sum.

Application of the Artificial Intelligence Algorithms for System Analysis of Multi Dimension Physiological Data for Developing Polyparametric Information System of Public Health Diagnostics

The polyparametric intelligence information system for diagnostics human functional state in medicine and public health is developed. The essence of the system consists in polyparametric describing of human functional state with the unified set of physiological parameters and using the polyparametric cognitive model developed as the tool for a system analysis of multitude data and diagnostics of a human functional state. The model is developed on the basis of general principles geometry and symmetry by algorithms of artificial intelligence systems. The architecture of the system is represented. The model allows analyzing traditional signs - absolute values of electrophysiological parameters and new signs generated by the model – relationships of ones. The classification of physiological multidimensional data is made with a transformer of the model. The results are presented to a physician in a form of visual graph – a pattern individual functional state. This graph allows performing clinical syndrome analysis. A level of human functional state is defined in the case of the developed standard (“ideal”) functional state. The complete formalization of results makes it possible to accumulate physiological data and to analyze them by mathematics methods.

Application of Artificial Intelligence Methods to Computer Design of Inorganic Compounds

In this paper the main problems for computer design of materials, which would have predefined properties, with the use of artificial intelligence methods are presented. The DB on inorganic compound properties and the system of DBs on materials for electronics with completely assessed information: phase diagram DB of material systems with semiconducting phases and DB on acousto-optical, electro-optical, and nonlinear optical properties are considered. These DBs are a source of information for data analysis. Using the DBs and artificial intelligence methods we have predicted thousands of new compounds in ternary, quaternary and more complicated chemical systems and estimated some of their properties (crystal structure type, melting point, homogeneity region etc.). The comparison of our predictions with experimental data, obtained later, showed that the average reliability of predicted inorganic compounds exceeds 80%. The perspectives of computational material design with the use of artificial intelligence methods are considered.

Application of the Artificial Intelligence Algorithms with a Cognitive Graphic as a Tool for a System Analysis of Electrophysiological Processes

Summarizing the accumulated experience for a long time in the polyparametric cognitive modeling of different physiological processes (electrocardiogram, electroencephalogram, electroreovasogram and others) and the development on this basis some diagnostics methods give ground for formulating a new methodology of the system analysis in biology. The gist of the methodology consists of parametrization of fractals of electrophysiological processes, matrix description of functional state of an object with a unified set of parameters, construction of the polyparametric cognitive geometric model with artificial intelligence algorithms. The geometry model enables to display the parameter relationships are adequate to requirements of the system approach. The objective character of the elements of the models and high degree of formalization which facilitate the use of the mathematical methods are advantages of these models. At the same time the geometric images are easily interpreted in physiological and clinical terms. The polyparametric modeling is an object oriented tool possessed advances functional facilities and some principal features.

Artificial intelligence and criminal evidence: A few topics

Abstract not available

Analysis on the connotation of probability in the artificial intelligence algorithm for economic decision making.

This paper analyzes the inner relations between classical sub-scheme probability and statistic probability, subjective probability and objective probability, prior probability and posterior probability, transition probability and probability of utility, and further analysis the goal, method, and its practical economic purpose which represent by these various probability from the perspective of mathematics, so as to deeply understand there connotation and its relation with economic decision making, thus will pave the route for scientific predication and decision making.