Connectivity and performance tradeoffs in the cascade correlationlearning architecture

The cascade correlation is a very flexible, efficient and fast algorithm for supervised learning. It incrementally builds the network by adding hidden units one at a time, until the desired input/output mapping is achieved. It connects all the previously installed units to the new unit being added. Consequently, each new unit in effect adds a new layer and the fan-in of the hidden and output units keeps on increasing as more units get added. The resulting structure could be hard to implement in VLSI, because the connections are irregular and the fan-in is unbounded. Moreover, the depth or the propagation delay through the resulting network is directly proportional to the number of units and can be excessive. We have modified the algorithm to generate networks with restricted fan-in and small depth (propagation delay) by controlling the connectivity. Our results reveal that there is a tradeoff between connectivity and other performance attributes like depth, total number of independent parameters, and learning time.     

Fuzzy sets-a convenient fiction for modeling vagueness andpossibility

This paper is a reply to Laviolette and Seaman's critical discussion of fuzzy set theory. Rather than questioning the interest of the Bayesian approach to uncertainty, some reasons why Bayesian find the idea of a fuzzy set not palatable are laid bare. Some links between fuzzy sets and probability that Laviolette and Seaman seem not to be aware of are pointed out. These links suggest that, contrary to the claim sometimes found in the literature, probability theory is not a special case of fuzzy set theory. The major objection to Laviolette and Seaman is that they found their critique on as very limited view of fuzzy sets, including debatable papers, while they fail to account for significant works pertaining to axiomatic derivation of fuzzy set connectives, possibility theory, fuzzy random variables, among others     

Management of multidimensional discrete data

Spatial database management involves two main categories of data: vector and raster data. The former has received a lot of in-depth investigation; the latter still lacks a sound framework. Current DBMSs either regard raster data as pure byte sequences where the DBMS has no knowledge about the underlying semantics, or they do not complement array structures with storage mechanisms suitable for huge arrays, or they are designed as specialized systems with sophisticated imaging functionality, but no general database capabilities (e.g., a query language). Many types of array data will require database support in the future, notably 2-D images, audio data and general signal-time series (1-D), animations (3-D), static or time-variant voxel fields (3-D and 4-D), and the ISO/IEC PIKS (Programmer's Imaging Kernel System) BasicImage type (5-D). In this article, we propose a comprehensive support ofmultidimensional discrete data (MDD) in databases, including operations on arrays of arbitrary size over arbitrary data types. A set of requirements is developed, a small set of language constructs is proposed (based on a formal algebraic semantics), and a novel MDD architecture is outlined to provide the basis for efficient MDD query evaluation.     

A semantic modeling approach for image retrieval by content

We introduce a semantic data model to capture the hierarchical, spatial, temporal, and evolutionary semantics of images in pictorial databases. This model mimics the user's conceptual view of the image content, providing the framework and guidelines for preprocessing to extract image features. Based on the model constructs, a spatial evolutionary query language (SEQL), which provides direct image object manipulation capabilities, is presented. With semantic information captured in the model, spatial evolutionary queries are answered efficiently. Using an object-oriented platform, a prototype medical-image management system was implemented at UCLA to demonstrate the feasibility of the proposed approach.     

Review of the Robotica software package for robotic manipulators

Robotica is a computer-aided design package for robotic nmanipulators developed at the Coordinated Science Laboratory at the University of Illinois at Urbana- Champaign. The package is a collection of function definitions for the Mathematica symbolic mathematics program. Robotica can be used either with an X- Windows graphical user interface (GUI) on a Sun Workstation or as an included function definition file within Mathematica. The primary feature of Robotica is the ability to compute, symbolically or numerically, the kinematic and dynamic equations of arbitrary robot systems utilizing the standard Denevit-Hartenburg (DH) kinematic convention. Robotica also provides the ability to visualize these arbitrary manipulators using the X- Windows graphical interface to the Mathematica graphics routines. The paper looks at the usage of Robotica at the Air Force Institute of Technology, comments on the features of Robotica, and needs for improvement and suggestions for future development     

Continuous measurement of cardiac output by the Fick principle in infants and children: comparison with the thermodilution method

OBJECTIVE: To compare a system that continuously monitors cardiac output by the Fick principle with measurements by the thermodilution technique in pediatric patients. DESIGN: Prospective direct comparison of the above two techniques. SETTING: Pediatric intensive care unit of a university hospital. PATIENTS: 25 infants and children, aged 1 week to 17 years (median 10 months), who had undergone open heart surgery were studied. Only patients without an endotracheal tube leak and without a residual shunt were included. METHODS: The system based on the Fick principle uses measurements of oxygen consumption taken by a metabolic monitor and of arterial and mixed venous oxygen saturation taken by pulse- and fiberoptic oximetry to calculate cardiac output every 20s. INTERVENTIONS: In every patient one pair of measurements was taken. Continuous Fick and thermodilution cardiac output measurements were performed simultaneously, with the examiners remaining ignorant of the results of the other method. RESULTS: Cardiac output measurements ranged from 0.21 to 4.55 l/min. A good correlation coefficient was found: r2 = 0.98; P < 0.001; SEE = 0.41 l/min. The bias is absolute values and in percent of average cardiac output was - 0.05 l/min or - 4.4% with a precision of 0.32 l/min or 21.3% at 2 SD, respectively. The difference was most marked in a neonate with low cardiac output. CONCLUSION: Continuous measurement of cardiac output by the Fick principle offers a convenient method for the hemodynamic monitoring of unstable infants and children.