No abstract

Ontological conceptualization refers to the process of creating an abstract view of the domain of interest through a set of interconnected concepts. In this paper, a thesaurus-based methodology is proposed for systematic ontological conceptualization in the manufacturing domain. The methodology has three main phases, namely, thesaurus development, thesaurus evaluation, and thesaurus conversion and it uses simple knowledge organization system (SKOS) as the thesaurus representation formalism. The concept-based nature of a SKOS thesaurus makes it suitable for identifying important concepts in the domain. To that end, novel thesaurus evaluation and thesaurus conversion metrics that exploit this characteristic are presented. The ontology conceptualization methodology is demonstrated through the development of a manufacturing thesaurus, referred to as ManuTerms. The concepts in ManuTerms can be converted into ontological classes. The whole conceptualization process is the stepping stone to developing more axiomatic ontologies. Although the proposed methodology is developed in the context of manufacturing ontology development, the underlying methods, tools, and metrics can be applied to development of any domain ontology. The developed thesaurus can serve as a standalone lightweight ontology and its concepts can be reused by other ontologies or thesauri.

A novel knowledge discovery technique using neural networks is presented. A neural network is trained to learn the correlations and relationships that exist in a dataset. The neural network is then pruned and modified to generalize the correlations and relationships. Finally, the neural network is used as a tool to discover all existing hidden trends in four different types of crimes (murder, rape, robbery, and auto theft) in US cities as well as to predict trends based on existing knowledge inherent in the network.

A biologically inspired visual system capable of motion detection and pursuit motion is implemented using a Discrete Leaky Integrate-and-Fire (DLIF) neuron model. The system consists of a visual world, a virtual retina, the neural network circuitry (DLIF) to process the information, and a set of virtual eye muscles that serve to move the input area (visual field) of the retina within the visual world. Temporal aspects of the DLIF model are heavily exploited including: spike propagation latency, relative spike timing, and leaky potential integration. A novel technique for motion detection is employed utilizing coincidence detection aspects of the DLIF and relative spike timing. The system as a whole encodes information using relative spike timing of individual action potentials as well as rate coded spike trains. Experimental results are presented in which the motion of objects is detected and tracked in real and animated video. Pursuit motion is successful using linear and also sinusoidal paths which include object velocity changes. The visual system exhibits dynamic overshoot correction heavily exploiting neural network characteristics. System performance is within the bounds of real-time applications.

No abstract