Lovell Hodge Ph.D.

The objective of this research is to investigate the scalability and optimality of an automated system for multiple sensor planning using multiple communicating agents. The problem domain is such that a single sensor system would not provide adequate information for a given sensor task. Due to the inherently complex interdependencies of multi-sensor systems, traditional optimization algorithms for sensor placement are not flexible enough to provide real time scalability and flexibility. This… Mehr zeigen

The objective of this research is to investigate the scalability and optimality of an automated system for multiple sensor planning using multiple communicating agents. The problem domain is such that a single sensor system would not provide adequate information for a given sensor task. Due to the inherently complex interdependencies of multi-sensor systems, traditional optimization algorithms for sensor placement are not flexible enough to provide real time scalability and flexibility. This research addresses those limitations. Empirical results suggest that polynomial convergence is maintained even as the number of sensors is increased. Weniger anzeigen

This paper presents an automated system for multiple sensor placement based on the coordinated decisions of independent, intelligent agents. The problem domain is such that a single sensor system would not provide adequate information for a given sensor task. Hence, it is necessary to incorporate multiple sensors in order to obtain complete information. The overall goal of the system is to provide the surface coverage necessary to perform feature inspection on one or more target objects in a… Mehr zeigen

This paper presents an automated system for multiple sensor placement based on the coordinated decisions of independent, intelligent agents. The problem domain is such that a single sensor system would not provide adequate information for a given sensor task. Hence, it is necessary to incorporate multiple sensors in order to obtain complete information. The overall goal of the system is to provide the surface coverage necessary to perform feature inspection on one or more target objects in a cluttered scene. This is accomplished by a group of cooperating intelligent sensors. In this system, the sensors are mobile, the target objects are stationary and each agent controls the position of a sensor and has the ability to communicate with other agents in the environment. By communicating desires and intentions, each agent develops a mental model of the other agents' preferences, which is used to avoid or resolve conflict situations. In this paper we utilize cameras as the sensors. The experimental results illustrate the feasibility of the autonomous deployment of the sensors and that this deployment can occur with sufficient accuracy as to allow the inspection task to be performed. Weniger anzeigen

This paper presents a multi-agent system for coordinating the deployment of multiple sensors in a modeled environment. The sensing task is the maximal sensor coverage of one or more targets in a scene and the position of each sensor is controlled by an autonomous agent. The agents rely on negotiation to achieve the level of coordination necessary to accomplish the given sensing task.

An ensemble of neural networks offers several advantages over classical single classifier systems when applied to complex pattern classification problems. However, the performance of the ensemble as a unit depends not only on the effective aggregation of the modules decisions, but also on the accuracy of the individual classification decisions of each module. The accuracy at the modular level is a result of the quality of training received by each module. This paper presents an adaptive… Mehr zeigen

An ensemble of neural networks offers several advantages over classical single classifier systems when applied to complex pattern classification problems. However, the performance of the ensemble as a unit depends not only on the effective aggregation of the modules decisions, but also on the accuracy of the individual classification decisions of each module. The accuracy at the modular level is a result of the quality of training received by each module. This paper presents an adaptive training algorithm that can be used to direct the training of the individual modules so as to improve the classification accuracy and training efficiency of the ensemble. Weniger anzeigen

The modular neural network offers several advantages over classical non-modular neural network approaches to complex pattern classification problems. However, the accuracy of the modular approach depends greatly on the accurate fusion of the individual classification decisions. The paper presents a method for improving the overall accuracy of modular neural networks by incorporating an adaptive decision fusion mechanism. The proposed algorithm offers significant improvement over typical modular… Mehr zeigen

The modular neural network offers several advantages over classical non-modular neural network approaches to complex pattern classification problems. However, the accuracy of the modular approach depends greatly on the accurate fusion of the individual classification decisions. The paper presents a method for improving the overall accuracy of modular neural networks by incorporating an adaptive decision fusion mechanism. The proposed algorithm offers significant improvement over typical modular networks by evolving a more informed decision fusion mechanism that can greatly improve the final classification decision for complex classification tasks. Weniger anzeigen

This paper presents an investigation of the use of artificial neural networks in a hierarchical arrangement for the classification of cell image data obtained from smears. The aim is to distinguish between various types of cells and possibly noncellular material based on one or more distinct feature sets obtained from the image data. The extremely divergent characteristics of the cell data makes this a real world classification problem with no easy solution. The paper focuses on the use of… Mehr zeigen

This paper presents an investigation of the use of artificial neural networks in a hierarchical arrangement for the classification of cell image data obtained from smears. The aim is to distinguish between various types of cells and possibly noncellular material based on one or more distinct feature sets obtained from the image data. The extremely divergent characteristics of the cell data makes this a real world classification problem with no easy solution. The paper focuses on the use of backpropagation and learning vector quantization as the artificial neural network classification algorithms. A methodology for the design of the classification hierarchy is presented and the results of experiments involving cell data from smears are analyzed. Weniger anzeigen