Kevin L. Priddy

Self-localization of wireless sensor networks using self-organizing maps

Recently there has been a renewed interest in the notion of deploying large numbers of networked sensors for applications ranging from environmental monitoring to surveillance. In a typical scenario a number of sensors are distributed in a region of interest. Each sensor is equipped with sensing, processing and communication capabilities. The information gathered from the sensors can be used to detect, track and classify objects of interest. For a number of locations the sensors location is crucial in interpreting the data collected from those sensors. Scalability requirements dictate sensor nodes that are inexpensive devices without a dedicated localization hardware such as GPS. Therefore the network has to rely on information collected within the network to self-localize. In the literature a number of algorithms has been proposed for network localization which uses measurements informative of range, angle, proximity between nodes. Recent work by Patwari and Hero relies on sensor data without explicit range estimates. The assumption is that the correlation structure in the data is a monotone function of the intersensor distances. In this paper we propose a new method based on unsupervised learning techniques to extract location information from the sensor data itself. We consider a grid consisting of virtual nodes and try to fit grid in the actual sensor network data using the method of self organizing maps. Then known sensor network geometry can be used to rotate and scale the grid to a global coordinate system. Finally, we illustrate how the virtual nodes location information can be used to track a target.

Dynamic optimization for optimal control of water distribution systems

In this paper we consider the design of intelligent control policies for water distribution systems. The controller presented in this paper is based upon a hybrid system that utilizes dynamic programming and rules as design constraints, to minimize average costs over a long time horizon under constraints on operation parameters. The method is very general and is reported here as a controller for water distribution system. In the example presented we obtain a 12.5 percent reduction in energy usage over the optimal level-based control design. We present the guiding principles used in the design and the results for a simulated system that is representative of a typical water pumping station. The design is fully adaptable to changing operating conditions and has applicability to a wide range of scheduling problems.

Reinforcement learning and design of nonparametric sequential decision networks

In this paper we discuss the design of sequential detection networks for nonparametric sequential analysis. We present a general probabilistic model for sequential detection problems where the sample size as well as the statistics of the sample can be varied. A general sequential detection network handles three decisions. First, the network decides whether to continue sampling or stop and make a final decision. Second, in the case of continued sampling the network chooses the source for the next sample. Third, once the sampling is concluded the network makes the final classification decision. We present a Q-learning method to train sequential detection networks through reinforcement learning and cross-entropy minimization on labeled data. As a special case we obtain networks that approximate the optimal parametric sequential probability ratio test. The performance of the proposed detection networks is compared to optimal tests using simulations.

Front Matter: Volume 6560

This PDF file contains the front matter associated with SPIE Proceedings Volume 6560, including the Title Page, Copyright information, Table of Contents, Introduction (if any), and the Conference Committee listing.

Computational intelligence: Is it real or smoke and mirrors?

With the recent release of the movie AI, there is interest in artificial intelligence and in just how far we can take computational intelligence. This paper discusses the advances made in the computational intelligence arena and brings perspective to what may be possible in the future.