Browsing by Subject "particle filter"
Now showing 1 - 2 of 2
Results Per Page
Sort Options
Item Modeling Gene Regulatory Networks from Time Series Data using Particle Filtering(2012-10-19) Noor, AminaThis thesis considers the problem of learning the structure of gene regulatory networks using gene expression time series data. A more realistic scenario where the state space model representing a gene network evolves nonlinearly is considered while a linear model is assumed for the microarray data. To capture the nonlinearity, a particle filter based state estimation algorithm is studied instead of the contemporary linear approximation based approaches. The parameters signifying the regulatory relations among various genes are estimated online using a Kalman filter. Since a particular gene interacts with a few other genes only, the parameter vector is expected to be sparse. The state estimates delivered by the particle filter and the observed microarray data are then fed to a LASSO based least squares regression operation, which yields a parsimonious and efficient description of the regulatory network by setting the irrelevant coefficients to zero. The performance of the aforementioned algorithm is compared with Extended Kalman filtering (EKF), employing Mean Square Error as fidelity criterion using synthetic data and real biological data. Extensive computer simulations illustrate that the particle filter based gene network inference algorithm outperforms EKF and therefore, it can serve as a natural framework for modeling gene regulatory networks.Item Robotic localization of hostile networked radio sources with a directional antenna(Texas A&M University, 2007-04-25) Hu, QiangOne of the distinguishing characteristics of hostile networked radio sources (e.g., enemy sensor network nodes), is that only physical layer information and limited medium access control (MAC) layer information of the network is observable. We propose a scheme to localize hostile networked radio sources based on the radio signal strength and communication protocol pattern analysis using a mobile robot with a directional antenna. We integrate a Particle Filter algorithm with a new sensing model which is built on a directional antenna model and Carrier Sense Multiple Access (CSMA)-based MAC protocol model. we model and analyze the channel idle probability and busy collision probability as a function of the number of radio sources in the CSMA protocol modeling. Based on the sensing model, we propose a particle-filter-based scheme to simultaneously estimate the number and the positions of networked radio sources. We provide a localization scheme based on the method of steepest descent for the purpose of performance comparison. Simulation results demonstrate that our proposed localization scheme has a better success rate than the scheme based on the steepest descent at different tolerant distances.