Object detection using feature subset selection

Past work on object detection has emphasized the issues of feature extraction and classification, however, relatively less attention has been given to the critical issue of feature selection. The main trend in feature extraction has been representing the data in a lower dimensional space, for example, using principal component analysis (PCA). Without using an effective scheme to select an appropriate set of features in this space, however, these methods rely mostly on powerful classification algorithms to deal with redundant and irrelevant features. In this paper, we argue that feature selection is an important problem in object detection and demonstrate that genetic algorithms (GAs) provide a simple, general, and powerful framework for selecting good subsets of features, leading to improved detection rates. As a case study, we have considered PCA for feature extraction and support vector machines (SVMs) for classification. The goal is searching the PCA space using GAs to select a subset of eigenvectors encoding important information about the target concept of interest. This is in contrast to traditional methods selecting some percentage of the top eigenvectors to represent the target concept, independently of the classification task. We have tested the proposed framework on two challenging applications: vehicle detection and face detection. Our experimental results illustrate significant performance improvements in both cases.     

Synchronization of stochastic Markovian jump neural networks with reaction-diffusion terms

In this paper, we address the synchronization problem of a class of stochastic Markovian jump reaction-diffusion neural networks with Dirichlet boundary conditions. By using the Lyapunov-Krasovskii functional method, feedback control approach, and stochastic analysis technique, the sufficient synchronization conditions including the information of reaction-diffusion terms are obtained, which are expressed as linear matrix inequalities (LMIs). Finally, the effectiveness of the developed methods is shown by simulation examples.     

Optimization of optical single sideband configurations for radio over fiber transmission and multi-type data communication over a DWDM link

Two new optical single side band (OSSB) configurations for radio frequency (RF) transmission of data are proposed based on the structures that have been designed for baseband digital data transmission. The performances of these schemes are evaluated based on the relevant eye diagrams and bit error rate (BER). The proposed configurations are studied and analyzed mathematically. Eye diagrams and BER’s indicate an acceptable performance for the suggested structures. Feasible settings for the RF electrical power of the links are considered and the link performance for each setting is evaluated. A 4-dense wavelength division multiplexing (4-DWDM) link is considered for transmitting different types of data over a single mode fiber (SMF). Baseband digital data in the format of OSSB and RF-OSSB signals are transmitted over a 4-DWDM link. Furthermore, the link performance is considered for different electrical power settings of OSSB signal in order to achieve efficient transmission for DWDM network.     

Automatic mapping of parallel applications on multicore architectures using the Servet benchmark suite

Servet is a suite of benchmarks focused on detecting a set of parameters with high influence on the overall performance of multicore systems. These parameters can be used for autotuning codes to increase their performance on multicore clusters. Although Servet has been proved to detect accurately cache hierarchies, bandwidths and bottlenecks in memory accesses, as well as the communication overhead among cores, up to now the impact of the use of this information on application performance optimization has not been assessed. This paper presents a novel algorithm that automatically uses Servet for mapping parallel applications on multicore systems and analyzes its impact on three testbeds using three different parallel programming models: message-passing, shared memory and partitioned global address space (PGAS). Our results show that a suitable mapping policy based on the data provided by this tool can significantly improve the performance of parallel applications without source code modification.