Basis For Pattern Recognition Research Articles

Electroencephalography Symmetry in Power, Waveform and Power Spectrum in Major Depression.

Depression is a harmful disease with high incidence. However, no effective method based on physiological information detection has been published to diagnose depression. Electroencephalography (EEG) has been used as a tool to detect physiological information of depressed patients and the symmetry of EEG receives much attention. This research focused on the symmetry of EEG in left and right homologous brain regions. 22 healthy volunteers and 41 volunteers of major depression were tested and three methods, average power ratio, waveform correlation and power spectral correlation, were adopted to measure the symmetry in all frequency bands and all brain regions. After t-test, homologous site pairs in particular frequency bands with significant differences between major depressed patients and controls were found out. Then sample entropy analysis was adopted, trying to figure out further connections between EEG symmetry and major depression. The accuracy tests were also taken and the average accuracy of some tests could reach 93.7%. The result of this research can hopefully serve as a theoretical basis for pattern recognition in the diagnosis of depression. The accuracy of pattern recognition based on multiple processing methods and sites will increase dramatically.

Predicting Motorway Traffic Performance by Data Fusion of Local Sensor Data and Electronic Toll Collection Data

In this article data fusion from different sources in order to improve estimation and prediction accuracy of traffic states on motorways is proposed. This is demonstrated in two case studies on an intraurban and an interurban motorway section in Austria. Data fusion combines local detector data and speed data from the Electronic Toll Collection (ETC) system for heavy goods vehicles (HGV). A macroscopic model for open motorway sections has been used to estimate passenger car and HGV density, applying a standard state-space model and a linear Kalman filter. The resulting historical database of 4 months of speed-density patterns has been used as a basis for pattern recognition. A nonparametric kernel predictor with memory length of 9 and 18 hours has been used to predict HGV speed for a prediction horizon of 15 minutes to 2 hours. The results showed a good overall prediction accuracy. Correlation analysis analysis showed little bias of predicted speed for free flow and congested time intervals, whereas transition states between free flow and congestion were frequently biases. The prediction accuracy can be improved by applying a combination of different prediction methods. However, the computational performance of the predictor needs to be further improved prior to implementation into a traffic management center.

Impact of sampled data on an optical joint transform correlator

Coherent optical systems are well known for performing certain operations such as Fourier and Fresnel transformation and pattern recognition. The basis for pattern recognition in many coherent optical systems is the correlator. This paper discusses the effect of undersampling in an optical joint transform correlator which has a sampled-data input, detectors of size 1 x i resolution elements in the Fourier plane, and detectors of size 1 x 1 resolution elements in the correlation plane, where i is an integer. After the undersampling, it is shown that the correlation plane still contains the needed data, the shape of the correlation surfaces are unchanged, and the different correlation terms just move closer together. It is shown that the penalty for undersampling is that the amount of input data must be reduced by a factor of i. It is also shown that a digital simulation using a discrete Fourier transform gives an accurate prediction of the optical correlator performance. Results from the simulation are given to verify the theory.

Representation of structured events and efficient procedures for their recognition

Structured events are configurations of objects in logical, spatial, temporal or activity relations. A parameterized structural representation system for this class of events is discussed. Parameters in such representations are arbitrarily chosen symbols used to insure consistent references to the same object in diverse relations. All-or-none matching of two representations is the basis for pattern recognition. In this framework, descriptions of pattern or concept prototypes act as structural templates for stimuli. As a result, recognition can be performed in a natural and structural way and is unaffected by manipulations of irrelevant variables. Typical recognition procedures are reviewed and a variety of alternative approaches are considered in light of the potential combinatorial explosions which might arise in applications of these procedures. One alternative is proposed which can exploit both redundancy among partially matching templates and computational parallelism in exhaustive search (recognition) problems. Another possibility considered is to find special recognition procedures for particular recognition problems. For example, to accomplish word recognition in speech understanding systems, highly practical techniques exist to match many templates in parallel (simultaneously) using only simple bit string operations. In addition, both the possibility of additional heuristic approaches to general recognition procedures and the use of less general relational representations are also considered in this paper.