Hugo D. Navone

Weed seeds identification by machine vision

Abstract The implementation of new methods for reliable and fast identification and classification of seeds is of major technical and economical importance in the agricultural industry. As in ocular inspection, the automatic classification of seeds should be based on knowledge of seed size, shape, color and texture. In this work, we assess the discriminating power of these characteristics for the unique identification of seeds of 57 weed species. Using the performance of a naive Bayes classifier as selection criterion, we identified a nearly optimal set of 12 (six morphological+four color+two textural) seed characteristics to be used as classification parameters. We found that, as expected, size and shape characteristics have larger discriminating power than color and textural ones. However, all these features are required to reach an identification performance acceptable for practical applications. In spite of its simplicity, the naive Bayes classifier reveals itself surprisingly good for the identification of seed species. This might be due to the careful selection of the feature set, leading to nearly independent parameters as assumed by this method. We also found that, using the same feature set, a more sophisticated classifier based on an artificial neural network committee performs only slightly better than this simple Bayesian approach.

Aggregation algorithms for neural network ensemble construction

How to generate and aggregate base learners to have optimal ensemble generalization capabilities is an important questions in building composite regression/classification machines. We present here an evaluation of several algorithms for artificial neural networks aggregation in the regression settings, including new proposals and comparing them with standard methods in the literature. We also discuss a potential problem with sequential algorithms: the non frequent but damaging selection through their heuristics of particularly bad ensemble members. We show that one can cope with this problem by allowing individual weighting of aggregate members. Our algorithms and their weighted modifications are favorably tested against other methods in the literature, producing a performance improvement on the standard statistical databases used as benchmarks.

Two-dimensional digital processing of speckle photography fringes. 3: Accuracy in angular determination

The performance of a previously published algorithm for the determination of the direction of speckle photography fringes is evaluated through computer simulation. Numerical results indicate that even in the extreme cases of patterns with very low fringe densities and visibilities contaminated with high noise levels, fringe direction can be determined with a fair degree of accuracy (0.5 degrees ).

Selecting diverse members of neural network ensembles

Ensembles of artificial neural networks have been used as classification/regression machines, showing improved generalization capabilities that outperform those of single networks. However, it has been recognized that for aggregation to be effective the individual network must be as accurate and diverse as possible. An important problem is, then, how to choose the aggregate members in order to have an optimal compromise between these two conflicting conditions. We propose here a new method for selecting members of regression/classification ensembles that leads to small aggregates with few but very diverse individual predictors. Using artificial neural networks as individual learners, the algorithm is favorably tested against other methods in the literature, producing a remarkable performance improvement on the standard statistical databases used as benchmarks. In addition, and as a concrete application, we study the sunspot time series and predict the remaining of the current cycle 23 of solar activity.

Predictions of the maximum amplitude for solar cycle 23 and its subsequent behavior using nonlinear methods

Two nonlinear methods are employed for the prediction of the maximum amplitude for solar cycle 23 and its declining behavior. First, a new heuristic method based on the second derivative of the (conveniently smoothed) sunspot data is proposed. The curvature of the smoothed sunspot data at cycle minimum appears to correlate (R ≃ 0.92) with the cycles later-occurring maximum amplitude. Secondly, in order to predict the near-maximum and declining activity of solar cycle 23, a neural network analysis of the annual mean sunspot time series is also performed. The results of the present study are then compared with some other recent predictions.

A late-stopping method for optimal aggregation of neural networks.

Ensembles of artificial neural networks have been used in the last years as classification/regression machines, showing improved generalization capabilities that outperform those of single networks. However, it has been recognized that for aggregation to be effective the individual networks must be as accurate and diverse as possible. An important problem is, then, how to tune the aggregate members in order to have an optimal compromise between these two conflicting conditions. We propose here a simple method for constructing regression/classification ensembles of neural networks that leads to overtrained aggregate members with an adequate balance between accuracy and diversity. The algorithm is favorably tested against other methods recently proposed in the literature, producing an improvement in performance on the standard statistical databases used as benchmarks. In addition, and as a concrete application, we apply our method to the sunspot time series and predict the remainder of the current cycle 23 of solar activity.

Automatic digital processing in speckle photography: comparison of two algorithms.

Two algorithms for analyzing speckle photography fringes for spacing and orientation using a digital image processing system are compared. Each algorithm was tested for accuracy and computer run-time through a computer simulation which includes the degradation of data by noise.

Models of cuspy triaxial stellar systems – III. The effect of velocity anisotropy on chaoticity

Fil: Carpintero, Daniel Diego. Consejo Nacional de Investigaciones Cientificas y Tecnicas. Centro Cientifico Tecnologico Conicet - La Plata. Instituto de Astrofisica La Plata. Universidad Nacional de La Plata. Facultad de Ciencias Astronomicas y Geofisicas. Instituto de Astrofisica la Plata; Argentina. Universidad Nacional de La Plata; Argentina

Evaluation Of An Automated Fringe Measurement Method For Analysis Of Speckle Photography Data

A recently published system for determining the spacing and direction of speckle photography fringes is tested for accuracy and computer run time through a computer simulation that includes the degradation of data by noise. Compared with a previously published processing method, the algorithm used in the new system determines fringe direction with higher accuracy and reduced computational effort. From the evaluation of fringe spacing, displacement components are also determined as a function of fringe density, visibility, and image resolution. Errors in displacement components are compared with those obtained using other algorithms.

Models of cuspy triaxial stellar systems - II. Regular orbits

Fil: Muzzio, Juan Carlos. Consejo Nacional de Investigaciones Cientificas y Tecnicas. Centro Cientifico Tecnologico la Plata. Instituto de Astrofisica de la Plata; Argentina