Okan K. Ersoy

Neural Network Approaches Versus Statistical Methods In Classification Of Multisource Remote Sensing Data

Neural network learning procedures and statistical classificaiton methods are applied and compared empirically in classification of multisource remote sensing and geographic data. Statistical multisource classification by means of a method based on Bayesian classification theory is also investigated and modified. The modifications permit control of the influence of the data sources involved in the classification process. Reliability measures are introduced to rank the quality of the data sources. The data sources are then weighted according to these rankings in the statistical multisource classification. Four data sources are used in experiments: Landsat MSS data and three forms of topographic data (elevation, slope, and aspect). Experimental results show that two different approaches have unique advantages and disadvantages in this classification application.

Gerchberg–Saxton and Yang–Gu algorithms for phase retrieval in a nonunitary transform system: a comparison

A detailed comparison of the original Gerchberg-Saxton and the Yang-Gu algorithms for the reconstruction of model images from two intensity measurements in a nonunitary transform system is presented. The Yang-Gu algorithm is a generalization of the Gerchberg-Saxton algorithm and is effective in solving the general amplitude-phase-retrieval problem in any linear unitary or nonunitary transform system. For a unitary transform system the Yang-Gu algorithm is identical to the Gerchberg-Saxton algorithm. The reconstruction of images from data corrupted with random noise is also investigated. The simulation results show that the Yang-Gu algorithm is relatively insensitive to the presence of noise in data. In all cases studied the Yang-Gu algorithm always resulted in a highly accurate recovered phase.

Parallel consensual neural networks

A new type of a neural-network architecture, the parallel consensual neural network (PCNN), is introduced and applied in classification/data fusion of multisource remote sensing and geographic data. The PCNN architecture is based on statistical consensus theory and involves using stage neural networks with transformed input data. The input data are transformed several times and the different transformed data are used as if they were independent inputs. The independent inputs are first classified using the stage neural networks. The output responses from the stage networks are then weighted and combined to make a consensual decision. In this paper, optimization methods are used in order to weight the outputs from the stage networks. Two approaches are proposed to compute the data transforms for the PCNN, one for binary data and another for analog data. The analog approach uses wavelet packets. The experimental results obtained with the proposed approach show that the PCNN outperforms both a conjugate-gradient backpropagation neural network and conventional statistical methods in terms of overall classification accuracy of test data.

Manifold-Learning-Based Feature Extraction for Classification of Hyperspectral Data: A Review of Advances in Manifold Learning

Advances in hyperspectral sensing provide new capability for characterizing spectral signatures in a wide range of physical and biological systems, while inspiring new methods for extracting information from these data. HSI data often lie on sparse, nonlinear manifolds whose geometric and topological structures can be exploited via manifold-learning techniques. In this article, we focused on demonstrating the opportunities provided by manifold learning for classification of remotely sensed data. However, limitations and opportunities remain both for research and applications. Although these methods have been demonstrated to mitigate the impact of physical effects that affect electromagnetic energy traversing the atmosphere and reflecting from a target, nonlinearities are not always exhibited in the data, particularly at lower spatial resolutions, so users should always evaluate the inherent nonlinearity in the data. Manifold learning is data driven, and as such, results are strongly dependent on the characteristics of the data, and one method will not consistently provide the best results. Nonlinear manifold-learning methods require parameter tuning, although experimental results are typically stable over a range of values, and have higher computational overhead than linear methods, which is particularly relevant for large-scale remote sensing data sets. Opportunities for advancing manifold learning also exist for analysis of hyperspectral and multisource remotely sensed data. Manifolds are assumed to be inherently smooth, an assumption that some data sets may violate, and data often contain classes whose spectra are distinctly different, resulting in multiple manifolds or submanifolds that cannot be readily integrated with a single manifold representation. Developing appropriate characterizations that exploit the unique characteristics of these submanifolds for a particular data set is an open research problem for which hierarchical manifold structures appear to have merit. To date, most work in manifold learning has focused on feature extraction from single images, assuming stationarity across the scene. Research is also needed in joint exploitation of global and local embedding methods in dynamic, multitemporal environments and integration with semisupervised and active learning.

Transform image enhancement

Blockwise transform image enhancement techniques are discussed. Previously, transform image enhancement has usually been based on the discrete Fourier transform (DFT) applied to the whole image. Two major drawbacks with the DFT are high complexity of implementation involving complex multiplications and additions, with intermediate results being complex numbers, and the creation of severe block effects if image enhancement is done blockwise. In addition, the quality of enhancement is not very satisfactory. It is shown that the best transforms for transform image coding, namely, the scrambled real discrete Fourier transform, the discrete cosine transform, and the discrete cosine-III transform, are also the best for image enhancement. Three techniques of enhancement discussed in detail are alpha-rooting, modified unsharp masking, and filtering motivated by the human visual system response (HVS). With proper modifications, it is observed that unsharp masking and HVS-motivated filtering without nonlinearities are basically equivalent. Block effects are completely removed by using an overlap-save technique in addition to the best transform.

Parallel, self-organizing, hierarchical neural networks

A new neural-network architecture called the parallel, self-organizing, hierarchical neural network (PSHNN) is presented. The new architecture involves a number of stages in which each stage can be a particular neural network (SNN). At the end of each stage, error detection is carried out, and a number of input vectors are rejected. Between two stages there is a nonlinear transformation of input vectors rejected by the previous stage. The new architecture has many desirable properties, such as optimized system complexity (in the sense of minimized self-organizing number of stages), high classification accuracy, minimized learning and recall times, and truly parallel architectures in which all stages operate simultaneously without waiting for data from other stages during testing. The experiments performed indicated the superiority of the new architecture over multilayered networks with back-propagation training.

Conjugate-gradient neural networks in classification of multisource and very-high-dimensional remote sensing data

Abstract Application of neural networks to classification of remote sensing data is discussed. Conventional two-layer backpropagation is found to give good results in classification of remote sensing data but is not efficient in training. A more efficient variant, based on conjugate-gradient optimization, is used for classification of multisource remote sensing and geographic data and very-high-dimensional data. The conjugate-gradient neural networks give excellent performance in classification of multisource data but do not compare as well with statistical methods in classification of very-high-dimcnsional data.

2K09 and thereafter : the coming era of integrative bioinformatics, systems biology and intelligent computing for functional genomics and personalized medicine research

Significant interest exists in establishing synergistic research in bioinformatics, systems biology and intelligent computing. Supported by the United States National Science Foundation (NSF), International Society of Intelligent Biological Medicine (http://www.ISIBM.org), International Journal of Computational Biology and Drug Design (IJCBDD) and International Journal of Functional Informatics and Personalized Medicine, the ISIBM International Joint Conferences on Bioinformatics, Systems Biology and Intelligent Computing (ISIBM IJCBS 2009) attracted more than 300 papers and 400 researchers and medical doctors world-wide. It was the only inter/multidisciplinary conference aimed to promote synergistic research and education in bioinformatics, systems biology and intelligent computing. The conference committee was very grateful for the valuable advice and suggestions from honorary chairs, steering committee members and scientific leaders including Dr. Michael S. Waterman (USC, Member of United States National Academy of Sciences), Dr. Chih-Ming Ho (UCLA, Member of United States National Academy of Engineering and Academician of Academia Sinica), Dr. Wing H. Wong (Stanford, Member of United States National Academy of Sciences), Dr. Ruzena Bajcsy (UC Berkeley, Member of United States National Academy of Engineering and Member of United States Institute of Medicine of the National Academies), Dr. Mary Qu Yang (United States National Institutes of Health and Oak Ridge, DOE), Dr. Andrzej Niemierko (Harvard), Dr. A. Keith Dunker (Indiana), Dr. Brian D. Athey (Michigan), Dr. Weida Tong (FDA, United States Department of Health and Human Services), Dr. Cathy H. Wu (Georgetown), Dr. Dong Xu (Missouri), Drs. Arif Ghafoor and Okan K Ersoy (Purdue), Dr. Mark Borodovsky (Georgia Tech, President of ISIBM), Dr. Hamid R. Arabnia (UGA, Vice-President of ISIBM), and other scientific leaders. The committee presented the 2009 ISIBM Outstanding Achievement Awards to Dr. Joydeep Ghosh (UT Austin), Dr. Aidong Zhang (Buffalo) and Dr. Zhi-Hua Zhou (Nanjing) for their significant contributions to the field of intelligent biological medicine.

Generalized discrete Hartley transforms

The discrete Hartley transform is generalized into four classes in the same way as the generalized discrete Fourier transform. Fast algorithms for the resulting transforms are derived. The generalized transforms are expected to be useful in applications such as digital filter banks, fast computation of the discrete Hartley transform for any composite number of data points, fast computations of convolution, and signal representation. The fast computation of skew-circular convolution by the generalized transforms for any composite number of data points is discussed in detail. >

Detection of ECG waveforms by neural networks.

In this study, ECG waveform detection was performed by using artificial neural networks (ANNs). Initially, the R peak of the QRS complex is detected, and then feature vectors are formed by using the amplitudes of the significant frequency components of the DFT spectrum. Grow and Learn (GAL) and Kohonen networks are comparatively investigated to detect four different ECG waveforms. The comparative performance results of GAL and Kohonen networks are reported.