Discriminative Orthogonal Neighborhood-Preserving Projections for Classification

Orthogonal neighborhood-preserving projection (ONPP) is a recently developed orthogonal linear algorithm for overcoming the out-of-sample problem existing in the well-known manifold learning algorithm, i.e., locally linear embedding. It has been shown that ONPP is a strong analyzer of high-dimensional data. However, when applied to classification problems in a supervised setting, ONPP only focuses on the intraclass geometrical information while ignores the interaction of samples from different classes. To enhance the performance of ONPP in classification, a new algorithm termed discriminative ONPP (DONPP) is proposed in this paper. DONPP 1) takes into account both intraclass and interclass geometries; 2) considers the neighborhood information of interclass relationships; and 3) follows the orthogonality property of ONPP. Furthermore, DONPP is extended to the semisupervised case, i.e., semisupervised DONPP (SDONPP). This uses unlabeled samples to improve the classification accuracy of the original DONPP. Empirical studies demonstrate the effectiveness of both DONPP and SDONPP.

Biologically Inspired Features for Scene Classification in Video Surveillance

Inspired by human visual cognition mechanism, this paper first presents a scene classification method based on an improved standard model feature. Compared with state-of-the-art efforts in scene classification, the newly proposed method is more robust, more selective, and of lower complexity. These advantages are demonstrated by two sets of experiments on both our own database and standard public ones. Furthermore, occlusion and disorder problems in scene classification in video surveillance are also first studied in this paper.

Classification of valence changes of trivalent rare earth ions in alkaline earth borates using artificial neural networks

The investigations of classification on the valence changes from RE3+ to RE2+ (RE = Eu, Sm, Yb, Tm) in host compounds of alkaline earth berate were performed using artificial neural networks (ANNs). For comparison, the common methods of pattern recognition, such as SIMCA, KNN, Fisher discriminant analysis and stepwise discriminant analysis were adopted. A learning set consisting of 24 host compounds and a test set consisting of 12 host compounds were characterized by eight crystal structure parameters. These parameters were reduced from 8 to 4 by leaps and bounds algorithm. The recognition rates from 87.5 to 95.8% and prediction capabilities from 75.0 to 91.7% were obtained. The results provided by ANN method were better than that achieved by the other four methods. (C) 1999 Elsevier Science B.V. All rights reserved.

MULTIVARIATE CLASSIFICATION BASED ON METAL CONTENTS IN HUMAN SENILE CATARACT LENSES

Multivariate classification methods were used to evaluate data on the concentrations of eight metals in human senile lenses measured by atomic absorption spectrometry. Principal components analysis and hierarchical clustering separated senile cataract lenses, nuclei from cataract lenses, and normal lenses into three classes on the basis of the eight elements. Stepwise discriminant analysis was applied to give discriminant functions with five selected variables. Results provided by the linear learning machine method were also satisfactory; the k-nearest neighbour method was less useful.

PenBase, the shrimp antimicrobial peptide penaeidin database: Sequence-based classification and recommended nomenclature

Antimicrobial peptides play a major role in innate immunity. The penaeidins, initially characterized from the shrimp Litopenaeus vannamei, are a family of antimicrobial peptides that appear to be expressed in all penaeid shrimps. As of recent, a large number of penaeid nucleotide sequences have been identified from a variety of penaeid shrimp species and these sequences currently reside in several databases under unique identifiers with no nomenclatural continuity. To facilitate research in this field and avoid potential confusion due to a diverse number of nomenclatural designations, we have made a systematic effort to collect, analyse, and classify all the penaeidin sequences available in every database. We have identified a common penaeidin signature and subsequently established a classification based on amino acid sequences. In order to clarify the naming process, we have introduced a 'penaeidin nomenclature' that can be applied to all extant and future penaeidins. A specialized database, PenBase, which is freely available at http://www.penbase.immunaqua.com, has been developed for the penaeidin family of antimicrobial peptides, to provide comprehensive information about their properties, diversity and nomenclature. (c) 2005 Elsevier Ltd. All rights reserved.

Extreme weathering/erosion during the Miocene Climatic Optimum: Evidence from sediment record in the South China Sea

Investigating the interplay between continental weathering and erosion, climate, and atmospheric CO2 concentrations is significant in understanding the mechanisms that force the Cenozoic global cooling and predicting the future climatic and environmental response to increasing temperature and CO2 levels. The Miocene represents an ideal test case as it encompasses two distinct extreme climate periods, the Miocene Climatic Optimum (MCO) with the warmest time since 35 Ma in Earth's history and the transition to the Late Cenozoic icehouse mode with the establishment of the east Antarctic ice sheet. However the precise role of continental weathering during this period of major climate change is poorly understood. Here we show changes in the rates of Miocene continental chemical weathering and physical erosion, which we tracked using the chemical index of alteration ( CIA) and mass accumulation rate ( MAR) respectively from Ocean Drilling Program (ODP) Site 1146 and 1148 in the South China Sea. We found significantly increased CIA values and terrigenous MARs during the MCO (ca. 17-15 Ma) compared to earlier and later periods suggests extreme continental weathering and erosion at that time. Similar high rates were revealed in the early-middle Miocene of Asia, the European Alps, and offshore Angola. This suggests that rapid sedimentation during the MCO was a global erosion event triggered by climate rather than regional tectonic activity. The close coherence of our records with high temperature, strong precipitation, increased burial of organic carbon and elevated atmospheric CO2 concentration during the MCO argues for long-term, close coupling between continental silicate weathering, erosion, climate and atmospheric CO2 during the Miocene. Citation: Wan, S., W. M. Kurschner, P. D. Clift, A. Li, and T. Li (2009), Extreme weathering/ erosion during the Miocene Climatic Optimum: Evidence from sediment record in the South China Sea, Geophys. Res. Lett., 36, L19706, doi: 10.1029/2009GL040279.

Recent 2000-year geological records of mud in the inner shelf of the East China Sea and their climatic implications

AXIS(14)C dating and grain-size analysis for Core DD2, located at the north of the Yangtze River-derived mud off the Zhejiang-Fujian coasts in the inner shelf of the East China Sea, provide us a high-resolution grain-size distribution curve varying with depth and time. Data in the upper mud layer of Core DD2 indicate that there are at least 9 abrupt grain-size increasing in recent 2000 years, with each corresponding very well with the low-temperature events in Chinese history, which might result from the periodical strengthening of the East Asian Winter Monsoon (EAWM), including the first-revealed maximum temperature lowering event at around 990 a BP. At the same time, the finer grain size section in Core DD2 agrees well with the Sui-Tang Warming Period (600-1000 a AD) defined previously by Zhu Kezhen, during which the climate had a warm, cold and warm fluctuation, with a dominated cooling period of 750-850 a AD. The Little Ice Age (LIA) can also be identified in the core. It starts around 1450 a AD and was followed by a subsequent cooling events at 1510, 1670 and 1840 a AD. Timing of these cold events revealed here still needs to be further verified owing to some current uncertainty of dating we used in this study.

Evaluation of a combined wavelet and a combined principal component analysis classification system for BCG diagnostic problem

Heart disease is one of the main factor causing death in the developed countries. Over several decades, variety of electronic and computer technology have been developed to assist clinical practices for cardiac performance monitoring and heart disease diagnosis. Among these methods, Ballistocardiography (BCG) has an interesting feature that no electrodes are needed to be attached to the body during the measurement. Thus, it is provides a potential application to asses the patients heart condition in the home. In this paper, a comparison is made for two neural networks based BCG signal classification models. One system uses a principal component analysis (PCA) method, and the other a discrete wavelet transform, to reduce the input dimensionality. It is indicated that the combined wavelet transform and neural network has a more reliable performance than the combined PCA and neural network system. Moreover, the wavelet transform requires no prior knowledge of the statistical distribution of data samples and the computation complexity and training time are reduced.

Classification of jinjiang oysters Crassostrea rivularis (Gould, 1861) from China, based on morphology and phylogenetic analysis

The jinjiang oyster Crassostrea rivularis [Gould, 1861. Descriptions of Shells collected in the North Pacific Exploring Expedition under Captains Ringgold and Rodgers. Proc. Boston Soc. Nat. Hist. 8 (April) 33-40] is one of the most important and best-known oysters in China. Based on the color of its flesh, two forms of C rivularis are recognized and referred to as the "white meat" and 11 red meat" oysters. The classification of white and red forms of this species has been a subject of confusion and debate in China. To clarify the taxonomic status of the two forms of C. rivularis, we collected and analyzed oysters from five locations along China's coast using both morphological characters and DNA sequences from mitochondrial 16S rRNA and cytochrome oxidase 1, and the nuclear 28S rRNA genes. Oysters were classified as white or red forms according to their morphological characteristics and then subjected to DNA sequencing. Both morphological and DNA sequence data suggest that the red and white oysters are two separate species. Phylogenetic analysis of DNA sequences obtained in this study and existing sequences of reference species show that the red oyster is the same species as C. ariakensis Wakiya [1929. Japanese food oysters. Jpn. J. Zool. 2, 359-367.], albeit the red oysters from north and south China are genetically distinctive. The white oyster is the same species as a newly described species from Hong Kong, C. hongkongensis Lam and Morton [2003. Mitochondrial DNA and identification of a new species of Crassostrea (Bivalvia: Ostreidae) cultured for centuries in the Pearl River Delta, Hong Kong, China. Aqua. 228, 1-13]. Although the name C. rivularis has seniority over C. ariakensis and C. hongkongensis, the original description of Ostrea rivularis by Gould [1861] does not fit shell characteristics of either the red or the white oysters. We propose that the name of C. rivularis Gould [1861] should be suspended, the red oyster should take the name C. ariakensis, and the white oyster should take the name C. hongkongensis. (C) 2004 Elsevier B.V. All rights reserved.