Data Classification Using Combination of Five Machine Learning Techniques

Data clustering plays a vital role in object identification. In real life we mainly use the concept in biometric identification and object detection. In this paper we use Fuzzy Weighted Rules, Fuzzy Inference System (FIS), Fuzzy C-Mean clustering (FCM), Support Vector Machine (SVM) and Artificial Neural Network (ANN) to distinguish three types of Iris data called Iris-Setosa, Iris-Versicolor and Iris-Virginica. Each class in the data table is identified by four-dimensional vector, where vectors are used as the input variable called: Sepal Length (SL), Sepal Width (SW), Petal Length (PL) and Petal Width (PW). The combination of five machine learning methods provides above 98% accuracy of class identification.

Is Pain Representation？

The argument given by strong representationalists about phenomenal consciousness usually has two steps. The first is to identify all phenomenal consciousness with representation. The second is to identify all phenomenal aspects of phenomenal consciousness with certain representational content. Pain is often thought to be a counterexample torepresentationalism. However, current objections from this perspective mostly focus on the second step and try to show that pains have some special qualities that representational content cannot explain. This paper objects to representationalism with regard to pain （that pain is not representation） by way of a focus on the first step. First, it shows that by borrowing the notion of ＂representation＂ from the causal co-variation theory of representation, representationalists are not able to demonstrate that pain is representation. Second, by laying out some well-accepted criteria for what counts as representation, it argues that pains do not satisfy them. Thus, pain is not representation.

Global trends in water and sediment fluxes of the world’s large rivers

Water and sediment transport from rivers to oceans is of primary importance in global geochemical cycle.Against the background of global change,this study examines the changes in water and sediment fluxes and their drivers for 4307 large rivers worldwide(basin area!1000 km2)based on the longest available records.Here we find that 24%of the world’s large rivers experienced significant changes in water flux and 40%in sediment flux,most notably declining trends in water and sediment fluxes in Asia’s large rivers and an increasing trend in suspended sediment concentrations in the Amazon River.In particular,nine binary patterns of changes in water-sediment fluxes are interpreted in terms of climate change and human impacts.The change of precipitation is found significantly correlated to the change of water flux in 71%of the world’s large rivers,while dam operation and irrigation rather control the change of sediment flux in intensively managed catchments.Globally,the annual water flux from rivers to sea of the recent years remained stable compared with the long-time average annual value,while the sediment flux has decreased by 20.8%.

Determination of specificity influencing residues for key transcription factor families

Transcription factors （TFs） are major modulators of transcription and subsequent cellular processes. The binding of TFs to specific regulatory elements is governed by their specificity. Considering the gap between known TFs sequence and specificity, specificity prediction frameworks are highly desired. Key inputs to such frameworks are protein residues that modulate the specificity of TF under consideration. Simple measures like mutual information （MI） to delineate specificity influencing residues （SIRs） from alignment fail due to structural constraints imposed by the three-dimensional structure of protein. Structural restraints on the evolution of the amino-acid sequence lead to identification of false SIRs. In this manuscript we extended three methods （direct information, PSICOV and adjusted mutual information） that have been used to disentangle spurious indirect protein residue-residue contacts from direct contacts, to identify SIRs from joint alignments of amino-acids and specificity. We predicted SIRs for homeodomain （HI））, helix-loop-helix, LacI and GntR families of TFs using these methods and compared to MI. Using various measures, we show that the performance of these three methods is comparable but better than MI. Implication of these methods in specificity prediction framework is discussed. The methods are implemented as an R package and available along with the alignments at http：//stormo.wustl.edu/SpecPred.