Naturally, cells in human body grow and divide in a controlled way to produce more cells to maintain health. Cancer affects human body when abnormal cells divide without control and becomes able to invade other tissues. The genetic material (DNA) of these cells becomes damaged or changed that affects normal cell growth and division. Early diagnosis is of considerable significance of the physici...

Current metrics used in summarizing networks, such as degree distribution, average diameter and clustering coefficient, provide a very coarse understanding of their structure. One would like to have finergrained summaries of networks which allow making distinction between structurally different networks. A class of such interesting graph statistics are the Small Subgraph Frequencies. These subg...

Traffic classification has wide applications in network management, from security monitoring to quality of service measurements. Recent research tends to apply machine learning techniques to flow statistical feature based classification methods. The nearest neighbor (NN)-based method has exhibited superior classification performance. It also has several important advantages, such as no requirem...

IMPROVING NEURAL NETWORK CLASSIFICATION TRAINING Michael E. Rimer Department of Computer Science Doctor of Philosophy The following work presents a new set of general methods for improving neural network accuracy on classification tasks, grouped under the label of classification-based methods. The central theme of these approaches is to provide problem representations and error functions that m...

Networks have become ubiquitous. Communication networks, financial transaction networks, networks describing physical systems, and social networks are all becoming increasingly important in our day-to-day life. Often, we are interested in models of how objects in the network influence each other (e.g., who infects whom in an epidemiological network), or we might want to predict an attribute of ...

In this paper we propose a new classification algorithm designed for application on complex networks motivated by algorithmic similarities between boosting learning and message passing. We consider a network classifier as a logistic regression where the variables define the nodes and the interaction effects define the edges. From this definition we represent the problem as a factor graph of loc...