The original version of this chapter contained an error in the third author’s name. The spelling of Chaim Yosefy’s name was incorrect in the header of the paper. The author name has been corrected.
The reliable segmentation of retinal vasculature can provide the means to diagnose and monitor the progression of a variety of diseases affecting the blood vessel network, including diabetes and hypertension. We leverage the power of convolutional neural networks to devise a reliable and fully automated method that can accurately detect, segment, and analyze retinal vessels. In particular, we propose a novel, fully convolutional deep neural network with an encoder-decoder architecture that employs dilated spatial pyramid pooling with multiple dilation rates to recover the lost content in the encoder and add multiscale contextual information to the decoder. We also propose a simple yet effective way of quantifying and tracking the widths of retinal vessels through direct use of the segmentation predictions. Unlike previous deep-learning-based approaches to retinal vessel segmentation that mainly rely on patch-wise analysis, our proposed method leverages a whole-image approach during training and inference, resulting in more efficient training and faster inference through the access of global content in the image. We have tested our method on two publicly available datasets, and our state-of-the-art results on both the DRIVE and CHASE-DB1 datasets attest to the effectiveness of our approach.
We present a domain-specific language called SAL(the Streaming Analytics Language) for processing data in a semi-streaming model. In particular we examine the use case of processing netflow data in order to identify malicious actors within a network. Because of the large volume of data generated from networks, it is often only feasible to process the data with a single pass, utilizing a streaming (O(polylog n) space requirements) or semi-streaming computing model ( O(n polylog n) space requirements). Despite these constraints, we are able to achieve an average of 0.87 for the AUC of the ROC curve for a set of situations dealing with botnet detection. The implementation of an interpreter for SAL, which we call SAM (Streaming Analytics Machine), achieves scaling results that show improved throughput to 61 nodes (976 cores), with an overall rate of 373,000 netflows per second or 32.2 billion per day. SAL provides a succinct way to describe common analyses that allow cyber analysts to find data of interest, and SAM is a scalable interpreter of the language.
Convolutional neural networks have been achieving the best possible accuracies in many visual pattern classification problems. However, due to the model capacity required to capture such representations, they are often oversensitive to overfitting and therefore require proper regularization to generalize well. In this paper, we present a combination of regularization techniques which work together to get better performance, we built plain CNNs, and then we used data augmentation, dropout and customized early stopping function, we tested and evaluated these techniques by applying models on five famous datasets, MNIST, CIFAR10, CIFAR100, SVHN, STL10, and we achieved three state-of-the-art-of (MNIST, SVHN, STL10) and very high-Accuracy on the other two datasets.
Machine learning techniques, regardless of being supervised or unsupervised, have attracted extensive research attention in handling data classification. Typically, among supervised machine learning algorithms, Support Vector Machine (SVM) and its extensions have been widely used in various areas due to their great prediction capability. These learning algorithms basically treat features of the instances independently when using them to do classification. However, in applications, features are commonly correlated with complex network structures. Ignoring such a characteristic and naively implementing the SVM algorithm may yield erroneous classification results. To address the limitation of the SVM algorithm, we propose new learning algorithms which accommodate network structures in the features of the instances. Our algorithms capitalize on graphical model theory and make use of the available R software package for SVM. The implementation of the proposed learning algorithms is computationally straightforward. We apply the new algorithms to analyze the data arising from a gene expression study.
