Nada Alzaben: End-to-End Routing in SDN Controllers Using Max-Flow Min-Cut Route Selection Algorithm

we present a novel max-flow min-cut based algorithm to solve the flow routing problem in the Software Defined Network Controller. Routing using traditional shortest path first algorithms often results in bottlenecks that cause performance degradation including higher energy use, reduced throughput, and increased slowdown. Our algorithm uses the max-flow min-cut algorithm to identify potential bottlenecks in order to avoid them in the flow routing decisions. Our simulations show that our max-flow min-cut based algorithm improves the network performance by minimizing the mean wait time by 15.1%, minimizing the mean slowdown by 6.1 %, minimizing the maximum completion time by 9.6 %, and maximize the mean throughput by 18.3 % compared to the Shortest Path algorithm. Explicitly considering congestion in determining routes, such as with our Max-Flow Min-Cut algorithm, is necessary to maximize performance.

Nada Alzaben
Program: PhD in Computer Science
Faculty mentor: Daniel Engels

Fidelia Nawar (U): Covid-19 Open Research Dataset (CORD-19) Extractor

Winner: Undergraduate Top 3
Winner: Lyle (Undergraduate)

The Covid-19 Open Research Dataset is a growing resource of coronavirus research and scientific papers on Covid-19. CORD-19 is designed to facilitate the development of information retrieval systems through its collection of structured full-text papers. This study aims to contribute to the SMU AI Club's efforts to develop a search engine that parses through CORD-19 articles in order to extract relevant data about protein, compound, chemical information, and more. In the study, we describe the mechanics of dependency parsing, highlighting challenges and key design decisions, and discuss tools and upcoming shared tasks related to the search engine project. We hope this resource will introduce a new way to search for desired data related to Covid-19 and further bring together the computing and biomedical community on campus.

Fidelia Nawar
Major: Computer Science
Faculty Mentor: David (King Ip) Lin

Ishna Satyarth: Application of Neural Networks in Quantum Chemistry

Winner: Computer Science (Graduate)

Understanding the motion of electrons in a molecule is a big piece of the puzzle to understand the quantum world that these sub-atomic particles live in. This complexity increases several folds when correlation of pairs of electrons are interpreted in the wave function. Current methods of including pair correlation are too expensive to apply to large molecules. Our goal is to reduce the error in the Tensor Hypercontraction approximation, which can reduce the cost of such calculations. Artificial Intelligence and in particular the application of neural networks can prove to be a savior in such situations of many unknown parameters. A neural network works like a collection of brain cells where each neuron is responsible for processing a single piece of information and increasing the number of neurons allows adding complexity in a systematic way. Since there are more than 22 different input variables accounting for the energy error, we will be using a multilayer perceptron model. Using an Artificial Neural Network, we have tried to structure them into a systematic network and tried to decipher how each variable contributes towards the outcome of total energy or bond strength. We are currently working on collecting as many data points to train our Neural Network, so that we can get the most accurate results in the future.

Ishna Satyarth
Program: PhD in Computer Science
Faculty mentor: Devin Matthews (Chemistry)