Wednesday, May 25, 2022
Media Contact: Jordanian Bishop | Editor, Brand Management Department | 405-744-7193 | [email protected]
The Oklahoma State University Coalition for the Advancement of Digital Research and Education (CADRE) recently partnered with Dell Technologies and Intel to recognize two students’ extraordinary use of data science and computing.
This year in CADRE 2022, Khaled Mohammed Saifuddin – a Ph.D. Candidate in the Department of Computer Science – Won first place in the Dell Intel Student Award for Outstanding Use of Data Science and Computing for his research work with advisor Dr. Esra Akbas, “Drug Abuse Detection in Twitter-sphere: Graph-Based Approach”.
The rate of non-medical opioid use has increased significantly since the early 2000s. Recently, the US government declared a national emergency to slow the death toll related to substance abuse (DA). In this research, Khaled presented a graph-based unique model that can automatically recognize DA from openly available social media data.
To achieve the goal, a significant amount of Twitter posts were first collected based on a list of keywords that also included some drug names and substance abuse terms. After that, the text data was represented as graph data, so-called text graphs, capable of handling complex structures and capturing local and global word-by-word co-occurrence.
Two different types of text charts were created from the tweets: document-level text charts and corpus-level text charts. Various graph neural networks were then applied to obtain the representation of nodes and graphs.
Finally, the plots were passed to a machine learning classifier to classify whether a tweet was related to DA or not. Thus, the text classification problem has been presented as a node and graph classification problem.
The experimental result shows that the proposed model outperforms the prior art baseline models with a maximum accuracy of 96.4%, almost 20% better than the baseline models.
Ishraque Zaman Borshon — a PhD student one Mechanical and Aerospace Engineering — received second place Dell Intel Student Award for Outstanding Use of Data Science and Computing for his research work: “Development of machine learning algorithms for a high-temperature up-cavity receiver for Scheffler concentrators.”
This technology starts with a parabolic dish that is used to store the sun’s energy by using curved mirrors to direct the energy to a receiver. The upward facing receiver is responsible for capturing the solar thermal energy in the most efficient and practical way. Designing the receiver requires extensive calculations and is known to be expensive. A design flaw could cost millions of dollars. In his research, Borshon developed software to efficiently calculate heat loss from a complex solar heat exchanger.
The first step in Borshon’s process was to identify the three main variables that contribute to convective heat loss, namely surface temperature, tilt angle, and flow velocity.
Conduction is the process of heat loss through physical contact with another object or body. Convection is the process of heat loss through the movement of air or water molecules across the skin.
Data was collected and incorporated into various models to determine the most accurate method for determining convective heat loss. The data indicated that the number-based physics model and the random forest model were the most suitable for development.
After collecting the data and building the necessary models, Borshon created software that allows users to enter predictions for each of the various variables to calculate the predicted heat loss, the Nusselt number (a measure of heat transfer by convection and conduction), and the convective heat transfer coefficient to display .
The heat loss prediction software can be found here: share.streamlit.io/ishraque2008/random_forest_heat_transfer/main.py.
For more information on the OSU Department of Computer Science, see cas.okstate.edu/department_of_computer_science/. To learn more about OSU’s School of Mechanical and Aerospace Engineering, go to ceat.okstate.edu/mae/.
Story by: Bailey Sisk | [email protected]