My name is Akshay Aravamudan. I am currently a Ph.D. student in Computer Engineering at Florida Institute of Technology. My research primarily comprises of machine learning applications. Under that rather broad umbrella, I have and continue to work on stochastic temporal point processes, machine learning on the edge and machine learning for hydrology. In the fall of 2023, I interned at Amazon as an applied scientist wherein I worked on a discrete event simulation for routing of support calls for the SPeXSci (Selling Partner Experience Science) team.

The following page is used to track my current research interest and to maintain a record of works, both academic and extra-curricular, that I have completed throughout my ongoing academic career. You can find my resume here. A collection of my published papers presentations can also be found on my Google scholar profile. Also do check out our research lab’s website here

News

1. [December 8, 2023]: We will be presenting our work titled "Regional Seismic Discrimination using Machine Learning" at AGU 2023!
2. [August 27, 2023]: I will be interning at Amazon, Seattle this Fall semester. Very excited to work with the team
3. [November 27, 2022]: Our 2022 ICML paper was featured in Florida Tech's news website https://news.fit.edu/academics-research/university-study-examines-viral-probability-of-social-media-posts/. Massive congratulations to the paper lead Xi Zhang!
4. [November 22, 2022]: Our paper "Anytime User Engagement Prediction in Information Cascades for Arbitrary Observation Periods" has been accepted to AAAI 2023! Super excited to be presenting our work in Washington, D.C, come February! More details to follow soon. Temporary location of the paper can be found [here](https://www.github.com/aaravamudan2014/Akshay-Aravamudan/blob/master/docs/Camera_ready_AAAI_2023__Anytime_User_Engagement_Prediction_in_Information_Cascades_for_Arbitrary_Observation_Periods.pdf).

Bio

I joined Florida Tech at 2014 to purse my Bachelor’s degree in computer engineering. I started with an interest in microcontrollers and microcomputers. During my undergraduate years, I developed a passion for machine learning, starting with a naive bayes classification tool. I got interested in the intricacies involved in developing complex models, which eventually led me down the path of neural networks. I ended up taking courses like Pattern Recognition and Neural Networks. I continued onto pursue my Master’s degree, working under adviesement of Dr. Georgios Anagnastopolous. My master’s thesis dealt with the study of information spread and more specifically utilizing it better understand the spread of software vulnerabilities in their domains.

Current Research Interests

1. Information Diffusion
2. Stochastic Temporal Point Processes
3. Machine Learning for Hydrology
4. Machine Learning for Seismology
5. Influence Characterization in Social Media

Publications

2023-

• Anytime User Engagement Prediction in Information Cascades for Arbitrary Observation Periods (Accepted as a presentation to AAAI 2023). Found here
• Regional Seismic Event Discrimination using Machine Learning Paper link Found here
• Improving Flash Flood Monitoring and Forecasting Capabilities in West Africa with Satellite Observations and Precipitation Forecasts Paper link Found here
• A multi-firearm, multi-orientation audio dataset of gunshots. Found here

2022

• Anytime Information Cascade Popularity Prediction via Self-Exciting Processes. Found here
• Advancing flood warning procedures in ungauged basins with machine learning. Journal of Hydrology. Paper link Found here

2021

• ACE: An ATAK Plugin for Enhanced Acoustic Situational Awareness at the Edge, in MILCOM 2021 - 2021 IEEE Military Communications Conference (MILCOM). Found here
• Influence Dynamics Among Narratives. In Social, Cultural, and Behavioral Modeling Found here
• Environmental Sound Classification with Tiny Transformers in Noisy Edge Environments, 2021 IEEE 7th World Forum on Internet of Things (WF-IoT). Found here .

Presentations

• Deep Residual Downscaling of Remote Sensing Imagery for Flood Hazard Assessment. In Abstract h42c-02, fall meeting, american geophysical union. [abstract & presentation]. Found here 
• Rasheed, Z., Aravamudan, A., Sefidmazgi, A. G., Anagnostopoulos, G., & Nikolopoulos (Presenter), E. (2021). Flood inducing storm detection and peak flow prediction with machine learning. Google Flood Forecasting Workshop 2021 Found here
• Zimeena Rasheed (Presenter), Akshay Aravamudan , G. C. Anagnostopoulos, A. G. Sefidmazgi, E. I. Nikolopoulos (2020). Machine learning for flood peak prediction in ungauged basins. In American Geophysical Union (AGU) Fall Meeting 2020. [extended abstract]. Found here 
• Xi Zhang(Presenter), Akshay Aravamudan,Anna Koufakou, Chathika Gunaratne, Ivan Garibay, G. C. Anagnostopoulos(2020). Predicting software vulnerability exploits from social media confabulations. Conference on Computational Social Science (IC2S2). [extended abstract & poster], Massachusetts Institute of Technology, Cambridge, MA. Found here 

Upcoming works

• Zhang, X., Aravamudan, A., & Anagnostopoulos, G. C. (2022). Predicting software vulnerability exploits from social media confabulations. [To be submitted on to IEEE Transactions on Dependable and Secure Computing].

Other projects of relevance

1. Container Migration
2. Discriminant Analysis classifier
3. Population Prediction LSTM
4. Branch and Bound: an OpenMP Implementation
5. Torque3D
6. File System for and FRAM

Contact info

I can be contacted via my email aaravamudan2014@my.fit.edu or via my Linkedin page