Erhan Guven

Dr. Erhan Guven is an AI Scientist at Johns Hopkins University Applied Physics Laboratory (APL). His research spans a broad spectrum of machine learning applications, including the development of algorithms to counter large language models, predictive analytics in financial systems, and various applications in cybersecurity, NLP, and bioinformatics. Dr. Guven has also led projects in speech emotion recognition, disease forecasting, and optimization methods for nuclear signal detection.

Prior to joining APL, he conducted significant research in speech signal processing, music information retrieval, authorship attribution, and bioinformatics, working on genome sequencing and cancer survivability prediction. His teaching contributions include courses in machine learning, NLP, graph analytics, and formal methods at Johns Hopkins and Loyola University Maryland.

Dr. Guven holds a Ph.D. in Computer Science from The George Washington University and has authored numerous publications in the fields of cybersecurity, machine learning, and disease forecasting. He is also the inventor of several patents related to speech emotion detection and VoIP technologies.

Education History

• Ph.D, Computer Science, George Washington University

Work Experience

Senior Professional Staff, JHU Applied Physics Laboratory

Publications

• DeLeo, Michael, and Erhan Guven. “Learning Chess With Language Models and Transformers.” arXiv preprint arXiv:2209.11902 (2022).
• “An open challenge to advance probabilistic forecasting for dengue epidemics.” Proceedings of the National Academy of Sciences 116.48 (2019): 24268-24274
• “Unsupervised Graph Analytics on Heterogeneous Network Device Data,” Complex Adaptive Systems, 2018, Chicago.
• “Ensemble method for dengue prediction.” PloS one 13.1 (2018): e0189988.
• “Prediction of Peaks of Seasonal Influenza in Military Health-Care Data: Supplementary Issue: Big Data Analytics for Health.” Biomedical engineering and computational biology 7 (2016): BECB-S36277.
• “A Survey of Data Mining and Machine Learning Methods for Cyber Security,” IEEE Communications Surveys & Tutorials 18.2 (2016): 1153-1176.
• “Fuzzy Association Rule Mining and Classification for the Prediction of Malaria in South Korea,” BMC Medical Informatics and Decision Making 15.1 (2015): 47.
• “Predicting Levels of Influenza Incidence,” Online Journal of Public Health Informatics 6 (1), 2014.
• “Prediction of High Incidence of Dengue in the Philippines,” PLoS neglected tropical diseases 8 (4), e2771, 2014.
• “An OpenCL Framework for Fuzzy Associative Classification and Its Application to Disease Prediction,” Complex Adaptive Systems, 2013, Baltimore.
• “Note and Timbre Classification by Local Features of Spectrogram,” Complex Adaptive Systems, 2012, Washington D.C.
• “Speech Emotion Recognition using a Backward Context,” IEEE Applied Imagery Pattern Recognition (AIPR) Workshop, 2010, Washington D.C.
• “Recognition of Emotions from Human Speech,” Artificial Neural Networks In Eng. (ANNIE), 2010, St. Louis, Missouri.
• “Sequence Signatures of Exon Dynamics in the Evolution of Alternative Splicing,” Cold Spring Harbor New York Meeting (2007) – The Biology of Genomes, 129, 2007, New York.
• “Predicting Breast Cancer Survivability using Data Mining Techniques,” 2006 SIAM International Conference on Data Mining, 2006, Bethesda, Maryland.

Honors and Awards

• Best Innovative Paper 3rd position at ANNIE (2010)
• Engineering Achievement Award, Texas Instruments (2001)

Professional Organizations

ACM (Association for Computing Machinery)
IEEE (Institute of Electrical and Electronics Engineers)