Machine Learning and Complex Systems Lab

Dept. of Computer Science and Engineering, Wright State U., Dayton, OH

Machine Learning and Complex Systems Lab
Dept. of CSE, Wright State University

We are a machine learning laboratory emphasizing method, model, and systems development. We study the properties of and develop new machine learning algorithms, and consider their application to understand and evaluate complex cybersecurity, sociotechnological, and geospatial systems. We focus on deep learning, explainable AI, and unsupervised learning that exploits the topology of data. We also study and characterize complex systems, often through network analytics and statistical graph modeling.

(Current) Keywords: Explainable AI, deep learning, topological data analysis, web systems modeling.

Representative Recent Publications:

  • A Broad Evaluation of the Tor English Content Ecosystem, ACM WebSci 2019 [pdf]
  • Reasoning over RDF Knowledge Bases using Deep Learning, preprint [pdf]
  • Visual Entailment Task for Visually-Grounded Learning, NeurIPS ViGIL Workshop, 2018 [pdf]
  • HELOC Applicant Risk Performance Evaluation by Topological Hierarchical Decomposition, NeurIPS Finance AI Workshop, 2018 [pdf]
  • Knowledge Graph Enhanced Community Detection and Characterization, WSDM 2018 [pdf]
  • Deep Neural Ranking for Crowdsourced Geopolitical Event Forecasting, ICMLN 2018 [pdf]
  • What Does Explainable AI Really Mean? A New Conceptualization of Perspectives, CeXAI, 2018 [pdf]
  • Seasonal Stochastic Blockmodeling for Anomaly Detection in Dynamic Networks, preprint [pdf]
  • Intrinsic Point of Interest Discovery from Trajectory Data, preprint [pdf]
  • EmojiNet: An Open Service and API for Emoji Sense Discovery, ICWSM 2017 [pdf]
  • People

    Visiting Students

    Giuseppe Nebbione, University of Pavia, Italy (Spring 2018)
    Nripesh Trivedi, Indian Institute of Technology Varanasi, (Summer 2015)

    Alumni (@ last known whereabouts)

    MS Alumni
    [Thesis pdf] Matt Piekenbrock (2018) @ PhD Student, Michigan State
    [Thesis pdf] Jace Robinson (2018) @ PhD Student, Purdue
    [Thesis pdf] Lakshika Balasuriya (2017) @ Data Science R&D, Gracenote
    [Thesis pdf] Nathan Rude (2016) @ Systems Engineer, LexisNexis Special Services
    [Thesis pdf] Samir Yelne (2016) @ Data Scientist, Cisco Systems

    Undergrad Alumni
    Logan Rickert (2018) @ Research Engineer, XX
    Scott Duberstein (2017) @ Research Engineer, Ball Aerospace
    Nripesh Trivedi (2015) @ PhD Student, UC Riverside

    6/6/19: On the Generalization Capability of Memory Networks for Reasoning accepted at ICML Workshop on Understanding and Improving Generalization in Deep Learning! This paper evaluates the degree to which memory networks are able to generically learn to perform entailment over any knowledge base, when the domain of training RDF triples are different from the domain of test triples. Great job Monireh, Sarker, and Ning!

    4/5/19: A Broad Evaluation of the Tor English Content Ecosystem accepted at ACM WebSci 2019! This paper presents our characterization of a comprehensive crawl (150k+ pages) of the Tor dark web encoded in English. It explores the properties and connectivity of Tor anchored on page content type, which is inferred via a graph-based topic labeling algorithm. This work represents what is likely the largest characterization of Tor to date. Big congratulations to Mahdieh!!

    3/20/19: Fuzzy Rough Set Feature Selection to Enhance Phishing Attack Detection accepted at IEEE Fuzzy Systems 2019! This work develops a novel application of fuzzy rough sets to identify html featuers useful for detecting phishing websites that are content and context independent. Congratulations Mahdieh!

    11/20/18: HELOC Applicant Risk Performance Evaluation by Topological Hierarchical Decomposition accepted at NuerIPS 2018 Workshop on Financial AI! This work introduces a novel algorithm for hierarchical exploration of the simplicial complex of a financial services dataset to promote explainable unsupervised learning. Congratulations Kyle!

    11/20/18: Visual Entailment Task for Visually-Grounded Learning accepted at NeurIPS 2018 Visually Grounded Interaction and Language Workshop. This paper introduces a novel research problem, dataset, and deep learning architecture to evaluate if natural language statements are entailed by visual facts in an image. Much of this work was done during Ning's NEC 2018 summer internship. Congratulations Ning!

    10/22/18: Knowledge Graph Enhanced Community Detection and Characterization accepted at WSDM 2019! This paper poses a new community detection method on networks that integrates contextual information about node attributes within a knowledge base. Community assignments and context labels are iteratively updated by a coordinate ascent algorithm that uses a novel "context similarity" kernel and optimization formulation. This work was driven by Shreyansh Bhatt of Kno.e.sis. Congratulations Shreyansh!

    9/28/18: Deep Neural Ranking for Crowdsourced Geopolitical Event Forecasting accepted at the 2018 International Conference on Machine Learning for Networking. This work shows how a tournament refereed by a deep neural network yields an accurate aggregated prediction from a crowd of forecasters, specifically in the context of geopolitical event forecasting. This research is the product of Giuseppe Nebbione's visit to WaCS during the spring of 2018. Congratulations Giuseppe!

    8/10/18: Interdisciplinarity in Data Science Pedagogy: A Foundational Design has been published in the Journal of Computer Information Systems. This article presents the design of an innovative data science course Dr. Doran developed with faculty from the College of Business.

    Publications

    2019

    1. M. Zabihimayvan, R. Sadeghi, D. Doran, and M. Allahyari. “A Broad Evaluation of the Tor English Content Ecosystem”, Proc. of ACM Intl. Conference on Web Science, 2019
    2. M. Zabihimayvan and D. Doran. “Fuzzy Rough Set Feature Selection to Enhance Phishing Attack Detection”, Proc. Of IEEE Intl. Conference on Fuzzy Systems, 2019
    3. S. Bhatt, S. Padhee, K. Chen, V. Shalin, D. Doran, A. Sheth, and B. Minnery. "Knowledge graph enhanced community detection and characterization", Proc. of ACM. Intl. Conference on Web Search and Data Mining, Melbourne, Austrailia, Feb. 2019

    2018

    1. M. Piekenbrock. "Intrinsic Point of Interest Discovery from Trajectory Data", MS Thesis, 2018
    2. J. Robinson. "Seasonality in Dynamic Stochastic Blockmodels", MS Thesis, 2018
    3. L. Balasuriya. "Finding Street Gang Member Profiles on Twitter", MS Thesis, 2018
    4. K. Brown, D. Doran, R. Kramer, and B. Reynolds. "HELOC Applicant Risk Performance Evaluation by Topological Hierarchical Decomposition", NIPS Workshop on Challenges and Opportunities for AI in Financial Services, 2018
    5. N. Xie, A. Kadav, F. Lai, and D. Doran. "Visual Entailment Task for Visually-Grounded Language Learning", NIPS Workshop on Visually-Grounded Interaction and Language, 2018
    6. G. Nebbione, D. Doran, S. Nadellea, and B. Minnery. "Deep Neural Ranking for Crowdsourced Geopolitical Event Forecasting", Proc. of Intl. Conference on Machine Learning for Networking, Paris, France, Nov. 2018
    7. N. Vlajic, M.E. Masri, G. Riva, D. Doran, and M. Barry. "Online Tracking of Kids and Teens by Means of Invisible Images: COOPA vs. GDPR", Proc. of ACM Intl. Workshop on Multimedia Privacy and Security, Toronto, Canada, Oct. 2018
    8. D. Asamoah, D. Doran, S. Schiller. “Interdisciplinarity in Data Science Pedagogy: A Foundational Design”, Journal of Computer Information Systems, Wiley, 2018 (accepted for publication)
    9. Y. Li, D.W. Kim, J. Zhang, and D. Doran. “TeaFilter: Detecting Suspicious Members in an Online Emotional Support Service”, EAI Intl. Conference on Security and Privacy in Communication Networks, Singapore, Aug. 2018
    10. M. Hashler, M. Piekenbrock, and D. Doran. “dbscan: Fast Density-based Clustering Algorithms in R”, Journal of Statistical Software, 2018 [pdf]
    11. K. Brown and D. Doran. “Contrasting Web Robot and Human Behaviors with Network Models’, Journal of Communications, ETPub, 2018 (accepted for publication)
    12. D. Doran. “Data Scientist”, Encyclopedia of Big Data, Springer, L. Schintler, C. McNeely (Eds.), 2018
    13. M. Zabihimayvan and D. Doran. “Some (Non-)Universal Properties of Web Robot Traffic”, IEEE Conference on Information Sciences and Systems, Princeton, NJ, March 2018

    2017

    1. J. Robinson and D. Doran. "Seasonal Stochastic Blockmodeling for Anomaly Detection in Dynamic Networks", Technical Report, arXiv 1712.05359, 2017 [pdf]
    2. M. Piekenbrock and D. Doran. "Intrinsic Point of Interest Discovery from Trajectory Data", Technical Report, arXiv 1712.05247, 2017 [pdf]
    3. D. Doran. “Graph and Link Mining”, Encyclopedia of Big Data, Springer, L. Schintler, C. McNeely (Eds.), 2017
    4. M. Zabihimayvan, R. Sadeghi, and D. Doran. "An Integrated Approach for Benign and Malicious Web Robot Detection", Expert Systems With Applications, 2017 [pdf]
    5. N. Xie, M. K. Sarker, D. Doran, P. Hitzler, and M. Raymer. “Relating Input Concepts to Convolutional Neural Network Decisions”, NIPS Workshop on Interpreting, Explaining, and Visualizing Deep Learning, Long Beach, CA, Dec. 2017 [pdf]
    6. K. Brown and D. Doran. “Realistic Traffic Generation for Web Robots”, Proc. of IEEE Intl. Conference on Machine Learning and Applications, Dec. 2017 [pdf]
    7. D. Doran, S. Schulz, and T. Besold. “What Does Explainable AI Really Mean? A New Conceptualization of Perspectives”, Proc. Of Intl. Workshop on Comprehensibility and Explainability in Artificial Intelligence and Machine Learning, Bari, Italy, Nov. 2017 [pdf]
    8. J. Robinson and D. Doran. “Seasonality in Dynamic Stochastic Blockmodels”, Proc. of ACM/IEEE Intl. Conference on Web Intelligence, Leipzig, Germany, Aug. 2017 [pdf]
    9. S. Wijeratne, L. Balasuriya, A. Sheth, and D. Doran. “A Semantics-Based Measure of Emoji Similarity”, Proc. Of IEEE/WIC/ACM Intl. Conference on Web Intelligence, Leipzig, Germany, Aug. 2017
    10. M. K. Sarker, N. Xie, D. Doran, M. Raymer, and P. Hitzler. “Explaining Trained Neural Networks with Semantic Web Technologies: First Steps”, Proc. Of 12th Intl. Workshop on Neural-Symbolic Learning and Reasoning, London, United Kingdom, Jul. 2017 [pdf]
    11. N. Xie, K. Brown, N. Rude, and D. Doran. “A Soft Computing Prefetcher to Mitigate Cache Degradation by Web Robots”, Proc. Of Intl. Symposium on Neural Networks, Sapporo, Japan, Jun. 2017 [pdf]
    12. S. Wijeratne, L. Balasuriya, A. Sheth, and D. Doran. “EmojiNet: An Open Service and API for Emoji Sense Discovery”, Proc. Of AAAI Intl. Conference on Weblogs and Social Media, Vancouver, CA, May 2017

    2016

    1. N. Rude. "Intelligent Caching to Mitigate the Impact of Web Robots on Web Server Performance", MS Thesis, 2016.
    2. S. Yelne. "Measures of User Interactions, Conversations, and Attacks in a Crowdsourced Emotional Support System", MS Thesis, 2016.
    3. N. Trivedi, D. Asamoah, and D. Doran. “Keep the Conversation Going: Engagement-Based Customer Segmentation for Online Social Service Platforms”, Information Systems Frontiers, 2016
    4. D. Asamoah, R. Sharda, N. Rude, and D. Doran. “RFID-Based Information Visibility for Hospital Operations: Exploring its Positive Effects using Discrete Event Simulation”, Healthcare Management Science, Springer, pp. 1-12, 2016
    5. D. Doran and S. Gokhale. “An Integrated Method for Real-Time and Offline Web Robot Detection”, Expert Systems, Wiley, 2016
    6. D. Doran, K.Severin, S. Gokhale, and A. Dagnino. “Social Media Enabled Human Sensing for Smart Cities”, AI Communications, IOS Press, Vol. 29, pp. 57-76, 2016
    7. D. Doran and A. Fox. “Operationalizing Central Place and Central Flow Theory with Mobile Phone Data”, Annals of Data Science, Springer, Vol. 3, No. 1, pp. 1-24, 2016
    8. L. Balasuriya, S. Wijeratne, D. Doran, and A. Sheth. “Signals Revealing Street Gang Members on Twitter”, 2016 ChASM workshop on Computational Approaches to Social Modeling, Seattle, WA, Nov. 2016
    9. S. Wijeratne, L. Balasuriya, A. Sheth, and D. Doran. “EmojiNet: Building a Machine Readable Sense Inventory for Emoji”, Proc. Of International Conference on Social Informatics, pp. 527-541, Seattle, WA, Nov. 2016
    10. L. Balasuriya, S. Wijeratne, D. Doran, and A. Sheth. “Finding Street Gang Members on Twitter”, Proc. of IEEE/ACM Intl. Conference on Advances in Social Network Analysis and Mining, pp. 685-692, San Francisco, CA, Aug. 2016
    11. M.C. Calzarossa, L. Massari, D. Doran, S. Yelne, N. Trivedi, and G. Moriarty. “Measuring the Users and Conversations of a Vibrant Online Emotional Support System”, Proc. Of IEEE Symposium on Computers and Communications, pp. 1193-1199, Messina, Italy, Jul. 2016
    12. S. Wijeratne, L. Balasuriya, D. Doran, and A. Sheth. “Word Embeddings to Enhance Twitter Gang Member Profile Identification”, 3rd Workshop on Semantic Machine Learning at Intl. Joint Conference on Artificial Intelligence, pp. 18-24, New York, NY, Jul. 2016
    13. M.C. Calzarossa, L. Massari, D. Doran, S. Yelne, N. Trivedi, and G. Moriarty. “Measuring the Users and Conversations of a Vibrant Online Emotional Support System”, Proc. Of IEEE Symposium on Computers and Communications, pp. 1193-1199, Messina, Italy, Jul. 2016
    14. M. Piekenbrock and D. Doran. "Exploring Information-Optimal Network Discretization for Dynamic Network Analysis", INSNA Sunbelt Conference, Newport Beach, CA, Apr. 2016

    2015

    1. D. Doran. “On the Discovery of Social Roles in Large Scale Social Systems”, Social Network Analysis and Mining, Springer, Vol. 5, No. 49, 2015
    2. N. Rude and D. Doran. “Request Type Prediction for Web Robot and Internet of Things Traffic”, Proc. Of IEEE Intl. Conference on Machine Learning and Applications, pp.988-993, Miami, FL, Dec. 2015
    3. D. Asamoah, D. Doran, and S. Schiller. “Teaching the Foundations of Data Science: An Interdisciplinary Approach”, SIGDSA Pre-ICIS Business Analytics Congress, Fort Worth, TX, Dec. 2015
    4. M. Maurice, M. Piekenbrock, and D. Doran. "WAMINet: An Open Source Library for Dynamic Geospace Analysis Using WAMI", Proc. of IEEE Intl. Symposium on Multimedia, Miami, Florida, Dec. 2015
    5. D. Doran, S. Yelne, L. Massari, M.C. Calzarossa, L. Jackson, and G. Moriarty. “Stay Awhile and Listen: User Interactions in a Crowdsourced System Offering Emotional Support”, Proc. of IEEE/ACM Intl. Conference on Advances in Social Network Analysis and Mining, pp. 667-674, Paris, France, Aug. 2015
    6. S. Kumar, P. Kapanipathi, D. Doran, P. Jain, and A. Sheth. “Entity Recommendations Using Hierarchical Knowledge Bases”, Proc. Of Intl. Workshop on Knowledge Discovery and Data Mining Meets Linked Open Data at European Semantic Web Conference, Portoroz, Slovenia, Jun. 2015
    7. S. Wijeratne, D. Doran, A. Sheth, and J. Dustin. “Analyzing the Social Media Footprint of Street Gangs”, Proc. Of IEEE Intl. Conference on Intelligence Security Informatics, pp. 91-96, Baltimore, MD, May 2015
    8. D. Doran, A. Fox, and V. Mendiratta. “Where do we Develop? Discovering Regions for Urban Investment in Senegal”, Intl. Conf. on the Analysis of Mobile Phone Datasets Data for Development Challenge Book of Abstracts: Scientific Papers, pp. 530-540, Cambridge, MA, Apr. 2015
    9. H. Alzhami, S. Gokhale, and D. Doran. “Understanding Social Effects in Online Networks”, Proc. Of IEEE Intl. Symposium on Social Computing and Semantic Data Mining, pp. 863-868, Anaheim, CA, Feb. 2015