Data Analysis and Machine Learning Efforts at SDM Group
       For papers under review, send an email to Alex Sim (asim at lbl dot gov)

Network Pattern searching and classification
Network Performance analysis and prediction
Machine Learning Based Data Analysis, Classification and Prediction
Statistical online streaming data pattern searching, data reduction - IDEALEM
All Other Data Analysis
  • Evaluating the Effects of Missing Values and Mixed Data Types on Social Sequence Clustering Using t-SNE Visualization
    ACM Journal of Data and Information Quality, 2019
  • Identifying Anomalous File Transfer Events in LCLS Workflow
    Workshop in Autonomous Infrastructure for Science (AI-Science 2018), 2018
  • Modeling Data Transfers: Change Point and Anomaly Detection
    International Workshop on Scalable Network Traffic Analytics (SNTA 2018), 2018
  • Detecting Anomalies in the LCLS Workflow
    the 3rd workshop on Open Science in Big Data (OSBD 2018), in conjunction with IEEE International Conference on Big Data, 2018
  • Convolutional Filtering for Accurate Signal Timing from Noisy Streaming Data
    IEEE International Conference on Big Data Intelligence and Computing (DataCom2017), 2017
  • Parameter Analysis of the VPIN (Volume synchronized of Informed Trading) Metric
    Quantitative Financial Risk Management: Theory and Practice, 2015, doi:10.1002/9781119080305.ch13
  • A Big Data Approach to Analyzing Market Volatility
    Algorithmic Finance, 2013, doi:10.3233/AF-13030
  • Efficient Operational Profiling of Systems Using Arrays on Execution Logs
    ISSRE, doi:10.1109/ISSRE.2008.45
  • Statistical tests for deterministic effects in broad time series
    Physica D, 1993, doi:10.1016/0167-2789(93)90188-7
  • Posters
    • Joint Sequence Analysis Challenges: How to Handle Missing Values and Mixed Variable Types
      SIAM Conference on Computational Science and Engineering (CSE19), 2019
    • Network Traffic Performance Prediction with Multivariate Clusters in Time Windows
      SIAM Conference on Computational Science and Engineering (CSE19), 2019.
    • Identification of Network Data Transfer Bottlenecks in HPC Systems
      International Conference for High Performance Computing, Networking, Storage and Analysis (SC'18), 2018
    • Accurate Signal Timing from High Frequency Streaming Data
      IEEE International Conference on Big Data (Big Data), 2017.
    • Feature Engineering and Classification Models for Partial Discharge Events in Power Transformers
      10th IEEE/ACM International Conference on Utility and Cloud Computing (UCC 2017), 2017
    • Diagnosing Parallel I/O Bottlenecks in HPC Applications
      International Conference for High Performance Computing, Networking, Storage and Analysis (SC'17), 2017
      Student Research Competition, 1st place winner.
    • Analysis of Variable Selection Methods on Scientific Cluster Measurement Data
      International Conference for High Performance Computing, Networking, Storage and Analysis (SC'16), 2016
      Student Research Competition, 2nd place winner.
    • Discovering Energy Resource Usage Patterns on Scientific Clusters
      International Conference for High Performance Computing, Networking, Storage and Analysis (SC'16), 2016
      Student Research Competition, 3rd place winner.
    • I/O Performance Analysis Framework on Measurement Data from Scientific Clusters
      International Conference for High Performance Computing, Networking, Storage and Analysis (SC'15), 2015
    • Real-Time Outlier Detection Algorithm for Finding Blob-Filaments in Plasma
      International Conference for High Performance Computing, Networking, Storage and Analysis (SC'14), 2014
  • Patents
    • Methods, systems, and devices for accurate signal timing of power component events,
      US Patent application no. 2019/0138371 A1, 2019.
    • Data reduction methods, systems and devices,
      US Patent pending serial no. 14/555,365, 2014.
    • Co-scheduling of network resource provisioning and host-to-host bandwidth reservation on high-performance network and storage systems,
      US Patent 8,705,342, 2014.