描述

E6893 Big Data Analytics Lecture 4: Real-Time Stream Analysis Ching-Yung Lin, Ph.D. Adjunct Professor, Dept. of Electrical Engineering and Computer Science September 29, 2023 1 E6893 Big Data Analytics – Lecture 4: Real-Time Stream Analysis © 2023 CY Lin, Columbia University Stream Analyses Technical Challenges 2 E6893 Big Data Analytics – Lecture 4: Real-Time Stream Analysis © 2023 CY Lin, Columbia University Example IP Packet Stream Instantiation rtsp ftp tcp ip http udp rtp audio video ntp Inputs Dataflow Graph By IBM Dense Information Gliding Team 3 E6893 Big Data Analytics – Lecture 4: Real-Time Stream Analysis © 2023 CY Lin, Columbia University Semantic MM Filtering rtsp ftp tcp ip http udp Advanced content analysis rtp audio video sess Interest Routing Interest keywords id Filtering sess ntp 4 Dataflow Graph Packet content analysis Inputs per PE rates Interested MM streams 200-500MB/s ~100MB/s E6893 Big Data Analytics – Lecture 4: Real-Time Stream Analysis 10 MB/s © 2023 CY Lin, Columbia University Resource-Accuracy Trade-Offs R X Y(X|q) X’ Y’’(X|q,R) Configurable Parameters of Processing Elements to maximize relevant information: Y’’(X | q, R) > Y’(X | q, R), with resource constraint. Required resource-efficient algorithms for: Classification, routing and filtering of signal-oriented data: (audio, video and, possibly, sensor data) 5 Input data X – Queries q – Resource R Y(X | q): Relevant information Y’(X | q, R) ` Y(X | q): Achievable subset given R E6893 Big Data Analytics – Lecture 4: Real-Time Stream Analysis © 2023 CY Lin, Columbia University Example: Distributed Video Signal Understanding (Lin et al.) TV broadcast, VCR, DVD discs, Video File Database, Webcam (Distributed Smart Sensors) Block diagram of the smart sensors (Server) Concept Detection Processing Elements PE1: 9.2.63.66: 1220 PE4: 9.2.63.66:1235 Face MPEGCDS PE2: 9.2.63.67 Features 1/2 EncodGOP Feature Event ing Extraction Extr

AI 摘要