Download presentation
Presentation is loading. Please wait.
Published byMargery Shepherd Modified over 9 years ago
1
MAR 03 2014 Capability Overview Deck Protean Analytics
2
Internet of Things A global network infrastructure, linking physical and virtual objects through the exploitation of data capture and communication capabilities. This infrastructure includes existing and evolving Internet and network developments. It will offer specific object-identification, sensor and connection capability as the basis for the development of independent cooperative services and applications. These will be characterised by a high degree of autonomous data capture, event transfer, network connectivity and interoperability 2 Definition from “Coordination and support action for global RFID-related activities and standardisation “
3
M2M Analytics
4
Protean | Platform Overview Is a centrally hosted, instrumented “Smart and Connected” platform servicing real- time business event streams using high-speed MPP Compute and Storage Grids Primarily based on the concepts and principles of Event Driven Architecture (EDA), Complex Event Processing (CEP) and Multi-Agent-Systems (MAS) Support for high speed data ingestion - Structured and Unstructured (Textual) Core Advanced Analytics enabled through Model Building, Data Mining and Machine Learning techniques (Supervised and Unsupervised) Context modelling creation across Time-Space-Value dimensions Enables creation of a Central Enterprise Data Refinery to enable “Source of Truth” for transactional information within the Enterprise Supports deployment on a Cloud (Amazon EC2) or at an Enterprise (local) 4
5
Core Components of the Platform... 5
6
Data IngestionData Cleansing Data Transformation Data Normalization Complex Event Processing Engine Business Process Instantiation Inferencing and Reasoning Engine Ontology Models Enterprise Business Services / Repository CMC Confidential Key Capabilities at CMC include building the High Scale Data and Compute Grids and implementation of Advanced Data Mining and Machine Learning techniques for the areas of interest for our clients… High Scale Clustered Data Grid In-Memory High Scale MPP Compute Grid Enterprise Data Warehouse Complex Event Processing Advanced Visualization Data Refinery Data Mining & Machine Learning Optimization Engine(s) Embed into Business Processes (Actionable Insights) Embed into Business Processes (Actionable Insights) Application Enrichment Capabilities Enterprise Business Apps Infrastructure Monitoring and ManagementSecure Computing Platform Semi-structured Data Traditional RDBMS, Data Marts, Data Warehouses Physical Records Real-time Business Events 6
7
A reference architecture blueprint for realizing the Big Data platform leveraging Free and Open Source Software (FOSS)….The platform has been deployed successfully across 4 large client implementations across various business domains…. CMC Confidential 7
8
Quick Snapshot of core technologies around which capabilities have been built within the CMC Big Data and Advanced Analytics practice…. CMC Confidential 8
9
Platform Reference Framework Core Architecture Patterns realized for high scale real-time data processing employing a combination of In-memory CEP, MAS techniques, Big Data and Advanced Analytics technologies... 9
10
Leveraging Data Mining and Machine Learning Constructs... The Data Mining / Machine Learning algorithm constructs such as Clustering, Classification, Association and Anomaly Detection techniques enable creation of “advanced models” that can detect deviant “behavior” in real-time and flag appropriately in the system, augmented with advanced visualization that lets the “expert” to decipher the patterns of interest.... 10
11
Batch Analytics | Reference Pattern To respond effectively in near real-time it’s important to apply analytics in advance, by crunching large amounts of data. The batch analytics pattern is also used for the process of investigation and improvement that’s used to improve the model efficiency through supervised and unsupervised machine learning techniques. 11
12
Real-time Analytics | Reference Pattern The need to respond to certain incoming interactions within milliseconds, e.g., to flag possible fraud, to bid on an auction, to respond to a routing request, or to make a recommendation. Typically these responses involve a fast response based on a model that was previously scored in cluster. Typically the processing sequence includes advanced correlation among events – to process them within the ‘context’ - as part of CEP framework. 12
13
A service based integration enables real-time information exchange with the larger Enterprise IT system landscape... 13
14
Case Studies
15
Telematics | Sample Screenshots / Capabilities
19
Homeland Security | Sample Case Study Create, Consolidate and Register a master set of trusted patterns of object behavior, movement Capture, Correlate and Fuse multi-sensor data in real-time for the objects being monitored The platform has been recognized as a huge step forward considering the volume and variety of data flowing in at potentially 5 second intervals – manually impossible to consume-comprehend-decide the usage in real-time Build an engine based on knowledge representation and driven by semantic technologies for reasoning and inferencing to detect anomalous behavior in real-time Accommodate additional reasoning and inferencing engines and logic at runt-time thereby allow extreme flexibility in the platform Deploy a supervised machine learning system that is sustainable and increases in value over time Simulation engine that can mimic real-world object behaviors and help generate new learning sets that can feed into the baselined and supervised machine learning model Integrate the platform with various homeland security agencies to transmit observations in real-time to augment / aid decision making 19
20
Healthcare | Sample Case Study Healthcare: Predicting 30-day Re-admission for a CHF Patient in real-time at a Hospital leveraging Advanced Supervised Machine Learning Models built over 12 million Patient Record sets Healthcare: Real-time / Early detecting of Sepsis pathways for an admitted Patient to enable timely interventions at the Hospital 20
21
THANK YOU
Similar presentations
© 2025 SlidePlayer.com. Inc.
All rights reserved.