Module: Data at Speed and Scale

Module Specifications..

Current Academic Year 2023 - 2024

Please note that this information is subject to change.

Module Title	Data at Speed and Scale
Module Code	CA4022
School	School of Computing
Module Co-ordinator	Semester 1: Alessandra Mileo Semester 2: Alessandra Mileo Autumn: Alessandra Mileo
Module Teachers	Alessandra Mileo
NFQ level	8	Credit Rating	7.5
Pre-requisite	None
Co-requisite	None
Compatibles	None
Incompatibles	None

None

Description

This module addresses the three Vs of Big Data: Volume, Velocity and Variety. This module will equip students with detailed knowledge of mining massive data sets, processing streams of data in real-time, and extracting knowledge from complex information. The module introduces the theory and practice of massively parallel data processing, leveraging different hardware and software infrastructures, including could-based infrastructures. It includes a practical component with development of Big Data analytics on suitable publicly-available test data using high-level languages and suitable libraries.

Learning Outcomes

1. Understand the nature and consequences of Big Data for processing and analytics
2. Design and Implement data-intensive applications using existing best-of-breed big data libraries and frameworks
3. Discuss the role of cloud services in the design of big data systems
4. Apply machine learning techniques to Big Data
5. Explore and curate large, complex datasets for use in analytics
6. Configure and deploy data analytics infrastructure
7. Understand and discuss some of the design considerations for high-performance analytics
8. Gain detailed knowledge of map-reduce, related distributed file systems and their open-source implementations

*Type*	*Hours*	*Description*
Workload	Full-time hours per semester
Lecture	36	Lectures and tutorials presenting the key theoretical aspects of the course. Lecture material will be provided in the form of online notes, research papers, technical documentation and multimedia content as applicable.
Laboratory	24	Hands-on Programming laboratory work and tutorials incorporating problem-based learning tasks, formative assessments, and student-led discussions. This will include significant technical work to configure, deploy, program and execute data analysis software.
Independent Study	190	Significant individual work including reading and understanding technical papers, research material, documentation. Preparation of continuous assessment, discussion of coursework with peers and group assignment.
Total Workload: 250

All module information is indicative and subject to change. For further information,students are advised to refer to the University's Marks and Standards and Programme Specific Regulations at: http://www.dcu.ie/registry/examinations/index.shtml

Indicative Content and Learning Activities

Big Data Processing and Mapreduce
Introduction to Big Data, and why Big Data analytics is different to conventional approaches. Introduction to the Mapreduce algorithm and its open-source implementation. The Hadoop ecosystem and how it can be used to analyse data.

Finding Similar Items
Theoretical topics include Locally-sensitive Hashing, Minhashing, Similarity-preserving summaries, Distance measures. These form the basis for organising and exploring Big Data.

Stream Processing
Handling real-time / stream data through the use of Filtering, Sampling, Estimation of Moments, and other techniques. Practical aspects include programming with Spark, Storm or a similar library.

Large-scale machine learning
Key topics include Item Similarity, Clustering, and evaluating performance.

Big Data Cloud
Configuring and using Amazon EC2, Elastic Mapreduce, Microsoft Azure and similar technologies. The students will deploy applications to these platforms as part of their assignments.

Assessment Breakdown
Continuous Assessment	100%	Examination Weight	0%

Type	Description	% of total	Assessment Date
Course Work Breakdown
Assignment	Obtain, explore, curate, and analyse a massive dataset, applying relevant analytical approaches and reporting on the results	30%	Week 4
Research Paper	Short Research Paper on a new trend, novel approach or new application in the area of Big Data Analytics	20%	Week 7
Project	Design and Implement a Data-driven application, optionally using machine learning and cloud infrastructure	50%	Week 10

Reassessment Requirement Type
Resit arrangements are explained by the following categories; 1 = A resit is available for all components of the module 2 = No resit is available for 100% continuous assessment module 3 = No resit is available for the continuous assessment component
This module is category 1

Indicative Reading List

Other Resources

None

Programme or List of Programmes

DS	BSc in Data Science
MCMEC	Micro-Credential Modules Eng & Comp
SMPEC	Single Module Programme (Eng & Comp)

Archives: