Module: Building Complex Computational Models

Module Specifications.

Current Academic Year 2024 - 2025

All Module information is indicative, and this portal is an interim interface pending the full upgrade of Coursebuilder and subsequent integration to the new DCU Student Information System (DCU Key).

As such, this is a point in time view of data which will be refreshed periodically. Some fields/data may not yet be available pending the completion of the full Coursebuilder upgrade and integration project. We will post status updates as they become available. Thank you for your patience and understanding.

Date posted: September 2024

Module Title	Building Complex Computational Models
Module Code	CA4024 (ITS) / CSC1111 (Banner)
Faculty	Engineering & Computing	School	Computing
Module Co-ordinator	Marija Bezbradica
Module Teachers	Martin Crane, Suzanne Little, Tai Mai
NFQ level	8	Credit Rating	7.5
Pre-requisite	Not Available
Co-requisite	Not Available
Compatibles	Not Available
Incompatibles	Not Available

None

Description

The purpose of this course is to demonstrate how to build models for simulations of complex systems and provide the underlying mathematical foundation necessary for constructions of such models. The course will teach students basic topics such as Time Series Analysis as well as more complex ones such as how to translate social or physical behaviour (from micro to macro environments) to computational prediction models and how to deduce unknown model parameters from noisy/incomplete data sets. Key topics will include Monde Carlo methods, Markov models, Cellular Automata and Agent Based Modelling.

Learning Outcomes

1. Understand the different types of Time Series Models and decompose a such a series into parts such as Trend, Seasonality and Residual Components
2. Examine ARMA/ ARIMA models to study suitable choice of coefficients and build ARMA/ ARIMA models for given datasets
3. Perform basic forecasting using time series models, recognising the limits of these forecasts
4. Understand what constitutes a complex system and differentiate between bottom-up and top-down approach to modelling.
5. Build probabilistic, predictive models using techniques such as Monte Carlo, Markov Chain MC, Hidden Markov models and Bayesian networks.
6. Construct spatial models using Cellular Automata and Agent Based techniques. Translate complex system of choice into a CA/ABM model.
7. Explore different languages and frameworks that can be used to implement models of complex systems (e.g. Flame, NetLogo etc.).

*Type*	*Hours*	*Description*
Workload	Full-time hours per semester
Lecture	36	Extracting unknown model parameters from complex data sets by using a set of techniques such as Inverse Monte Carlo, Gibbs Sampling, Simulated Annealing.
Independent Study	36	Review of class material (recorded lectures etc)
Laboratory	24	Hands-on experience in modelling frameworks for complex systems as covered during lectures.
Independent Study	92	No Description
Total Workload: 188

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

Fundamentals of Time Series Analysis
What is a time series? Some common examples of Time Series? Decomposing a time series into Trend, Seasonal and Residual Components. Building an ARMA, ARIMA and SARIMA model. Introduction to Forecasting

Fundamentals of complexity and probability
What is a complex system? Botom-up vs. top-down approach. Explaining the need for modelling. Discussing emergent systems. Reviewing probability distributions sampling, power-law, eigenvalues and eigenvectors, uncertainty and confidence intervals.

Random number generation
Pseudo-random numbers and random variables, Linear congruential generator, Mersenne Twister, generation of random distribution data (inverse transformation and acceptance-rejection method).

Probabilistic Modelling Methods
Direct Monte Carlo, Markov Chain MC, Hidden Markov models, Bayesian networks, basics of Genetic Algorithms.

Spatial Models
Translating physical systems into Cellular Automata/Agent Based Models with emphasis on properties, behaviour and granularity. Reference CA/ABM models for various applications.

Inverse Models
Extracting unknown model parameters from complex data sets by using a set of techniques such as Inverse Monte Carlo, Gibbs Sampling, Simulated Annealing.

Assessment Breakdown
Continuous Assessment	40%	Examination Weight	60%

Type	Description	% of total	Assessment Date
Course Work Breakdown
Loop Quiz	A loop quiz on Time Series	20%	Week 5
Assignment	Building a complex system model using techniques covered on lectures.	20%	n/a

Reassessment Requirement Type
Resit arrangements are explained by the following categories: Resit category 1: A resit is available for both* components of the module. Resit category 2: No resit is available for a 100% continuous assessment module. Resit category 3: No resit is available for the continuous assessment component where there is a continuous assessment and examination element.
* ‘Both’ is used in the context of the module having a Continuous Assessment/Examination split; where the module is 100% continuous assessment, there will also be a resit of the assessment
This module is category 1

Indicative Reading List

Heppenstall, A.J., Crooks, A.T., See, L.M., Batty, M.,: 0, Agent-Based Models of Geographical Systems, 978-90-481-89
Asmussen, Søren, Glynn, Peter W.,: 0, Stochastic Simulation: Algorithms and Analysis, 978-0-387-690
Boccara, N.: 2010, Modeling Complex Systems, 978-1-4419-65
Daphne Koller,Nir Friedman: 2009, Probabilistic Graphical Models, MIT Press, Cambridge, MASS, 9780262013192
Uri Wilensky,William Rand: 2015, An Introduction to Agent-Based Modeling, MIT Press, 9780262731898

Other Resources

43726, Website, Rob Hyndman, 0, Forecasting: Principles & Practice, https://otexts.com/fpp2/,