Proceedings

Jim Tung, MathWorks

Organizations with digital transformation initiatives are making the shift from visionary ambitions to practical projects. These organizations have defined their high-level digital transformation objectives, and are now looking to their engineers and scientists to achieve them. This will involve learning new technologies, collaborating with unfamiliar groups, and proposing new products and services. To meet this challenge, technical organisations must master how to systematically use data and models, not only during the research and development stages, but also across groups throughout the lifecycle of the offering. An effective digital transformation plan needs to consider changes in people’s skills, processes, and technology. Join us as Jim Tung describes this pragmatic approach to digital transformation and demonstrates how engineering and scientific teams are leveraging data and models to achieve their digital transformation objectives.

Sigfredo Fuentes, University of Melbourne

Over the last decade, the occurrence of bushfires has worsened. Australia has experienced one of the longest and most severe bushfire events in recorded history, gravely affecting wine regions. From the recent bushfire event, Adelaide Hills, an iconic wine region, has lost more than a third of its grapevine plantations. Smoke produced from bushfires can pollute vineyards by contaminating berries with unsavoury compounds, known as smoke taint, that are later passed to the wine. Wines tainted by smoke present sensorial aromas described as ash, smoky, burnt and medicinal, which can spoil an entire vintage. At present, there are no available tools for winegrowers to assess smoke contamination and make an informed decision on what amelioration measures can be implemented. The Digital Agriculture, Food and Wine group at the University of Melbourne has devised short- and long-range remote sensing techniques and e-noses coupled with Artificial Intelligence using MATLAB to obtain Machine Learning models to assess smoke contamination in grapevines and smoke taint in final wines.

Michelle Hirsch, MathWorks
Heather Gorr, MathWorks

Are you getting the most out of MATLAB^®, or are you still using it just the way you were taught your first year in university? With over 2,000 people working year-round to design, build, test, and document MathWorks products, it is a safe bet that there are more than a few useful features you don’t know.

This fast-paced talk will introduce at least 21 features you can start using today to make your use of MATLAB more efficient, more effective, and more fun. Some features will be very new, while others may be 5, 10, or maybe even more than 15 years old. How many of them will be new to you?

Seth DeLand, MathWorks

While many organizations get excited about adopting machine learning techniques, success does not come easy. Come to this talk to learn about applications where machine learning generates considerable ROI, including fleet data analysis, energy forecasting, and smart manufacturing.  We will also demonstrate how engineers are integrating machine learning techniques with their controls and signal processing workflows to improve system performance.

Throughout the presentation we will highlight new features in MATLAB^® that accelerate deploying machine learning. This includes applying automation techniques to feature selection, model selection, and hyperparameter optimization (AutoML). We will also cover new ways for integrating machine learning models with production workflows such as updating deployed models and C/C++ code generation.

Come to this talk to learn how your peers have applied machine learning, and to get inspiration for how machine learning could be applied to your own work.

Adam Sifounakis, MathWorks

How do you manage your code and models as they grow, become more complex, and require multiple people to work on them simultaneously?

This session will introduce some of the software development tools available in MATLAB^® and Simulink^® to better manage your files, track changes, work collaboratively, and write more robust applications. We will also discuss how to automate testing and deploy your tests to continuous integration (CI) systems to ensure your application always works.

Highlights:

• Managing your code and model dependencies using Projects
• Tracking changes and working collaboratively using source control (Git)
• Writing better, robust, and portable code and models
• Creating tests to prove your applications works as expected
• Leveraging CI systems (such as Jenkins) to automate testing and reporting

Peter Brady, MathWorks

Learn about new capabilities in the MATLAB^® product families to support your research, design, and development workflows. This talk highlights features for deep learning, machine learning, and other application areas. You will see new tools for preprocessing and analyzing data; developing algorithms; creating interactive apps; packaging and sharing simulations; and modeling, simulating, and verifying designs.

Harshita Bhurat, MathWorks

Identifying product defects and reducing manufacturing errors in industrial applications can help reduce labor and manufacturing costs. While traditional techniques for automated optical inspection tend to be brittle, deep learning based techniques are more robust and accurate.

Whether you are new to deep learning or an expert, MATLAB^® can help you detect and localize different types of abnormalities so you can replace traditional inspection processes with accurate, repeatable, and reliable vision inspection.

Hisham El-Masry, MathWorks

Many organizations use one or more cloud environments for efficiency, scalability, and mobility, especially for the development and deployment of AI models and applications.  Cloud environments can be difficult to set up, maintain, and ultimately use. 

In this talk we show you how to configure and use MATLAB^® in cloud environments, demonstrated with an AI workflow. We will use several cloud environments:

• Your own private cloud environment hosted on-premise
• Public clouds such as AWS or Azure
• The MathWorks Cloud with MATLAB Online™
• A hybrid cloud setup, using two or more of these cloud environments

In each cloud configuration, we will show how MATLAB, MATLAB Parallel Server™, and MATLAB Production Server™ can be used.

Ruth-Anne Marchant, MathWorks

Learn about new capabilities in the Simulink^® product families to support your research, design, and development workflows. This talk highlights features for physical modelling, algorithm development, team collaboration, and other application areas. You will see a high-level overview of the major capabilities and how you can use Simulink to design, simulate, implement, and test a variety of time-varying systems, including controls, signal processing, physical modelling, and automatic code generation.

Marco Dragic, MathWorks
Paul Urban, MathWorks

Developing complex systems with quickly evolving customer requirements presents challenges for development, verification, and compliance with safety standards.

Model-Based Design accelerates agile system development by allowing you to gain early insights into system feasibility and to speed development through simulation, automatic code generation, and continuous testing. With test-driven development, requirements are first captured as test cases that drive the implementation. Model-Based Design provides a framework that supports test-diven development. Bringing together these approaches achieves agility in the system development process. As a result, development teams can better understand customer requirements, quickly respond to changes, identify errors earlier, refactor the design, and deliver working systems faster. We will discuss how you can apply test-driven development by authoring tests that drive system development and implementation in the context of Model-Based Design.

Jens Lerche, MathWorks

In this session, we will show how industrial systems engineers can use desktop simulation to design and test control logic and predictive algorithms without the need for a physical prototype.

Through automatic generation of C/C++ code and code compliant with the IEC 61131-3 standard, you can accelerate deployment of embedded algorithms onto industrial controllers like PLCs, and stay hardware platform independent.

We show how to leverage simulation models of industrial systems using Model-Based Design to develop control logic and condition monitoring algorithms, automatically generate code for PLCs, and perform real-time testing.