AI, or artificial intelligence, is powering a massive shift in the roles that computers play in our personal and professional lives. Most technical organizations expect to gain or strengthen their competitive advantage through the use of AI. But are you in a position to fulfill that expectation, to transform your research, your products, or your business using AI?
Chris Hayhurst looks at the techniques that compose AI (deep learning, computer vision, robotics, and more), enabling you to identify opportunities to leverage it in your work. You will also learn how MATLAB® and Simulink® are giving engineers and scientists AI capabilities that were previously available only to highly-specialized software developers and data scientists.
Fighter Aircraft Development with Model-Based System Engineering: A Report from the Trenches
Over the last decade, model-based systems engineering (MBSE) has been heralded as the future in systems development. It would not be inaccurate to state that there is a certain hype associated with modeling and models. Hence, it is relevant to critically assess the end user experience. What is the experience of the engineers in the trenches? Do contemporary tools and methods stand up to the test when used in development of complex multidisciplinary systems, such as a fighter aircraft?
This presentation elaborates on experiences from the use of MBSE within the development of Gripen E/F at SAAB Aeronautics. It starts by exemplifying some distinct factors that make fighter aircraft development challenging—both from a technical and from an organizational point of view. This is followed by an overview of MBSE domains and the SAAB Aeronautics team’s experience from modeling in those domains, with some special focus on the use of Simulink® in the development of multidisciplinary systems. The presentation is concluded with an evaluation of desired improvement in MBSE methods and tools.
Unlocking the Power of Machine Learning
Machine learning is driving innovation in many application areas, including predictive maintenance, digital health and patient monitoring, financial portfolio forecasting, and advanced driver assistance. Developing machine learning models and deploying them on embedded systems or cloud infrastructure often still requires significant expertise with signal processing, big data, and model optimization.
In the context of obtaining insights from real-world data, this talk addresses how MATLAB® empowers engineers and scientists without significant signal processing and machine learning expertise to tackle challenges like:
- Importing, visualizing, and preprocessing time-series and other data
- Detecting and extracting features in time, frequency, and time-frequency domains from signals
- Exploring advanced signal processing and transfer learning techniques for time-series classification
- Evaluating multiple models and working with large amounts of data
- Optimizing performance, including hyperparameter tuning
- Deploying models in production IT systems or on embedded devices
Demystifying Deep Learning
Deep learning can achieve state-of-the-art accuracy for many tasks considered algorithmically unsolvable using traditional machine learning, including classifying objects in a scene or recognizing optimal paths in an environment. Gain practical knowledge of the domain of deep learning and discover new MATLAB® features that simplify these tasks and eliminate the low-level programming. From prototype to production, you’ll see demonstrations on building and training neural networks and hear a discussion on automatically converting a model to CUDA® to run natively on GPUs.
Deploying Deep Learning Networks to Embedded GPUs and CPUs
Designing and deploying deep learning and computer vision applications to embedded CPU and GPU platforms is challenging because of resource constraints inherent in embedded devices. A MATLAB® based workflow facilitates the design of these applications, and automatically generated C or CUDA® code can be deployed on boards like Jetson TX2 and DRIVE™ PX and achieve very fast inference. The presentation illustrates how MATLAB supports all major phases of this workflow. Starting with algorithm design, the algorithm may employ deep learning networks augmented with traditional computer vision techniques and can be tested and verified within MATLAB. Next, these networks are trained using GPU and parallel computing support for MATLAB either on the desktop, cluster, or the cloud. Finally, GPU Coder™ generates portable and optimized C/C++ and/or CUDA® code from the MATLAB algorithm, which is then cross-compiled and deployed to CPUs and/or Tegra® board. Benchmarks show that performance of the auto-generated CUDA code is ~2.5x faster than MXNet, ~5x faster than Caffe2, ~7x faster than TensorFlow®, and on par with TensorRT™ implementation.
How We Develop MATLAB Applications: From Idea to Commercialization
Stardots develops applications for researchers and engineers using MATLAB® and MATLAB Compiler™. To that end, the company has built a system for distributing, licensing, downloading, installation, and upgrading to ensure a smooth user experience. In addition, they have developed a MATLAB based framework for intuitive graphical interfaces, big data databases, and logs. Using this system, they are now ready to harness the power of MATLAB to deliver intuitive, visually pleasing applications to enable data-driven insights to the scientific community. They have received many inquiries to productize algorithms, in various disciplines, for the general market. This presentation demonstrates an in-house developed sensor application, Evolved Horizon™, as an example of Stardots philosophy and business model.
Predictive Maintenance: From Development to IoT Deployment
Interest in predictive maintenance is increasing as more and more companies see it as a key application for data analytics that run on the Internet of Things. This talk covers the development of these predictive maintenance algorithms, as well as their deployment on the two main nodes of the IoT—the edge and the cloud.
Master Class: Scaling up MATLAB Analytics with Kafka and Cloud Services
As the size and variety of your engineering data has grown, so has the capability to access, process, and analyze those (big) engineering data sets in MATLAB®. With the rise of streaming data technologies and large-scale cloud infrastructure, the volume and velocity of this data has increased significantly, and this has motivated new approaches to handle data-in-motion. This presentation and demo highlights the use of MATLAB as a data analytics platform with best-in-class stream processing frameworks and cloud infrastructure to express MATLAB based workflows that enable decision-making in “near-real-time” through the application of machine learning models. It demonstrates how to use MATLAB Production Server™ to deploy these models on streams of data from Apache® Kafka®. The demonstration shows a full workflow from the development of a machine learning model in MATLAB to deploying it to work with a real-world sized problem running on the cloud.
Managing Performance and Safety in a Multidomain Complex System with Model-Based Design
Increasing environmental awareness has made electrification a major technology driver. Autonomous electric vehicles in highly dynamic scenarios (braking) are characterized by physical and algorithmic complexity. Through this example, this presentation highlights how Model-Based Design allows integration of components while capturing critical multidomain interactions (heat, electricity, and movement). Such simulation platform is instrumental for developing safe and performant technology in an agile manner shortening time-to-market. Reuse of such models for detection of faults and degradation along with real-time testing will be also tackled.
Automating Best Practices to Improve Design Quality
Years of engineering expertise and best practices form the basis for the industry standards used in developing high integrity and mission critical systems. The standards include proven guidelines which can improve the quality of any design. Learn how you can take advantage of best practices from standards such as ISO 26262, DO-178/DO-331, IEC 61508, MISRA®, and others to find errors earlier in your process and improve the quality of your Simulink® models.
Real-Time Testing in a Modern, Agile Development Workflow
Real-time testing has become more and more important for staying innovative, shortening time-to-market by starting to test earlier, and avoiding expensive prototypes. In this presentation, you will see how to enable a high degree of reuse going from desktop development to verification of your design in the real world, both for a rapid prototyping and a hardware-in-the-loop (HIL) scenario. For rapid prototyping, the presentation will cover the latest advancements targeting FPGA technology. For HIL, it will show how to set up a structured framework that can be reused for both desktop and real-time tests.
A Model-Based Design Adoption Story from Bombardier Transportation
Bombardier Transportation, Rolling Stock Equipment delivers world-class propulsion systems for trains. The propulsion system’s main functionality is to convert electrical power to tractive effort to make the train move. The control system consists of multiple different sub-parts that together control various parts of a joint electrical circuit. With new development and applications including major customization needs, there is a consistent challenge to deliver on time with maintained quality. The propulsion system and control teams at Bombardier Transportation in Västerås decided to adopt Model-Based Design to address these challenges.
The goal of this presentation is to share the experience of transforming from virtually no use of Model-Based Design to where we are today. The presentation outlines the vital steps of our adoption story, including the need for changes, problem statements, use cases, commercial aspects, challenges, and the business case.
Master Class: Hardware and Software Co-Design for Motor Control Applications
Electric motors are everywhere and are finding new applications every day. The technology to control motors is also evolving to be based on new platforms, such as Xilinx® Zynq®, that combine embedded processors with the programmable logic of FPGAs.
In this talk, you will learn how C and HDL code generation are used to produce implementations on Xilinx Zynq SoCs. You will also explore practical methods for developing motor controllers targeting Zynq SoCs, including the use of new HDL debugging capabilities.