The current set of research methods on ictresearchmethods.nl contains only one research method that refers to machine learning: the “Data analytics” method in the “Lab” strategy. This does not reflect the way of working in ML projects, where Data Analytics is not a method to answer one question but the main goal of the project. For ML projects, the Data Analytics method should be divided in several smaller steps, each becoming a method of its own. In other words, we should treat the Data Analytics (or more appropriate ML engineering) process in the same way the software engineering process is treated in the framework. In the remainder of this post I will briefly discuss each of the existing research methods and how they apply to ML projects. The methods are organized by strategy. In the discussion I will give pointers to relevant tools or literature for ML projects.
LINK
This chapter discusses several aspects related to engineering methods in wind turbine design codes. Current engineering models for rotor aerodynamics topic are built around the Blade Element Momentum (BEM) theory. The Blade Element Momentum theory in itself is very basic, e.g., it is derived for two-dimensional, stationary, homogenous, and non-yawed conditions. For this reason, several engineering models have been developed which overcome these simplifications and which act as add-ons to the basic BEM theory. This chapter describes the BEM theory, the most important engineering add-ons, and an assessment of BEM with engineering add-ons with results from higher fidelity models and measurements.
LINK
Both Software Engineering and Machine Learning have become recognized disciplines. In this article I analyse the combination of the two: engineering of machine learning applications. I believe the systematic way of working for machine learning applications is at certain points different from traditional (rule-based) software engineering. The question I set out to investigate is “How does software engineering change when we develop machine learning applications”?. This question is not an easy to answer and turns out to be a rather new, with few publications. This article collects what I have found until now.
LINK
The pace of technology advancements continues to accelerate, and impacts the nature of systems solutions along with significant effects on involved stakeholders and society. Design and engineering practices with tools and perspectives, need therefore to evolve in accordance to the developments that complex, sociotechnical innovation challenges pose. There is a need for engineers and designers that can utilize fitting methods and tools to fulfill the role of a changemaker. Recognized successful practices include interdisciplinary methods that allow for effective and better contextualized participatory design approaches. However, preliminary research identified challenges in understanding what makes a specific method effective and successfully contextualized in practice, and what key competences are needed for involved designers and engineers to understand and adopt these interdisciplinary methods. In this proposal, case study research is proposed with practitioners to gain insight into what are the key enabling factors for effective interdisciplinary participatory design methods and tools in the specific context of sociotechnical innovation. The involved companies are operating at the intersection between design, technology and societal impact, employing experts who can be considered changemakers, since they are in the lead of creative processes that bring together diverse groups of stakeholders in the process of sociotechnical innovation. A methodology will be developed to capture best practices and understand what makes the deployed methods effective. This methodology and a set of design guidelines for effective interdisciplinary participatory design will be delivered. In turn this will serve as a starting point for a larger design science research project, in which an educational toolkit for effective participatory design for socio-technical innovation will be designed.
Artificial Intelligence (AI) wordt realiteit. Slimme ICT-producten die diensten op maat leveren accelereren de digitalisering van de maatschappij. De grote innovaties van de komende jaren –zelfrijdende auto’s, spraakgestuurde virtuele assistenten, autodiagnose systemen, robots die autonoom complexe taken uitvoeren – zijn datagedreven en hebben een AI-component. Dit gaat de rol van professionals in alle domeinen, gezondheidzorg, bouwsector, financiële dienstverlening, maakindustrie, journalistiek, rechtspraak, etc., raken. ICT is niet meer volgend en ondersteunend (een ‘enabling’ technologie), maar de motor die de transformatie van de samenleving in gang zet. Grote bedrijven, overheidsinstanties, het MKB, en de vele startups in de Brainport regio zijn innovatieve datagedreven scenario’s volop aan het verkennen. Dit wordt nog eens versterkt door de democratisering van AI; machine learning en deep learning algoritmes zijn beschikbaar zowel in open source software als in Cloud oplossingen en zijn daarmee toegankelijk voor iedereen. Data science wordt ‘applied’ en verschuift van een PhD specialisme naar een HBO-vaardigheid. Het stadium waarin veel bedrijven nu verkeren is te omschrijven als: “Help, mijn AI-pilot is succesvol. Wat nu?” Deze aanvraag richt zich op het succesvol implementeren van AI binnen de context van softwareontwikkeling. De onderzoeksvraag van dit voorstel is: “Hoe kunnen we state-of-the-art data science methoden en technieken waardevol en verantwoord toepassen ten behoeve van deze slimme lerende ICT-producten?” De postdoc gaat fungeren als een linking pin tussen alle onderzoeksprojecten en opdrachten waarbij studenten ICT-producten met AI (machine learning, deep learning) ontwikkelen voor opdrachtgevers uit de praktijk. Door mee te kijken en mee te denken met de studenten kan de postdoc overzicht en inzicht creëren over alle cases heen. Als er overzicht is kan er daarna ook gestuurd worden op de uit te voeren cases om verschillende deelaspecten samen met de studenten te onderzoeken. Deliverables zijn rapporten, guidelines en frameworks voor praktijk en onderwijs, peer-reviewed artikelen en kennisdelingsevents.
The consistent demand for improving products working in a real-time environment is increasing, given the rise in system complexity and urge to constantly optimize the system. One such problem faced by the component supplier is to ensure their product viability under various conditions. Suppliers are at times dependent on the client’s hardware to perform full system level testing and verify own product behaviour under real circumstances. This slows down the development cycle due to dependency on client’s hardware, complexity and safety risks involved with real hardware. Moreover, in the expanding market serving multiple clients with different requirements can be challenging. This is also one of the challenges faced by HyMove, who are the manufacturer of Hydrogen fuel cells module (https://www.hymove.nl/). To match this expectation, it starts with understanding the component behaviour. Hardware in the loop (HIL) is a technique used in development and testing of the real-time systems across various engineering domain. It is a virtual simulation testing method, where a virtual simulation environment, that mimics real-world scenarios, around the physical hardware component is created, allowing for a detailed evaluation of the system’s behaviour. These methods play a vital role in assessing the functionality, robustness and reliability of systems before their deployment. Testing in a controlled environment helps understand system’s behaviour, identify potential issues, reduce risk, refine controls and accelerate the development cycle. The goal is to incorporate the fuel cell system in HIL environment to understand it’s potential in various real-time scenarios for hybrid drivelines and suggest secondary power source sizing, to consolidate appropriate hybridization ratio, along with optimizing the driveline controls. As this is a concept with wider application, this proposal is seen as the starting point for more follow-up research. To this end, a student project is already carried out on steering column as HIL
