Additions to the book "Systems Design and Engineering" by Bonnema et.al. Subjects were chosen based on the Systems Engineering needs for Small and Medium Enterprises, as researched in the SESAME project. The
MULTIFILE
The past two years I have conducted an extensive literature and tool review to answer the question: “What should software engineers learn about building production-ready machine learning systems?”. During my research I noted that because the discipline of building production-ready machine learning systems is so new, it is not so easy to get the terminology straight. People write about it from different perspectives and backgrounds and have not yet found each other to join forces. At the same time the field is moving fast and far from mature. My focus on material that is ready to be used with our bachelor level students (applied software engineers, profession-oriented education), helped me to consolidate everything I have found into a body of knowledge for building production-ready machine learning (ML) systems. In this post I will first define the discipline and introduce the terminology for AI engineering and MLOps.
LINK
This chapter discusses how to build production-ready machine learning systems. There are several challenges involved in accomplishing this, each with its specific solutions regarding practices and tool support. The chapter presents those solutions and introduces MLOps (machine learning operations, also called machine learning engineering) as an overarching and integrated approach in which data engineers, data scientists, software engineers, and operations engineers integrate their activities to implement validated machine learning applications managed from initial idea to daily operation in a production environment. This approach combines agile software engineering processes with the machine learning-specific workflow. Following the principles of MLOps is paramount in building high-quality production-ready machine learning systems. The current state of MLOps is discussed in terms of best practices and tool support. The chapter ends by describing future developments that are bound to improve and extend the tool support for implementing an MLOps approach.
LINK
Inleiding en praktijkvraag De groeiende wereldbevolking gecombineerd met de klimaatverandering zorgt voor een de noodzaak tot een duurzame voedselvoorziening (KIA missie Landbouw, voedsel & water). Een significante reductie van gewasbestrijdingsmiddelen is daarbinnen een belangrijke doelstelling. Robotica maakt als technologie motor van de precisielandbouw plant specifieke precisie-bestrijding mogelijk. Het projectconsortium onderzoekt een semiautonoom samenwerkend grond-luchtrobot platform voor de precisielandbouw. Projectdoelstelling De doelstelling van het project AGRobot Platform is dan ook: “Onderzoek de mogelijkheden van een semi-autonoom samenwerkend grond-lucht robotplatform voor de precisielandbouw”. De hoofddoelstelling wordt binnen dit project beantwoordt door de deliverables uit de volgende subdoelstellingen: 1. Case studie onderzoek naar de mogelijke voordelen van het grond-luchtrobotplatform 2. Onderzoek naar de benodigde technologieën voor een grond-luchtrobotplatform 3. Ontwikkelen van een eerste (mogelijk case-specifieke) demonstrator 4. Ontwikkelen van (nieuwe) samenwerkingsvormen. Vraagsturing & Netwerkvorming Riwo Engineering is een industriële automatiseeerder die met zijn grondrobots en control-besturingssytemen actief is in de veeteelt. DRONEXpert gebruikt hyperspectrale camera’s onder drones voor het bemeten van gewassen. Saxion mechatronica onderzoekt met de onderzoekslijn unmanned robotic systems hoe de nieuwste robotica technologieën systemen mogelijk maakt voor ongestructureerde omgevingen. De partners bezitten gezamenlijk een enorm netwerk (TValley, Space53, euRobotics) en klanten om via de case studies de kansen te achterhalen en te realiseren. Innovatie Nergens ter wereld is een samenwerkend grond-luchtrobot platform actief in de precisielandbouw. Voor OostNederland, met naast veel robotica kennis ook veel Agro-kennis, zal het project letterlijk de KIEM zijn voor nieuwe projecten waaruit de valorisatie kansen richting heel Europa gaan. Activiteitenplan & Projectorganisatie Het project wordt geleid door de lector Dr. Ir. D.A.Bekke en uitgevoerd door Abeje Mersha en Mark Reiling samen met het deelnemend MKB. Het project bestaat uit 4 werkpakketten die achtereenvolgens antwoordt geven op de gestelde subdoelstellingen. Aan elk werkpakket zijn deliverables gekoppeld.
Various companies in diagnostic testing struggle with the same “valley of death” challenge. In order to further develop their sensing application, they rely on the technological readiness of easy and reproducible read-out systems. Photonic chips can be very sensitive sensors and can be made application-specific when coated with a properly chosen bio-functionalized layer. Here the challenge lies in the optical coupling of the active components (light source and detector) to the (disposable) photonic sensor chip. For the technology to be commercially viable, the price of the disposable photonic sensor chip should be as low as possible. The coupling of light from the source to the photonic sensor chip and back to the detectors requires a positioning accuracy of less than 1 micrometer, which is a tremendous challenge. In this research proposal, we want to investigate which of the six degrees of freedom (three translational and three rotational) are the most crucial when aligning photonic sensor chips with the external active components. Knowing these degrees of freedom and their respective range we can develop and test an automated alignment tool which can realize photonic sensor chip alignment reproducibly and fully autonomously. The consortium with expertise and contributions in the value chain of photonics interfacing, system and mechanical engineering will investigate a two-step solution. This solution comprises a passive pre-alignment step (a mechanical stop determines the position), followed by an active alignment step (an algorithm moves the source to the optimal position with respect to the chip). The results will be integrated into a demonstrator that performs an automated procedure that aligns a passive photonic chip with a terminal that contains the active components. The demonstrator is successful if adequate optical coupling of the passive photonic chip with the external active components is realized fully automatically, without the need of operator intervention.
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.
Lectoraat, onderdeel van NHL Stenden Hogeschool
