Over the past few decades, education systems, especially in higher education, have been redefined. Such reforms inevitably require reconsideration of operational notions and definitions of quality, along with a number of related concepts. This reconsideration aligns with the core of higher education reforms: improving efficacy and compatibility with emerging social demands while adapting to competitiveness and accountability trends. As primary players in the teaching and learning process, online tutors have a protagonistic role and, therefore, must be equipped with a suitable set of competencies and attributes in addition to content knowledge. This quantitative research aims to analyze the perceptions of 250 online tutors working in European higher education institutions, distributed in 5 knowledge areas: Business, Education, Humanities, Sciences and Health. This descriptive and exploratory nonexperimental study reveals the technological and pedagogical skills and competencies that online tutors consider fundamental for effective online teaching and proposes professional development actions to ensure quality online teaching.
DOCUMENT
In this post I give an overview of the theory, tools, frameworks and best practices I have found until now around the testing (and debugging) of machine learning applications. I will start by giving an overview of the specificities of testing machine learning applications.
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 ELSA AI lab Northern Netherlands (ELSA-NN) is committed to the promotion of healthy living, working and ageing. By investigating cultural, ethical, legal, socio-political, and psychological aspects of the use of AI in different decision-makingcontexts and integrating this knowledge into an online ELSA tool, ELSA-NN aims to contribute to knowledge about trustworthy human-centric AI and development and implementation of health technology innovations, including AI, in theNorthern region.The research in ELSA-NN will focus on developing and mapping ELSA knowledge around three general concepts of importance for the development, monitoring and implementation of trustworthy and human-centric AI: availability, use,and performance. These concepts will be explored in two lines of research: 1) use case research investigating the use of different AI applications with different types of data in different decision-making contexts at different time periods duringthe life course, and 2) an exploration among stakeholders in the Northern region of needs, knowledge, (digital) health literacy, attitudes and values concerning the use of AI in decision-making for healthy living, working and ageing. Specificfocus will be on investigating low social economic status (SES) perspectives, since health disparities between high and low SES groups are growing world-wide, including in the Northern region and existing health inequalities may increase with theintroduction and use of innovative health technologies such as AI.ELSA-NN will be integrated within the AI hub Northern-Netherlands, the Health Technology Research & Innovation Cluster (HTRIC) and the Data Science Center in Health (DASH). They offer a solid base and infrastructure for the ELSA-NNconsortium, which will be extended with additional partners, especially patient/citizens, private, governmental and researchrepresentatives, to have a quadruple-helix consortium. ELSA-NN will be set-up as a learning health system in which much attention will be paid to dialogue, communication and education.
UNStudio, een in Amsterdam gevestigd, internationaal toonaangevend architectenbureau, wil hun Green Mile-plan1 voor het centrum van Amsterdam uitwerken om een 'post-pandemisch groen stedenbouwkundig ontwerp' voor de stad te onderzoeken - kunnen groene gebieden worden (her) ontworpen om ruimte aan voetgangers te geven, terwijl voorkomen wordt dat mensen zich niet op dezelfde plek ophopen? De Corona-pandemie benadrukte ook de noodzaak om vaart te zetten achter duurzaamheidsdoelstellingen, waaronder de ambitie om groenere stedelijke omgevingen te creëren. In dit voorstel wordt stadsmeubilair voor de Green Mile ontworpen en gerealiseerd met hergebruikte materialen, en met post-pandemische stedenbouwkundige en bouwkundige principes. GPGroot en Schijf, leveranciers van rest- en gebruikte bouwmaterialen2, willen hun kennis over circulaire materiaalverwerking en -levering in de stedelijke context graag verder ontwikkelen. Het initiatief van UNStudio biedt een unieke kans om deze kennis te ontwikkelen, in samenwerking met de HvA en het onderzoek in de Robot Studio, dat zich tot nu toe met name richt op circulair gebruik van hout voor binnen-toepassingen. Het project volgt een iteratief ontwerpproces van parametrisch ontwerp en digitale productie. Bij het ontwerp wordt rekening gehouden met functionele eisen en beschikbare materialen, evenals met de specifieke kenmerken van de stedelijke context waar het prototype zou kunnen worden geplaatst. De productie van het prototype zal worden uitgevoerd met 6-assige robots in de HvA Robot Studio. De resultaten zijn ontwerpen en een prototype, maar ook kennis over het verbinden van parametrisch ontwerp en robotproductie met buitentoepassingen, met bijzondere aandacht voor rest- en gebruikte materialen. Innovatieve aspecten zijn de overstap naar structureel belaste buitentoepassingen en het gebruik van een breder scala aan materialen dan alleen hout. Hiermee kan het project bijdragen aan de ontwikkeling van “smart industry” en de circulaire economie, beide relevant voor de maatschappelijke uitdagingen zoals vastgelegd in de nationale Kennis- en Innovatie-Agenda’s voor wetenschap en technologie.
Automating logistics/agrifood vehicles requires dependable, accurate positioning. Automated vehicles, or mobile robots, constantly need to know their exact position to follow the trajectories required to perform their tasks. Precise outdoor localization is helped by the increased price/performance ratio of RTK-GNSS solutions. However, this technology is sensitive to signal deterioration by e.g. biomass and large structures like poles/buildings. Robust localization requires additional localization technologies. Several absolute and relative positioning technologies exist and available sensor fusion solutions allow for combining these technologies. However, robot developers require modularity, and no integral solutions exist. Commercial solutions are either customized or high-priced testing solutions. Academics mainly propose specific sensing combinations and lack industrial applicability. Market demand articulation expresses the need for redundancy besides modularity, both for vehicle safety and system resilience, referring to the current geopolitical GPS jamming reality. MAPS aims for an open-source, ROS2-based, multi-modal, robust and modular localization solution for outdoor logistics and agrifood applications, enabling dependable and safe vehicle automation, allowing both sectors to handle labor shortages, introduce durable solutions and enhance resilience. MAPS focuses on a sensor fusion approach allowing modularity, with integrated redundancy. It includes online confidence level estimation, supporting both continuous fusion and modality switching, aiming for location/situation aware behavior and allowing for market-requested hybrid in-vehicle/infra solutions. MAPS intents to maximally utilize the consortium’s vehicle dynamics knowledge - including vehicle-(soft)soil interaction - in the solution for plausibility and dead reckoning. An accompanying PhD/EngD research is foreseen. With project partners enabling scalable, industry-grade solutions MAPS aims to bridge the gap between academic-level research and market-desired applicability. MAPS is independent, though aims to cooperate with AIFusIOn from Saxion on re-usable architectures and integration of AIFusIOn specifics, like AI-based situational awareness and indoor-outdoor switching, if both are granted.
