Zoekresultaten

Some new results on correlation-preserving factor scores prediction methods

Anderson and Rubin and McDonald have proposed a correlation-preserving method of factor scores prediction which minimizes the trace of a residual covariance matrix for variables. Green has proposed a correlation-preserving method which minimizes the trace of a residual covariance matrix for factors. Krijnen, Wansbeek and Ten Berge have proposed minimizing the determinant rather than the trace of the latter covariance matrix, and offered an iterative procedure to that effect. In the present paper it is shown that the iterative procedure can be replaced by a closed-form solution. When all unique variances are strictly positive, this solution is the same as McDonald's. The solution coincides with Green's solution in certain special cases, for instance, when the factors are orthogonal.

The business rule type jungle

Decisions and business rules are essential Components of an organization. Combined, these components form a basis for securing the implementation of new laws, regulations and internal policies into processes, work instructions and information systems. To ensure proper implementation, business rule types must be taken into account, as the functions per type may be different. The current body of knowledge on decision and business rule management offers some insights into different types of business rules, however, these types are often presented as a secondary focus of a contribution or set in stone without proper evidence supporting these claims. This study therefore aims to explore the different business rule types utilized in the body of knowledge as well as practice. This will form a basis to determine possible overlap and inconsistencies and aid in establishing the functional differences between the defined business rule types. By applying a literature review, semi-structured interviews and secondary data analysis, we observed that the current body of knowledge shows serious diffusion with regards to business rule types, the same holds for practice. Therefore, future research should focus to research these differences in detail with the aim to harmonize the proliferation of business rule types.

Een beetje straling, is dat goed voor je?

Een fles rode wijn per dag drinken is ongezond, maar een glas per dag reduceert mogelijk de kans op hartkwalen. Dit is een voorbeeld van ‘hormese’: het verschijnsel dat een agens dat in grote hoeveelheden schadelijk is, bij lage doses juist gezond is. Iets vergelijkbaars geldt voor zonlicht: lage doses worden geassocieerd met positieve gezondseffecten, hoge doses met verbranden en een hogere kans op huidkanker. Er zijn onderzoekers die zich op het omstreden standpunt stellen dat ook ioniserende straling hormetische eigenschappen heeft. In dit artikel gaan we nader in op de verschillende standpunten omtrent lage-dosiseffecten, de argumenten voor en tegen hormese en de consequenties van recente inzichten.

Requirements and challenges for hybrid intelligence

The potential for Artificial Intelligence is widely proclaimed. Yet, in everyday educational settings the use of this technology is limited. Particularly, if we consider smart systems that actually interact with learners in a knowledgeable way and as such support the learning process. It illustrates the fact that teaching professionally is a complex challenge that is beyond the capabilities of current autonomous robots. On the other hand, dedicated forms of Artificial Intelligence can be very good at certain things. For example, computers are excellent chess players and automated route planners easily outperform humans. To deploy this potential, experts argue for a hybrid approach in which humans and smart systems collaboratively accomplish goals. How to realize this for education? What does it entail in practice? In this contribution, we investigate the idea of a hybrid approach in secondary education. As a case-study, we focus on learners acquiring systems thinking skills and our recently for this purpose developed pedagogical approach. Particularly, we discuss the kind of Artificial Intelligence that is needed in this situation, as well as which tasks the software can perform well and which tasks are better, or necessarily, left with the teacher.

Embedded Autonomous Agents in Products Supporting Repair and Recycling

This paper describes a concept where products are equipped with agents that will assist in recycling and repairing the product. These so-called product agents represent the product in cyberspace and are capable to negotiate with other products in case of recycling or repair. Some product agents of broken products will offer spare parts, other agents will look for spare parts to repair a broken product. On the average this will enlarge the lifetime of a product and in some cases prevent wasting resources. Apart from reuse of spare parts these agents will also help to locate rare elements in a device, so these elements can be recycled more easily.

Teaching computational thinking to primary school students via unplugged programming lessons