This interview focuses on employee performance and HR Analytics.
MULTIFILE
The objective of the study described in this paper is to define safety metrics that are based on the utilisation of resources. The background of this research is a specific need of the aviation industry where small and medium-sized enterprises lack large amounts of safety-related data to measure and demonstrate their safety performance proactively. The research department of the Aviation Academy has initiated a 4-year study, which will test the possibility to develop new safety indicators that will be able to represent safety levels proactively without the benefit of large data sets. The research team has reviewed the academic and professional literature about safety performance indicators and has performed surveys into 13 companies in order to explore what, how, and why safety performance indicators are used and whether there is a statistically linear relation between SMS process metrics and safety outcomes. The preliminary results showed that companies do not use data from all SMS processes in the development of safety performance indicators, they do not ground the selection of indicators on specific criteria, they implement SMS process in different ways, but they are eager to use alternative metrics, including ones potentially to be derived on the basis of contemporary safety models and views. As part of the development of alternative safety metrics, safety performance indicators were defined that are based on the difference between required resources and available resources. Resources are people, time, equipment and budget. This work is inspired by the general notion that a large gap between ‘work as imagined’ and ‘work as done’ has a negative influence on the level of safety. Work as imagined in this context is represented by available resources and work as done by required resources. The metrics were defined by a combination of literature research and semi-structured interviews with operational practitioners in the aviation industry. The suitability of the metrics will subsequently be tested in pilot studies within the aviation industry.
DOCUMENT
Albeit the widespread application of recommender systems (RecSys) in our daily lives, rather limited research has been done on quantifying unfairness and biases present in such systems. Prior work largely focuses on determining whether a RecSys is discriminating or not but does not compute the amount of bias present in these systems. Biased recommendations may lead to decisions that can potentially have adverse effects on individuals, sensitive user groups, and society. Hence, it is important to quantify these biases for fair and safe commercial applications of these systems. This paper focuses on quantifying popularity bias that stems directly from the output of RecSys models, leading to over recommendation of popular items that are likely to be misaligned with user preferences. Four metrics to quantify popularity bias in RescSys over time in dynamic setting across different sensitive user groups have been proposed. These metrics have been demonstrated for four collaborative filteri ng based RecSys algorithms trained on two commonly used benchmark datasets in the literature. Results obtained show that the metrics proposed provide a comprehensive understanding of growing disparities in treatment between sensitive groups over time when used conjointly.
DOCUMENT
The AR in Staged Entertainment project focuses on utilizing immersive technologies to strengthen performances and create resiliency in live events. In this project The Experiencelab at BUas explores this by comparing live as well as pre-recorded events that utilize Augmented Reality technology to provide an added layer to the experience of the user. Experiences will be measured among others through observational measurements using biometrics. This projects runs in the Experience lab of BUas with partners The Effenaar and 4DR Studio and is connected to the networks and goals related to Chronosphere, Digireal and Makerspace. Project is powered by Fieldlab Events (PPS / ClickNL)..
Evaluating player game experiences through biometric measurementsThe BD4CG (Biometric Design for Casual Games project) worked in a highly interdisciplinary context with several international partners. The aim of our project was to popularize the biometric method, which is a neuro-scientific approach to evaluating the player experience. We specifically aimed at the casual games sector, where casual games can be defined as video or web-based games with simple and accessible game mechanics, non threatening themes and generally short play sessions. Popular examples of casual games are Angry Birds and FarmVille. We focussed on this sector because it is growing fast, but its methodologies have not grown with it yet. Especially the biometrics method has so far been almost exclusively used domain by the very large game developers (such as Valve and EA). The insights and scientific output of this project have been enthusiastically embraced by the international academic arena. The aim of the grant was to focus on game producers in the casual sector, and we have done so but we also established further contacts with the game sector in general. Thirty-one outputs were generated, in the form of presentations, workshops, and accepted papers in prominent academic and industry journals in the field of game studies and game user research. Partners: University of Antwerpen, RANJ, Forward Games, Double Jungle, Realgames, Dreams of Danu, Codemasters, Dezzel, Truimph Studios, Golabi Studios
Aanleiding De luchtvaart wordt steeds veiliger. Toch zijn er alleen al in Nederland jaarlijks zo'n 11.000 issues met luchtvaartveiligheid. Wereldwijd vinden er elke dag ongelukken plaats die leiden tot schade aan vliegtuigen. Om de veiligheid verder te verbeteren is er nieuwe internationale regelgeving opgesteld. Onder deze regels moeten de maatschappijen alle incidenten en ongelukken analyseren en zo veiligheidsrisico's identificeren nog voordat deze zich voordoen. Het probleem is dat kleine en middelgrote luchtvaartmaatschappijen onvoldoende vliegbewegingen maken om genoeg goede data hiervoor te hebben. Doelstelling De centrale vraag die de onderzoekers in dit RAAK-project willen beantwoorden: Wat is de relatie tussen veiligheidsmanagement en veiligheidsperformance van luchtvaartmaatschappijen? Het onderzoek wil kleine en middelgrote luchtvaartmaatschappijen helpen bij het meten van de veiligheid van hun bedrijf, zonder dat ze grote hoeveelheden veiligheidsdata tot hun beschikking hebben. Het onderzoek zal geschikte veiligheidsindicatoren identificeren, een longlist ontwikkelen met meetwaarden voor safetymanagement, en een shortlist genereren en valideren van bruikbare meetwaarden. Deze kennis wordt vertaald in een online dashboard voor de industrie, zodat de veiligheid objectiever beoordeeld kan worden. Beoogde resultaten Een concreet resultaat van dit project is een online dashboard waarmee kleine en middelgrote luchtvaartmaatschappijen hun veiligheid kunnen beoordelen, inclusief handleiding. Er zullen masterclasses veiligheid worden georganiseerd voor de luchtvaartindustrie. Het projectteam zal de opgedane kennis verspreiden via wetenschappelijke artikelen in relevante peer-reviewed tijdschriften, een website, presentaties bij bedrijven en tijdens bijeenkomsten, en een afsluitende conferentie.
