Collaboratively editing game worlds and the underlying asset version management techniques present us with many challenges when using a traditional Version Control System (VCS). This paper suggests a new method that will aid in the tracking, branching, and selection of asset versions within a game development pipeline. A prototype has been developed which demonstrated im-provements in both productivity and usability providing greater visibility of incremental asset changes and alterations to their relationships which equated to approximately a 30% better user experience when compared to an existing industry VCS.
DOCUMENT
Estimating the remaining useful life (RUL) of an asset lies at the heart of prognostics and health management (PHM) of many operations-critical industries such as aviation. Mod- ern methods of RUL estimation adopt techniques from deep learning (DL). However, most of these contemporary tech- niques deliver only single-point estimates for the RUL without reporting on the confidence of the prediction. This practice usually provides overly confident predictions that can have severe consequences in operational disruptions or even safety. To address this issue, we propose a technique for uncertainty quantification (UQ) based on Bayesian deep learning (BDL). The hyperparameters of the framework are tuned using a novel bi-objective Bayesian optimization method with objectives the predictive performance and predictive uncertainty. The method also integrates the data pre-processing steps into the hyperparameter optimization (HPO) stage, models the RUL as a Weibull distribution, and returns the survival curves of the monitored assets to allow informed decision-making. We vali- date this method on the widely used C-MAPSS dataset against a single-objective HPO baseline that aggregates the two ob- jectives through the harmonic mean (HM). We demonstrate the existence of trade-offs between the predictive performance and the predictive uncertainty and observe that the bi-objective HPO returns a larger number of hyperparameter configurations compared to the single-objective baseline. Furthermore, we see that with the proposed approach, it is possible to configure models for RUL estimation that exhibit better or comparable performance to the single-objective baseline when validated on the test sets.
DOCUMENT
Data-driven modeling is an imperative tool in various industrial applications, including many applications in the sectors of aeronautics and commercial aviation. These models are in charge of providing key insights, such as which parameters are important on a specific measured outcome or which parameter values we should expect to observe given a set of input parameters. At the same time, however, these models rely heavily on assumptions (e.g., stationarity) or are “black box” (e.g., deep neural networks), meaning that they lack interpretability of their internal working and can be viewed only in terms of their inputs and outputs. An interpretable alternative to the black box models and with considerably less assumptions is symbolic regression (SR). SR searches for the optimal model structure while simultaneously optimizing the model’s parameters without relying on an a priori model structure. In this work, we apply SR on real-life exhaust gas temperature (EGT) data, collected at high frequencies through the entire flight, in order to uncover meaningful algebraic relationships between the EGT and other measurable engine parameters. The experimental results exhibit promising model accuracy, as well as explainability returning an absolute difference of 3°C compared to the ground truth and demonstrating consistency from an engineering perspective.
DOCUMENT
Hoofdstuk 12 uit deel III: Uses of cultural technologies. The essays in this volume discuss both the culture of technology that we live in today, and culture as technology. Within the chapters of the book cultures of technology and cultural technologies are discussed, focussing on a variety of examples, from varied national contexts. The book brings together internationally recognised scholars from the social sciences and humanities, covering diverse themes such as intellectual property, server farms and search engines, cultural technologies and epistemology, virtual embassies, surveillance, peer-to-peer file-sharing, sound media and nostalgia and much more. It contains both historical and contemporary analyses of technological phenomena as well as epistemological discussions on the uses of technology.
LINK
DOCUMENT
The objective of this paper is a reflective discussion on the validity of the construct Information Literacy in the perspective of changing information and communication technologies. The research question that will be answered is: what is the impact of technological developments on the relevance of the Information Literacy concept? Technological developments that will be discussed are: - content integration (federated search engines) - amateur publishing (user generated content) - use of social networks to find information - personalisation and push technology - loss of context / fragmentation of information. Research methods: desk research and critical analysis of the results that were found. The analysis of the influence of the discussed technologies on the Information Literacy concept is represented by arrow diagrams. Findings: The Information Literacy concept refers to a set of sub skills varying from retrieval skills to critical use of scholar information. Changing technologies reduce the significance of the more instrumental sub skills of the Information Literacy concept. On the other hand, higher order cognitive skills (for instance critical evaluation of resources and analysis of content) become more and more important for students and professionals who try to solve their information problems. The paper concludes with a description of the facets of the Information Literacy concept that need extra attention in the education of the knowledge workers of the future. [De hier gepubliceerde versie is het 'accepted paper' van het origineel dat is gepubliceerd op www.springerlink.com . De officiële publicatie kan worden gedownload op http://www.springerlink.com/content/n32j3um878720h40/abstract/]
DOCUMENT
This paper describes the participatory development process of a web-based communication system focusing on disease management, particularly infection control of Methicillin-resistant Staphylococcus aureus (MRSA). These infections are becoming a major public health issue; they can have serious consequences such as pneumonia, sepsis or death [1]. This makes it even more important for people to be provided with up-to-date and reliable information. Users of a bilingual communication system (Dutch and German) participated in the development process via a needs assessment, the co-creation of the content and the system via usability tests, and in the summative evaluation of the usage of the system. The system enabled users to search efficiently and effectively for practical and relevant information. Moreover, we found that the participation of the intended users is a prerequisite to create a fit between the needs and expectations of the end-users, the technology and the social context of usage of technology. The summative evaluation showed that the system was frequently used (approximately 11,000 unique visitors per month). The most popular categories include ‘MRSA in general’ (20%, both languages) and ‘Acquiring MRSA’ (17% NL, 13% GER). Most users enter the site using internet search engines (Google) instead of the on-site search engine. When they are on the site, they prefer convenient searching via FAQ or related questions. Furthermore, the results showed that the participation of stakeholders is a prerequisite for a successful implementation of the system. To guide the participation of stakeholders we developed a roadmap that integrates human-centered development with business modelling activities.
DOCUMENT
The user experience of our daily interactions is increasingly shaped with the aid of AI, mostly as the output of recommendation engines. However, it is less common to present users with possibilities to navigate or adapt such output. In this paper we argue that adding such algorithmic controls can be a potent strategy to create explainable AI and to aid users in building adequate mental models of the system. We describe our efforts to create a pattern library for algorithmic controls: the algorithmic affordances pattern library. The library can aid in bridging research efforts to explore and evaluate algorithmic controls and emerging practices in commercial applications, therewith scaffolding a more evidence-based adoption of algorithmic controls in industry. A first version of the library suggested four distinct categories of algorithmic controls: feeding the algorithm, tuning algorithmic parameters, activating recommendation contexts, and navigating the recommendation space. In this paper we discuss these and reflect on how each of them could aid explainability. Based on this reflection, we unfold a sketch for a future research agenda. The paper also serves as an open invitation to the XAI community to strengthen our approach with things we missed so far.
MULTIFILE
Purpose The purpose of this paper is to synthesize the fragmented literature on organizational citizenship behavior (OCB), leader–member exchange (LMX), learning, innovative work behavior (IWB) and employee performance across different countries, disciplines and organizations, thereby broadening the literature breath and making gap identification comprehensive. Second, it provides information on how much studies have been concentrated on Africa with the goal of provoking scholarly work in a unique cultural setting on the interrelatedness of these concepts. Design/methodology/approach Relevant literature search was undertaken using key search terms, “employee performance,” “OCB,” “LMX,” “IWB,” “individual learning” and “team learning.” Findings The findings show positive relationships between the behaviors and employee performance. They also reveal an interesting diversity in the study across multidisciplinary fields holding both cultural and contextual significance for academia and practitioners. Research limitations/implications – The limitation of literature to peer-reviewed journals from the authors’ university library might have missed important information not in this domain. Further studies must make use of additional search terms and engines excluded from this study to provide a more comprehensive analysis. Practical implications The paper has important managerial implications for practitioners. The analysis can support the understanding of employee performance from a broader and more diverse view points; and help in providing insight into real-life opportunities, constraints and solutions in enhancing performance management. Originality/value – This systematic literature review highlights important knowledge gaps which need to be explored especially in the African and Ghanaian contexts.
DOCUMENT
“Hoe kunnen bedrijfsregel management systemen geclassificeerd worden?” Voor bedrijven kan deze classificatie een belangrijke rol spelen in het selectieproces van een BRMS. Er bestaan meerdere classificatieschema’s van BRMS’en. Drie veelgebruikte schema’s zijn: 1) een classificatie naar de variabiliteit van een bedrijfsregel, 2) een classificatie naar de levenscyclus van een bedrijfsregel en 3) een classificatie naar de waardepropositie van een bedrijfsregel. In dit artikel gaan we dieper in op het tweede classificatieschema: de classificatie naar de levenscyclus van een bedrijfsregel.
LINK
