The current set of research methods on ictresearchmethods.nl contains only one research method that refers to machine learning: the “Data analytics” method in the “Lab” strategy. This does not reflect the way of working in ML projects, where Data Analytics is not a method to answer one question but the main goal of the project. For ML projects, the Data Analytics method should be divided in several smaller steps, each becoming a method of its own. In other words, we should treat the Data Analytics (or more appropriate ML engineering) process in the same way the software engineering process is treated in the framework. In the remainder of this post I will briefly discuss each of the existing research methods and how they apply to ML projects. The methods are organized by strategy. In the discussion I will give pointers to relevant tools or literature for ML projects.
LINK
Assistive technology supports maintenance or improvement of an individual’s functioning and independence, though for people in need the access to assistive products is not always guaranteed. This paper presents a generic quality framework for assistive technology service delivery that can be used independent of the setting, context, legislative framework, or type of technology. Based on available literature and a series of discussions among the authors, a framework was developed. It consists of 7 general quality criteria and four indicators for each of these criteria. The criteria are: accessibility; competence; coordination; efficiency; flexibility; user centeredness, and infrastructure. This framework can be used at a micro level (processes around individual users), meso level (the service delivery scheme or programme) or at a macro level (the whole country). It aims to help identify in an easy way the main strengths and weaknesses of a system or process, and thus guide possible improvements. As a next step in the development of this quality framework the authors propose to organise a global consultancy process to obtain responses from stakeholders across the world and to plan a number of case studies in which the framework is applied to different service delivery systems and processes in different countries.
DOCUMENT
This study proposes a systematic value chain approach to helping businesses identify and eliminate inefficiencies. The authors have developed a robust framework, which food-sector entrepreneurs can use to increase profitability of an existing business or to create new profitable opportunities. The value chain approach provides win-win opportunities for players within the value chain. To test the robustness of the framework, the authors use food waste as an example of a critical inefficiency and apply it to two different food sector business cases, each operating in diverse conditions. Because the suggested framework addresses the core elements and parameters for the existence and competitiveness of a business, the model can be adapted to other sectors.
DOCUMENT
In recent years, numerous environmental psychology studies have demonstrated that contact with nature as opposed to urban settings can improve an individual’s mood, can lead to increased levels of vitality, and can offer an opportunity to recover from stress. According to Attention Restoration Theory (ART) the restorative potential of natural environments is situated in the fact that nature can replenish depleted attentional resources. This replenishment takes place, in part, because nature is deemed to be a source of fascination, with fascination being described as having an ‘‘attentional’’, an‘‘affective’’ and an ‘‘effort’’ dimension. However, the claim that fascination with nature involves these three dimensions is to a large extent based on intuition or derived from introspection-based measurement methods, such as self-reports. In three studies, we aimed to more objectively assess whether these three dimensions indeed applied to experiences related to natural environments, before any (attentional) depletion has taken place. The instruments that were used were: (a) the affect misattribution procedure (Study 1), (b) the dot probe paradigm (Study 2) and (c) a cognitively effortful task (Study 3).These instrument were respectively aimed at verifying the affective, attentional and effort dimension of fascination. Overall, the results provide objective evidence for the claims made within the ART framework, that natural as opposed to urban settings are affectively positive (cfr., affective dimension) and that people have an attentional bias to natural (rather than urban) environments (cfr., attentional dimension). The results regarding the effort dimension are less straightforward, and suggest that this dimension only becomes important in sufficiently difficult cognitive tasks.
DOCUMENT
from the article: "In this paper, we explore the characteristics of posters as an efficient and effective probing tool for hospital nurse participation in the development of processes, services or products. The main challenge in this respect is the limited time and attention available to nurses during their work shifts. For this, we analysed the design and effectiveness of posters from earlier projects and used existing knowledge on probing for preliminary guidelines focused on design elements, context of placement, and fit with work process. We then designed a poster for gathering insights during nurses’ work shifts into their administrative tasks and perceived relevance. To evaluate, this table poster design was consecutively placed on three nursing units in a Dutch hospital. Activities of nurses with the poster and necessary interventions were analysed and used for further insights into the characteristics of effective posters for this specific target group. The research raised new questions about how best to elicit nurses’ participation during work shifts."
LINK
Behaviour change design has much to gain with the integration of insights from the behavioural sciences in the design process. However, this integration needs to be done without hampering the creative process. In two rich design cases aimed at health and safety behaviour change, we describe our efforts to develop a method for theory driven design based on the Double Diamond. Our method attempts to integrate insights from the Persuasive by Design-model (PbD) for behaviour change into the entire design process. Our case studies demonstrate that our method indeed augments the integration of theory and evidence in our designs, but only if the Double Diamond process model is complemented with an evaluation phase, and insights from the PbD-model are derived using rich, well developed tools.
DOCUMENT
Social media platforms such as Facebook, YouTube, and Twitter have millions of users logging in every day, using these platforms for commu nication, entertainment, and news consumption. These platforms adopt rules that determine how users communicate and thereby limit and shape public discourse.2 Platforms need to deal with large amounts of data generated every day. For example, as of October 2021, 4.55 billion social media users were ac tive on an average number of 6.7 platforms used each month per internet user.3 As a result, platforms were compelled to develop governance models and content moderation systems to deal with harmful and undesirable content, including disinformation. In this study: • ‘Content governance’ is defined as a set of processes, procedures, and systems that determine how a given platform plans, publishes, moder ates, and curates content. • ‘Content moderation’ is the organised practice of a social media plat form of pre-screening, removing, or labelling undesirable content to reduce the damage that inappropriate content can cause.
MULTIFILE
Many students persistently misinterpret histograms. This calls for closer inspection of students’ strategies when interpreting histograms and case-value plots (which look similar but are diferent). Using students’ gaze data, we ask: How and how well do upper secondary pre-university school students estimate and compare arithmetic means of histograms and case-value plots? We designed four item types: two requiring mean estimation and two requiring means comparison. Analysis of gaze data of 50 students (15–19 years old) solving these items was triangulated with data from cued recall. We found five strategies. Two hypothesized most common strategies for estimating means were confirmed: a strategy associated with horizontal gazes and a strategy associated with vertical gazes. A third, new, count-and-compute strategy was found. Two more strategies emerged for comparing means that take specific features of the distribution into account. In about half of the histogram tasks, students used correct strategies. Surprisingly, when comparing two case-value plots, some students used distribution features that are only relevant for histograms, such as symmetry. As several incorrect strategies related to how and where the data and the distribution of these data are depicted in histograms, future interventions should aim at supporting students in understanding these concepts in histograms. A methodological advantage of eye-tracking data collection is that it reveals more details about students’ problem-solving processes than thinking-aloud protocols. We speculate that spatial gaze data can be re-used to substantiate ideas about the sensorimotor origin of learning mathematics.
LINK
Modern manufacturing has to deal with global competition, in which customers have high purchasing power. Production efficiency and rapid response to customer demand are dominant conditions for enterprises to stay successful. Reconfigurable Manufacturing Systems (RMSs) are designed to have a modular architecture in both mechanical design and control system. The architecture enables change of the machine structure quickly, by adding and removing parts of the system, and by changing the corresponding software programming. It can handle short times to market. This paper presents an ‘Index-Method’ to monitor the reconfiguration of RMS. The method is able to categorise the reconfiguration and related development in seven stages. It focusses specifically on the Independence Axiom. The main goal is to find all relevant parameters to cause interactions, and to decouple them. The solution, aiming to be scientifically vigorous and practically applicable, was applied to a true case; the development of a manufacturing system for an inkjet print head for industrial applications. The realisation of the system required the development of new process technology. The index-method may be considered successful. It has the ability to structure the configuration process of RMSs. The method harmonises well with the industry known V-model.
DOCUMENT
How and where can Dutch design entrepreneurs find work in Germany? This was the question DutchDFA put to the research team at Inholland University of Applied Sciences in February 2010. But the researchers took a different angle, and generated unexpected data, revealing patterns, and valuable new insights into practicing design and architecture abroad.
DOCUMENT
