Abstract Despite the numerous business benefits of data science, the number of data science models in production is limited. Data science model deployment presents many challenges and many organisations have little model deployment knowledge. This research studied five model deployments in a Dutch government organisation. The study revealed that as a result of model deployment a data science subprocess is added into the target business process, the model itself can be adapted, model maintenance is incorporated in the model development process and a feedback loop is established between the target business process and the model development process. These model deployment effects and the related deployment challenges are different in strategic and operational target business processes. Based on these findings, guidelines are formulated which can form a basis for future principles how to successfully deploy data science models. Organisations can use these guidelines as suggestions to solve their own model deployment challenges.
DOCUMENT
This review of meta-analyses of outcome studies of adults receiving Computer-Based Health Education (CBHE) has two goals. The first is to provide an overview of the efficacy of CBHE interventions, and the second is to identify moderators of these effects. A systematic literature search resulted in 15 meta-analyses of 278 controlled outcome studies. The meta-analyses were analysed with regard to reported (overall) effect sizes, heterogeneity and interaction effects. The results indicate a positive relationship between CBHE interventions and improvements in health-related outcomes, with small overall effect sizes compared to non-computer-based interventions. The sustainability of the effects was observed for up to six months. Outcome moderators (31 variables) were studied in 12 meta-analyses and were clustered into three categories: intervention features (20 variables), participant characteristics (five variables) and study features (six variables). No relationship with effectiveness was found for four intervention features, theoretical background, use of internet and e-mail, intervention setting and self-monitoring; two participant features, age and gender; and one study feature, the type of analysis. Regarding the other 24 identified features, no consistent results were observed across meta-analyses. To enhance the effectiveness of CBHE interventions, moderators of effects should be studied as single constructs in high-quality study designs. http://www.journalofinterdisciplinarysciences.com/ https://www.linkedin.com/in/leontienvreeburg/
DOCUMENT
Brochure from the Inauguration of Klaas Dijkstra, professor Computer Vision and Data Science
DOCUMENT
![I’M A.I. IMage Processing and Artificial Intelligence [Inaugurele rede]](https://publinova-harvester-content-prod.s3.amazonaws.com/thumbnails/files/previews/pdf/20250506132441657988.LS20Brochure20Professorship20CVDS20FINAL20WEB2028129-thumbnail-400x300.png)
Computer security incident response teams (CSIRTs) respond to a computer security incident when the need arises. Failure of these teams can have far-reaching effects for the economy and national security. CSIRTs often have to work on an ad hoc basis, in close cooperation with other teams, and in time constrained environments. It could be argued that under these working conditions CSIRTs would be likely to encounter problems. A needs assessment was done to see to which extent this argument holds true. We constructed an incident response needs model to assist in identifying areas that require improvement. We envisioned a model consisting of four assessment categories: Organization, Team, Individual and Instrumental. Central to this is the idea that both problems and needs can have an organizational, team, individual, or technical origin or a combination of these levels. To gather data we conducted a literature review. This resulted in a comprehensive list of challenges and needs that could hinder or improve, respectively, the performance of CSIRTs. Then, semi-structured in depth interviews were held with team coordinators and team members of five public and private sector Dutch CSIRTs to ground these findings in practice and to identify gaps between current and desired incident handling practices. This paper presents the findings of our needs assessment and ends with a discussion of potential solutions to problems with performance in incident response. https://doi.org/10.3389/fpsyg.2017.02179 LinkedIn: https://www.linkedin.com/in/rickvanderkleij1/
MULTIFILE
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
Background: The strain on health care services is increasing due to an ageing population and the increasing prevalence of chronic health conditions. eHealth could contribute to optimise effective and efficient care to older adults with one or more chronic health conditions in the general practice. Aim: The aim of this study was to identify the needs, barriers and facilitators amongst community-dwelling older adults (60þ) suffering from one or more chronic health conditions, in using online eHealth applications to support general practice services. Methods: A qualitative study, using semi-structured followed by think-aloud interviews, was conducted in the Netherlands. The semi-structured interviews, supported by an interview guide were conducted and analysed thematically. The think-aloud method was used to collect data about the cognitive process while the participant was completing a task within online eHealth applications. Verbal analysis according to the Chi approach was conducted to analyse the think-aloud interviews. Findings: A total of n = 19 older adults with a mean age of 73 years participated. The ability to have immediate contact with the GP on important health issues was identified as an important need. Identified barriers were non-familiarity with the online eHealth applications and a mismatch of user health needs. The low computer experience resulted in non-familiarity with the online eHealth applications. Faltering applications resulted in participants refusing to participate in the use of online eHealth applications. Convenience, efficiency and the instant availability of eHealth via applications were identified as important facilitators. Conclusion: To improve the use and acceptability of eHealth applications amongst older adults in the general practice, the applications should be tailored to meet individual needs. More attention should be given to improving the user-friendliness of these applications and to the promotion of the benefits such as facilitating older adults independent living for longer.
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
Editorial on the Research Topic "Leveraging artificial intelligence and open science for toxicological risk assessment"
LINK
Integrated curricula seem promising for the increase of attention on science and technology in primary education. A clear picture of the advantages and disadvantages of integration efforts could help curriculum innovation. This review has focussed on integrated curricula in primary education from 1994 to 2011. The integrated curricula were categorized according to a taxonomy of integration types synthesized from the literature. The characteristics that we deemed important were related to learning outcomes and success/fail factors. A focus group was formed to facilitate the process of analysis and to test tentative conclusions. We concluded that the levels in our taxonomy were linked to (a) student knowledge and skills, the enthusiasm generated among students and teachers, and the teacher commitment that was generated; and (b) the teacher commitment needed, the duration of the innovation effort, the volume and comprehensiveness of required teacher professional development, the necessary teacher support, and the effort needed to overcome tensions with standard curricula. Almost all projects were effective in increasing the time spent on science at school. Our model resolves Czerniac’s definition problem of integrating curricula in a productive manner, and it forms a practical basis for decision-making by making clear what is needed and what output can be expected when plans are being formulated to implement integrated education.
DOCUMENT
Purpose – In the domain of healthcare, both process efficiency and the quality of care can be improved through the use of dedicated pervasive technologies. Among these applications are so-called real-time location systems (RTLS). Such systems are designed to determine and monitor the location of assets and people in real time through the use of wireless sensor networks. Numerous commercially available RTLS are used in hospital settings. The nursing home is a relatively unexplored context for the application of RTLS and offers opportunities and challenges for future applications. The paper aims to discuss these issues. Design/methodology/approach – This paper sets out to provide an overview of general applications and technologies of RTLS. Thereafter, it describes the specific healthcare applications of RTLS, including asset tracking, patient tracking and personnel tracking. These overviews are followed by a forecast of the implementation of RTLS in nursing homes in terms of opportunities and challenges. Findings – By comparing the nursing home to the hospital, the RTLS applications for the nursing home context that are most promising are asset tracking of expensive goods owned by the nursing home in orderto facilitate workflow and maximise financial resources, and asset tracking of personal belongings that may get lost due to dementia. Originality/value – This paper is the first to provide an overview of potential application of RTLS technologies for nursing homes. The paper described a number of potential problem areas that can be addressed by RTLS. Published by Emerald Publishing Limited Original article: https://doi.org/10.1108/JET-11-2017-0046 For this paper Joost van Hoof received the Highly Recommended Award from Emerald Publishing Ltd. in October 2019: https://www.emeraldgrouppublishing.com/authors/literati/awards.htm?year=2019
MULTIFILE
