Machine learning models have proven their use in the medical field, assisting physicians in early diagnosis of serious diseases. Diabetic retinopathy is one of such diseases that could benefit from early detection, but the amount of data available to train accurate models is limited. This challenge could be tackled through the use of synthetic data in the training of machine learning models. This paper proposes a novel procedure for the generation of synthetic data-sets for diabetic retinopathy that accurately reflect the characteristics and complexities of real-world medical data-sets. By employing a systematic literature review in combination with an expert study, this research aims to improve the data generation that underpins the performance and reliability of AI systems for diabetic retinopathy detection, enhancing early detection and treatment accessibility. Special attention is paid to inherent, human-centered issues in the synthetic data generation to mitigate representation risks.
LINK
As a teacher in ICT and Media Design at Fontys University of Applied Sciences I know but all too well what many of my students want. They are part of a makers community. Most of them just want to build cool stuff with whatever (new) technology may be relevant. My students are by grosso modo millennials or even post-millennials: a synthetic generation for whom the concept of digital ‘transformation’ is alien (van Doorn, Duivestein, & Pepping, 2019). So most of my students are digitals natives: they use ICT as a tool to make a positive impact on society. But does that mean they use their (ICT) skills to build the right things? Or more specifically: do they automatically build things in a right manner? I don’t think so and I will be happy to explain my reflective thoughts about this later on in this essay. But let me give you an example from my daily practice first.
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)
We present a novel architecture for an AI system that allows a priori knowledge to combine with deep learning. In traditional neural networks, all available data is pooled at the input layer. Our alternative neural network is constructed so that partial representations (invariants) are learned in the intermediate layers, which can then be combined with a priori knowledge or with other predictive analyses of the same data. This leads to smaller training datasets due to more efficient learning. In addition, because this architecture allows inclusion of a priori knowledge and interpretable predictive models, the interpretability of the entire system increases while the data can still be used in a black box neural network. Our system makes use of networks of neurons rather than single neurons to enable the representation of approximations (invariants) of the output.
LINK
Author supplied: Abstract—The growing importance and impact of new technologies are changing many industries. This effect is especially noticeable in the manufacturing industry. This paper explores a practical implementation of a hybrid architecture for the newest generation of manufacturing systems. The papers starts with a proposition that envisions reconfigurable systems that work together autonomously to create Manufacturing as a Service (MaaS). It introduces a number of problems in this area and shows the requirements for an architecture that can be the main research platform to solve a number of these problems, including the need for safe and flexible system behaviour and the ability to reconfigure with limited interference to other systems within the manufacturing environment. The paper highlights the infrastructure and architecture itself that can support the requirements to solve the mentioned problems in the future. A concept system named Grid Manufacturing is then introduced that shows both the hardware and software systems to handle the challenges. The paper then moves towards the design of the architecture and introduces all systems involved, including the specific hardware platforms that will be controlled by the software platform called REXOS (Reconfigurable EQuipletS Operating System). The design choices are provided that show why it has become a hybrid platform that uses Java Agent Development Framework (JADE) and Robot Operating System (ROS). Finally, to validate REXOS, the performance is measured and discussed, which shows that REXOS can be used as a practical basis for more specific research for robust autonomous reconfigurable systems and application in industry 4.0. This paper shows practical examples of how to successfully combine several technologies that are meant to lead to a faster adoption and a better business case for autonomous and reconfigurable systems in industry.
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
Recalling that a majority of those who need assistive technology do not have access to it, and that this has a significant impact on the education, livelihood, health and well-being of individuals, and on families, communities and societies, Member States adopted a resolution on Improving access to assistive technology during the 71st World Health Assembly in May 2018. Among other mandates, Member States requested the Director-General of the World Health Organization (WHO) to prepare a global report on effective access to assistive technology in the context of an integrated approach, based on the best available scientific evidence and international experience, with the participation of all levels within the organization and in collaboration with all relevant stakeholders. In fulfilling this commitment, aiming to improve access to assistive technology, this global report: • presents the first comprehensive data set of its kind and analysis of current assistive technology access; • draws the attention of governments and civil societies to the need for, and benefits of, assistive technology, including its return on investment; • makes recommendations for concrete actions that will improve access; • supports implementation of the UN Convention on the Rights of Persons with Disabilities; and • contributes towards achieving the Sustainable Development Goals, especially in making universal health coverage (UHC) inclusive – leaving no one behind. The global report explores assistive technology from a variety of perspectives.
DOCUMENT
This research investigates the integration of stakeholders' values into the digital frameworks of Collective Management Organizations (CMOs) within the Dutch music copyright system. Utilizing Q methodology, the study captures diverse perspectives from composers, lyricists, publishers, and CMO representatives on values, value tensions, norms, and system requirements. A pilot study with four experts tested data collection methods and refined the study design for a larger, follow-up study involving 30 participants. Preliminary findings, based on factor analysis of participant rankings of 30 statements, reveal two distinct perspectives: one focused on "Fairness and Accountability," emphasizing trust-building and equitable treatment, and the other on "Technological Efficiency and Transparency," prioritizing clear information, verification mechanisms, and advanced IT systems. Qualitative insights from participant interviews provide nuanced understanding, highlighting the importance of transparency in royalty processes, balanced application of technology, and equitable royalty distribution in the digital age. This research contributes to the modernization of copyright management systems offering a conceptual model adaptable to other creative (Intellectual Property) industries
MULTIFILE
The Co-Design Pressure Cooker was set up to gather knowledge on co-design in product development activities of Small-to-Medium Enterprises(SMEs). This booklet gives an impression of ten projects conducted in the Province of Utrecht, the Netherlands. In these ten projects, a total of 22 companies were involved. 5000 booklets have already been printed in Dutch and handed out to SMEs for knowledge dissemination. We have received ample requests from the international community, which leads us to believe that there is an international audience for the cases conducted and knowledge gathered. This is why we decided to publish an English version of this booklet. The booklet will be followed by a scientific publication on the knowledge gathered for the academic community. Feel free to contact us for more information on this project
DOCUMENT
The aim of this report is to give an overview of current state of the art in the occurrence and policies regarding affordable age-friendly and eco-friendly solutions in the partner countries. The report consists of the findings from the literature review, the comparative analysis and the reporting of good practices. It aims for the consortium as a whole to gain an understanding of the state of the art and on affordable age and eco-friendly solutions in partner countries and particularly the home and community fields, and to present that knowledge in the form of a written report. The literature review, the analysis of barriers and facilitators, and the survey on existing or even planning good practices in the project countries, will help the partners to build and update a strong knowledge base in these fields. To be closer to the practical issues that define the adaptability of eco and age-friendly solutions in community, the consortium decided to use mostly grey literature and websites for tools and advice, such as governmental pages. Common grey literature publication types include reports (annual, research, technical, project, etc.), working papers, government documents, white papers and evaluations, which will help all partners to reach conclusions around the common field between age and eco-friendly developments. Barriers and facilitators found in each project country will be used for stipulating the right consequence of actions needed, to propose a sound methodology that could – in combination with other actions and stakeholders – promote the implementation of age and eco-friendly principles into the public and private sphere of care for older people. Finally, the selection of good representative practices by each project country can be the basis for a report, and a publication, that depicts the level of maturity and progress of the notions of age-friendliness and eco-friendliness, as well as their impact on the care of older people.
DOCUMENT
