Light scattering is a fundamental property that can be exploited to create essential devices such as particle analysers. The most common particle size analyser relies on measuring the angle-dependent diffracted light from a sample illuminated by a laser beam. Compared to other non-light-based counterparts, such a laser diffraction scheme offers precision, but it does so at the expense of size, complexity and cost. In this paper, we introduce the concept of a new particle size analyser in a collimated beam configuration using a consumer electronic camera and machine learning. The key novelty is a small form factor angular spatial filter that allows for the collection of light scattered by the particles up to predefined discrete angles. The filter is combined with a light-emitting diode and a complementary metal-oxide-semiconductor image sensor array to acquire angularly resolved scattering images. From these images, a machine learning model predicts the volume median diameter of the particles. To validate the proposed device, glass beads with diameters ranging from 13 to 125 µm were measured in suspension at several concentrations. We were able to correct for multiple scattering effects and predict the particle size with mean absolute percentage errors of 5.09% and 2.5% for the cases without and with concentration as an input parameter, respectively. When only spherical particles were analysed, the former error was significantly reduced (0.72%). Given that it is compact (on the order of ten cm) and built with low-cost consumer electronics, the newly designed particle size analyser has significant potential for use outside a standard laboratory, for example, in online and in-line industrial process monitoring.
MULTIFILE
This position paper is part of a long-term research project on human-machine co-creativity with older adults. The goal is to investigate how robots and AI-generated content can contribute to older adults’ creative experiences, with a focus on collaborative drawing and painting. The research has recently started, and current activities are centred around literature studies, interviews with seniors and artists, and developing initial prototypes. In addition, a course “Drawing with Robots”, is being developed to establish collaboration between human and machine learners: older adults, artists, students, researchers, and artificial agents. We present this courseas a learning community and as an opportunity for studying how explainable AI and creative dialogues can be intertwined in human-machine co-creativity with older adults.
City governments increasingly experiment with civic participation in the procurement and the realization of smart city technologies in order to improve the incorporation of human values. In this paper, a model is proposed with the level of participation, the continuity of participation and the extent of institutional embedding to illustrate how challenging these experiments are. The City of Amsterdam also experiments with its procurement approach for a new camera car service that ensures an ethically responsible, privacy-friendly and secure collection of images from public space. Two starting points drive this change: 1) in order to have more control over the data, the municipality develops its own machine learning models for processing the images and 2) a multi-stakeholder co-design project including a citizen panel – is an integral part of the process in which the service is designed and realized. To support this new procurement process, a group of design-researchers were involved in a collaborative case study to identify requirements relevant for the tender. An analysis of the case study findings along the three dimensions brings us to the conclusion that the approach developed by the City of Amsterdam is a fruitful encounter between ‘doing ethics’ and procurement. The lessons of this procurement approach for ‘doing ethics’ are claimed to be of value for other practical contexts and further research.
Smart city technologies, including artificial intelligence and computer vision, promise to bring a higher quality of life and more efficiently managed cities. However, developers, designers, and professionals working in urban management have started to realize that implementing these technologies poses numerous ethical challenges. Policy papers now call for human and public values in tech development, ethics guidelines for trustworthy A.I., and cities for digital rights. In a democratic society, these technologies should be understandable for citizens (transparency) and open for scrutiny and critique (accountability). When implementing such public values in smart city technologies, professionals face numerous knowledge gaps. Public administrators find it difficult to translate abstract values like transparency into concrete specifications to design new services. In the private sector, developers and designers still lack a ‘design vocabulary’ and exemplary projects that can inspire them to respond to transparency and accountability demands. Finally, both the public and private sectors see a need to include the public in the development of smart city technologies but haven’t found the right methods. This proposal aims to help these professionals to develop an integrated, value-based and multi-stakeholder design approach for the ethical implementation of smart city technologies. It does so by setting up a research-through-design trajectory to develop a prototype for an ethical ‘scan car’, as a concrete and urgent example for the deployment of computer vision and algorithmic governance in public space. Three (practical) knowledge gaps will be addressed. With civil servants at municipalities, we will create methods enabling them to translate public values such as transparency into concrete specifications and evaluation criteria. With designers, we will explore methods and patterns to answer these value-based requirements. Finally, we will further develop methods to engage civil society in this processes.
