9607 research outputs found
Sort by
Decision factors for the selection of AI-based decision support systems—The case of task delegation in prognostics
No full textDecision support systems (DSS) integrating artificial intelligence (AI) hold the potential to significantly enhance organizational decision-making performance and speed in areas such as prognostics in machine maintenance. A key issue for organizations aiming to leverage this potential is to select an appropriate AI-based DSS. In this paper, we develop a delegation perspective to identify decision factors and underlying AI system characteristics that affect the selection of AI-based DSS. Utilizing the analytical hierarchy process method, we derive decision weights for these characteristics and apply them to three archetypes of AI-based DSS designed for prognostics. Additionally, we explore how users’ expertise levels impact their preferences for specific AI system characteristics. The results confirm that Performance is the most important decision factor, followed by Effort and Transparency. In line with these results, we find that the archetypes of prognostics systems using Direct Remaining Useful Life estimation and Similarity-based Matching best fit user preferences. Moreover, we find that novices and experts strongly prefer visual over structural explanations, while users with moderate expertise also value structural explanations to develop their skills further
A Corrosive Decline
No full textThis piece is written in the wake of damaging projects of extractive capitalism. As the Trump administration pulls back government support for clean energy, energy policy and market forces are past the tipping point of change. Trump brings uncertainty to the structural reorganization of the global economy, yet he will not reverse it. Writing from Denmark, David Struthers looks to the Indigenous analyses of ongoing colonialism to make an argument against a corrosive authoritarian encroachment
Patch Explorer: Interpreting Diffusion Models through Interaction
No full textWe introduce Patch Explorer, an interactive interface for visualizing and manipulating the patches as they are processed by cross-attention heads. Built on interventions via NNsight, our interface lets users inspect and manipulate individual attention heads over layers and timesteps. Interaction via the interface reveals that attention heads independently capture semantics, like a unicorn’s horn, in diffusion models. Next to offering a way to analyze its behavior, users can also intervene with Patch Explorer to edit semantic associations within diffusion models, like adding a unicorn horn to a horse. Our interface also helps understand the role of a diffusion timestep through precise interventions. By providing a visualization tool with interactivity based on attention heads, we aim to shed light on their role in generative processes
Navigating Demand Uncertainty in Container Shipping: Deep Reinforcement Learning for Enabling Adaptive and Feasible Master Stowage Planning
No full textReinforcement learning (RL) has shown promise in solving various combinatorial optimization problems. However, conventional RL faces challenges when dealing with real-world constraints, especially when action space feasibility is explicit and dependent on the corresponding state or trajectory. In this work, we focus on using RL in container shipping, often considered the cornerstone of global trade, by dealing with the critical challenge of master stowage planning. The main objective is to maximize cargo revenue and minimize operational costs while navigating demand uncertainty and various complex operational constraints, namely vessel capacity and stability, which must be dynamically updated along the vessel's voyage. To address this problem, we implement a deep reinforcement learning framework with feasibility projection to solve the master stowage planning problem (MPP) under demand uncertainty. The experimental results show that our architecture efficiently finds adaptive, feasible solutions for this multi-stage stochastic optimization problem, outperforming traditional mixed-integer programming and RL with feasibility regularization. Our AI-driven decision-support policy enables adaptive and feasible planning under uncertainty, optimizing operational efficiency and capacity utilization while contributing to sustainable and resilient global supply chains.<br/
MorSeD: Morphological Segmentation of Danish and its Effect on Language Modeling
No full textCurrent language models (LMs) mostly exploit subwords as input units based on statistical co-occurrences of characters. Adjacently, previous work has shown that modeling morphemes can aid performance for Natural Language Processing (NLP) models. However, morphemes are challenging to obtain as there is no annotated data in most languages. In this work, we release a wide-coverage Danish morphological segmentation evaluation set. We evaluate a range of unsupervised token segmenters and evaluate the downstream effect of using morphemes as input units for transformer-based LMs. Our results show that popular subword algorithms perform poorly on this task, scoring at most an F1 of 57.6 compared to 68.0 for an unsupervised morphological segmenter (Morfessor). Furthermore, evaluate a range of segmenters on the task of language modeling
Digitalization, Data and Welfare:Sociotechnical Approaches to Service Delivery
No full textThis insightful book investigates the growing use of digital technologies to support welfare provision and examines which digital tools can have the greatest impact. It explores how these technologies influence and are influenced by social and cultural relations, working life, education, healthcare, markets, and organizations.Vasilis Galis and Vasileios-Spyridon Vlassis bring together renowned experts who analyze digital technologies for welfare provision as sociotechnical phenomena, that is, the welfare state is mutually constructed by welfare practices and digital technologies, an outcome of organizational reconfiguration, political–economic visions, and socio-technical imaginaries. They demonstrate that digitalization is not simply a question of implementing digital technologies but also an introduction of new governmental ideas that transform both the public sector and its services as well as inter-state and state-society relations. The book explores how the rapid implementation of digital tools in the provision of welfare services is bringing fundamental changes to welfare and provides experienced-based accounts of the transformations occurring in public service work.Digitalization, Data and Welfare is an essential resource for students and academics in welfare studies. Its practical insights into inter-state and state-society relations will also greatly benefit welfare policymakers and practitioners in innovation, science and technology
MarineLLM-PDDL: Generation of Planning Domains for Marine Vessels Using Past Incident Response Plans
No full textTesting the hardware and software of marine vessels in field trials is a necessity to avoid technical and environmental catastrophes. Conducting tests with large vessels is costly. Multiple realistic domain descriptions based on past missions could increase the value of simulation tests, reducing the need for expensive field tests. In this paper, we generate scenarios from unstructured Incident Response Plan (IRP) documents using Large Language Models (LLMs), converting them to standard structured planning programs. The two synthesized marine test-domain datasets contain approximately 90% parsable, 75% solvable, and 57% correct planning programs
Participation in Design-after-design::Reconfiguring Relations Between Citizens and Public Institutions
Get PDFParticipatory Design (PD), originally situated within workplace contexts, has increasingly expanded into new domains, notably the public sector, where citizens are increasingly invited to participate in the design of public services. As digital services mediate more aspects of citizens’ interactions with the state, questions about access become increasingly urgent. The growing demand for citizens to possess digital competencies risks reinforcing existing social inequalities, particularly among individuals with limited access, skills, or support. Yet, institutional structures and constraints frequently hinder the empowerment of citizens due to misalignments between institutional priorities and the democratic ethos that underpins PD. Consequently, citizens are often reduced to informants rather than being recognised as equal partners in designing public services that shape their lives.Grounded in PD’s foundational commitment to redistributing power through democratic engagement, there is a critical need to investigate how citizen participation can be enacted in more sustainable and equitable design of digital public services. This thesis addresses these challenges by exploring how PD researchers can engage with institutional structures, allowing for sustained impact. The following question guides the research: How can reconfiguring relations between citizens and institutions empower citizens and promote participation in the design of digital public services?The research employs a qualitative methodology combining ethnographic and PD approaches. It is based on an empirical study conducted in Denmark, involving IT helpdesk volunteers, library staff, and public employees in the exploration and design of digital public services. Central to the study are design experiments—situated interventions that explore new opportunities for citizen participation during the use of digital public services. These experiments serve as real-world sites for examining how participation unfolds in practice.Based on the design experiments, the thesis offers critical reflections on the limitations and possibilities of PD within institutional constraints, emphasising the potential for long-term engagement beyond the initial design phases. It proposes strategies for promoting more sustainable and equitable relationships between institutions and citizens by aligning PD efforts with ongoing public sector development. Finally, it presents an empirical prototype demonstrating how PD can challenge and reconfigure relations through inclusive, democratic values.Ultimately, this work contributes to current debates on the future of PD in public sector contexts by advocating for more sustained and politically engaged forms of participation. Additionally, it encourages public institutions to reimagine citizens not just as service users but as active collaborators—before, during, and after design and implementation.<br/
Fréchet Distance in Unweighted Planar Graphs.
No full textThe Fréchet distance is a distance measure between trajectories in ℝ^d or walks in a graph G. Given constant-time shortest path queries, the Discrete Fréchet distance D_G(P, Q) between two walks P and Q can be computed in O(|P|⋅|Q|) time using a dynamic program. Driemel, van der Hoog, and Rotenberg [SoCG'22] show that for weighted planar graphs this approach is likely tight, as there can be no strongly-subquadratic algorithm to compute a 1.01-approximation of D_G(P, Q) unless the Orthogonal Vector Hypothesis (OVH) fails.Such quadratic-time conditional lower bounds are common to many Fréchet distance variants. However, they can be circumvented by assuming that the input comes from some well-behaved class: There exist (1+ε)-approximations, both in weighted graphs and in ℝ^d, that take near-linear time for c-packed or κ-straight walks in the graph. In ℝ^d there also exists a near-linear time algorithm to compute the Fréchet distance whenever all input edges are long compared to the distance. We consider computing the Fréchet distance in unweighted planar graphs. We show that there exist no strongly-subquadratic 1.25-approximations of the discrete Fréchet distance between two disjoint simple paths in an unweighted planar graph in strongly subquadratic time, unless OVH fails. This improves the previous lower bound, both in terms of generality and approximation factor. We subsequently show that adding graph structure circumvents this lower bound: If the graph is a regular tiling with unit-weighted edges, then there exists an Õ((|P|+|Q|)^{1.5})-time algorithm to compute D_G(P, Q). Our result has natural implications in the plane, as it allows us to define a new class of well-behaved curves that facilitate (1+ε)-approximations of their discrete Fréchet distance in subquadratic time
Attuning to Global Health: Health Data Infrastructuring, Epidemiological Accountability and Digital Labor in Ghana
No full textDrawing on ethnographic fieldwork among Ghanaian officials and international developers in the field of health information systems, we investigate how innovations in health data infrastructures are aligned with global practices of epidemiological accountability. The digital health information system DHIS2 has been adopted in various low- and middle-income countries, including Ghana. While global stakeholders render public health a matter of efficiency and accountability, public health professionals attune at various levels to emerging global health priorities and data practices, e.g. the translation of standard case definitions and quantitative measures into local contexts, or innovations in reporting channels of key public health indicators