Search for: All records

Diagnosing Alzheimer's Disease (AD) early and cost-effectively is crucial. Recent advancements in Large Language Models (LLMs) like ChatGPT have made accurate, affordable AD detection feasible. Yet, HIPAA compliance and the challenge of integrating these models into hospital systems limit their use. Addressing these constraints, we introduce ADetectoLocum, an open-source LLM equipped model designed for AD risk detection within hospital environments. This model evaluates AD risk through spontaneous patient speech, enhancing diagnostic processes without external data exchange. Our approach secures local deployment and significantly surpasses previous models in predictive accuracy for AD detection, especially in early-stage identification. ADetectoLocum therefore offers a reliable solution for AD diagnostics in healthcare institutions. 

We conduct three-dimensional direct numerical simulations to investigate the mixing, entrainment and energy budgets of gravity currents emerging from two-layer stratified locks. Depending on the density and layer thickness ratios, we find that either the upper layer or lower layer fluid can propagate faster, and that the density structure of the overall gravity current can range from strongly stratified to near-complete mixing. We furthermore observe that intermediate values of the density ratio can maximise mixing between the gravity current layers. Based on the vorticity budget, we propose a theoretical model for predicting the overall gravity current height, along with the front velocity of the two layers, for situations in which the lower layer moves faster than the upper layer. The model identifies the role of the height and thickness ratios in determining the velocity structure of the current, and it clarifies the dynamics of the ambient counter-current. A detailed analysis of the energy budget quantifies the conversion of potential into kinetic energy as a function of the governing parameters, along with the energy transfer between the different layers of the gravity current and the ambient fluid. Depending on the values of the density and layer thickness ratios, we find that the lower lock layer can gain or lose energy, whereas the upper layer always loses energy. 

Elastic surface waves pumping is realized by a smart pillar-type metasurface. 

Abstract. Driven by foundation models, recent progress in AI and machine learning has reached unprecedented complexity. For instance, the GPT-3 language model consists of 175 billion parameters and a training-data size of 570 GB. While it has achieved remarkable performance in generating text that is difficult to distinguish from human-authored content, a single training of the model is estimated to produce over 550 metric tons of CO2 emissions. Likewise, we see advances in GeoAI research improving large-scale prediction tasks like satellite image classification and global climate modeling, to name but a couple. While these models have not yet reached comparable complexity and emissions levels, spatio-temporal models differ from language and image-generation models in several ways that make it necessary to (re)train them more often, with potentially large implications for sustainability. While recent work in the machine learning community has started calling for greener and more energy-efficient AI alongside improvements in model accuracy, this trend has not yet reached the GeoAI community at large. In this work, we bring this issue to not only the attention of the GeoAI community but also present ethical considerations from a geographic perspective that are missing from the broader, ongoing AI-sustainability discussion. To start this discussion, we propose a framework to evaluate models from several sustainability-related angles, including energy efficiency, carbon intensity, transparency, and social implications. We encourage future AI/GeoAI work to acknowledge its environmental impact as a step towards a more resource-conscious society. Similar to the current push for reproducibility, future publications should also report the energy/carbon costs of improvements over prior work. 

Abstract Qualitative spatial/temporal reasoning (QSR/QTR) plays a key role in research on human cognition, e.g., as it relates to navigation, as well as in work on robotics and artificial intelligence. Although previous work has mainly focused on various spatial and temporal calculi, more recently representation learning techniques such as embedding have been applied to reasoning and inference tasks such as query answering and knowledge base completion. These subsymbolic and learnable representations are well suited for handling noise and efficiency problems that plagued prior work. However, applying embedding techniques to spatial and temporal reasoning has received little attention to date. In this paper, we explore two research questions: (1) How do embedding-based methods perform empirically compared to traditional reasoning methods on QSR/QTR problems? (2) If the embedding-based methods are better, what causes this superiority? In order to answer these questions, we first propose a hyperbolic embedding model, called HyperQuaternionE, to capture varying properties of relations (such as symmetry and anti-symmetry), to learn inversion relations and relation compositions (i.e., composition tables), and to model hierarchical structures over entities induced by transitive relations. We conduct various experiments on two synthetic datasets to demonstrate the advantages of our proposed embedding-based method against existing embedding models as well as traditional reasoners with respect to entity inference and relation inference. Additionally, our qualitative analysis reveals that our method is able to learn conceptual neighborhoods implicitly. We conclude that the success of our method is attributed to its ability to model composition tables and learn conceptual neighbors, which are among the core building blocks of QSR/QTR.