For low-dimensional data sets with a large amount of data points, standard kernel methods are usually not feasible for regression anymore. Besides simple linear models or involved heuristic deep learning models, grid-...
详细信息
Background Augmented reality apps merge real world with virtual experiences and can be used to remotely assess complex instrumental activities of daily living (iADL) that are affected early in Alzheimer’s disease (AD...
Background Augmented reality apps merge real world with virtual experiences and can be used to remotely assess complex instrumental activities of daily living (iADL) that are affected early in Alzheimer’s disease (AD). Our aim was to compare standard clinical measures with an augmented reality app to assess iADL that are related to memory and spatial navigation in early AD and its feasibility in the home-setting. Method We administered an augmented reality app (Altoida Inc., Washington DC, USA) in an on-going cross-sectional study (RADAR-AD: Remote Assessment of Disease and Relapse – Alzheimer’s Disease) in three groups: 1) amyloid negative healthy controls (HC, N = 49); and amyloid positive 2) preclinical AD (PreAD, N = 17); and 3) prodromal AD (ProAD, N = 29) (Table 1). Altoida’s research algorithm DNS-MCI (Digital Neuro Signature) produces the outcome of a machinelearning model trained to identify cognitively normal individuals from those with cognitive impairment). DNS-MCI reflects performance in app-based tasks assessing memory and visuo-spatial function (placing and finding virtual objects, fire drill simulation) further including attention and motor performance (reaction time, finger tapping, navigational trajectory). At baseline, app-based tasks were performed in the clinic together with a standard neuropsychological assessment and iADL questionnaires (Figure 1). Participants were furthermore given the option of using Altoida in the home environment. Result The DNS-MCI score could significantly distinguish HC and PreAD participants from the ProAD group and was correlated with all neuropsychological tests and iADL questionnaires (Figures 1 and 2). Participants used the app on average 3-4 times at home (Table 1). Baseline in-clinic assessments were strongly correlated with at-home assessments (r = 0.53, p <.001). Conclusion App-based augmented reality tasks are applicable in the home setting and successful in capturing cognitive impairment in early AD. Future
The years 2023 and 2024 were characterized by unprecedented warming across the globe, underscoring the urgency of climate action. Robust science advice for decision makers on subjects as complex as climate change requ...
详细信息
To predict the quality of a process outcome with given process parameters in real-time, surrogate models are often adopted. A surrogate model is a statistical model that interpolates between data points obtained eithe...
To predict the quality of a process outcome with given process parameters in real-time, surrogate models are often adopted. A surrogate model is a statistical model that interpolates between data points obtained either by process measurements or deterministic models of the process. However, in manufacturing processes the amount of useful data is often limited, and therefore setting up a sufficiently accurate surrogate model is challenging. The present contribution shows how to handle limited data in a surrogate modeling approach using the example of a cup drawing process. The purpose of the surrogate model is to classify the quality of the drawn cup and to predict its final geometry. These classification and regression tasks are solved via machinelearning methods. The training data is sampled on a relatively wide range varying three parameters of a finite element simulation, namely sheet metal thickness, blank holder force, and friction. The geometrical features of the cup are extracted using domain knowledge. Besides this knowledge-based approach, an outlook is given for a data-driven surrogate modeling approach.
Relation extraction is frequently and successfully addressed by machinelearning methods. The downside of this approach is the need for annotated training data, typically generated in tedious manual, cost intensive wo...
详细信息
ISBN:
(纸本)9781622764907
Relation extraction is frequently and successfully addressed by machinelearning methods. The downside of this approach is the need for annotated training data, typically generated in tedious manual, cost intensive work. Distantly supervised approaches make use of weakly annotated data, like automatically annotated corpora. Recent work in the biomedical domain has applied distant supervision for protein-protein interaction (PPI) with reasonable results making use of the IntAct database. Such data is typically noisy and heuristics to filter the data are commonly applied. We propose a constraint to increase the quality of data used for training based on the assumption that no self-interaction of real-world objects are described in sentences. In addition, we make use of the University of Kansas Proteomics Service (KUPS) database. These two steps show an increase of 7 percentage points (pp) for the PPI corpus AIMed. We demonstrate the broad applicability of our approach by using the same workflow for the analysis of drug-drug interactions, utilizing relationships available from the drug database DrugBank. We achieve 37.31 % in F_1 measure without manually annotated training data on an independent test set.
Hydraulic axial pumps equipped with cam-driven commutation unit (PWK pumps) proved their high efficiency up to 55 MPa and ability to work self-sucking, even at high speed. Displacement of PWK pump may easily be change...
详细信息
暂无评论