6,376 research outputs found
V-Elliot: Design, evaluate and tune visual recommender systems
The paper introduces Visual-Elliot (V-Elliot), a reproducibility framework for Visual Recommendation systems (VRSs) based on Elliot. framework provides the widest set of VRSs compared to other recommendation frameworks in the literature (i.e., 6 state-of-the-art models which have been commonly employed as baselines in recent works). The framework pipeline spans from the dataset preprocessing and item visual features loading to easily train and test complex combinations of visual models and evaluation settings. V-Elliot provides an extended set of features to ease the design, testing, and integration of novel VRSs into V-Elliot. The framework exploits of dataset filtering/splitting functions, 40 evaluation metrics, five hyper-parameter optimization methods, more than 50 recommendation algorithms, and two statistical hypothesis tests. The files of this demonstration are available at: github.com/sisinflab/elliot
[Dining room with persimmon silk curtains and matching walls and ceiling, a pair of brass chained jardiniere fern stands (ca. 1870), a silver and glass epergne and a painting by Ric Elliot, Sydney, ca. 1971] [transparency] /
Title devised by cataloguer from caption list and information in publication: Australian decor.; Part of the Warren T. Harding and David C. Lorimer collection of interior design.; Similar image published in: Australian decor / Warren T. Harding [and] David C. Lorimer. Photos by David Beal. [Melbourne] : Nelson, [1971]; Also available in an electronic version via the Internet at: http://nla.gov.au/nla.pic-vn3288459. Photographer David Beal was employed by the firm Decor Associates Pty. Ltd. in whom Warren T. Harding and David C. Lorimer were partners, to photograph homes and business premises they had decorated. Some of these photographs were used in the publication: Australian decor / Warren T. Harding [and] David C. Lorimer. Photos by David Beal. [Melbourne] : Nelson, [1971]
Nostalgia counteracts the negative relation between threat appraisals and intrinsic motivation in educational context
We examined the coping potential of nostalgia in an educational setting. In particular, we investigated whether nostalgia can protect students from the pernicious link between threat appraisal and low intrinsic motivation. Undergraduate students (N = 382) reported threat and challenge appraisals in regards to a class they were taking, their nostalgia, as well as their intrinsic motivation. Threat appraisals predicted reduced intrinsic motivation, but were also prognostic of increased nostalgia. Nostalgia, in turn, was associated with increased intrinsic motivation. Thus, the negative direct association of threat appraisals with intrinsic motivation was counteracted by a positive indirect association via increased nostalgia — a statistical suppression pattern. Nostalgia appears to have implications for achievement contexts
Quantification and mapping of regulating and provisioning services in urban areas making use of a system dynamics model
Oral Presentation
Abstract:
There is a growing evidence that the use of statistical, process-based, and mechanistic models can provide robust information for the quantification and mapping of provisioning and regulating services. These models can allow identification and relation of main factors of biophysical structures and processes, taking into account how the condition of ecosystems or living features (e.g. health conditions of trees) could increase or decrease the supply of ecosystem services (ES). However, they i) usually assume that conditions do not change over time; ii) rarely consider causal loop interactions among biophysical structures, processes and human actions; iii) do not model multiple ES at once. In this research, we present a system dynamics modelling approach to quantify and map several regulation and provisioning services and disservices simultaneously supplied by urban nature-based solutions, which acknowledges temporal changes in the system. To illustrate the approach, we develop and present the results of an urban forest model applied to Valdebebas Park (Madrid, Spain). Five regulating services (carbon sequestration, temperature regulation, air pollutant filtration, and water flow maintenance), one provisioning service (plant material for direct use or processing), and one provisioning disservice (plant residues for landfill or waste treatment) were quantified and mapped in biophysical units. The model includes morbidity dynamics of trees triggered by their location (street vs open spaces), lack of water, and waterlogging, as well as the influence of human management. The results show the potential of system dynamics models to quantify bundles of ES in a spatio-temporally explicit form and their usefulness to inform decision making in urban interventions.
Key words: System Dynamics; Nature-based Solutions; Ecosystem Services; Ecosystem Disservices
Modelling Benefits and Costs of Urban Forest: Application to Valdebebas Park (Madrid, Spain)
Oral Presentation
Abstract:
Process-based models are gaining relevance for the quantification of benefits and costs derived from urban nature-based solutions (e.g. urban forests, green roofs) as a way to inform decision makers. We developed a system dynamics approach to quantify the net environmental and economic benefits of urban nature-based solutions. Based on our system dynamics approach, we present a proof-of-concept model of urban forest to quantify their net economic benefits, which was applied to a zone of Valdebebas Park (Madrid, Spain). The proof of concept model quantifies three ecosystem services (carbon sequestration, temperature and humidity regulation, and potential wood provision) and takes into account investment costs, and two operational costs (re-planting dead trees, and waste treatment of plant residues) in a spatio-temporal explicit form. The model uses a regular grid of cells of 100x100 meters and calculates ecosystem services (benefits) and costs at a monthly temporal resolution. For the application to Valdebebas Park, we modelled the ecosystems services (benefits) and operational costs in the form of biophysical outputs for 50 years. Later, we converted the biophysical outputs into monetary units making use of benefit transfer functions and aggregating outputs into yearly time steps. As part of the model, tree death is included making use of binomial probability functions, which incorporates stochasticity into the model. As a result of the application, advantages and current limitations of the model were discussed as well as its usefulness for decision making.
Key words: System Dynamics; MIMES; Nature-based Solutions; Ecosystem Services; Biophysical Valuation; Monetary Valuatio
How to perform reproducible experiments in the ELLIOT recommendation framework: Data processing, model selection, and performance evaluation
Recommender Systems have shown to be an effective way to alleviate the over-choice problem and provide accurate and tailored recommendations. However, the impressive number of proposed recommendation algorithms, splitting strategies, evaluation protocols, metrics, and tasks, has made rigorous experimental evaluation particularly challenging. ELLIOT is a comprehensive recommendation framework that aims to run and reproduce an entire experimental pipeline by processing a simple configuration file. The framework loads, filters, and splits the data considering a vast set of strategies. Then, it optimizes hyperparameters for several recommendation algorithms, selects the best models, compares them with the baselines, computes metrics spanning from accuracy to beyond-accuracy, bias, and fairness, and conducts statistical analysis. The aim is to provide researchers a tool to ease all the experimental evaluation phases (and make them reproducible), from data reading to results collection. ELLIOT is freely available on GitHub at https://github.com/sisinflab/elliot
Dataset in support of Guenther, R.G. et al., 2022. "Effects of temperature and pH on the growth, calcification, and biomechanics of two species of articulated coralline algae"
This dataset supports the manuscript: Guenther, R.G. et al., 2022. "Effects of temperature and pH on the growth, calcification, and biomechanics of two species of articulated coralline algae" in Marine Ecology Progress Series.
DOI: https://doi.org/10.3354/meps14166.
Full author listing is Rebecca Guenther, Elliot M. A. Porcher, Emily Carrington, Patrick T. Martone
An Out-of-the-Box Application for Reproducible Graph Collaborative Filtering extending the Elliot Framework
Graph convolutional networks (GCNs) are taking over collaborative filtering-based recommendation. Their message-passing schema effectively distills the collaborative signal throughout the user-item graph by propagating informative content from neighbor to ego nodes. In this demonstration, we show how to run complete experimental pipelines with six state-of-the-art graph recommendation models in Elliot (i.e., our framework for recommender system evaluation). We seek to highlight four main features, namely: (i) we support reproducibility in PyTorch Geometric (i.e., the library we use to implement the baselines); (ii) reproduced graph models span across various GCN families; (iii) we prepare a Docker image to provide a self-consistent ecosystem for the running of experiments. Codes, datasets, and a video tutorial to install and launch the application are accessible at: https://github.com/sisinflab/Graph-Demo
Constructive Knowledge Engineering
Knowledge engineering research has shifted from the transfer, expert-driven metaphor for system development to an interpretative, model-driven metaphor. The paper examines the relationship between these two metaphors and introduces a third: constructive, problem-driven engineering. The paper postulates a theoretical construction of the interrelationships between these in terms of the epistemology of expertise, the engineering process, and representational issues. The constructive approach is further illuminated with example systems, and a set of guidelines for applying the constructive approach is provided
FIGURE 8 in Lithodidae from the Ross Sea, Antarctica, with descriptions of two new species (Crustacea: Decapoda: Anomura)
FIGURE 8. Paralomis stevensi sp. nov., male holotype (cl 74.6 mm, cw 75.7 mm, NIWA 23842). A, carapace, dorsal view. B, right antenna, dorsal view. C, right first ambulatory leg and proximal portion of second and third ambulatory legs, dorsal view. D, dactylus of right first ambulatory leg, dorsal view.Published as part of Ahyong, Shane T. & Dawson, Elliot W., 2006, Lithodidae from the Ross Sea, Antarctica, with descriptions of two new species (Crustacea: Decapoda: Anomura), pp. 45-68 in Zootaxa 1303 on page 61, DOI: 10.5281/zenodo.17367
- …
