Search for: All records

Abstract Plastics have become an integral component in agricultural production as mulch films, nets, storage bins and in many other applications, but their widespread use has led to the accumulation of large quantities in soils. Rational use and reduction, collection, reuse, and innovative recycling are key measures to curb plastic pollution from agriculture. Plastics that cannot be collected after use must be biodegradable in an environmentally benign manner. Harmful plastic additives must be replaced with safer alternatives to reduce toxicity burdens and included in the ongoing negotiations surrounding the United Nations Plastics Treaty. Although full substitution of plastics is currently not possible without increasing the overall environmental footprint and jeopardizing food security, alternatives with smaller environmental impacts should be used and endorsed within a clear socio-economic framework. Better monitoring and reporting, technical innovation, education and training, and social and economic incentives are imperative to promote more sustainable use of plastics in agriculture. 

Supervised dimensionality reduction for sequence data learns a transformation that maps the observations in sequences onto a low-dimensional subspace by maximizing the separability of sequences in different classes. It is typically more challenging than conventional dimensionality reduction for static data, because measuring the separability of sequences involves non-linear procedures to manipulate the temporal structures. In this paper, we propose a linear method, called Order-preserving Wasserstein Discriminant Analysis (OWDA), and its deep extension, namely DeepOWDA, to learn linear and non-linear discriminative subspace for sequence data, respectively. We construct novel separability measures between sequence classes based on the order-preserving Wasserstein (OPW) distance to capture the essential differences among their temporal structures. Specifically, for each class, we extract the OPW barycenter and construct the intra-class scatter as the dispersion of the training sequences around the barycenter. The inter-class distance is measured as the OPW distance between the corresponding barycenters. We learn the linear and non-linear transformations by maximizing the inter-class distance and minimizing the intra-class scatter. In this way, the proposed OWDA and DeepOWDA are able to concentrate on the distinctive differences among classes by lifting the geometric relations with temporal constraints. Experiments on four 3D action recognition datasets show the effectiveness of OWDA and DeepOWDA.