Ways to build text collections for training classifiers

We report on solving the problem of forming a Russian-language text collection (dataset) consisting of bibliographic descriptions of scientific articles for training classifiers. Various approaches to creating such collections are considered. The expediency of using expert estimates for assigning class labels is assessed. The known datasets are analyzed, the requirements for the generated text array are formulated, and the choice of the subject area (Computer Science) is justified. We propose a technology of forming collection in conditions of the shortage of Russian-language articles. To do this we use automated translation of publications (bibliographic descriptions) from available English-language electronic libraries (ACM digital library, IEEE Xplore digital library, CiteSeerX) with additional expert quality control of the translation. The bibliographic collection thus formed was studied using methods of clustering (Latent Semantic Analysis) and visualization (Principal Component Analysis). Training and test samples were compiled and «standard» classifiers (K-Nearest Neighbor Method, Logistic Regression, Random Forest) were used. Then we calculated standard quality measures (accuracy, precision, recall). The rigid and soft classification were carried out. For rigid and soft classification all calculated measures (for the studied classifiers) ranged within [0.79; 0.87], and [0.91; 0.95], respectively. The experiments showed almost identical results for Russian and English bibliographic descriptions (the difference did not exceed 2%). The proposed method of forming text collections reduces the complexity of the labeling process compared to the expert approach, solves the problem of the lack of Russian-language documents, allows formation of sufficiently large balanced bibliographic datasets for training and testing classifiers.

Analyses on salt-marsh vegetation composition changes in the Venice lagoon in the last twenty years

<p>Coastal salt-marshes are important eco-geomorphic features of coastal landscapes providing valuable ecosystem services, but unfortunately, they are among the most vulnerable ecosystems around the world. Their survival is mainly threatened by sea-level rise, wave erosion and human pressure. Halophytic vegetation distribution and dynamics control salt-marsh erosional and depositional patterns, critically determining marsh survival through complex bio-morphodynamic feedbacks. Although a number of studies have proposed species-classification methods and analyzed halophytic vegetation species distribution, our knowledge of the temporal evolution of species composition remains limited. To fill these gaps and better describe vegetation composition changes in time, we developed a novel classification method which is based on the Random Forest soft classification algorithm, and applied the method to two multi-spectral images of the San Felice marsh in the Venice lagoon (Italy) acquired in 2001 and 2019. The Random Forest soft classification achieves high accuracy (0.60 < <em>R</em><sup>2</sup> < 0.96) in the estimation of the fractional abundance of each species in both images. We also determined the local dominant species, i.e. the species with the highest fractional abundance in each pixel. Our observations on the dominant species in 2001 and 2019 show that: 1) the area dominated by <em>Juncus</em> and <em>Spartina</em> decreased dramatically in such period; 2) the area dominated by <em>Limonium </em>almost maintained constant; 3) a noticeable decrease in the bare-soil area occurred due to the encroachment of <em>Salicornia</em> between 2001 and 2019. We also noticed that the probability distribution of the dominant patch area of each species is consistent with a power-law distribution, with different slopes for different vegetation species at different times. We suggest that vegetation composition changes are related to sea-level rise and to the species-specific inundation tolerance.</p>

Metrology of convex-shaped nanoparticles via soft classification machine learning of TEM images

The shape of nanoparticles is a key performance parameter for many applications, ranging from nanophotonics to nanomedicines. However, the unavoidable shape variations, which occur even in precision-controlled laboratory synthesis, can...

Assessing the Fractional Abundance of Highly Mixed Salt-Marsh Vegetation Using Random Forest Soft Classification

Coastal salt marshes are valuable and critical components of tidal landscapes, currently threatened by increasing rates of sea level rise, wave-induced lateral erosion, decreasing sediment supply, and human pressure. Halophytic vegetation plays an important role in salt-marsh erosional and depositional patterns and marsh survival. Mapping salt-marsh halophytic vegetation species and their fractional abundance within plant associations can provide important information on marsh vulnerability and coastal management. Remote sensing has often provided valuable methods for salt-marsh vegetation mapping; however, it has seldom been used to assess the fractional abundance of halophytes. In this study, we developed and tested a novel approach to estimate fractional abundance of halophytic species and bare soil that is based on Random Forest (RF) soft classification. This approach can fully use the information contained in the frequency of decision tree “votes” to estimate fractional abundance of each species. Such a method was applied to WorldView-2 (WV-2) data acquired for the Venice lagoon (Italy), where marshes are characterized by a high diversity of vegetation species. The proposed method was successfully tested against field observations derived from ancillary field surveys. Our results show that the new approach allows one to obtain high accuracy (6.7% < root-mean-square error (RMSE) < 18.7% and 0.65 < R2 < 0.96) in estimating the sub-pixel fractional abundance of marsh-vegetation species. Comparing results obtained with the new RF soft-classification approach with those obtained using the traditional RF regression method for fractional abundance estimation, we find a superior performance of the novel RF soft-classification approach with respect to the existing RF regression methods. The distribution of the dominant species obtained from the RF soft classification was compared to the one obtained from an RF hard classification, showing that numerous mixed areas are wrongly labeled as populated by specific species by the hard classifier. As for the effectiveness of using WV-2 for salt-marsh vegetation mapping, feature importance analyses suggest that Yellow (584–632 nm), NIR 1 (near-infrared 1, 765–901 nm) and NIR 2 (near-infrared 2, 856–1043 nm) bands are critical in RF soft classification. Our results bear important consequences for mapping and monitoring vegetation-species fractional abundance within plant associations and their dynamics, which are key aspects in biogeomorphic analyses of salt-marsh landscapes.

Garment Categorization Using Data Mining Techniques

The apparel industry houses a huge amount and variety of data. At every step of the supply chain, data is collected and stored by each supply chain actor. This data, when used intelligently, can help with solving a good deal of problems for the industry. In this regard, this article is devoted to the application of data mining on the industry’s product data, i.e., data related to a garment, such as fabric, trim, print, shape, and form. The purpose of this article is to use data mining and symmetry-based learning techniques on product data to create a classification model that consists of two subsystems: (1) for predicting the garment category and (2) for predicting the garment sub-category. Classification techniques, such as Decision Trees, Naïve Bayes, Random Forest, and Bayesian Forest were applied to the ‘Deep Fashion’ open-source database. The data contain three garment categories, 50 garment sub-categories, and 1000 garment attributes. The two subsystems were first trained individually and then integrated using soft classification. It was observed that the performance of the random forest classifier was comparatively better, with an accuracy of 86%, 73%, 82%, and 90%, respectively, for the garment category, and sub-categories of upper body garment, lower body garment, and whole-body garment.