Hard and soft clustering of categorical time series based on two novel distances with an application to biological sequences

Quantile-based fuzzy C-means clustering of multivariate time series: Robust techniques

The bootstrap for testing the equality of two multivariate time series with an application to financial markets

Oil palm is the second most cultivated oilseed crop in the world after soybeans, with more than 23 million hectares cultivated worldwide; it has become crucial for the economy of many countries. In Colombia, it is one of the most developed agricultural sectors, and every year the sector promotes the development of technologies that lead to greater sustainability of agricultural and food systems and address the challenges and opportunities of agribusiness. In this research, the central focus was the adoption of irrigation technologies, which is limited despite significant efforts and investments in physical and human capital. On many occasions, the typology of farmers has been associated with low technology implementation. Thus, linking the typology of farmers according to certain commonalities or differences is an essential step in exploring the factors that explain the adoption. In addition, the ranking also helps in the understanding of existing adoption constraints, as well as finding opportunities for change. This study aimed to determine the socioeconomic and demographic typology of those who adopt irrigation technologies. The analysis was performed using categorical principal component analysis to reduce dimensionality and fuzzy cluster analysis to classify the groups. As a result, four groups of producers that differ in terms of their demographic and socioeconomic characteristics were obtained, where the groups “population with female leadership” and “diversified population” were the adopters of irrigation technologies. The most outstanding characteristics of these two groups were the profitability of the harvest and the age of the producers. Determining the typology of farmers is a fundamental step in expanding the technology adoption process through agricultural extension services, which represent a way of reaching producers directly. In addition, these results allow decision makers to participate in this dynamic reflectively and intentionally (such as governments, researchers, and technology transferors).

/pdf/typology-of-irrigation-technology-adopters-in-oil-palm-22pad7ib.pdf

Typology of Irrigation Technology Adopters in Oil Palm Production: A Categorical Principal Components and Fuzzy Logic Approach

Two novel distances for ordinal time series and their application to fuzzy clustering

A novel procedure to perform fuzzy clustering of multivariate time series generated from different dependence models is proposed. Different amounts of dissimilarity between the generating models or changes on the dynamic behaviours over time are some arguments justifying a fuzzy approach, where each series is associated to all the clusters with specific membership levels. Our procedure considers quantile-based cross-spectral features and consists of three stages: (i) each element is characterized by a vector of proper estimates of the quantile cross-spectral densities, (ii) principal component analysis is carried out to capture the main differences reducing the effects of the noise, and (iii) the squared Euclidean distance between the first retained principal components is used to perform clustering through the standard fuzzy C-means and fuzzy C-medoids algorithms. The performance of the proposed approach is evaluated in a broad simulation study where several types of generating processes are considered, including linear, nonlinear and dynamic conditional correlation models. Assessment is done in two different ways: by directly measuring the quality of the resulting fuzzy partition and by taking into account the ability of the technique to determine the overlapping nature of series located equidistant from well-defined clusters. The procedure is compared with the few alternatives suggested in the literature, substantially outperforming all of them whatever the underlying process and the evaluation scheme. Two specific applications involving air quality and financial databases illustrate the usefulness of our approach.

Pierpaolo-D'Urso

Papers

Quantile-based fuzzy clustering of multivariate time series in the frequency domain