Marche Polytechnic University

About: Marche Polytechnic University is a education organization based out in Ancona, Italy. It is known for research contribution in the topics: Population & Cancer. The organization has 5905 authors who have published 15769 publications receiving 382286 citations. The organization is also known as: Universitá Politecnica delle Marche & Universita Politecnica delle Marche.

Phytosociology today: Methodological and conceptual evolution

Abstract: A concise methodological and conceptual overview of the present state of phytosociology, 100 years after its foundation, is presented. The fullness of phytosociology as a synecological science is highlighted. This scientific approach, which was inherent in phytosociology from the very beginning, has made great strides forward thanks to the detailed analysis of the conditions of vegetation populations, from the community level to that of dynamic successions found in landscape contexts. This has led to the creation and development of several integrated areas of analysis that have helped to produce highly predictive models based on the distribution of environmental gradients, which thus act as valid bio-indicators that can be used in environmental and planning management. The development of phytosociology has led over time to the need to reconsider the basic concept of association. In this article, we propose a new definition of association, updating the one drawn up by Braun-Blanquet in 1928, so th...

A Human Activity Recognition System Using Skeleton Data from RGBD Sensors

Abstract: The aim of Active and Assisted Living is to develop tools to promote the ageing in place of elderly people, and human activity recognition algorithms can help to monitor aged people in home environments. Different types of sensors can be used to address this task and the RGBD sensors, especially the ones used for gaming, are cost-effective and provide much information about the environment. This work aims to propose an activity recognition algorithm exploiting skeleton data extracted by RGBD sensors. The system is based on the extraction of key poses to compose a feature vector, and a multiclass Support Vector Machine to perform classification. Computation and association of key poses are carried out using a clustering algorithm, without the need of a learning algorithm. The proposed approach is evaluated on five publicly available datasets for activity recognition, showing promising results especially when applied for the recognition of AAL related actions. Finally, the current applicability of this solution in AAL scenarios and the future improvements needed are discussed.