Constrained self-organizing feature map to preserve feature extraction topology

In many classification problems, it is necessary to consider the specific location of an n-dimensional space from which features have been calculated. For example, considering the location of features extracted from specific areas of a two-dimensional space, as an image, could improve the understanding of a scene for a video surveillance system. In the same way, the same features extracted from different locations could mean different actions for a 3D HCI system. In this paper, we present a self-organizing feature map able to preserve the topology of locations of an n-dimensional space in which the vector of features have been extracted. The main contribution is to implicitly preserving the topology of the original space because considering the locations of the extracted features and their topology could ease the solution to certain problems. Specifically, the paper proposes the n-dimensional constrained self-organizing map preserving the input topology (nD-SOM-PINT). Features in adjacent areas of the n-dimensional space, used to extract the feature vectors, are explicitly in adjacent areas of the nD-SOM-PINT constraining the neural network structure and learning. As a study case, the neural network has been instantiate to represent and classify features as trajectories extracted from a sequence of images into a high level of semantic understanding. Experiments have been thoroughly carried out using the CAVIAR datasets (Corridor, Frontal and Inria) taken into account the global behaviour of an individual in order to validate the ability to preserve the topology of the two-dimensional space to obtain high-performance classification for trajectory classification in contrast of non-considering the location of features. Moreover, a brief example has been included to focus on validate the nD-SOM-PINT proposal in other domain than the individual trajectory. Results confirm the high accuracy of the nD-SOM-PINT outperforming previous methods aimed to classify the same datasets.

Breaking down complex saproxylic communities: understanding sub-networks structure and implications to network robustness

Saproxylic insect communities inhabiting tree hollow microhabitats correspond with large food webs which simultaneously are constituted by multiple types of plant-animal and animal-animal interactions, according to the use of trophic resources (wood- and insect-dependent sub-networks), or to trophic habits or interaction types (xylophagous, saprophagous, xylomycetophagous, predators and commensals). We quantitatively assessed which properties of specialised networks were present in a complex networks involving different interacting types such as saproxylic community, and how they can be organised in trophic food webs. The architecture, interacting patterns and food web composition were evaluated along sub-networks, analysing their implications to network robustness from random and directed extinction simulations. A structure of large and cohesive modules with weakly connected nodes was observed throughout saproxylic sub-networks, composing the main food webs constituting this community. Insect-dependent sub-networks were more modular than wood-dependent sub-networks. Wood-dependent sub-networks presented higher species degree, connectance, links, linkage density, interaction strength, and were less specialised and more aggregated than insect-dependent sub-networks. These attributes defined high network robustness in wood-dependent sub-networks. Finally, our results emphasise the relevance of modularity, differences among interacting types and interrelations among them in modelling the structure of saproxylic communities and in determining their stability.

Effect of the porous structure in carbon materials for CO2 capture at atmospheric and high-pressure

Activated carbons prepared from petroleum pitch and using KOH as activating agent exhibit an excellent behavior in CO2 capture both at atmospheric (∼168 mg CO2/g at 298 K) and high pressure (∼1500 mg CO2/g at 298 K and 4.5 MPa). However, an exhaustive evaluation of the adsorption process shows that the optimum carbon structure, in terms of adsorption capacity, depends on the final application. Whereas narrow micropores (pores below 0.6 nm) govern the sorption behavior at 0.1 MPa, large micropores/small mesopores (pores below 2.0–3.0 nm) govern the sorption behavior at high pressure (4.5 MPa). Consequently, an optimum sorbent exhibiting a high working capacity for high pressure applications, e.g., pressure-swing adsorption units, will require a poorly-developed narrow microporous structure together with a highly-developed wide microporous and small mesoporous network. The appropriate design of the preparation conditions gives rise to carbon materials with an extremely high delivery capacity ∼1388 mg CO2/g between 4.5 MPa and 0.1 MPa. Consequently, this study provides guidelines for the design of carbon materials with an improved ability to remove carbon dioxide from the environment at atmospheric and high pressure.

Analyzing the commercial activities of a street network by ranking their nodes: a case study in Murcia, Spain

Urban researchers and planners are often interested in understanding how economic activities are distributed in urban regions, what forces influence their special pattern and how urban structure and functions are mutually dependent. In this paper, we want to show how an algorithm for ranking the nodes in a network can be used to understand and visualize certain commercial activities of a city. The first part of the method consists of collecting real information about different types of commercial activities at each location in the urban network of the city of Murcia, Spain. Four clearly differentiated commercial activities are studied, such as restaurants and bars, shops, banks and supermarkets or department stores, but obviously we can study other. The information collected is then quantified by means of a data matrix, which is used as the basis for the implementation of a PageRank algorithm which produces a ranking of all the nodes in the network, according to their significance within it. Finally, we visualize the resulting classification using a colour scale that helps us to represent the business network.

The intellectual structure of research in hospitality management: A literature review using bibliometric methods of the journal International Journal of Hospitality Management

The purpose of this study is to analyze the existing literature on hospitality management from all the research papers published in The International Journal of Hospitality Management (IJHM) between 2008 and 2014. The authors apply bibliometric methods – in particular, author citation and co-citation analyses (ACA) – to identify the main research lines within this scientific field; in other words, its ‘intellectual structure’. Social network analysis (SNA) is also used to perform a visualization of this structure. The results of the analysis allow us to define the different research lines or fronts which shape the intellectual structure of research on hospitality management.