This paper proposes latent representation models for improving network anomaly detection. Well-known anomaly detection algorithms often suffer from challenges posed by network data, such as high dimension and sparsity, and a lack of anomaly data for training, model selection, and hyperparameter tuning. Our approach is to introduce new regularizers to a classical autoencoder (AE) and a variational AE, which force normal data into a very tight area centered at the origin in the nonsaturating area of the bottleneck unit activations. These trained AEs on normal data will push normal points toward the origin, whereas anomalies, which differ from normal data, will be put far away from the normal region. The models are very different from common regularized AEs, sparse AE, and contractive AE, in which the regularized AEs tend to make their latent representation less sensitive to changes of the input data. The bottleneck feature space is now used as a new data representation. A number of one-class learning algorithms are used for evaluating the proposed models. The experiments testify that our models help these classifiers to perform efficiently and consistently on high-dimensional and sparse network datasets, even with relatively few training points. More importantly, the models can minimize the effect of model selection on these classifiers since their performance is insensitive to a wide range of hyperparameter settings.

Searches of the Web using Google, and database searches of the academic and practitioner literature, return a large number of differing and varied definitions of the concept of business analytics. This article reviews the growing literature on Business Analytics (BA) using traditional and qualitative research tools. Our searches included using Google Search to identify examples of business analytics applications, and a focused keyword search of the available practitioner and academic literatures. Text analytics techniques identified frequently used terms in prior definitions of business analytics. Our empirical, inductive approach provides a basis for proposing and explaining a formal sentence definition for Business Analytics. The analysis provides a starting point for operationalising a measure for the business analytics construct. Additionally, understanding business analytics can help managers assess skill deficiencies and evaluate claims about relevance of tools and techniques. Finally, carefully defining the Business Analytics concept should provide stimulus for new research ideas.

Tuber melanosporum (Ascomycota, Pezizales) is an ectomycorrhizal fungus that produces highly appreciated hypogeous fruiting bodies called black truffles. The aim of this paper was to research the composition of ectomycorrhiza-associated fungal and bacterial communities in T. melanosporum oak plantations. Results of this paper showed the competitive effect of T. melanosporum on other fungal species, especially other mycorrhizal and pathogenic species. T. melanosporum was shown to be associated mainly with bacteria, some of them important for their properties as mycorrhizal helper bacteria. A dendrogram analysis of co-occurrence showed that T. melanosporum tended to co-occur with the following bacteria species: Singulisphaera limicola, Nannocistis excedens and Sporosarcina globispora. In addition, it was linked to fungal species such as Mortierella elongata, M. minutissima, Cryptococcus uzbekistanensis, C. chernovii and C. aerius. This study provides an exhaustive analysis of the diversity, structure and composition of fungal and bacterial communities associated with T. melanosporum to enhance understanding of the biology, composition and role of these communities in truffle plantations.