Fast Rule Mining over Multi-dimensional Windows

Association rule mining is an indispensable tool for discovering
insights from large databases and data warehouses.
The data in a warehouse being multi-dimensional, it is often
useful to mine rules over subsets of data defined by selections
over the dimensions. Such interactive rule mining
over multi-dimensional query windows is difficult since rule
mining is computationally expensive. Current methods using
pre-computation of frequent itemsets require counting
of some itemsets by revisiting the transaction database at
query time, which is very expensive. We develop a method
(RMW) that identifies the minimal set of itemsets to compute
and store for each cell, so that rule mining over any
query window may be performed without going back to the
transaction database. We give formal proofs that the set of
itemsets chosen by RMW is sufficient to answer any query
and also prove that it is the optimal set to be computed
for 1 dimensional queries. We demonstrate through an extensive
empirical evaluation that RMW achieves extremely
fast query response time compared to existing methods, with
only moderate overhead in pre-computation and storage

Environmental context determines multi-trophic effects of consumer species loss

Loss of biodiversity and nutrient enrichment are two of the main human impacts on ecosystems globally, yet we understand very little about the interactive effects of multiple stressors on natural communities and how this relates to biodiversity and ecosystem functioning. Advancing our understanding requires the following: (1) incorporation of processes occurring within and among trophic levels in natural ecosystems and (2) tests of context-dependency of species loss effects. We examined the effects of loss of a key predator and two groups of its prey on algal assemblages at both ambient and enriched nutrient conditions in a marine benthic system and tested for interactions between the loss of functional diversity and nutrient enrichment on ecosystem functioning. We found that enrichment interacted with food web structure to alter the effects of species loss in natural communities. At ambient conditions, the loss of primary consumers led to an increase in biomass of algae, whereas predator loss caused a reduction in algal biomass (i.e. a trophic cascade). However, contrary to expectations, we found that nutrient enrichment negated the cascading effect of predators on algae. Moreover, algal assemblage structure varied in distinct ways in response to mussel loss, grazer loss, predator loss and with nutrient enrichment, with compensatory shifts in algal abundance driven by variation in responses of different algal species to different environmental conditions and the presence of different consumers. We identified and characterized several context-dependent mechanisms driving direct and indirect effects of consumers. Our findings highlight the need to consider environmental context when examining potential species redundancies in particular with regard to changing environmental conditions. Furthermore, non-trophic interactions based on empirical evidence must be incorporated into food web-based ecological models to improve understanding of community responses to global change.

Interactive management control via analytic hierarchy process (AHP). An empirical study in a public university hospital

Management control in public university hospitals is a challenging task because of continuous changes due to external pressures (e.g. economic pressures, stakeholder focuses and scientific progress) and internal complexities (top management turnover, shared leadership, technological evolution, and researcher oriented mission). Interactive budgeting contributed to improving vertical and horizontal communication between hospital and stakeholders and between different organizational levels. This paper describes an application of Analytic Hierarchy Process (AHP) to enhance interactive budgeting in one of the biggest public university hospital in Italy. AHP improved budget allocation facilitating elicitation and formalization of units' needs. Furthermore, AHP facilitated vertical communication among manager and stakeholders, as it allowed multilevel hierarchical representation of hospital needs, and horizontal communication among staff of the same hospital, as it allowed units' need prioritization and standardization, with a scientific multi-criteria approach, without using complex mathematics. Finally, AHP allowed traceability of a complex decision making processes (as budget allocation), this aspect being of paramount importance in public sectors, where managers are called to respond to many different stakeholders about their choices.