Binarised regression tasks: methods and evaluation metrics

Some supervised tasks are presented with a numerical output but decisions have to be made in a discrete, binarised, way, according to a particular cutoff. This binarised regression task is a very common situation that requires its own analysis, different from regression and classification—and ordinal regression. We first investigate the application cases in terms of the information about the distribution and range of the cutoffs and distinguish six possible scenarios, some of which are more common than others. Next, we study two basic approaches: the retraining approach, which discretises the training set whenever the cutoff is available and learns a new classifier from it, and the reframing approach, which learns a regression model and sets the cutoff when this is available during deployment. In order to assess the binarised regression task, we introduce context plots featuring error against cutoff. Two special cases are of interest, the \( UCE \) and \( OCE \) curves, showing that the area under the former is the mean absolute error and the latter is a new metric that is in between a ranking measure and a residual-based measure. A comprehensive evaluation of the retraining and reframing approaches is performed using a repository of binarised regression problems created on purpose, concluding that no method is clearly better than the other, except when the size of the training data is small.     

On the composition of ISO 25964 hierarchical relations (BTG,BTP, BTI)

Knowledge organization systems (KOS) can use different types of hierarchical relations: broader generic (BTG), broader partitive (BTP), and broader instantial (BTI). The latest ISO standard on thesauri (ISO 25964) has formalized these relations in a corresponding OWL ontology (De Smedt et al., ISO 25964 part 1: thesauri for information retrieval: RDF/OWL vocabulary, extension of SKOS and SKOS-XL. http://purl.org/iso25964/skos-thes, 2013) and expressed them as properties: broaderGeneric, broaderPartitive, and broaderInstantial, respectively. These relations are used in actual thesaurus data. The compositionality of these types of hierarchical relations has not been investigated systematically yet. They all contribute to the general broader (BT) thesaurus relation and its transitive generalization broader transitive defined in the SKOS model for representing KOS. But specialized relationship types cannot be arbitrarily combined to produce new statements that have the same semantic precision, leading to cases where inference of broader transitive relationships may be misleading. We define Extended properties (BTGE, BTPE, BTIE) and analyze which compositions of the original “one-step” properties and the Extended properties are appropriate. This enables providing the new properties with valuable semantics usable, e.g., for fine-grained information retrieval purposes. In addition, we relax some of the constraints assigned to the ISO properties, namely the fact that hierarchical relationships apply to SKOS concepts only. This allows us to apply them to the Getty Art and Architecture Thesaurus (AAT), where they are also used for non-concepts (facets, hierarchy names, guide terms). In this paper, we present extensive examples derived from the recent publication of AAT as linked open data.     

A novel methodology to predict urban traffic congestion with ensemble learning

Urban traffic congestion prediction is a very hot topic due to the environmental and economical impacts that currently implies. In this sense, to be able to predict bottlenecks and to provide alternatives to the circulation of vehicles becomes an essential task for traffic management. A novel methodology, based on ensembles of machine learning algorithms, is proposed to predict traffic congestion in this paper. In particular, a set of seven algorithms of machine learning has been selected to prove their effectiveness in the traffic congestion prediction. Since all the seven algorithms are able to address supervised classification, the methodology has been developed to be used as a binary classification problem. Thus, collected data from sensors located at the Spanish city of Seville are analyzed and models reaching up to 83 % are generated.     

Parallel simulation of Population Dynamics P systems: updates and roadmap

Population Dynamics P systems are a type of multienvironment P systems that serve as a formal modeling framework for real ecosystems. The accurate simulation of these probabilistic models, e.g. with Direct distribution based on Consistent Blocks Algorithm, entails large run times. Hence, parallel platforms such as GPUs have been employed to speedup the simulation. In 2012, the first GPU simulator of PDP systems was presented. However, it was able to run only randomly generated PDP systems. In this paper, we present current updates made on this simulator, involving an input modu le for binary files and an output module for CSV files. Finally, the simulator has been experimentally validated with a real ecosystem model, and its performance has been tested with two high-end GPUs: Tesla C1060 and K40.     

Quantitative mass spectrometry for colorectal cancer proteomics

This review documents the uses of quantitative MS applied to colorectal cancer (CRC) proteomics for biomarker discovery and molecular pathway profiling. Investigators are adopting various labeling and label-free MS approaches to quantitate differential protein levels in cells, tumors, and plasma/serum. We comprehensively review recent uses of this technology to examine mouse models of CRC, CRC cell lines, their secretomes and subcellular fractions, CRC tumors, CRC patient plasma/serum, and stool samples. For biomarker discovery these approaches are uncovering proteins with potential diagnostic and prognostic utility, while in vitro cell culture experiments are characterizing proteomic and phosphoproteomic responses to disrupted signaling pathways due to mutations or to inhibition of drugable enzymes.     

Multi-objective optimization with an adaptive resonance theory-based estimation of distribution algorithm

The introduction of learning to the search mechanisms of optimization algorithms has been nominated as one of the viable approaches when dealing with complex optimization problems, in particular with multi-objective ones. One of the forms of carrying out this hybridization process is by using multi-objective optimization estimation of distribution algorithms (MOEDAs). However, it has been pointed out that current MOEDAs have an intrinsic shortcoming in their model-building algorithms that hamper their performance. In this work, we put forward the argument that error-based learning, the class of learning most commonly used in MOEDAs is responsible for current MOEDA underachievement. We present adaptive resonance theory (ART) as a suitable learning paradigm alternative and present a novel algorithm called multi-objective ART-based EDA (MARTEDA) that uses a Gaussian ART neural network for model-building and a hypervolume-based selector as described for the HypE algorithm. In order to assert the improvement obtained by combining two cutting-edge approaches to optimization an extensive set of experiments are carried out. These experiments also test the scalability of MARTEDA as the number of objective functions increases.     

Evaluating opportunistic networks in disaster scenarios

Forwarding data in scenarios where devices have sporadic connectivity is a challenge. An example scenario is a disaster area, where forwarding information generated in the incident location, like victims' medical data, to a coordination point is critical for quick, accurate and coordinated intervention. New applications are being developed based on mobile devices and wireless opportunistic networks as a solution to destroyed or overused communication networks. But the performance of opportunistic routing methods applied to emergency scenarios is unknown today. In this paper, we compare and contrast the efficiency of the most significant opportunistic routing protocols through simulations in realistic disaster scenarios in order to show how the different characteristics of an emergency scenario impact in the behaviour of each one of them.     

The Economic Impact of Water Evaporation Losses from Water Reservoirs in the Segura Basin,SE Spain

In this paper we assess the economic impact of evaporation losses from great dams (GDs) and on-farm agricultural water reservoirs (AWRs) in the semi-arid Segura River basin, SE Spain. Evaporation losses from water reservoirs reduce the high water use efficiency reached in agriculture by means of other techniques such as well-built water pipes or drip irrigation and have a substantial economic impact. Evaporation losses have been calculated using Class-A pan evaporation data and pan coefficients, whereas their economic impact has been assessed using an economic mathematical programming model that simulates land and water allocation in the different irrigated areas of the basin. Our results show that annual evaporation from GDs and AWRs represents 8.7% of the water currently available for irrigation in the Segura basin. The economic impact of such losses has been estimated in a reduction of 6.3% of the value of agricultural production and 5.4% of the farm net margin. As less water is effectively available for farmers the basin’s irrigated area is reduced in a 7.5%. This impact is greater, in both absolute and relative terms, in the areas accommodating the most intensive and profitable irrigated agriculture. The applied methodology and results could be useful to regional water agencies and collective irrigation schemes for future planning and management, including the assessment of alternatives for reducing evaporation from reservoirs.