An overview of the use of neural networks for data mining tasks

In the recent years, the area of data mining has been experiencing considerable demand for technologies that extract knowledge from large and complex data sources. There has been substantial commercial interest as well as active research in the area that aim to develop new and improved approaches for extracting information, relationships, and patterns from large datasets. Artificial neural networks (NNs) are popular biologically-inspired intelligent methodologies, whose classification, prediction, and pattern recognition capabilities have been utilized successfully in many areas, including science, engineering, medicine, business, banking, telecommunication, and many other fields. This paper highlights from a data mining perspective the implementation of NN, using supervised and unsupervised learning, for pattern recognition, classification, prediction, and cluster analysis, and focuses the discussion on their usage in bioinformatics and financial data analysis tasks. © 2012 Wiley Periodicals, Inc.

Trust and relational embeddedness: exploring a paradox of trust pattern development in key supplier relationships

This paper explores the role of trust as an enabler and constraint between buyers and suppliers engaged in long-term relationships. According to the relational view, cooperative strategies require trust-based mutual commitments to co-create value. However, complete pictures of the positive and negative outcomes from trust development have yet to be fully developed. In particular, trust as an originator of path dependent constraints resulting from over embeddedness is yet to be integrated into the relational view. We use a case-based methodology to explore whether trust is an optimizing phenomenon in key supplier relationships. Two cases where trust development processes demonstrate a paradox of trust-building behaviors cultivate different outcomes constraining value co-creation.

The role of hydrological transience in peatland pattern formation

The sloping flanks of peatlands are commonly patterned with non-random, contour-parallel stripes of distinct microhabitats such as hummocks, lawns and hollows. Patterning seems to be governed by feedbacks among peatland hydrological processes, plant micro-succession, plant litter production and peat decomposition. An improved understanding of peatland patterning may provide important insights into broader aspects of the long-term development of peatlands and their likely response to future climate change.

An overview of interactive visual data mining techniques for knowledge discovery

n the past decade, the analysis of data has faced the challenge of dealing with very large and complex datasets and the real-time generation of data. Technologies to store and access these complex and large datasets are in place. However, robust and scalable analysis technologies are needed to extract meaningful information from these datasets. The research field of Information Visualization and Visual Data Analytics addresses this need. Information visualization and data mining are often used complementary to each other. Their common goal is the extraction of meaningful information from complex and possibly large data. However, though data mining focuses on the usage of silicon hardware, visualization techniques also aim to access the powerful image-processing capabilities of the human brain. This article highlights the research on data visualization and visual analytics techniques. Furthermore, we highlight existing visual analytics techniques, systems, and applications including a perspective on the field from the chemical process industry.

Price discovery of credit spreads in tranquil and crisis periods

In this paper we investigate the price discovery process in single-name credit spreads obtained from bond, credit default swap (CDS), equity and equity option prices. We analyse short term price discovery by modelling daily changes in credit spreads in the four markets with a vector autoregressive model (VAR). We also look at price discovery in the long run with a vector error correction model (VECM). We find that in the short term the option market clearly leads the other markets in the sub-prime crisis (2007-2009). During the less severe sovereign debt crisis (2009-2012) and the pre-crisis period, options are still important but CDSs become more prominent. In the long run, deviations from the equilibrium relationship with the option market still lead to adjustments in the credit spreads observed or implied from other markets. However, options no longer dominate price discovery in any of the periods considered. Our findings have implications for traders, credit risk managers and financial regulators.

Grouping of 24 apple cultivars on the basis of starch degradation rate and their fruit pattern

The ripening processes of 24 apple cultivars were examined in the United Kingdom National Fruit Collection in 2010. Basically the starch content, and additionally ground colour, water-soluble solids content and flesh firmness were studied during ripening. The degradation of the starch content was evaluated using a 0–10 scale. A starch degradation value of 50% was taken to be the optimum harvest date, with harvest beginning at a value of 40% and finishing at 60%. Depending on the cultivar, this represented a harvest window of 9 to 21 days. Later ripening cultivars matured more slowly, leading to a longer harvesting period, with the exception of cv. Feuillemorte. Pronounced differences were observed among the cultivars on the basis of the starch degradation pattern, allowing them to be divided into four groups. Separate charts were elaborated for each group that are recommended for use in practice.

Problems with binary pattern measures for flood model evaluation

As the calibration and evaluation of flood inundation models are a prerequisite for their successful application, there is a clear need to ensure that the performance measures that quantify how well models match the available observations are fit for purpose. This paper evaluates the binary pattern performance measures that are frequently used to compare flood inundation models with observations of flood extent. This evaluation considers whether these measures are able to calibrate and evaluate model predictions in a credible and consistent way, i.e. identifying the underlying model behaviour for a number of different purposes such as comparing models of floods of different magnitudes or on different catchments. Through theoretical examples, it is shown that the binary pattern measures are not consistent for floods of different sizes, such that for the same vertical error in water level, a model of a flood of large magnitude appears to perform better than a model of a smaller magnitude flood. Further, the commonly used Critical Success Index (usually referred to as F<2 >) is biased in favour of overprediction of the flood extent, and is also biased towards correctly predicting areas of the domain with smaller topographic gradients. Consequently, it is recommended that future studies consider carefully the implications of reporting conclusions using these performance measures. Additionally, future research should consider whether a more robust and consistent analysis could be achieved by using elevation comparison methods instead.

MALDI mass spectrometry in prostate cancer biomarker discovery

Matrix-assisted laser desorption/ionisation (MALDI) mass spectrometry (MS) is a highly versatile and sensitive analytical technique, which is known for its soft ionisation of biomolecules such as peptides and proteins. Generally, MALDI MS analysis requires little sample preparation, and in some cases like MS profiling it can be automated through the use of robotic liquid-handling systems. For more than a decade now, MALDI MS has been extensively utilised in the search for biomarkers that could aid clinicians in diagnosis, prognosis, and treatment decision making. This review examines the various MALDI-based MS techniques like MS imaging, MS profiling and proteomics in-depth analysis where MALDI MS follows fractionation and separation methods such as gel electrophoresis, and how these have contributed to prostate cancer biomarker research. This article is part of a Special Issue entitled: Biomarkers: A Proteomic Challenge.

Collaborative personal profiling for web service ranking and recommendation

Web service is one of the most fundamental technologies in implementing service oriented architecture (SOA) based applications. One essential challenge related to web service is to find suitable candidates with regard to web service consumer’s requests, which is normally called web service discovery. During a web service discovery protocol, it is expected that the consumer will find it hard to distinguish which ones are more suitable in the retrieval set, thereby making selection of web services a critical task. In this paper, inspired by the idea that the service composition pattern is significant hint for service selection, a personal profiling mechanism is proposed to improve ranking and recommendation performance. Since service selection is highly dependent on the composition process, personal knowledge is accumulated from previous service composition process and shared via collaborative filtering where a set of users with similar interest will be firstly identified. Afterwards a web service re-ranking mechanism is employed for personalised recommendation. Experimental studies are conduced and analysed to demonstrate the promising potential of this research.

Attribution of the spatial pattern of CO2-forced sea level change to ocean surface flux changes

Climate models taking part in the coupled model intercomparison project phase 5 (CMIP5) all predict a global mean sea level rise for the 21st century. Yet the sea level change is not spatially uniform and differs among models. Here we evaluate the role of air–sea fluxes of heat, water and momentum (windstress) to find the spatial pattern associated to each of them as well as the spread they can account for. Using one AOGCM to which we apply the surface flux changes from other AOGCMs, we show that the heat flux and windstress changes dominate both the pattern and the spread, but taking the freshwater flux into account as well yields a sea level change pattern in better agreement with the CMIP5 ensemble mean. Differences among the CMIP5 control ocean temperature fields have a smaller impact on the sea level change pattern.

Information analytics for healthcare service discovery

The concept of being ‘patient-centric’ is a challenge to many existing healthcare service provision practices. This paper focuses on the issue of referrals, where multiple stakeholders, i.e. general practitioners and patients, are encouraged to make a consensual decision based on patient needs. In this paper, we present an ontology-enabled healthcare service provision, which facilitates both patients and GPs in jointly deciding upon the referral decision. In the healthcare service provision model, we define three types of profile, which represents different stakeholders’ requirements. This model also comprises of a set of healthcare service discovery processes: articulating a service need, matching the need with the healthcare service offerings, and deciding on a best-fit service for acceptance. As a result, the healthcare service provision can carry out coherent analysis using personalised information and iterative processes that deal with requirements change over time.

Hierarchical clustering based web service discovery

This paper presents a hierarchical clustering method for semantic Web service discovery. This method aims to improve the accuracy and efficiency of the traditional service discovery using vector space model. The Web service is converted into a standard vector format through the Web service description document. With the help of WordNet, a semantic analysis is conducted to reduce the dimension of the term vector and to make semantic expansion to meet the user’s service request. The process and algorithm of hierarchical clustering based semantic Web service discovery is discussed. Validation is carried out on the dataset.

Discovery of a mammalian splice variant of myostatin that stimulates myogenesis

Myostatin plays a fundamental role in regulating the size of skeletal muscles. To date, only a single myostatin gene and no splice variants have been identified in mammals. Here we describe the splicing of a cryptic intron that removes the coding sequence for the receptor binding moiety of sheep myostatin. The deduced polypeptide sequence of the myostatin splice variant (MSV) contains a 256 amino acid N-terminal domain, which is common to myostatin, and a unique C-terminus of 65 amino acids. Western immunoblotting demonstrated that MSV mRNA is translated into protein, which is present in skeletal muscles. To determine the biological role of MSV, we developed an MSV over-expressing C2C12 myoblast line and showed that it proliferated faster than that of the control line in association with an increased abundance of the CDK2/Cyclin E complex in the nucleus. Recombinant protein made for the novel C-terminus of MSV also stimulated myoblast proliferation and bound to myostatin with high affinity as determined by surface plasmon resonance assay. Therefore, we postulated that MSV functions as a binding protein and antagonist of myostatin. Consistent with our postulate, myostatin protein was co-immunoprecipitated from skeletal muscle extracts with an MSV-specific antibody. MSV over-expression in C2C12 myoblasts blocked myostatin-induced Smad2/3-dependent signaling, thereby confirming that MSV antagonizes the canonical myostatin pathway. Furthermore, MSV over expression increased the abundance of MyoD, Myogenin and MRF4 proteins (P,0.05), which indicates that MSV stimulates myogenesis through the induction of myogenic regulatory factors. To help elucidate a possible role in vivo, we observed that MSV protein was more abundant during early post-natal muscle development, while myostatin remained unchanged, which suggests that MSV may promote the growth of skeletal muscles. We conclude that MSV represents a unique example of intra-genic regulation in which a splice variant directly antagonizes the biological activity of the canonical gene product.

Relationship of dayside auroral precipitations to the open-closed separatrix and the pattern of convective flow

The implications are discussed of acceleration of magnetospheric ions by reflection off two magnetopause Alfvén waves, launched by the reconnection site into the inflow regions on both sides of the boundary. The effects of these waves on the ion populations, predicted using the model described by Lockwood et al. [1996], offer a physical interpretation of all the various widely used classifications of precipitation into the dayside ionosphere, namely, central plasma sheet, dayside boundary plasma sheet (BPS), void, low-latitude boundary layer (LLBL), cusp, mantle, and polar cap. The location of the open-closed boundary and the form of the convection flow pattern are discussed in relation to the regions in which these various precipitations are typically found. Specifically, the model predicts that both the LLBL and the dayside BPS precipitations are on newly opened field lines and places the convection reversal within the LLBL, as is often observed. It is shown that this offers solutions to a number of paradoxes and problems that arise if the LLBL and BPS precipitations are thought of as being on closed field lines. This model is also used to make quantitive predictions of the longitudinal extent and latitudinal width of the cusp, as a function of solar wind density.