Consumer perception, facts and possibilities to improve acceptability of health and sensory characteristics of pork

Changes at consumer level, as well as an image decline of the meat sector, resulted in considerable decreases of fresh meat consumption. Consumer orientation is considered as a prerequisite to slow down or reverse the adverse fresh pork consumption evolution. Consumer perception of pork is taken as the starting point of this article. Focus is first on assessing differences between facts related to nutritional value and healthiness aspects of pork and their perception by Belgian meat consumers. Second, possibilities of improving pork characteristics are identified. Pork is perceived worst as compared to beef and poultry on the attributes leanness, healthiness, taste and tenderness. Consumer-oriented response strategies should focus at improving these intrinsic quality characteristics, before other elements like traceability, labelling or marketing can be implemented successfully. The possibilities to improve nutritional value, healthiness and sensory characteristics pertain to selection, pig diet composition, transport, slaughter and post-slaughter circumstances. A successful adoption of consumer orientation urges for co-operation throughout the entire pork production chain. The identified topics are key attention points for adequate production and marketing by the pork sector, as well as for consequent communication by government and public services.     

Cost‐sensitive learning and decision making for massachusetts pip claim fraud data

In this article, we investigate the issue of cost‐sensitive classification for a data set of Massachusetts closed personal injury protection (PIP) automobile insurance claims that were previously investigated for suspicion of fraud by domain experts and for which we obtained cost information. After a theoretical exposition on cost‐sensitive learning and decision‐making methods, we then apply these methods to the claims data at hand to contrast the predictive performance of the documented methods for a selection of decision tree and rule learners. We use standard logistic regression and (smoothed) naive Bayes as benchmarks. © 2004 Wiley Periodicals, Inc. Int J Int Syst 19: 1197–1215, 2004.     

Managing for Better Business-IT Alignment

Business-IT alignment is a complex and multidimensional problem that remains among the top-10 issues for many organizations. IT investment decisions usually fall to CIOs, and often the temptation is to base the decision to buy solely on superior technology. Clearly, organizations can gain a competitive advantage by such investments, but basing them only on the bells and whistles of a particular platform is foolhardy. Any competitive advantage would vanish as soon as the next platform enters the market, and the technological edge that the organization had briefly gained would evaporate. There are four themes in securing B-IT alignment: the role of IT, the business case, IT management intensity, and IT metrics, IT's role is important because not all organizations use IT in the same manner. The next three themes are natural intersections for business and IT investment. The business case is important because it determines how business and IT collaborate to justify the IT investment. The degree of IT management intensity both during and after the actual IT investment determines the organization's commitment to continuous process improvement. Finally, IT metrics are critical to demonstrate to business executives IT investment's value-generating potential     

Benchmarking Least Squares Support Vector Machine Classifiers

In Support Vector Machines (SVMs), the solution of the classification problem is characterized by a (convex) quadratic programming (QP) problem. In a modified version of SVMs, called Least Squares SVM classifiers (LS-SVMs), a least squares cost function is proposed so as to obtain a linear set of equations in the dual space. While the SVM classifier has a large margin interpretation, the LS-SVM formulation is related in this paper to a ridge regression approach for classification with binary targets and to Fisher's linear discriminant analysis in the feature space. Multiclass categorization problems are represented by a set of binary classifiers using different output coding schemes. While regularization is used to control the effective number of parameters of the LS-SVM classifier, the sparseness property of SVMs is lost due to the choice of the 2-norm. Sparseness can be imposed in a second stage by gradually pruning the support value spectrum and optimizing the hyperparameters during the sparse approximation procedure. In this paper, twenty public domain benchmark datasets are used to evaluate the test set performance of LS-SVM classifiers with linear, polynomial and radial basis function (RBF) kernels. Both the SVM and LS-SVM classifier with RBF kernel in combination with standard cross-validation procedures for hyperparameter selection achieve comparable test set performances. These SVM and LS-SVM performances are consistently very good when compared to a variety of methods described in the literature including decision tree based algorithms, statistical algorithms and instance based learning methods. We show on ten UCI datasets that the LS-SVM sparse approximation procedure can be successfully applied.     

Identification of peptides, selected by phage display technology, that inhibit von Willebrand factor binding to collagen

A repeated selection of phages from a cyclic hexapeptide phage display library resulted in an enrichment of phages that bound to the monoclonal antibody (MoAb) 82D6A3 (an anti-von Willebrand Factor [vWF] antibody that inhibits binding of vWF to collagen). Two clones were selected that bound both to MoAb 82D6A3 and to rat tail collagen type I in a specific and dose-dependent manner. The two phage clones were further used in a two-direction competition experiment with vWF. vWF was able to displace phages from collagen in a dose-dependent manner with an IC50 of 35 micrograms/mL and phages were able to inhibit vWF binding to collagen. With the use of specific primers, the sequence of the cysteine-flanked hexapeptide inserts could be deduced. The two phage clones carried an almost identical sequence, CVWLWEQC and CVWLWENC, with a substitution of an N for a Q at position 6 of the hexapeptide. Sequence comparison with the known vWF sequence showed the presence of a comparable sequence at position 1129-1136 (VWTLPDQC), located between the collagen-binding A3-domain and the D4-domain. The two cyclic peptides, the putative corresponding vWF peptide, and a peptide with a scrambled cyclic sequence were synthesized. The two cyclic peptides inhibited vWF binding to rat tail collagen type I in a dose-dependent manner, whereas the linear vWF peptide and the scrambled cyclic peptide were inactive. For half maximal inhibition, 100 +/- 12.7 micromol/L and 34.8 +/- 8.59 micromol/L (mean +/- SEM, n = 3) of the N- and the Q-peptide, respectively, were needed. The two cyclic peptides were also able to inhibit vWF binding to calfskin and human collagen type I, but effective concentrations were some 5 to 10 times higher.     

MET15 as a visual selection marker for Candida albicans

To develop better molecular genetic tools for the diploid yeast Candida albicans, the suitability of the MET15 gene as a visual selection marker was studied. Both MET15 alleles of C. albicans CAI-4 were isolated by functional complementation of a Saccharomyces cerevisiae strain lacking the MET15 gene. Growth of this complemented strain on Pb(2+)-containing medium was associated with a colour shift of brown into white colonies. The MET15 alleles of C. albicans were located on chromosome 4 by pulsed-field gel electrophoresis and Southern blotting. A met15-deficient strain of C. albicans CAI-4 was generated using the ura blaster technique. This strain showed a brown colony colour on Pb(2+)-containing medium, which corresponded with the colony colour of a S. cerevisiae strain lacking the MET15 gene. Unexpectedly, the met15-deficient strain of C. albicans still grew on methionine-depleted medium. However, this growth was severely delayed. In addition, complementation of this strain with an integrative or replicative plasmid containing either of the MET15 alleles resulted in the formation of white transformants on Pb(2+)-containing medium. These transformants grew very well on methionine-depleted medium. Colony sectoring was obtained with the replicative plasmid and not with the integrative one. This study demonstrates that the MET15 gene of C. albicans is suitable as a visual marker and therefore can be used to identify transformants and study plasmid stability. GenBank Accession Nos for MET15 nucleotide sequences are AF188273, AF188274 and AF188275.     

Formally analysing the concepts of domestic violence

The types of police inquiries performed these days are incredibly diverse. Often data processing architectures are not suited to cope with this diversity since most of the case data is still stored as unstructured text. In this paper Formal Concept Analysis (FCA) is showcased for its exploratory data analysis capabilities in discovering domestic violence intelligence from a dataset of unstructured police reports filed with the Amsterdam-Amstelland police in the Netherlands. From this data analysis it is shown that FCA can be a powerful instrument to operationally improve policing practice. For one, it is shown that the definition of domestic violence employed by the police is not always as clear as it should be, making it hard to use it effectively for classification purposes. In addition, this paper presents newly discovered knowledge for automatically classifying certain cases as either domestic or non-domestic violence. Moreover, it provides practical advice for detecting incorrect classifications performed by police officers. A final aspect to be discussed is the problems encountered because of the sometimes unstructured way of working of police officers. The added value of this paper resides in both using FCA for exploratory data analysis, as well as with the application of FCA for the detection of domestic violence.     

Knowledge discovery in a direct marketing case using least squares support vector machines

We study the problem of repeat‐purchase modeling in a direct marketing setting using Belgian data. More specifically, we investigate the detection and qualification of the most relevant explanatory variables for predicting purchase incidence. The analysis is based on a wrapped form of input selection using a sensitivity based pruning heuristic to guide a greedy, stepwise, and backward traversal of the input space. For this purpose, we make use of a powerful and promising least squares support vector machine (LS‐SVM) classifier formulation. This study extends beyond the standard recency frequency monetary (RFM) modeling semantics in two ways: (1) by including alternative operationalizations of the RFM variables, and (2) by adding several other (non‐RFM) predictors. Results indicate that elimination of redundant/irrelevant inputs allows significant reduction of model complexity. The empirical findings also highlight the importance of frequency and monetary variables, while the recency variable category seems to be of somewhat lesser importance to the case at hand. Results also point to the added value of including non‐RFM variables for improving customer profiling. More specifically, customer/company interaction, measured using indicators of information requests and complaints, and merchandise returns provide additional predictive power to purchase incidence modeling for database marketing. © 2001 John Wiley & Sons, Inc.     

Inferring comprehensible business/ICT alignment rules

We inferred business rules for business/ICT alignment by applying a novel rule induction algorithm on a data set containing rich alignment information polled from 641 organisations in 7 European countries. The alignment rule set was created using AntMiner+, a rule induction technique with a reputation of inducing accurate, comprehensible, and intuitive predictive models from data. Our data set consisted of 18 alignment practices distilled from an analysis of relevant publications and validated by a Delphi panel of experts. The goal of our study was to describe practical guidelines for managers in obtaining better alignment of ICT investments with business requirements. Our obtained rule set showed the multi-disciplinary nature of B/ICT alignment. We discuss implication of the alignment rules for practitioners.