Set Of Prediction Rules Research Articles

A knowledge resources fusion method based on rough set theory for quality prediction

Quality prediction of the complex surface parts manufacturing process can be automated by designing a knowledge fusion model based on rough set algorithm. Such a model can be constructed by combining qualitative and quantitative knowledge resources modeling, and quality data mining. In this procedure, knowledge fusion model is used to merge knowledge resources in production process into data mining models, which could mine more abundant decision rules for various production conditions. This work exposes the correlation of knowledge resources that fuses in such indiscernibility correlation relation and the function relations. Quality prediction is shown for an operational evaluation processes and a set of prediction rules with varying precision and different structural forms. Results on quality prediction of multi axis milling for large hydraulic turbine blades show that knowledge fusion model alleviates the uncertainty of sample data and improves product quality conversely. Moreover, the prediction method is indeed beneficial to high quality and precision manufacture.

The coordination- and photochemistry of copper(i) complexes: variation of N^N ligands from imidazole to tetrazole.

The prediction of coordination modes is of high importance when structure-property relationships are discussed. Herein, the coordination chemistry of copper(i) with pyridine-amines with a varying number of coordinating N-atoms, namely pyridine-benzimidazole, -triazole and -tetrazole, or their deprotonated analogues, and different phosphines was systematically studied and the photoluminescence properties of all synthesized complexes examined and related to DFT data. Each complex was characterized by single-crystal X-ray analysis and elemental analysis, and a set of prediction rules derived for the coordination chemistry of copper(i) with these ligands. A mononuclear cationic coordination motif was found for PPh3 or DPEPhos with all N^N ligands, which exhibits blue to green luminescence of MLCT character d(Cu) → π*(pyridine-amine ligand) with quantum yields up to 46%. With the deprotonated N^N ligands, mononuclear neutral complexes were only expected with DPEPhos. The emission's nature of this complex type is strongly dependent on the electronic effects of the N^N ligand and was characterized as (ML + IL)CT transition. In contrast to the high quantum yields up to 78% for the tetrazolate complexes (as reported before), the triazolate and imidazolate based complexes show much lower emission efficiencies below 10%. Besides the mononuclear copper(i) complexes, cluster-type complexes were obtained, which show moderate luminescence in the blue to green region of the visible spectrum (469-505 nm).

Determining the Propensity for Academic Dishonesty Using Decision Tree Analysis

This article investigates the propensity for academic dishonesty by university students using the partitioning method of decision tree analysis. A set of prediction rules are presented, and conclusions are drawn. To provide context for the decision tree approach, the partition process is compared with results of more traditional probit regression models. Results of the decision tree analysis complement the probit models in terms of predictive accuracy and confirm results previously found in the literature. In particular, students’ moral character—whether they believe cheating is acceptable—is found to be the most important factor in determining the propensity for academic dishonesty.

Using Data-Driven Rules to Predict Mortality in Severe Community Acquired Pneumonia

Prediction of patient-centered outcomes in hospitals is useful for performance benchmarking, resource allocation, and guidance regarding active treatment and withdrawal of care. Yet, their use by clinicians is limited by the complexity of available tools and amount of data required. We propose to use Disjunctive Normal Forms as a novel approach to predict hospital and 90-day mortality from instance-based patient data, comprising demographic, genetic, and physiologic information in a large cohort of patients admitted with severe community acquired pneumonia. We develop two algorithms to efficiently learn Disjunctive Normal Forms, which yield easy-to-interpret rules that explicitly map data to the outcome of interest. Disjunctive Normal Forms achieve higher prediction performance quality compared to a set of state-of-the-art machine learning models, and unveils insights unavailable with standard methods. Disjunctive Normal Forms constitute an intuitive set of prediction rules that could be easily implemented to predict outcomes and guide criteria-based clinical decision making and clinical trial execution, and thus of greater practical usefulness than currently available prediction tools. The Java implementation of the tool JavaDNF will be publicly available.

Evolutionary decision rules for predicting protein contact maps

Protein structure prediction is currently one of the main open challenges in Bioinformatics. The protein contact map is an useful, and commonly used, representation for protein 3D structure and represents binary proximities (contact or non-contact) between each pair of amino acids of a protein. In this work, we propose a multi-objective evolutionary approach for contact map prediction based on physico-chemical properties of amino acids. The evolutionary algorithm produces a set of decision rules that identifies contacts between amino acids. The rules obtained by the algorithm impose a set of conditions based on amino acid properties to predict contacts. We present results obtained by our approach on four different protein data sets. A statistical study was also performed to extract valid conclusions from the set of prediction rules generated by our algorithm. Results obtained confirm the validity of our proposal.

Redefining the p53 response element

The tumor suppressor p53 is a master transcriptional regulator that affects a diverse range of cellular events. Surprisingly, even with >100 validated p53 response element (RE) sequences available, the effect of p53 binding on transcriptional behavior is seldom predictable and no functional rules have been described. Here, we report a systematic study on the role of specific nucleotides within the p53RE by using p21, a well-known target for p53 activation and contrasting it with Lasp1, a gene recently identified to be repressed by p53. Functional assays revealed a specific dinucleotide core combination within the CWWG motif of the p53RE to be the key factor that determines whether p53 transcriptionally activates or represses a target gene. The triplet RRR and YYY sequences flanking the core CWWG motif were also shown to play an important role in modulating the transcriptional behavior of p53. With the establishment of a set of predictive rules, we were able to reassess 162 published p53REs and showed that the attributed function for 20/162 p53REs studied were in fact erroneous. A significant proportion of p53REs (39/162) were found to be repressive, which is substantially higher than what is currently thought. Hence this clearer definition of the transcriptional behavior of p53 interaction with its RE will provide better insight toward the understanding of its fundamental role in cellular networks.

Problem solution sustenance in XCS: Markov chain analysis of niche support distributions and the impact on computational complexity

Michigan-style learning classifier systems iteratively evolve a distributed solution to a problem in the form of potentially overlapping subsolutions. Each problem niche is covered by subsolutions that are represented by a set of predictive rules, termed classifiers. The genetic algorithm is designed to evolve classifier structures that together cover the whole problem space and represent a complete problem solution. An obvious challenge for such an online evolving, distributed knowledge representation is to continuously sustain all problem subsolutions covering all problem niches, that is, to ensure niche support. Effective niche support depends both on the probability of reproduction and on the probability of deletion of classifiers in a niche. In XCS, reproduction is occurrence-based whereas deletion is support-based. In combination, niche support is assured effectively. In this paper we present a Markov chain analysis of the niche support in XCS, which we validate experimentally. Evaluations in diverse Boolean function settings, which require non-overlapping and overlapping solution structures, support the theoretical derivations. We also consider the effects of mutation and crossover on niche support. With respect to computational complexity, the paper shows that XCS is able to maintain (partially overlapping) niches with a computational effort that is linear in the inverse of the niche occurrence frequency.

Mining user access patterns with traversal constraint for predicting web page requests

The recent increase in HyperText Transfer Protocol (HTTP) traffic on the World Wide Web (WWW) has generated an enormous amount of log records on Web server databases. Applying Web mining techniques on these server log records can discover potentially useful patterns and reveal user access behaviors on the Web site. In this paper, we propose a new approach for mining user access patterns for predicting Web page requests, which consists of two steps. First, the Minimum Reaching Distance (MRD) algorithm is applied to find the distances between the Web pages. Second, the association rule mining technique is applied to form a set of predictive rules, and the MRD information is used to prune the results from the association rule mining process. Experimental results from a real Web data set show that our approach improved the performance over the existing Markov-model approach in precision, recall, and the reduction of user browsing time.

Differing processing requirements of four recombinant antigens containing a single defined T-cell epitope for presentation by major histocompatibility complex class II.

A set of predictive rules governing the likelihood of generating a particular peptide-major histocompatibility complex (MHC) class II complex from an intact antigen has not been fully elucidated. We investigated the influence of positional and structural constraints in the region of the epitope by designing a set of recombinant antigens that each contained the well-characterized T-cell epitope moth cytochrome c (MCC) (88-103), which is specifically recognized by the monoclonal antibody (mAb) D4 when complexed with H-2Ek. Our model antigens contained MCC(88-103) either peripherally, at or towards the C-terminus, or internally. Their abilities to bind directly to soluble H-2Ek, and the extent of D4 epitope formation from them by antigen processing-competent and -incompetent cell lines, were determined. Here we report that three of these four antigens yielded MCC(88-103)/H-2Ek complexes independently of the conventional MHC class II antigen-processing and presentation pathway, and in each case the epitope was carried peripherally; two bound directly as intact proteins, probably as a result of spatial separation of the epitope from the major globular domain, and one was processed to peptide by a cell-surface protease. One protein, which carried the epitope inserted into an internal loop, acted as a conventional processing-dependent MCC(88-103) delivery vehicle. Thus, this epitope has different presentation requirements depending on its context. These antigens constitute a panel whose framework could be modified to further define predictive rules for antigen processing for presentation through the different MHC class II complex-generating pathways.

Developing Prediction Rules and Evaluating Observation Patterns Using Categorical Clinical Markers

Substantial uncertainty often remains at the time that important diagnostic or therapeutic decisions must be made, despite the availability of multiple clinical indicators. Multiple indicators may be used to define observation patterns that are associated with the presence or absence of disease. Clinical prediction rules based on groups of observation patterns have been used to quantify probabilities and reduce error rates for some medical problems, but efficient use of multiple indicators remains a major challenge in medical practice. Medical outcomes and clinical observations are frequently categorical. Two statistical techniques appropriate for generating prediction rules from categorical data are logit analysis (LA) and recursive partitioning analysis (RPA). LA and RPA were compared in evaluating observation patterns for fractures among 666 upper-extremity injuries in children, and in developing prediction rules for selective radiographic assessment. Fracture estimates and error reductions provided by RPA and LA were very similar. Each technique generated a set of prediction rules with a range of misclassification probabilities, and evaluated the probabilities of fracture for all observation patterns. LA used more information than RPA in observation pattern evaluations, however, and provided fracture estimates specific to each pattern. With currently available statistical software, RPA output provides better statistical guidance in generating prediction rules, whereas LA provides more statistical information of use in evaluating observation patterns. LA warrants attention similar to that conferred on RPA. It appears that complementary use of LA and RPA would be valuable in developing clinical guidelines.

Applications of artificial intelligence for chemical inference. Part XI. Analysis of carbon-13 nuclear magnetic resonance data for structure elucidation of acyclic amines

This paper describes a computer program entitled AMINE, which uses a set of predictive rules to deduce the structures of acyclic amines from their empirical formulae and 13C n.m.r. spectra. The results of testing the program on 102 amines indicate that AMINE is quite accurate and selective, even for large amines with many millions of structural isomers, and demonstrate that the computerized analysis of 13C n.m.r. data can be a powerful analytical tool. The logical structure of the program is outlined here, including a section on the general problem of spectrum matching. Generalizations of the methods used by AMINE are suggested.