Search results

1 – 10 of 235
Per page
102050
Citations:
Loading...
Access Restricted. View access options
Article
Publication date: 1 March 1981

RICHARD FORSYTH

BEAGLE (Biological Evolutionary Algorithm Generating Logical Expressions) is a computer package for producing decision‐rules by induction from a database. It works on the…

108

Abstract

BEAGLE (Biological Evolutionary Algorithm Generating Logical Expressions) is a computer package for producing decision‐rules by induction from a database. It works on the principle of “Naturalistic Selection” whereby rules that fit the data badly are “killed off” and replaced by “mutations” of better rules or by new rules created by “mating” two better adapted rules. The rules are Boolean expressions represented by tree structures. The software consists of two Pascal programs, HERB (Heuristic Evolutionary Rule Breeder) and LEAF (Logical Evaluator And Forecaster). HERB improves a given starting set of rules by running over several simulated generations. LEAF uses the rules to classify samples from a database where the correct membership may not be known. Preliminary tests on three different databases have been carried out—on hospital admissions (classing heart patients as deaths or survivors), on athletic physique (classing Olympic finalists as long‐distance runners or sprinters) and on football results (categorizing games into draws and non‐draws). It appears from the tests that the method works better than the standard discriminant analysis technique based on a linear discriminant function, and hence that this long‐neglected approach warrants further investigation.

Details

Kybernetes, vol. 10 no. 3
Type: Research Article
ISSN: 0368-492X

Access Restricted. View access options
Article
Publication date: 1 May 1984

Richard Forsyth

With the dramatic rise of Expert Systems has come a renewed interest in the ‘fuel’ that drives them—knowledge. For it is specialist knowledge which gives Expert Systems their…

202

Abstract

With the dramatic rise of Expert Systems has come a renewed interest in the ‘fuel’ that drives them—knowledge. For it is specialist knowledge which gives Expert Systems their power. But extracting knowledge from human experts in symbolic form has proved arduous and labour‐intensive. So the idea of machine learning is enjoying a renaissance.

Details

Aslib Proceedings, vol. 36 no. 5
Type: Research Article
ISSN: 0001-253X

Access Restricted. View access options
Article
Publication date: 1 March 1978

P.J. Sallis

Apart from functional details, the book makes two general points. The first refers to the growing usefulness of BASIC as a programming language for beginners. The author points to…

23

Abstract

Apart from functional details, the book makes two general points. The first refers to the growing usefulness of BASIC as a programming language for beginners. The author points to the increase in availability of micro‐computers and their almost universal use of BASIC as the user language. This indicates, he assumes, that BASIC will become even more widely used by non‐professional programmers. The second point is an inferental one leading from the first. That is, if BASIC has a continuing or even increasing usefulness for non‐professionals who want to have some grasp of a complete language, then it is probably suitable for students of librarianship who are in just that category. At advanced levels of appreciation it may be that BASIC has its limitations for use with library applications, but where time to teach this subject is short and the need is specific, BASIC is ideal. This is the general argument of the author.

Details

Program, vol. 12 no. 3
Type: Research Article
ISSN: 0033-0337

Access Restricted. View access options
Article
Publication date: 1 January 1986

Emerson Hilker

We have long been obsessed with the dream of creating intelligent machines. This vision can be traced back to Greek civilization, and the notion that mortals somehow can create…

2051

Abstract

We have long been obsessed with the dream of creating intelligent machines. This vision can be traced back to Greek civilization, and the notion that mortals somehow can create machines that think has persisted throughout history. Until this decade these illusions have borne no substance. The birth of the computer in the 1940s did cause a resurgence of the cybernaut idea, but the computer's role was primarily one of number‐crunching and realists soon came to respect the enormous difficulties in crafting machines that could accomplish even the simplest of human tasks.

Details

Collection Building, vol. 7 no. 3
Type: Research Article
ISSN: 0160-4953

Access Restricted. View access options
Article
Publication date: 1 January 1988

ROY RADA, HAFEDH MILI, GARY LETOURNEAU and DOUG JOHNSTON

An indexing language is made more accessible to searchers and indexers by the presence of entry terms or near‐synonyms. This paper first presents an evaluation of existing entry…

91

Abstract

An indexing language is made more accessible to searchers and indexers by the presence of entry terms or near‐synonyms. This paper first presents an evaluation of existing entry terms and then presents and tests a strategy for creating entry terms. The key tools in the evaluation of the entry terms are documents already indexed into the Medical Subject Headings (MeSH) and an automatic indexer. If the automatic indexer can better map the title to the index terms with the use of entry terms than without entry terms, then the entry terms have helped. Sensitive assessment of the automatic indexer requires the introduction of measures of conceptual closeness between the computer and human output. With the tools described in this paper, one can systematically demonstrate that certain entry terms have ambiguous meanings. In the selection of new entry terms another controlled vocabulary or thesaurus, called the Systematized Nomenclature of Medicine (SNOMED), was consulted. An algorithm for mapping terms from SNOMED to MeSH was implemented and evaluated with the automatic indexer. The new SNOMED‐based entry terms did not help indexing but did show how new concepts might be identified which would constitute meaningful amendments to MeSH. Finally, an improved algorithm for combining two thesauri was applied to the Computing Reviews Classification Structure (CRCS) and MeSH. CRCS plus MeSH supported better indexing than did MeSH alone.

Details

Journal of Documentation, vol. 44 no. 1
Type: Research Article
ISSN: 0022-0418

Available. Content available
Article
Publication date: 13 February 2007

Stuart Hannabuss

167

Abstract

Details

Library Review, vol. 56 no. 1
Type: Research Article
ISSN: 0024-2535

Keywords

Access Restricted. View access options
Article
Publication date: 28 July 2020

Sathyaraj R, Ramanathan L, Lavanya K, Balasubramanian V and Saira Banu J

The innovation in big data is increasing day by day in such a way that the conventional software tools face several problems in managing the big data. Moreover, the occurrence of…

187

Abstract

Purpose

The innovation in big data is increasing day by day in such a way that the conventional software tools face several problems in managing the big data. Moreover, the occurrence of the imbalance data in the massive data sets is a major constraint to the research industry.

Design/methodology/approach

The purpose of the paper is to introduce a big data classification technique using the MapReduce framework based on an optimization algorithm. The big data classification is enabled using the MapReduce framework, which utilizes the proposed optimization algorithm, named chicken-based bacterial foraging (CBF) algorithm. The proposed algorithm is generated by integrating the bacterial foraging optimization (BFO) algorithm with the cat swarm optimization (CSO) algorithm. The proposed model executes the process in two stages, namely, training and testing phases. In the training phase, the big data that is produced from different distributed sources is subjected to parallel processing using the mappers in the mapper phase, which perform the preprocessing and feature selection based on the proposed CBF algorithm. The preprocessing step eliminates the redundant and inconsistent data, whereas the feature section step is done on the preprocessed data for extracting the significant features from the data, to provide improved classification accuracy. The selected features are fed into the reducer for data classification using the deep belief network (DBN) classifier, which is trained using the proposed CBF algorithm such that the data are classified into various classes, and finally, at the end of the training process, the individual reducers present the trained models. Thus, the incremental data are handled effectively based on the training model in the training phase. In the testing phase, the incremental data are taken and split into different subsets and fed into the different mappers for the classification. Each mapper contains a trained model which is obtained from the training phase. The trained model is utilized for classifying the incremental data. After classification, the output obtained from each mapper is fused and fed into the reducer for the classification.

Findings

The maximum accuracy and Jaccard coefficient are obtained using the epileptic seizure recognition database. The proposed CBF-DBN produces a maximal accuracy value of 91.129%, whereas the accuracy values of the existing neural network (NN), DBN, naive Bayes classifier-term frequency–inverse document frequency (NBC-TFIDF) are 82.894%, 86.184% and 86.512%, respectively. The Jaccard coefficient of the proposed CBF-DBN produces a maximal Jaccard coefficient value of 88.928%, whereas the Jaccard coefficient values of the existing NN, DBN, NBC-TFIDF are 75.891%, 79.850% and 81.103%, respectively.

Originality/value

In this paper, a big data classification method is proposed for categorizing massive data sets for meeting the constraints of huge data. The big data classification is performed on the MapReduce framework based on training and testing phases in such a way that the data are handled in parallel at the same time. In the training phase, the big data is obtained and partitioned into different subsets of data and fed into the mapper. In the mapper, the features extraction step is performed for extracting the significant features. The obtained features are subjected to the reducers for classifying the data using the obtained features. The DBN classifier is utilized for the classification wherein the DBN is trained using the proposed CBF algorithm. The trained model is obtained as an output after the classification. In the testing phase, the incremental data are considered for the classification. New data are first split into subsets and fed into the mapper for classification. The trained models obtained from the training phase are used for the classification. The classified results from each mapper are fused and fed into the reducer for the classification of big data.

Details

Data Technologies and Applications, vol. 55 no. 3
Type: Research Article
ISSN: 2514-9288

Keywords

Access Restricted. View access options
Article
Publication date: 24 December 2024

Jillian Alderman, Joetta Forsyth, Charla Griffy-Brown and Richard Walton

This study explores the relationship between US public firms’ dividend policies and CEO selection. Specifically, we examine the association between successor CEOs’ prior…

6

Abstract

Purpose

This study explores the relationship between US public firms’ dividend policies and CEO selection. Specifically, we examine the association between successor CEOs’ prior employment and firms’ payout policies around CEO turnover events.

Design/methodology/approach

Using Execucomp, we identify a sample of 1,021 S&P 1500 firms with CEO turnover events occurring from 2010 to 2016. We categorize successor CEOs by their prior position as a public insider (hired internally from the public firm), public outsider (hired from a different public firm) or private outsider (hired from a private firm). We investigate dividend policies around CEO turnovers using differences-in-means and probit analyses.

Findings

Firms that hired private CEOs were 11.0% less likely to have paid a dividend in the year prior to the CEO turnover. However, those firms that had paid a dividend in the prior year were 5.4% more likely to subsequently drop their dividend. This finding supports a distinct effect that is related to the successor CEOs’ prior experience managing private firms, rather than an “outsider” effect: payout policies of firms that hired public outsiders were no different from those that hired public insiders.

Originality/value

We show that public firms that hire private CEOs tend to have dividend policies similar to those of private firms. This evidence suggests that human capital developed at private firms is applied when CEOs transfer to public firms. We show that outsiders from public firms behave differently from outsiders from private firms, and we are the first to measure the frequency of each kind of CEO successor: public insiders, public outsiders and private outsiders. These findings suggest a method to indirectly study private firms using more readily available data from public firms led by private CEOs.

Details

Managerial Finance, vol. ahead-of-print no. ahead-of-print
Type: Research Article
ISSN: 0307-4358

Keywords

Access Restricted. View access options
Article
Publication date: 12 June 2009

Caroline Ritchie, Felix Ritchie and Richard Ward

The purpose of this paper is to investigate drinking patterns; attitudes towards alcohol consumption and alcohol‐related behaviours amongst differing groups of young adults. A…

2023

Abstract

Purpose

The purpose of this paper is to investigate drinking patterns; attitudes towards alcohol consumption and alcohol‐related behaviours amongst differing groups of young adults. A further aim is to investigate whether the drinking behaviours of undergraduate populations can be considered to be representative of young adult behaviours in general.

Design/methodology/approach

Four groups of young adult alcohol consumers are identified. The participants in the first two groups are aged between 18 and 23, one group being undergraduates and the second non‐graduates in work. Participants in the second two groups are aged between 24 and 29, one group comprising graduates in work, the second non‐graduates in work. 120 questionnaires were completed; 30 in each sample group, with an even gender distribution. Follow up one‐to‐one interviews are carried out with representatives from each group.

Findings

Although a small study it is evident that whilst there are some similarities in behaviours between the differing sample groups significant differences in alcohol‐related behaviours dominate.

Practical implications

The results suggest that utilising the results of research carried out amongst student populations to inform government policies with regard to the behaviour of young adults in general is unlikely to be successful in changing drinking behaviours.

Originality/value

This paper produces new insights into current drinking cultures and attitudes towards drinking in differing groups of young adults. Specifically, it compares behavioural norms between graduate and non‐graduate populations challenging much current research which is based upon student samples as being representative of the young adult population as a whole.

Details

Worldwide Hospitality and Tourism Themes, vol. 1 no. 2
Type: Research Article
ISSN: 1755-4217

Keywords

Access Restricted. View access options
Article
Publication date: 1 January 1978

WAYNE K. HOY, C.J. TARTER and PATRICK FORSYTH

The theoretical and practical significance of the concept of subordinate loyalty to immediate superior is developed, and then, an empirical exploration of administration behavior…

118

Abstract

The theoretical and practical significance of the concept of subordinate loyalty to immediate superior is developed, and then, an empirical exploration of administration behavior that best predicts subordinate loyalty to elementary and secondary principals is undertaken. Data were collected from the principals and faculties in eighty public schools. Those characteristics of principal behavior accounting for the greatest explanation of loyalty are Thrust, Consideration, Initiating Structure, and Nonauthoritarianism; however, somewhat contrasting profiles emerge in predicting teacher loyalty in elementary and secondary schools. While Initiating Structure of the principal has high value in the secondary schools, it is Consideration, not Initiating Structure, which is most salient in elementary schools.

Details

Journal of Educational Administration, vol. 16 no. 1
Type: Research Article
ISSN: 0957-8234

1 – 10 of 235
Per page
102050