Journal of Information and Organizational Sciences (JIOS)
Not a member yet
455 research outputs found
Sort by
Two Stage Comparison of Classifier Performances for Highly Imbalanced Datasets
During the process of knowledge discovery in data, imbalanced learning data often emerges and presents a significant challenge for data mining methods. In this paper, we investigate the influence of class imbalanced data on the classification results of artificial intelligence methods, i.e. neural networks and support vector machine, and on the classification results of classical classification methods represented by RIPPER and the Naïve Bayes classifier. All experiments are conducted on 30 different imbalanced datasets obtained from KEEL (Knowledge Extraction based on Evolutionary Learning) repository. With the purpose of measuring the quality of classification, the accuracy and the area under ROC curve (AUC) measures are used. The results of the research indicate that the neural network and support vector machine show improvement of the AUC measure when applied to balanced data, but at the same time, they show the deterioration of results from the aspect of classification accuracy. RIPPER results are also similar, but the changes are of a smaller magnitude, while the results of the Naïve Bayes classifier show overall deterioration of results on balanced distributions. The number of instances in the presented highly imbalanced datasets has significant additional impact on the classification performances of the SVM classifier. The results have shown the potential of the SVM classifier for the ensemble creation on imbalanced datasets
Ontology in Information Security
The past several years we have witnessed that information has become the most precious asset, while protection and security of information is becoming an ever greater challenge due to the large amount of knowledge necessary for organizations to successfully withstand external threats and attacks. This knowledge collected from the domain of information security can be formally described by security ontologies. A large number of researchers during the last decade have dealt with this issue, and in this paper we have tried to identify, analyze and systematize the relevant papers published in scientific journals indexed in selected scientific databases, in period from 2004 to 2014. This paper gives a review of literature in the field of information security ontology and identifies a total of 52 papers systematized in three groups: general security ontologies (12 papers), specific security ontologies (32 papers) and theoretical works (8 papers). The papers were of different quality and level of detail and varied from presentations of simple conceptual ideas to sophisticated frameworks based on ontology
Boosting Ensembles of Heavy Two-Layer Perceptrons for Increasing Classification Accuracy in Recognizing Shifted-Turned-Scaled Flat Images with Binary Features
A method of constructing boosting ensembles of heavy two-layer perceptrons is stated. The benchmark classification problem is recognition of shifted-turned-scaled flat images of a medium format with binary features. The boosting gain is suggested in two aspects. The earliest one is the ratio of minimal recognition error percentage among the ensemble perceptrons to the recognition error percentage performed by the ensemble. The second gain type is the ratio of minimal variance of perceptrons’ recognition error percentages over 26 classes to variance of the ensemble’s recognition error percentages over 26 classes. Both ratios increase as the number of perceptron classifiers in the ensemble increase. The ensemble of 36 classifiers performs with increased accuracy, where recognition error percentage is decreased for 33 %, and the variance is decreased for more than 50 %. Further increment of classifiers into ensemble cannot increase accuracy much as there is the saturation effect of the boosting gain. And the gain itself depends on the range of noise modeling object’s distortions. Thus, the heavier perceptron classifier the less gain is expected
From the Editor
Dear authors, reviewers and readers,you have 39 (2) issue of the Journal of Information and Organizational Sciences in front of you. In this issue you will find seven high quality papers: six original scientific papers and one survey paper. The papers in this issue again cover very different aspects of communication sciences and informatics.I have to address thanks to the authors who have trust in the quality of our Journal and send their papers for publishing, to reviewers who incorporate their knowledge into the improvement of the papers, and to advisory, editorial and publishing boards who make the publishing of the journalpossible.At the end I want to emphasize that from the next issue Journal will have new visual design, which is presented at the end of this issue. I hope that authors will have no problems to adapt their future papers in accordance to it.I wish you a pleasant reading.Alen LovrenčićEdito
Do You Walk the Talk in Quality Culture?
We present an action research project to foster quality culture in business processes. The client setting is in the food industry, a vital sector for our society and one of the most regulated in the world. Food production involves auditing throughout the supply chain and a demanding information system (IS), with numerous requirements grounded on the organizational policies. Our ISO2 approach – for joint development of IS and quality management system (QMS) – was tailored with a set of routines and artifacts to promote quality culture in the maintenance process of the selected organization. This contribution enables a graphical visualization of existing gaps between the high-level principles endorsed by an organization and its confirmation: (1) instantiating company policies at process level; (2) contrasting the assessment of the process owner and of the quality auditor; and (3) comparing the desired and the real practices in a specific business process. An audit from a food retail group confirmed the positive outcome of ISO2 approach in what regards the internalization of quality principles while developing the IS. Moreover, we performed a longitudinal evaluation to verify enduring effects of the ISO2 approach in business processes. We gathered evidence that ISO2 can (1) improve process users’ awareness of quality culture; (2) suggest an approach to increase trust in company policies; and (3) contribute to business process improvements
Individual Entrepreneurial Behavior in Croatian IT Firms: The Contribution of Strategic Thinking Skills
This article addresses the contribution of strategic thinking skills in explaining individual entrepreneurial behavior in Croatian IT firms. Strategic thinking skills were assessed according to entrepreneurs’ use of systems thinking, reflecting, and reframing. Individual entrepreneurial behavior was measured by their inclination towards risk-taking, innovativeness, and proactiveness. Our study of 136 IT entrepreneurs in Croatia confirmed that entrepreneurs with a more developed use of strategic thinking skills exhibit stronger entrepreneurial behaviors. In fact, proactiveness as an element of IEB had a strong relation to all components of strategic thinking skills. Systems thinking as an element of strategic thinking skills showed to be a predictor of all individual entrepreneurial behavior elements
Measuring the Utilization of On-Page Search Engine Optimization in Selected Domain
Search engine optimization (SEO) techniques involve „on-page“ and „off-page“ actions taken by web developers and SEO specialists with aim to increase the ranking of web pages in search engine results pages (SERP) by following recommendations from major search engine companies. In this paper we explore the possibility of creating a metric for evaluating on-page SEO of a website. A novel „k-rank“ metric is proposed which takes into account not only the presence of certain tags in HTML of a page, but how those tags are used with selected keywords in selected domain. The „k-rank“ is tested in domain of education by inspecting 20 university websites and comparing them with expert scores. The overview of results showed that „k-rank“ can be used as a metric for on-page SEO
An Overview of Graph-Based Keyword Extraction Methods and Approaches
The paper surveys methods and approaches for the task of keyword extraction. The systematic review of methods was gathered which resulted in a comprehensive review of existing approaches. Work related to keyword extraction is elaborated for supervised and unsupervised methods, with a special emphasis on graph-based methods. Various graph-based methods are analyzed and compared. The paper provides guidelines for future research plans and encourages the development of new graph-based approaches for keyword extraction
Measuring Public Procurement for Innovation on the Country Level and the Role of ICT Support
Using of public procurement as a tool for promoting innovations has captured interest of many researchers in recent years. However, most of the research is focused on the impact of public procurement on the company's innovativeness. The article discusses the findings of the literature on this topic and proposes a model on how to transfer the concept from the company level to the level of the whole country. One of the biggest problems is unavailability of appropriate measures of this phenomenon, so the authors suggest that the concept of Public procurement for innovation can be approximated by participation of criterion of the most economically advantageous tender (MEAT). Implementation of this criterion in choosing the best offer can be supported and facilitated by using of ICT which can improve the efficiency of procurement process and enable more innovations