Azene Zenebe

User preferences discovery using fuzzy models

User preferences discovery aims to learn the patterns of user preferences for various services or items such as movies. Preferences discovery is essential to the development of intelligent personalization applications. Based on decision and utility theories, traditional approaches to preferences discovery explicitly query users about the behavior of value function, or utility of every outcome with respect to each decision criterion. Consequently, these approaches are generally error-prone and labor intensive. Although implicit elicitation approaches have been proposed to address the above limitations, extent approaches largely ignore multi-valued nature of item features and uncertainty associated with item features and user preferences. To address uncertainty due to vagueness and imprecision, this research proposed a general framework for preferences discovery based on fuzzy set theories. In addition, new fuzzy models were created for preferences discovery and representation. Further, an algorithm was developed to predict user preferences with uncertainty, and visualization of item features, user feedback, and the discovered preferences helped improve the interpretation of the discovered knowledge. The results of the simulation evaluation using a benchmark movie dataset revealed that the proposed preference discovery method: (1) doubled the accuracy of preference discovery as compared to random prediction; and (2) outperformed conventional techniques in making movie recommendation. These findings suggest that fuzzy models are effective for preferences patterns discovery, and personalized recommendation application.

Representation and Reasoning Under Uncertainty in Deception Detection: A Neuro-Fuzzy Approach

An analysis of the process and human cognitive model of deception detection (DD) shows that DD is infused with uncertainty, especially in high-stake situations. There is a recent trend toward automating DD in computer-mediated communication. However, extant approaches to automatic DD overlook the importance of representation and reasoning under uncertainty in DD. They represent uncertain cues as crisp values and can only infer whether deception occurs, but not to what extent deception occurs. Based on uncertainty theories and the analyses of uncertainty in DD, we propose a model to represent cues and to reason for DD under uncertainty, and address the uncertainty due to imprecision and vagueness in DD using fuzzy sets and fuzzy logic. Neuro-fuzzy models were developed to discover knowledge for DD. The evaluation results on five data sets showed that the neuro-fuzzy method not only was a good alternative to traditional machine-learning techniques but also offered superior interpretability and reliability. Moreover, the gains of neuro-fuzzy systems over traditional systems became larger as the level of uncertainty associated with DD increased. The findings of this paper have theoretical, methodological, and practical implications to DD and fuzzy systems research.

Modeling and Handling Uncertainty in Deception Detection

Deception detection (DD) is infused with uncertainty due to vagueness and imprecision. To address the above issue, we developed a Model of Uncertainty in Deception Detection (MUDD) and selected the Neuro-Fuzzy classifier to predict deception. A Neuro-fuzzy model integrates the fuzzy set and logic for handling uncertainty with artificial neural network for learning DD models from the data. The performance of the models was empirically tested with deception data collected from synchronous computer-mediated communication. The results show that the performance of the Neuro-fuzzy model is comparable to that of the best model from the traditional machine learning paradigm. Moreover, they have better interpretability, stability, and reliability. We can draw significant theoretical, mathematical, and practical implications to the deception research from this study.

Relationship between individual's entrepreneurship intention, and adoption and knowledge of information technology and its applications: an empirical study

Entrepreneurial tendency appears to be influenced by individuals’ adoption and knowledge of information technology (IT) and its applications. This is mainly due to the shift in business environment to digital economy and the dependence on IT. Scholars have overlooked the relationships between individuals’ IT adoption and knowledge, and entrepreneurial tendency. This research addresses this gap in the literature. We surveyed 169 students using questionnaire that measures their enterprising tendency, IT knowledge, and IT adoption. The results of correlation analysis showed significant positive relationships between individuals’ entrepreneurial tendency, on the one hand, and their IT knowledge and IT adoption, on the other hand. Furthermore, the results of the analysis of variance revealed significant differences in the relationships by gender and age. The practical implication of this research is that entrepreneurial institutions and development centers need to incorporate IT and its applications at the front end in their effort to train entrepreneurs.

The Influence of Some Macroeconomic Factors on the Growth of Micro Firms in the United States

The purpose of this study was to investigate the influence of some aggregate domes-tic economic forces (i.e., government consumption expenditures and gross Investment; gross private domestic investment and personal consumption expenditures) on the growth of micro firms (businesses with fewer than 20 employees) in the U.S. between the years 1988-2012. The study classified micro firms into three categories (a) firms with employment between 0 and 4 employees, (b) firms with employment between 5 and 9 employees, and (c) firms with employment between 10 and 19 employees. In aggregation, the firms are termed “very small enterprises” by the U.S. Census Bureau. The data for the period 1988-2012 was reviewed, analyzed, and subjected to statistical analysis. It was found that a strong positive correlation exists between each of the aggregate domestic forces and the number of micro-firms in each of the three categories of micro-firms as well as all micro-firms in aggregate. The OLS regression results show all macro variables significantly affecting the growth of micro firms in the size range 10-19 employees. The evidence is more mixed in the other two size categories. The stepwise regression results are more mixed.

Integrating usability and accessibility in information assurance education

One of the emerging challenges in information assurance (IA) is usability and accessibility. Usability refers to the extent in which a security system is easy to learn, remember and use by users; and accessibility refers to the quality of a security system being in situation to be used by all kind of users including those who have specific types of cognitive, physical, or perceptual disabilities. The majority of computer and information security faculty who teach security and assurance courses are not familiar with the topics of usability and accessibility, especially the latter, and do not incorporate these topics into their classes despite that a number of results of research on usability are presented in SOUPS and other HCI conferences. What is lacking is strong effort to integrate these resources into teaching and research. Hence, this project attempts to narrow the gap by building and supporting a national community of faculty members who will integrate usability and accessibility in Information Assurance (IA) education and research.