Jin-Xing Hao

A new approach to intrusion detection using Artificial Neural Networks and fuzzy clustering

Many researches have argued that Artificial Neural Networks (ANNs) can improve the performance of intrusion detection systems (IDS) when compared with traditional methods. However for ANN-based IDS, detection precision, especially for low-frequent attacks, and detection stability are still needed to be enhanced. In this paper, we propose a new approach, called FC-ANN, based on ANN and fuzzy clustering, to solve the problem and help IDS achieve higher detection rate, less false positive rate and stronger stability. The general procedure of FC-ANN is as follows: firstly fuzzy clustering technique is used to generate different training subsets. Subsequently, based on different training subsets, different ANN models are trained to formulate different base models. Finally, a meta-learner, fuzzy aggregation module, is employed to aggregate these results. Experimental results on the KDD CUP 1999 dataset show that our proposed new approach, FC-ANN, outperforms BPNN and other well-known methods such as decision tree, the naive Bayes in terms of detection precision and detection stability.

A comparative assessment of ensemble learning for credit scoring

Both statistical techniques and Artificial Intelligence (AI) techniques have been explored for credit scoring, an important finance activity. Although there are no consistent conclusions on which ones are better, recent studies suggest combining multiple classifiers, i.e., ensemble learning, may have a better performance. In this study, we conduct a comparative assessment of the performance of three popular ensemble methods, i.e., Bagging, Boosting, and Stacking, based on four base learners, i.e., Logistic Regression Analysis (LRA), Decision Tree (DT), Artificial Neural Network (ANN) and Support Vector Machine (SVM). Experimental results reveal that the three ensemble methods can substantially improve individual base learners. In particular, Bagging performs better than Boosting across all credit datasets. Stacking and Bagging DT in our experiments, get the best performance in terms of average accuracy, type I error and type II error.

Toward a Fuzzy Domain Ontology Extraction Method for Adaptive e-Learning

With the widespread applications of electronic learning (e-Learning) technologies to education at all levels, increasing number of online educational resources and messages are generated from the corresponding e-Learning environments. Nevertheless, it is quite difficult, if not totally impossible, for instructors to read through and analyze the online messages to predict the progress of their students on the fly. The main contribution of this paper is the illustration of a novel concept map generation mechanism which is underpinned by a fuzzy domain ontology extraction algorithm. The proposed mechanism can automatically construct concept maps based on the messages posted to online discussion forums. By browsing the concept maps, instructors can quickly identify the progress of their students and adjust the pedagogical sequence on the fly. Our initial experimental results reveal that the accuracy and the quality of the automatically generated concept maps are promising. Our research work opens the door to the development and application of intelligent software tools to enhance e-Learning.

A multilevel model for effects of social capital and knowledge sharing in knowledge-intensive work teams

Abstract Although it is a widely held belief that social capital facilitates knowledge sharing among individuals, there is little research that has deeply investigated the impacts of social capital at different levels on an individuals knowledge sharing behavior. To address this research gap, this study combines a multilevel approach and an optimal network configuration view to investigate the multilevel effects of social capital on individuals’ knowledge sharing in knowledge intensive work teams. This study makes a distinction between the social capital at the team-level and that of social capital at the individual level to examine their cross-level and direct effects on an individuals sharing of explicit and tacit knowledge. A survey involving 343 participants in 47 knowledge-intensive teams was conducted for testing the multilevel model. The results reveal that social capital at both levels jointly influences an individuals explicit and tacit knowledge sharing. Further, when individuals possess a moderate betweenness centrality and the whole team holds a moderate network density, team members’ knowledge sharing can be maximized. These findings offer a more comprehensive and precise understanding of the multilevel impacts of social capital on team members’ knowledge sharing behavior, thus contributing to the social capital theory, as well as knowledge management research and practices.

Combining social network and semantic concept analysis for personalized academic researcher recommendation

The rapid proliferation of information technologies especially Web 2.0 techniques has changed the fundamental ways how things can be done in many areas, including how researchers could communicate and collaborate with each other. The presence of the sheer volume of researchers and research information on the Web has led to the problem of information overload. There is a pressing need to develop researcher recommendation agents such that users can be provided with personalized recommendations of the researchers they can potentially collaborate with for mutual research benefits. In academic contexts, recommending suitable research partners to researchers can facilitate knowledge discovery and exchange, and ultimately improve the research productivity of researchers. Existing expertise recommendation research usually investigates the expert recommending problem from two independent dimensions, namely, their social relations and expertise information. The main contribution of this paper is that we propose a network based researcher recommendation approach which combines social network analysis and semantic concept analysis in a unified framework to improve the effectiveness of personalized researcher recommendation. The results of our experiment show that the proposed approach significantly outperforms the other baseline methods. Moreover, how our proposed framework can be applied to the real-world academic contexts is explained based on a case study.

A comparative study of two automatic document classification methods in a library setting

In current library practice, trained human experts usually carry out document cataloguing and indexing based on a manual approach. With the explosive growth in the number of electronic documents available on the Internet and digital libraries, it is increasingly difficult for library practitioners to categorize both electronic documents and traditional library materials using just a manual approach. To improve the effectiveness and efficiency of document categorization at the library setting, more in-depth studies of using automatic document classification methods to categorize library items are required. Machine learning research has advanced rapidly in recent years. However, applying machine learning techniques to improve library practice is still a relatively unexplored area. This paper illustrates the design and development of a machine learning based automatic document classification system to alleviate the manual categorization problem encountered within the library setting. Two supervised machine learning algorithms have been tested. Our empirical tests show that supervised machine learning algorithms in general, and the k-nearest neighbours (KNN) algorithm in particular, can be used to develop an effective document classification system to enhance current library practice. Moreover, some concrete recommendations regarding how to practically apply the KNN algorithm to develop automatic document classification in a library setting are made. To our best knowledge, this is the first in-depth study of applying the KNN algorithm to automatic document classification based on the widely used LCC classification scheme adopted by many large libraries.

Towards Context-Sensitive Domain Ontology Extraction

Although there has been a surge of interest in applying domain ontologies to facilitate communications among computers and human users, engineering of these ontologies turns out to be very labor intensive and time consuming. Recently, some learning methods have been proposed for automatic or semi-automatic extraction of ontologies. Nevertheless, the accuracy and computational efficiency of these methods should be improved to support large scale ontology extraction for real-world applications. This paper illustrates a novel domain ontology extraction method. In particular, contextual information of the knowledge sources is exploited for the extraction of high quality domain ontologies. By combining lexico-syntactic and statistical learning approaches, the accuracy and the computational efficiency of the extraction process can be improved. Empirical studies have confirmed that the proposed method can extract reliable domain ontology to improve the performance of information retrieval and facilitate human users to discover and refine domain ontology

The effect of social media on tourism destination marketing: A media-synchronicity-theory based exploration

Nowadays social media are increasingly used in tourism destination marketing. In this paper, we first analyze the distinctive features of social media, i.e., Sociability, Mobility, and Purposiveness. Based on Media synchronicity theory (MST), we then redefine the marketing as a series of communication processes, and elaborate the features of social media on supporting their synchronicity with tourism destination marketing. The main objectives of this study is to explore the effects of social median on tourism destination marketing, and the study entails important theoretical and practical contributions to enhance our understanding of why social media are used in tourism destination marketing, as well as when and how they should be used.

Mapping smart tourism research in China: A semantic and social network analysis using CiteSpace

Understanding how domain knowledge grows and evolves over time is critical to innovation in science and technology. In this study, a knowledge domain of smart tourism research in China is visually mapped through CiteSpace by a combination of semantic network analysis of research subjects and social network analysis of collaboration research network. Smart tourism related literature was collected from the leading scientific literature database CNKI in China. The results reveal the thematic patterns and emerging trends in research of smart tourism in China. The results also identify the influential smart tourism research institutes and scholars in China. The combination of semantic and social network analysis can provide a complete innovation landscape of an emerging field of science. Practical and theoretical implications are also discussed.

Comparisons of word representations for convolutional neural network: An exploratory study on tourism Weibo classification

Word representations, which are critical to the performance of convolutional neural network, has attracted considerable attention from many researchers. Two popular categories of word representations for convolutional neural network are the pre-trained representation, which requires training on external web documents, and the internal presentation, which relies on the internal text features. Although prior studies always claim that their models are better than previous ones based on various evaluation criteria, very little research compares the two categories of word representations. In this study, we reported our initial attempt to compare the two categories of word representation models for conventional neural network in the context of tourism Weibo classification. We have designed two experiments to examine their differences on classification performance. Results show that the performance of the pre-trained representation depends on the domain and the size of the training corpus, while the performance of the internal representation without the training process, can achieve equivalent performance for the domain of tourism Weibo classification. We also discussed the theoretical and practical implications for this study.