Search results

The task of internet intrusion detection is to detect anomalous network connections caused by intrusive activities. There have been many intrusion detection schemes proposed, most of which apply both normal and intrusion data to construct classifiers. However, normal data and intrusion data are often seriously imbalanced because intrusive connection data are usually difficult to collect. Internet intrusion detection can be considered as a novelty detection problem, which is the identification of new or unknown data, to which a learning system has not been exposed during training. This paper aims to address this issue.

In this paper, a novelty detection‐based intrusion detection system is proposed by combining the self‐organizing map (SOM) and the kernel auto‐associator (KAA) model proposed earlier by the first author. The KAA model is a generalization of auto‐associative networks by training to recall the inputs through kernel subspace. For anomaly detection, the SOM organizes the prototypes of samples while the KAA provides data description for the normal connection patterns. The hybrid SOM/KAA model can also be applied to classify different types of attacks.

Using the KDD CUP, 1999 dataset, the performance of the proposed scheme in separating normal connection patterns from intrusive connection patterns was compared with some state‐of‐art novelty detection methods, showing marked improvements in terms of the high intrusion detection accuracy and low false positives. Simulations on the classification of attack categories also demonstrate favorable results of the accuracy, which are comparable to the entries from the KDD CUP, 1999 data mining competition.

The hybrid model of SOM and the KAA model can achieve significant results for intrusion detection.

Content‐based image retrieval (CBIR) is an important research area for automatically retrieving images of user interest from a large database. Due to many potential applications, facial image retrieval has received much attention in recent years. Similar to face recognition, finding appropriate image representation is a vital step for a successful facial image retrieval system. Recently, many efficient image feature descriptors have been proposed and some of them have been applied to face recognition. It is valuable to have comparative studies of different feature descriptors in facial image retrieval. And more importantly, how to fuse multiple features is a significant task which can have a substantial impact on the overall performance of the CBIR system. The purpose of this paper is to propose an efficient face image retrieval strategy.

In this paper, three different feature description methods have been investigated for facial image retrieval, including local binary pattern, curvelet transform and pyramid histogram of oriented gradient. The problem of large dimensionalities of the extracted features is addressed by employing a manifold learning method called spectral regression. A decision level fusion scheme fuzzy aggregation is applied by combining the distance metrics from the respective dimension reduced feature spaces.

Empirical evaluations on several face databases illustrate that dimension reduced features are more efficient for facial retrieval and the fuzzy aggregation fusion scheme can offer much enhanced performance. A 98 per cent rank 1 retrieval accuracy was obtained for the AR faces and 91 per cent for the FERET faces, showing that the method is robust against different variations like pose and occlusion.

The proposed method for facial image retrieval has a promising potential of designing a real‐world system for many applications, particularly in forensics and biometrics.

We investigate whether council audit committees relate to municipal fiscal policies. We find that municipalities with audit committees are associated with greater levels of own-source revenue, in that they finance municipal operations with locally raised revenues driven by charges and fees compared to municipalities without audit committees. Furthermore, municipalities with audit committees are associated with less new debt than those without audit committees, indicating more conservative use of external financing. Overall, our results are consistent with municipal audit committees, in addition to monitoring the financial reporting function, playing an advisory role in fiscal decisions, especially when the cost of local government to citizens is high.

The purpose of this paper is to propose an effective method to perform off‐line signature verification and identification by applying a local shape descriptor pyramid histogram of oriented gradients (PHOGs), which represents local shape of an image by a histogram of edge orientations computed for each image sub‐region, quantized into a number of bins. Each bin in the PHOG histogram represents the number of edges that have orientations within a certain angular range.

Automatic signature verification and identification are then studied in the general binary and multi‐class pattern classification framework, with five different common applied classifiers thoroughly compared.

Simulation experiments show that PHOG has obvious advantages in the extraction of discriminating information from handwriting signature images compared with many previously proposed signature feature extraction approaches. The experiments also demonstrate that several classifiers, including k‐nearest neighbour, multiple layer perceptron and support vector machine (SVM) can all give very satisfactory performance with regard to false acceptance rate (FAR) and false rejection rate (FRR). On a public benchmarking signature database “Grupo de Procesado Digital de Senales” (GPDS), experiments demonstrate an FRR of 4.0 percent and an FAR 3.25 percent from SVM for skillful forgery, which compares sharply with the latest published results of FRR 16.4 percent and FAR 14.2 percent on the same dataset. Experiments on a second DAVAB off‐line signature database also illustrate the superiority of the proposed method. The related issue, off‐line signature recognition, which is to find the identification of the signature owner from a given signature database, is also investigated based on the PHOG features, showing superb classification accuracies of 99 and 96 percent for GPDS and DAVAB datasets, respectively.

The proposed method for off‐line signature verification and recognition has a promising potential of designing a real‐world system for many applications, particularly in forensics and biometrics.

Many applications in intelligent transportation demand accurate categorization of vehicles. The purpose of this paper is to propose a working image-based vehicle classification system. The first component vehicle detection is implemented by applying Dalal and Triggs's histograms of oriented gradients features and linear support vector machine (SVM) classifier. The second component vehicle classification, which is the emphasis of this paper, is accomplished by an improved stacked generalization. As an effective ensemble learning strategy, stacked generalization has been proposed to combine multiple models using the concept of a meta-learner. However, it was found that the well-known meta-learning scheme multi-response linear regression (MLR) for stacked generalization performs poorly on the vehicle classification.

A new meta-learner is then proposed based on kernel principal component regression (KPCR). The stacked generalization scheme consists of a heterogeneous classifier ensemble with seven base classifiers, i.e. linear discriminant classifier, fuzzy k-nearest neighbor, logistic regression, Parzen classifier, Gaussian mixture model, multiple layer perceptron and SVM.

Experimental results using more than 2,500 images from four types of vehicles (bus, light truck, car and van) demonstrated the effectiveness of the proposed approach. The improved stacked generalization produced consistently better results when compared to any of the single base classifier used and four other beta learning algorithms, including MLR, majority voting, logistic regression and decision template.

With the seven base classifiers, the KPCR-based stacking offers a performance of 96 percent accuracy and 95 percent κ coefficient, thus exhibiting promising potentials for real-world applications.

Due to climate change and an increasing concentration of the world’s population in vulnerable areas, how to manage catastrophe risk efficiently and cover disaster losses fairly is still a universal dilemma.

This paper applies a law and economic approach.

China’s mechanism for managing catastrophic disaster risk is in many ways unique. It emphasizes government responsibilities and works well in many respects, especially in disaster emergency relief. Nonetheless, China’s mechanism which has the vestige of a centrally planned economy needs reform.

I propose a catastrophe insurance market-enhancing framework which marries the merits of both the market and government to manage catastrophe risks. There are three pillars of the framework: (i) sustaining a strong and capable government; (ii) government enhancement of the market, neither supplanting nor retarding it; (iii) legalizing the relationship between government and market to prevent government from undermining well-functioning market operations. A catastrophe insurance market-enhancing framework may provide insights for developing catastrophe insurance in China and other transitional nations.

First, this paper analyzes China’s mechanism for managing catastrophic disaster risks and China’s approach which emphasizes government responsibilities will shed light on solving how to manage catastrophe risk efficiently and cover disaster losses fairly. Second, this paper starts a broader discussion about government stimulation of developing catastrophe insurance and this framework can stimulate attention to solve the universal dilemma.

This chapter examines China’s corporate governance and accounting environment that shapes the adoption of internationally acceptable principles and standards. Specifically, it examines international influences, including supranational organizations; foreign investors and international accounting firms; domestic institutional influences, including the political system, economic system, legal system, and cultural system; and accounting infrastructure. China’s convergence is driven by desired efficiency of the corporate sector and legitimacy of participating in the global market. Influenced heavily by international forces in the context of globalization, corporate governance and accounting practices are increasingly becoming in line with internationally acceptable standards and codes. While convergence assists China in obtaining legitimacy, improving efficiency is likely to be adversely affected given that corporate governance and accounting in China operate in an environment that differs considerably from those of Anglo-American countries. An examination of the corporate governance and accounting environment in China suggests heavy government involvement within underdeveloped institutions. While the Chinese government has made impressive progress in developing the corporate governance and accounting environment for the market economy, China’s unique institutional setting is likely to affect how the imported concepts are interpreted and implemented.

This paper examines the effect of restrictions on executive pay and high CEOs’ compensation on bank performance following the “2008 UK bank rescue policy”.

Using the difference-in-difference estimation technique we assess the relationship between executive compensation and financial performance of rescued banks relative to non-rescued banks over the period 1999–2019.

Our main finding indicates that the relationship between executive compensation and financial performance declines in rescued banks relative to non-rescued banks. Further, we document that performance continues to deteriorate in rescued banks relative to non-rescued banks. Our results are robust to different estimation techniques.

This study contributes to the literature that examines the efficacy of government bailouts during the 2008 crisis. To the best of the author’s knowledge, this study is among the first to examine the long-term implications of bank rescue and pay restrictions on executive compensation and performance post–rescue.

This paper aims to examine interbank market practices in a crisis to understand the importance of trust in dealing with control problems and managing risk in inter-organizational relationships (IORs).

A qualitative field study was conducted to collect data from two case-study banks and two key banking industry institutions.

The findings illustrate the use of trust-based partner-selection criteria such as guaranteed banks (i.e., banks granted special status by key banking industry institutions) and “clan-related” banks. In addition, the findings present several trust-based performance-control processes regarding the selected counterparties, such as negative expectations, goodwill and information sharing.

This paper highlights IORs and considers how associated control problems and risks are affected by trust in the context of a large-scale crisis.

The findings provide insights into interbank market practices during the global financial crisis with respect to partner selection and performance control.

The empirical case of the banking industry helps broaden our understanding of inter-IORs.

This study identifies measures to recover economic growth and build sustainable societies and markets in post-COVID-19 scenarios – with a perspective of resilience and adaptability to climate change and massive biodiversity loss. Additionally, this study uncovers the interventions implemented to address economic, environmental and social consequences of past crises based on a systematic literature review. Specifically, this chapter provides answers to the following six questions:

1. What has been done in the past to rebuild social, economic and environmental balance after global crises?

2. Where (geographical region) did the analysis on measures taken concentrate?

3. When have scholars analysed past measures to rebuild business and society after a global crisis?

4. How did the past measures to rebuild business and society after the global crisis take place?

5. Who promotes the measures to rebuild business and society after a global crisis takes place?

6. Why is it important to study the previous literature on past measures to rebuild business and society after a global crisis takes place?

What has been done in the past to rebuild social, economic and environmental balance after global crises?

Where (geographical region) did the analysis on measures taken concentrate?

When have scholars analysed past measures to rebuild business and society after a global crisis?

How did the past measures to rebuild business and society after the global crisis take place?

Who promotes the measures to rebuild business and society after a global crisis takes place?

Why is it important to study the previous literature on past measures to rebuild business and society after a global crisis takes place?

Finally, this chapter identifies future research opportunities to rebuild business and society after the past global crises.