Lee McCluskey

Predicting phishing websites based on self-structuring neural network

AbstractInternet has become an essential component of our everyday social and financial activities. Nevertheless, internet users may be vulnerable to different types of web threats, which may cause financial damages, identity theft, loss of private information, brand reputation damage and loss of customer’s confidence in e-commerce and online banking. Phishing is considered as a form of web threats that is defined as the art of impersonating a website of an honest enterprise aiming to obtain confidential information such as usernames, passwords and social security number. So far, there is no single solution that can capture every phishing attack. In this article, we proposed an intelligent model for predicting phishing attacks based on artificial neural network particularly self-structuring neural networks. Phishing is a continuous problem where features significant in determining the type of web pages are constantly changing. Thus, we need to constantly improve the network structure in order to cope with these changes. Our model solves this problem by automating the process of structuring the network and shows high acceptance for noisy data, fault tolerance and high prediction accuracy. Several experiments were conducted in our research, and the number of epochs differs in each experiment. From the results, we find that all produced structures have high generalization ability.

Autonomic Transport Management Systems—Enabler for Smart Cities, Personalized Medicine, Participation and Industry Grid/Industry 4.0

Today’s societies are facing great challenges in transforming living environments in a way better serving people’s demands of the future. A key point in this transformation is reinventing cities as smart cities, where the core services are integrated in a way that ensures a high quality of life while minimizing the usage of resources [Smart cities in Europe. Serie Research Memoranda 0048, VU University Amsterdam, Faculty of Economics, Business Administration and Econometrics 1]. Setting up smart cities resp. transforming cities to smart cities includes the development of smart transport systems as a main service all other services rely on. Thinking about current mega trends like Individualization of Products (Mass Customization) in so called Industry grid also known as Industry 4.0 [Umsetzungsempfehlungen fur das Zukunftsprojekt Industrie 4.0 2] (Industrie 4.0 describes the industry in the 4th industrial revolution to customized mass production after mechanization, mass production, digitalization [Map ‘n’ tag. Thinking highways 3]), Personalized Medicine or the need of better support for disabled and older people in an aging society, the interconnection of involved bodies is a premise. In virtual world this means integration of data networks and ICTs in the physical world this means establishing individual and personalized transport services that cover individual mobility and individual distribution of goods. To ensure the best utilization of infrastructure while having less employable people in an aging society a high grade of automation and information integration is needed. We call this a smart transport system as the next step in development of today’s intelligent transport systems (ITS) and propose establishing this ITS of the future as an autonomic system to meet all the different requirements and ensure a high reliability of the overall system. Reliability is essential since most other services of the living environment smart city, will rely on transport systems. This chapter gives an overview on state of research based on current literature and recent publications of the authors (see references) and focus on the ICT system needed to manage transportation the autonomic transport management system.

A dynamic self-structuring neural network model to combat phishing

Creating a neural network based classification model is commonly accomplished using the trial and error technique. However, this technique has several difficulties in terms of time wasted and the availability of experts. In this article, an algorithm that simplifies structuring neural network classification models is proposed. The algorithm aims at creating a large enough structure to learn models from the training dataset that can be generalised on the testing dataset. Our algorithm dynamically tunes the structure parameters during the training phase aiming to derive accurate non-overfitting classifiers. The proposed algorithm has been applied to phishing website classification problem and it shows competitive results with respect to various evaluation measures such as harmonic mean (F1-score), precision, and classification accuracy.

The First Competition on Knowledge Engineering for Planning and Scheduling

We report on the staging of the first competition on knowledge engineering for AI planning and scheduling systems, held in Monterey, California, in colocation with the ICAPS 2005 conference. The background and motivation is discussed, together with the relationship of this new competition with the current international planning competition. We report on the new competitions format, its outcome, and the benefits we hope it will bring to the research area.

Introduction to the Special Issue on Knowledge Engineering Tools and Techniques for Automated Planning and Scheduling Systems

A reinforced bicycle pack includes a bag having a back, front, top, bottom and two sides, with a sleeve on each side extending from the back bottom area toward the front top area. The support frame has a lateral portion extending along the back top of the bag and leg portions which extend downwardly toward the bottom of the bag. The two leg portions end in two angled portions which extend from the back bottom area toward the front top area of the bag. One of the leg portions is received in each of the sleeves to support and erect the bag. There are means for attaching the lateral portion to the bag and for engaging the horizontal portion with the bicycle.

A new rule pruning text categorisation method

Associative classification integrates association rule and classification in data mining to build classifiers that are highly accurate than that of traditional classification approaches such as greedy and decision tree. However, the size of the classifiers produced by associative classification algorithms is usually large and contains insignificant rules. This may degrade the classification accuracy and increases the classification time, thus, pruning becomes an important task. In this paper, we investigate the problem of rule pruning in text categorisation and propose a new rule pruning techniques called High Precedence. Experimental results show that HP derives higher quality and more scalable classifiers than those produced by current pruning methods (lazy and database coverage). In addition, the number of rules generated by the developed pruning procedure is often less than that of lazy pruning.

More steps towards process automation for optical fabrication

In the context of Industrie 4.0, we have previously described the roles of robots in optical processing, and their complementarity with classical CNC machines, providing both processing and automation functions. After having demonstrated robotic moving of parts between a CNC polisher and metrology station, and auto-fringe-acquisition, we have moved on to automate the wash-down operation. This is part of a wider strategy we describe in this paper, leading towards automating the decision-making operations required before and throughout an optical manufacturing cycle.

Preface to special issue on planning and scheduling

Planning, scheduling and constraint satisfaction are important areas in artificial intelligence (AI) with broad practical applicability. Many real-world problems can be formulated as AI planning and scheduling (P&S) problems, where resources must be allocated to optimize overall performance objectives. Frequently, solving these problems requires an adequate mixture of planning, scheduling and resource allocation to competing goal activities over time in the presence of complex state-dependent constraints. Constraint satisfaction plays an important role in solving such real-life problems, and integrated techniques that manage P&S with constraint satisfaction are particularly useful. Knowledge engineering supports the solution of such problems by providing adequate modelling techniques and knowledge extraction techniques for improving the performance of planners and schedulers. Briefly speaking, knowledge engineering tools serve as a bridge between the real world and P&S systems.

Looking at the Class Associative Classification Training Algorithm

Associative classification (AC) is a branch in data mining that utilises association rule discovery methods in classification problems. In this paper, we propose a new training method called Looking at the Class (LC), which can be adapted by any rule-based AC algorithm. Unlike the traditional Classification based on Association rule (CBA) training method, which joins disjoint itemsets regardless of their class labels, our method joins only itemsets with similar class labels during the training phase. This prevents the accumulation of too many unnecessary merging during learning, and consequently results in huge saving (58%-91%) with reference of computational time and memory on large datasets.