User behaviour modelling in a multi-dimensional environment for personalization and recommendation

Handling information overload online, from the user's point of view is a big challenge, especially when the number of websites is growing rapidly due to growth in e-commerce and other related activities. Personalization based on user needs is the key to solving the problem of information overload. Personalization methods help in identifying relevant information, which may be liked by a user. User profile and object profile are the important elements of a personalization system. When creating user and object profiles, most of the existing methods adopt two-dimensional similarity methods based on vector or matrix models in order to find inter-user and inter-object similarity. Moreover, for recommending similar objects to users, personalization systems use the users-users, items-items and users-items similarity measures. In most cases similarity measures such as Euclidian, Manhattan, cosine and many others based on vector or matrix methods are used to find the similarities. Web logs are high-dimensional datasets, consisting of multiple users, multiple searches with many attributes to each. Two-dimensional data analysis methods may often overlook latent relationships that may exist between users and items. In contrast to other studies, this thesis utilises tensors, the high-dimensional data models, to build user and object profiles and to find the inter-relationships between users-users and users-items. To create an improved personalized Web system, this thesis proposes to build three types of profiles: individual user, group users and object profiles utilising decomposition factors of tensor data models. A hybrid recommendation approach utilising group profiles (forming the basis of a collaborative filtering method) and object profiles (forming the basis of a content-based method) in conjunction with individual user profiles (forming the basis of a model based approach) is proposed for making effective recommendations. A tensor-based clustering method is proposed that utilises the outcomes of popular tensor decomposition techniques such as PARAFAC, Tucker and HOSVD to group similar instances. An individual user profile, showing the user's highest interest, is represented by the top dimension values, extracted from the component matrix obtained after tensor decomposition. A group profile, showing similar users and their highest interest, is built by clustering similar users based on tensor decomposed values. A group profile is represented by the top association rules (containing various unique object combinations) that are derived from the searches made by the users of the cluster. An object profile is created to represent similar objects clustered on the basis of their similarity of features. Depending on the category of a user (known, anonymous or frequent visitor to the website), any of the profiles or their combinations is used for making personalized recommendations. A ranking algorithm is also proposed that utilizes the personalized information to order and rank the recommendations. The proposed methodology is evaluated on data collected from a real life car website. Empirical analysis confirms the effectiveness of recommendations made by the proposed approach over other collaborative filtering and content-based recommendation approaches based on two-dimensional data analysis methods.

Personalised search – a hybrid approach for web information retrieval and its evaluation

Nowadays, everyone can effortlessly access a range of information on the World Wide Web (WWW). As information resources on the web continue to grow tremendously, it becomes progressively more difficult to meet high expectations of users and find relevant information. Although existing search engine technologies can find valuable information, however, they suffer from the problems of information overload and information mismatch. This paper presents a hybrid Web Information Retrieval approach allowing personalised search using ontology, user profile and collaborative filtering. This approach finds the context of user query with least user’s involvement, using ontology. Simultaneously, this approach uses time-based automatic user profile updating with user’s changing behaviour. Subsequently, this approach uses recommendations from similar users using collaborative filtering technique. The proposed method is evaluated with the FIRE 2010 dataset and manually generated dataset. Empirical analysis reveals that Precision, Recall and F-Score of most of the queries for many users are improved with proposed method.

Delegation framework for federated systems

It is not uncommon for enterprises today to be faced with the demand to integrate and incor- porate many different and possibly heterogeneous systems which are generally independently designed and developed, to allow seamless access. In effect, the integration of these systems results in one large whole system that must be able, at the same time, to maintain the local autonomy and to continue working as an independent entity. This problem has introduced a new distributed architecture called federated systems. The most challenging issue in federated systems is to find answers for the question of how to efficiently cooperate while preserving their autonomous characteristic, especially the security autonomy. This thesis intends to address this issue. The thesis reviews the evolution of the concept of federated systems and discusses the organisational characteristics as well as remaining security issues with the existing approaches. The thesis examines how delegation can be used as means to achieve better security, especially authorisation while maintaining autonomy for the participating member of the federation. A delegation taxonomy is proposed as one of the main contributions. The major contribution of this thesis is to study and design a mechanism to support dele- gation within and between multiple security domains with constraint management capability. A novel delegation framework is proposed including two modules: Delegation Constraint Man- agement module and Policy Management module. The first module is designed to effectively create, track and manage delegation constraints, especially for delegation processes which require re-delegation (indirect delegation). The first module employs two algorithms to trace the root authority of a delegation constraint chain and to prevent the potential conflict when creating a delegation constraint chain if necessary. The first module is designed for conflict prevention not conflict resolution. The second module is designed to support the first module via the policy comparison capability. The major function of this module is to provide the delegation framework the capability to compare policies and constraints (written under the format of a policy). The module is an extension of Lin et al.'s work on policy filtering and policy analysis. Throughout the thesis, some case studies are used as examples to illustrate the discussed concepts. These two modules are designed to capture one of the most important aspects of the delegation process: the relationships between the delegation transactions and the involved constraints, which are not very well addressed by the existing approaches. This contribution is significant because the relationships provide information to keep track and en- force the involved delegation constraints and, therefore, play a vital role in maintaining and enforcing security for transactions across multiple security domains.

Trust-based automated recommendation making

Recommender systems are one of the recent inventions to deal with ever growing information overload in relation to the selection of goods and services in a global economy. Collaborative Filtering (CF) is one of the most popular techniques in recommender systems. The CF recommends items to a target user based on the preferences of a set of similar users known as the neighbours, generated from a database made up of the preferences of past users. With sufficient background information of item ratings, its performance is promising enough but research shows that it performs very poorly in a cold start situation where there is not enough previous rating data. As an alternative to ratings, trust between the users could be used to choose the neighbour for recommendation making. Better recommendations can be achieved using an inferred trust network which mimics the real world "friend of a friend" recommendations. To extend the boundaries of the neighbour, an effective trust inference technique is required. This thesis proposes a trust interference technique called Directed Series Parallel Graph (DSPG) which performs better than other popular trust inference algorithms such as TidalTrust and MoleTrust. Another problem is that reliable explicit trust data is not always available. In real life, people trust "word of mouth" recommendations made by people with similar interests. This is often assumed in the recommender system. By conducting a survey, we can confirm that interest similarity has a positive relationship with trust and this can be used to generate a trust network for recommendation. In this research, we also propose a new method called SimTrust for developing trust networks based on user's interest similarity in the absence of explicit trust data. To identify the interest similarity, we use user's personalised tagging information. However, we are interested in what resources the user chooses to tag, rather than the text of the tag applied. The commonalities of the resources being tagged by the users can be used to form the neighbours used in the automated recommender system. Our experimental results show that our proposed tag-similarity based method outperforms the traditional collaborative filtering approach which usually uses rating data.

PySSM : a Python module for Bayesian inference of linear Gaussian state space models

PySSM is a Python package that has been developed for the analysis of time series using linear Gaussian state space models (SSM). PySSM is easy to use; models can be set up quickly and efficiently and a variety of different settings are available to the user. It also takes advantage of scientific libraries Numpy and Scipy and other high level features of the Python language. PySSM is also used as a platform for interfacing between optimised and parallelised Fortran routines. These Fortran routines heavily utilise Basic Linear Algebra (BLAS) and Linear Algebra Package (LAPACK) functions for maximum performance. PySSM contains classes for filtering, classical smoothing as well as simulation smoothing.

CAT-SLAM : probabilistic localisation and mapping using a continuous appearance-based trajectory

This paper describes a new system, dubbed Continuous Appearance-based Trajectory Simultaneous Localisation and Mapping (CAT-SLAM), which augments sequential appearance-based place recognition with local metric pose filtering to improve the frequency and reliability of appearance-based loop closure. As in other approaches to appearance-based mapping, loop closure is performed without calculating global feature geometry or performing 3D map construction. Loop-closure filtering uses a probabilistic distribution of possible loop closures along the robot’s previous trajectory, which is represented by a linked list of previously visited locations linked by odometric information. Sequential appearance-based place recognition and local metric pose filtering are evaluated simultaneously using a Rao–Blackwellised particle filter, which weights particles based on appearance matching over sequential frames and the similarity of robot motion along the trajectory. The particle filter explicitly models both the likelihood of revisiting previous locations and exploring new locations. A modified resampling scheme counters particle deprivation and allows loop-closure updates to be performed in constant time for a given environment. We compare the performance of CAT-SLAM with FAB-MAP (a state-of-the-art appearance-only SLAM algorithm) using multiple real-world datasets, demonstrating an increase in the number of correct loop closures detected by CAT-SLAM.

Machine vision toolbox for MATLAB, release 3 [Software]

The Toolbox, combined with MATLAB ® and a modern workstation computer, is a useful and convenient environment for investigation of machine vision algorithms. For modest image sizes the processing rate can be sufficiently ``real-time'' to allow for closed-loop control. Focus of attention methods such as dynamic windowing (not provided) can be used to increase the processing rate. With input from a firewire or web camera (support provided) and output to a robot (not provided) it would be possible to implement a visual servo system entirely in MATLAB. Provides many functions that are useful in machine vision and vision-based control. Useful for photometry, photogrammetry, colorimetry. It includes over 100 functions spanning operations such as image file reading and writing, acquisition, display, filtering, blob, point and line feature extraction, mathematical morphology, homographies, visual Jacobians, camera calibration and color space conversion.

Particle wave

“Particle Wave” is comprised of six lenticular panels hung in an even, horizontal sequence. Each panel alternates between two solid colour fields as you move past it. There are six colours in total, with each colour represented twice in the spectrum. From left to right, the panels move through yellow, orange, magenta, violet, blue, green and back to yellow. The work’s title refers to the two competing theories of light, which can be understood as either paradoxical or complementary. Like these theories, the experience of viewing the work catches us in a double bind. While we can orient ourselves to see solid colour fields one by one, we are never able to fully capture them all at once. In fact, it is only through our continual movement, and the subsequent transitioning of visible colours that we register the complete spectrum. Through this viewing experience, “Particle Wave” actively engages with our peripheral vision and the transitory nature of perception. It plays with the fundamental pleasures of colour and vision, and the uneasy seduction of being unable to grasp multiple phenomena simultaneously.

Flight trial of an electro-optical sense-and-avoid system

This paper presents the flight trials of an electro-optical (EO) sense-and-avoid system onboard a Cessna host aircraft (camera aircraft). We focus on the autonomous collision avoidance capability of the sense-and-avoid system; that is, closed-loop integration with the onboard aircraft autopilot. We also discuss the system’s approach to target detection and avoidance control, as well as the methodology of the flight trials. The results demonstrate the ability of the sense-and-avoid system to automatically detect potential conflicting aircraft and engage the host Cessna autopilot to perform an avoidance manoeuvre, all without any human intervention

Publicly verifiable ciphertexts

In many applications, where encrypted traffic flows from an open (public) domain to a protected (private) domain, there exists a gateway that bridges the two domains and faithfully forwards the incoming traffic to the receiver. We observe that indistringuishability against (adaptive) chosen-ciphertext attacks (IND-CCA), which is a mandatory goal in face of active attacks in a public domain, can be essentially relaxed to indistinguishability against chosen-plaintext attacks (IND-CPA) for ciphertexts once they pass the gateway that acts as an IND-CCA/CPA filter by first checking the validity of an incoming IND-CCA ciphertext, then transforming it (if valid) into an IND-CPA ciphertext, and forwarding the latter to the receipient in the private domain. "Non-trivial filtering" can result in reduced decryption costs on the receivers' side. We identify a class of encryption schemes with publicaly verifiable ciphertexts that admit generic constructions of (non-trivial) IND-CCA/CPA filters. These schemes are characterized by existence of public algorithms that can distinguish between valid and invalid ciphertexts. To this end, we formally define (non-trivial) public verifiability of ciphertexts for general encryption schemes, key encapsulation mechanisms, and hybrid encryption schemes, encompassing public-key, identity-based, and tag-based encryption flavours. We further analyze the security impact of public verifiability and discuss generic transformations and concrete constructions that enjoy this property.

Discovering relevant features for effective query formulation

The quality of discovered features in relevance feedback (RF) is the key issue for effective search query. Most existing feedback methods do not carefully address the issue of selecting features for noise reduction. As a result, extracted noisy features can easily contribute to undesirable effectiveness. In this paper, we propose a novel feature extraction method for query formulation. This method first extract term association patterns in RF as knowledge for feature extraction. Negative RF is then used to improve the quality of the discovered knowledge. A novel information filtering (IF) model is developed to evaluate the proposed method. The experimental results conducted on Reuters Corpus Volume 1 and TREC topics confirm that the proposed model achieved encouraging performance compared to state-of-the-art IF models.

Fusion of morphological images for airborne target detection

Several track-before-detection approaches for image based aircraft detection have recently been examined in an important automated aircraft collision detection application. A particularly popular approach is a two stage processing paradigm which involves: a morphological spatial filter stage (which aims to emphasize the visual characteristics of targets) followed by a temporal or track filter stage (which aims to emphasize the temporal characteristics of targets). In this paper, we proposed new spot detection techniques for this two stage processing paradigm that fuse together raw and morphological images or fuse together various different morphological images (we call these approaches morphological reinforcement). On the basis of flight test data, the proposed morphological reinforcement operations are shown to offer superior signal to-noise characteristics when compared to standard spatial filter options (such as the close-minus-open and adaptive contour morphological operations). However, system operation characterised curves, which examine detection verses false alarm characteristics after both processing stages, illustrate that system performance is very data dependent.

Relative entropy rate based model selection for linear hybrid system filters of uncertain nonlinear systems

Hybrid system representations have been exploited in a number of challenging modelling situations, including situations where the original nonlinear dynamics are too complex (or too imprecisely known) to be directly filtered. Unfortunately, the question of how to best design suitable hybrid system models has not yet been fully addressed, particularly in the situations involving model uncertainty. This paper proposes a novel joint state-measurement relative entropy rate based approach for design of hybrid system filters in the presence of (parameterised) model uncertainty. We also present a design approach suitable for suboptimal hybrid system filters. The benefits of our proposed approaches are illustrated through design examples and simulation studies.

Text mining in negative relevance feedback

It is a big challenge to clearly identify the boundary between positive and negative streams. Several attempts have used negative feedback to solve this challenge; however, there are two issues for using negative relevance feedback to improve the effectiveness of information filtering. The first one is how to select constructive negative samples in order to reduce the space of negative documents. The second issue is how to decide noisy extracted features that should be updated based on the selected negative samples. This paper proposes a pattern mining based approach to select some offenders from the negative documents, where an offender can be used to reduce the side effects of noisy features. It also classifies extracted features (i.e., terms) into three categories: positive specific terms, general terms, and negative specific terms. In this way, multiple revising strategies can be used to update extracted features. An iterative learning algorithm is also proposed to implement this approach on RCV1, and substantial experiments show that the proposed approach achieves encouraging performance.

Measurement of ventilation and cardiac related impedance changes with electrical impedance tomography

Introduction Electrical impedance tomography (EIT) has been shown to be able to distinguish both ventilation and perfusion. With adequate filtering the regional distributions of both ventilation and perfusion and their relationships could be analysed. Several methods of separation have been suggested previously, including breath holding, electrocardiograph (ECG) gating and frequency filtering. Many of these methods require interventions inappropriate in a clinical setting. This study therefore aims to extend a previously reported frequency filtering technique to a spontaneously breathing cohort and assess the regional distributions of ventilation and perfusion and their relationship. Methods Ten healthy adults were measured during a breath hold and while spontaneously breathing in supine, prone, left and right lateral positions. EIT data were analysed with and without filtering at the respiratory and heart rate. Profiles of ventilation, perfusion and ventilation/perfusion related impedance change were generated and regions of ventilation and pulmonary perfusion were identified and compared. Results Analysis of the filtration technique demonstrated its ability to separate the ventilation and cardiac related impedance signals without negative impact. It was, therefore, deemed suitable for use in this spontaneously breathing cohort. Regional distributions of ventilation, perfusion and the combined ΔZV/ΔZQ were calculated along the gravity axis and anatomically in each position. Along the gravity axis, gravity dependence was seen only in the lateral positions in ventilation distribution, with the dependent lung being better ventilated regardless of position. This gravity dependence was not seen in perfusion. When looking anatomically, differences were only apparent in the lateral positions. The lateral position ventilation distributions showed a difference in the left lung, with the right lung maintaining a similar distribution in both lateral positions. This is likely caused by more pronounced anatomical changes in the left lung when changing positions. Conclusions The modified filtration technique was demonstrated to be effective in separating the ventilation and perfusion signals in spontaneously breathing subjects. Gravity dependence was seen only in ventilation distribution in the left lung in lateral positions, suggesting gravity based shifts in anatomical structures. Gravity dependence was not seen in any perfusion distributions.