V1-inspired features induce a weighted margin in SVMs

Image representations derived from simplified models of the primary visual cortex (V1), such as HOG and SIFT, elicit good performance in a myriad of visual classification tasks including object recognition/detection, pedestrian detection and facial expression classification. A central question in the vision, learning and neuroscience communities regards why these architectures perform so well. In this paper, we offer a unique perspective to this question by subsuming the role of V1-inspired features directly within a linear support vector machine (SVM). We demonstrate that a specific class of such features in conjunction with a linear SVM can be reinterpreted as inducing a weighted margin on the Kronecker basis expansion of an image. This new viewpoint on the role of V1-inspired features allows us to answer fundamental questions on the uniqueness and redundancies of these features, and offer substantial improvements in terms of computational and storage efficiency.

The association between objectively measured neighbourhood features and walking for transport in mid-aged adults

The aim of this paper is to examine the association between a range of objectively measured neighbourhood features and the likelihood of mid-aged adults walking for transport. Increased walking for transport would bring multiple benefits, including improved population and environmental health. As part of the baseline HABITAT study, 10,745 residents of Brisbane, Australia, aged 40–65 years, from 200 neighbourhoods were asked about the time they spent walking for transport. Walking data were collected by mail survey and the physical environmental features of neighbourhoods were compiled using a geographic information systems database. Walking for transport was categorised into four levels and the association between walking and each neighbourhood characteristic was examined using multilevel multinomial models. A number of threshold trends were evident; for example, off-road bikeways were consistently associated with walking between 60 and 150 min per week. Living within 500 m of public transit was also an important predictor but only for those who walked for less than 150 min per week. Interventions targeting these neighbourhood characteristics may lead to improved environmental quality, lower rates of overweight and obesity and associated chromic disease.

Ontology-based feature modeling for construction information extraction from a building information model

A building information model (BIM) provides a rich representation of a building's design. However, there are many challenges in getting construction-specific information from a BIM, limiting the usability of BIM for construction and other downstream processes. This paper describes a novel approach that utilizes ontology-based feature modeling, automatic feature extraction based on ifcXML, and query processing to extract information relevant to construction practitioners from a given BIM. The feature ontology generically represents construction-specific information that is useful for a broad range of construction management functions. The software prototype uses the ontology to transform the designer-focused BIM into a construction-specific feature-based model (FBM). The formal query methods operate on the FBM to further help construction users to quickly extract the necessary information from a BIM. Our tests demonstrate that this approach provides a richer representation of construction-specific information compared to existing BIM tools.

Providing query support to leverage BIM for construction

Building information modeling (BIM) is an emerging technology and process that provides rich and intelligent design information models of a facility, enabling enhanced communication, coordination, analysis, and quality control throughout all phases of a building project. Although there are many documented benefits of BIM for construction, identifying essential construction-specific information out of a BIM in an efficient and meaningful way is still a challenging task. This paper presents a framework that combines feature-based modeling and query processing to leverage BIM for construction. The feature-based modeling representation implemented enriches a BIM by representing construction-specific design features relevant to different construction management (CM) functions. The query processing implemented allows for increased flexibility to specify queries and rapidly generate the desired view from a given BIM according to the varied requirements of a specific practitioner or domain. Central to the framework is the formalization of construction domain knowledge in the form of a feature ontology and query specifications. The implementation of our framework enables the automatic extraction and querying of a wide-range of design conditions that are relevant to construction practitioners. The validation studies conducted demonstrate that our approach is significantly more effective than existing solutions. The research described in this paper has the potential to improve the efficiency and effectiveness of decision-making processes in different CM functions.

Matching relevance features with ontological concepts

In order to comprehend user information needs by concepts, this paper introduces a novel method to match relevance features with ontological concepts. The method first discovers relevance features from user local instances. Then, a concept matching approach is developed for matching these features to accurate concepts in a global knowledge base. This approach is significant for the transition of informative descriptor and conceptional descriptor. The proposed method is elaborately evaluated by comparing against three information gathering baseline models. The experimental results shows the matching approach is successful and achieves a series of remarkable improvements on search effectiveness.

Deriving construction features from an IFC model

In recent years, there has been a growing interest from the design and construction community to adopt Building Information Models (BIM). BIM provides semantically-rich information models that explicitly represent both 3D geometric information (e.g., component dimensions), along with non-geometric properties (e.g., material properties). While the richness of design information offered by BIM is evident, there are still tremendous challenges in getting construction-specific information out of BIM, limiting the usability of these models for construction. In this paper, we describe our approach for extracting construction-specific design conditions from a BIM model based on user-defined queries. This approach leverages an ontology of features we are developing to formalize the design conditions that affect construction. Our current implementation analyzes the component geometry and topological relationships between components in a BIM model represented using the Industry Foundation Classes (IFC) to identify construction features. We describe the reasoning process implemented to extract these construction features, and provide a critique of the IFC’s to support the querying process. We use examples from two case studies to illustrate the construction features, the querying process, and the challenges involved in deriving construction features from an IFC model.

Optimisation of bio-oil extraction process from Beauty Leaf (Calophyllum inophyllum) oil seed as a second generation biodiesel source

The Beauty Leaf tree (Calophyllum inophyllum) is a potential source of non-edible vegetable oil for producing future generation biodiesel because of its ability to grow in a wide range of climate conditions, easy cultivation, high fruit production rate, and the high oil content in the seed. This plant naturally occurs in the coastal areas of Queensland and the Northern Territory in Australia, and is also widespread in south-east Asia, India and Sri Lanka. Although Beauty Leaf is traditionally used as a source of timber and orientation plant, its potential as a source of second generation biodiesel is yet to be exploited. In this study, the extraction process from the Beauty Leaf oil seed has been optimised in terms of seed preparation, moisture content and oil extraction methods. The two methods that have been considered to extract oil from the seed kernel are mechanical oil extraction using an electric powered screw press, and chemical oil extraction using n-hexane as an oil solvent. The study found that seed preparation has a significant impact on oil yields, especially in the screw press extraction method. Kernels prepared to 15% moisture content provided the highest oil yields for both extraction methods. Mechanical extraction using the screw press can produce oil from correctly prepared product at a low cost, however overall this method is ineffective with relatively low oil yields. Chemical extraction was found to be a very effective method for oil extraction for its consistence performance and high oil yield, but cost of production was relatively higher due to the high cost of solvent. However, a solvent recycle system can be implemented to reduce the production cost of Beauty Leaf biodiesel. The findings of this study are expected to serve as the basis from which industrial scale biodiesel production from Beauty Leaf can be made.

Conserved and variable features of gag structure and arrangement in immature retrovirus particles

The assembly of retroviruses is driven by oligomerization of the Gag polyprotein. We have used cryo-electron tomography together with subtomogram averaging to describe the three-dimensional structure of in vitro-assembled Gag particles from human immunodeficiency virus, Mason-Pfizer monkey virus, and Rous sarcoma virus. These represent three different retroviral genera: the lentiviruses, betaretroviruses and alpharetroviruses. Comparison of the three structures reveals the features of the supramolecular organization of Gag that are conserved between genera and therefore reflect general principles of Gag-Gag interactions and the features that are specific to certain genera. All three Gag proteins assemble to form approximately spherical hexameric lattices with irregular defects. In all three genera, the N-terminal domain of CA is arranged in hexameric rings around large holes. Where the rings meet, 2-fold densities, assigned to the C-terminal domain of CA, extend between adjacent rings, and link together at the 6-fold symmetry axis with a density, which extends toward the center of the particle into the nucleic acid layer. Although this general arrangement is conserved, differences can be seen throughout the CA and spacer peptide regions. These differences can be related to sequence differences among the genera. We conclude that the arrangement of the structural domains of CA is well conserved across genera, whereas the relationship between CA, the spacer peptide region, and the nucleic acid is more specific to each genus.

Hydrogeological Features of the Lockyer Valley

The Lockyer Valley is situated 80 km west of Brisbane and is bounded on the sou th and west by the Great Dividing Range. The valley is a major western sub - catchment of the larger Brisbane River drainage system and is drained by the Lockyer Creek. The Lockyer catchment forms approximately 20% of the total Brisbane River catchment and has an area of around 2900 km2. The Lockyer Creek is an ephemeral drainage system, and the stream and associated alluvium are the main source for irrigation water supply in the Lockyer Valley. The catchment is comprised of a number of well -defined, elongate tributaries in the south, and others in the north, which are more meandering in nature.

Modelling the flow of cane constituents through the milling process of a raw sugar factory

This thesis reports on an investigation to develop an advanced and comprehensive milling process model of the raw sugar factory. Although the new model can be applied to both, the four-roller and six-roller milling units, it is primarily developed for the six-roller mills which are widely used in the Australian sugar industry. The approach taken was to gain an understanding of the previous milling process simulation model "MILSIM" developed at the University of Queensland nearly four decades ago. Although the MILSIM model was widely adopted in the Australian sugar industry for simulating the milling process it did have some incorrect assumptions. The study aimed to eliminate all the incorrect assumptions of the previous model and develop an advanced model that represents the milling process correctly and tracks the flow of other cane components in the milling process which have not been considered in the previous models. The development of the milling process model was done is three stages. Firstly, an enhanced milling unit extraction model (MILEX) was developed to access the mill performance parameters and predict the extraction performance of the milling process. New definitions for the milling performance parameters were developed and a complete milling train along with the juice screen was modelled. The MILEX model was validated with factory data and the variation in the mill performance parameters was observed and studied. Some case studies were undertaken to study the effect of fibre in juice streams, juice in cush return and imbibition% fibre on extraction performance of the milling process. It was concluded from the study that the empirical relations developed for the mill performance parameters in the MILSIM model were not applicable to the new model. New empirical relations have to be developed before the model is applied with confidence. Secondly, a soluble and insoluble solids model was developed using modelling theory and experimental data to track the flow of sucrose (pol), reducing sugars (glucose and fructose), soluble ash, true fibre and mud solids entering the milling train through the cane supply and their distribution in juice and bagasse streams.. The soluble impurities and mud solids in cane affect the performance of the milling train and further processing of juice and bagasse. New mill performance parameters were developed in the model to track the flow of cane components. The developed model is the first of its kind and provides some additional insight regarding the flow of soluble and insoluble cane components and the factors affecting their distribution in juice and bagasse. The model proved to be a good extension to the MILEX model to study the overall performance of the milling train. Thirdly, the developed models were incorporated in a proprietary software package "SysCAD’ for advanced operational efficiency and for availability in the ‘whole of factory’ model. The MILEX model was developed in SysCAD software to represent a single milling unit. Eventually the entire milling train and the juice screen were developed in SysCAD using series of different controllers and features of the software. The models developed in SysCAD can be run from macro enabled excel file and reports can be generated in excel sheets. The flexibility of the software, ease of use and other advantages are described broadly in the relevant chapter. The MILEX model is developed in static mode and dynamic mode. The application of the dynamic mode of the model is still under progress.

Modelling users' contextual querying behaviour for web image searching

The rapid growth of visual information on Web has led to immense interest in multimedia information retrieval (MIR). While advancement in MIR systems has achieved some success in specific domains, particularly the content-based approaches, general Web users still struggle to find the images they want. Despite the success in content-based object recognition or concept extraction, the major problem in current Web image searching remains in the querying process. Since most online users only express their needs in semantic terms or objects, systems that utilize visual features (e.g., color or texture) to search images create a semantic gap which hinders general users from fully expressing their needs. In addition, query-by-example (QBE) retrieval imposes extra obstacles for exploratory search because users may not always have the representative image at hand or in mind when starting a search (i.e. the page zero problem). As a result, the majority of current online image search engines (e.g., Google, Yahoo, and Flickr) still primarily use textual queries to search. The problem with query-based retrieval systems is that they only capture users’ information need in terms of formal queries;; the implicit and abstract parts of users’ information needs are inevitably overlooked. Hence, users often struggle to formulate queries that best represent their needs, and some compromises have to be made. Studies of Web search logs suggest that multimedia searches are more difficult than textual Web searches, and Web image searching is the most difficult compared to video or audio searches. Hence, online users need to put in more effort when searching multimedia contents, especially for image searches. Most interactions in Web image searching occur during query reformulation. While log analysis provides intriguing views on how the majority of users search, their search needs or motivations are ultimately neglected. User studies on image searching have attempted to understand users’ search contexts in terms of users’ background (e.g., knowledge, profession, motivation for search and task types) and the search outcomes (e.g., use of retrieved images, search performance). However, these studies typically focused on particular domains with a selective group of professional users. General users’ Web image searching contexts and behaviors are little understood although they represent the majority of online image searching activities nowadays. We argue that only by understanding Web image users’ contexts can the current Web search engines further improve their usefulness and provide more efficient searches. In order to understand users’ search contexts, a user study was conducted based on university students’ Web image searching in News, Travel, and commercial Product domains. The three search domains were deliberately chosen to reflect image users’ interests in people, time, event, location, and objects. We investigated participants’ Web image searching behavior, with the focus on query reformulation and search strategies. Participants’ search contexts such as their search background, motivation for search, and search outcomes were gathered by questionnaires. The searching activity was recorded with participants’ think aloud data for analyzing significant search patterns. The relationships between participants’ search contexts and corresponding search strategies were discovered by Grounded Theory approach. Our key findings include the following aspects: - Effects of users' interactive intents on query reformulation patterns and search strategies - Effects of task domain on task specificity and task difficulty, as well as on some specific searching behaviors - Effects of searching experience on result expansion strategies A contextual image searching model was constructed based on these findings. The model helped us understand Web image searching from user perspective, and introduced a context-aware searching paradigm for current retrieval systems. A query recommendation tool was also developed to demonstrate how users’ query reformulation contexts can potentially contribute to more efficient searching.

Robust image hash functions using higher order spectra

Robust hashing is an emerging field that can be used to hash certain data types in applications unsuitable for traditional cryptographic hashing methods. Traditional hashing functions have been used extensively for data/message integrity, data/message authentication, efficient file identification and password verification. These applications are possible because the hashing process is compressive, allowing for efficient comparisons in the hash domain but non-invertible meaning hashes can be used without revealing the original data. These techniques were developed with deterministic (non-changing) inputs such as files and passwords. For such data types a 1-bit or one character change can be significant, as a result the hashing process is sensitive to any change in the input. Unfortunately, there are certain applications where input data are not perfectly deterministic and minor changes cannot be avoided. Digital images and biometric features are two types of data where such changes exist but do not alter the meaning or appearance of the input. For such data types cryptographic hash functions cannot be usefully applied. In light of this, robust hashing has been developed as an alternative to cryptographic hashing and is designed to be robust to minor changes in the input. Although similar in name, robust hashing is fundamentally different from cryptographic hashing. Current robust hashing techniques are not based on cryptographic methods, but instead on pattern recognition techniques. Modern robust hashing algorithms consist of feature extraction followed by a randomization stage that introduces non-invertibility and compression, followed by quantization and binary encoding to produce a binary hash output. In order to preserve robustness of the extracted features, most randomization methods are linear and this is detrimental to the security aspects required of hash functions. Furthermore, the quantization and encoding stages used to binarize real-valued features requires the learning of appropriate quantization thresholds. How these thresholds are learnt has an important effect on hashing accuracy and the mere presence of such thresholds are a source of information leakage that can reduce hashing security. This dissertation outlines a systematic investigation of the quantization and encoding stages of robust hash functions. While existing literature has focused on the importance of quantization scheme, this research is the first to emphasise the importance of the quantizer training on both hashing accuracy and hashing security. The quantizer training process is presented in a statistical framework which allows a theoretical analysis of the effects of quantizer training on hashing performance. This is experimentally verified using a number of baseline robust image hashing algorithms over a large database of real world images. This dissertation also proposes a new randomization method for robust image hashing based on Higher Order Spectra (HOS) and Radon projections. The method is non-linear and this is an essential requirement for non-invertibility. The method is also designed to produce features more suited for quantization and encoding. The system can operate without the need for quantizer training, is more easily encoded and displays improved hashing performance when compared to existing robust image hashing algorithms. The dissertation also shows how the HOS method can be adapted to work with biometric features obtained from 2D and 3D face images.

Aircraft collision avoidance using spherical visual predictive control and single point features

This paper presents practical vision-based collision avoidance for objects approximating a single point feature. Using a spherical camera model, a visual predictive control scheme guides the aircraft around the object along a conical spiral trajectory. Visibility, state and control constraints are considered explicitly in the controller design by combining image and vehicle dynamics in the process model, and solving the nonlinear optimization problem over the resulting state space. Importantly, range is not required. Instead, the principles of conical spiral motion are used to design an objective function that simultaneously guides the aircraft along the avoidance trajectory, whilst providing an indication of the appropriate point to stop the spiral behaviour. Our approach is aimed at providing a potential solution to the See and Avoid problem for unmanned aircraft and is demonstrated through a series.

Mapping semantic knowledge for unsupervised text categorisation

Text categorisation is challenging, due to the complex structure with heterogeneous, changing topics in documents. The performance of text categorisation relies on the quality of samples, effectiveness of document features, and the topic coverage of categories, depending on the employing strategies; supervised or unsupervised; single labelled or multi-labelled. Attempting to deal with these reliability issues in text categorisation, we propose an unsupervised multi-labelled text categorisation approach that maps the local knowledge in documents to global knowledge in a world ontology to optimise categorisation result. The conceptual framework of the approach consists of three modules; pattern mining for feature extraction; feature-subject mapping for categorisation; concept generalisation for optimised categorisation. The approach has been promisingly evaluated by compared with typical text categorisation methods, based on the ground truth encoded by human experts.

Pharmacokinetics of isofraxidin in rat plasma after oral administration of the extract of acanthopanax senticosus using HPLC with solid phase extraction method

High-performance liquid chromatography coupled with solid phase extraction method was developed for determination of isofraxidin in rat plasma after oral administration of Acanthopanax senticosus extract (ASE), and pharmacokinetic parameters of isofraxidin either in ASE or pure compound were measured. The HPLC analysis was performed on a Dikma Diamonsil RP(18) column (4.6 mm x 150 mm, 5 microm) with the isocratic elution of solvent A (acetonitrile) and solvent B (0.1% aqueous phosphoric acid, v/v) (A : B = 22 : 78) and the detection wavelength was set at 343 nm. The calibration curve was linear over the range of 0.156-15.625 microg/ml. The limit of detection was 60 ng/ml. The intra-day precision was 5.8%, and the inter-day precision was 6.0%. The recovery was 87.30+/-1.73%. When the dosage of ASE is equal to pure compound caculated by the amount of isofraxidin, it has been found to have two maximum concentrations in plasma while the pure compound only showed one peak in the plasma concentration-time curve. The determined content of isofraxidin in plasma after oral administration of ASE is the total contents of free isofraxidin and its precursors in ASE in vitro. The pharmacokinetic characteristics of ASE showed the priority of the extract and the properities of traditional Chinese medicine.