Spectral–texture feature extraction using statistical moments with application to object-based vegetation species classification

The use of appropriate features to characterise an output class or object is critical for all classification problems. In order to find optimal feature descriptors for vegetation species classification in a power line corridor monitoring application, this article evaluates the capability of several spectral and texture features. A new idea of spectral–texture feature descriptor is proposed by incorporating spectral vegetation indices in statistical moment features. The proposed method is evaluated against several classic texture feature descriptors. Object-based classification method is used and a support vector machine is employed as the benchmark classifier. Individual tree crowns are first detected and segmented from aerial images and different feature vectors are extracted to represent each tree crown. The experimental results showed that the proposed spectral moment features outperform or can at least compare with the state-of-the-art texture descriptors in terms of classification accuracy. A comprehensive quantitative evaluation using receiver operating characteristic space analysis further demonstrates the strength of the proposed feature descriptors.

Economic development, enlightenment and creative transformation : creative industries in the New China

This paper examines some of the implications for China of the creative industries agenda as drawn by some recent commentators. The creative industries have been seen by many commentators as essential if China is to move from an imitative low-value economy to an innovative high value one. Some suggest that this trajectory is impossible without a full transition to liberal capitalism and democracy - not just removing censorship but instituting 'enlightenment values'. Others suggest that the development of the creative industries themselves will promote social and political change. The paper suggests that the creative industries takes certain elements of a prior cultural industries concept and links it to a new kind of economic development agenda. Though this agenda presents problems for the Chinese government it does not in itself imply the kind of radical democratic political change with which these commentators associate it. In the form in which the creative industries are presented – as part of an informational economy rather than as a cultural politics – it can be accommodated by a Chinese regime doing ‘business as usual’.

Workplace mobbing : expulsion, exclusion, and transformation

The issue of workplace bullying has received considerable attention in recent times in both the academic literature and in the print and electronic media. The stereotypical bullying scenario can be described as the “bully boss” model, where those in more senior positions tend to bully the staff they supervise. By way of contrast, this paper presents the findings of a three year exemplarian action research study into the lesser known phenomenon of workplace mobbing. Consistent with grounded theory methods, the findings are discussed in the context of emergent propositions in relation to the broader social, cultural, and organisational factors that can perpetuate workplace mobbing in the public sector.

The sample complexity of pattern classification with neural networks: the size of the weights is more important than the size of the network

Sample complexity results from computational learning theory, when applied to neural network learning for pattern classification problems, suggest that for good generalization performance the number of training examples should grow at least linearly with the number of adjustable parameters in the network. Results in this paper show that if a large neural network is used for a pattern classification problem and the learning algorithm finds a network with small weights that has small squared error on the training patterns, then the generalization performance depends on the size of the weights rather than the number of weights. For example, consider a two-layer feedforward network of sigmoid units, in which the sum of the magnitudes of the weights associated with each unit is bounded by A and the input dimension is n. We show that the misclassification probability is no more than a certain error estimate (that is related to squared error on the training set) plus A3 √((log n)/m) (ignoring log A and log m factors), where m is the number of training patterns. This may explain the generalization performance of neural networks, particularly when the number of training examples is considerably smaller than the number of weights. It also supports heuristics (such as weight decay and early stopping) that attempt to keep the weights small during training. The proof techniques appear to be useful for the analysis of other pattern classifiers: when the input domain is a totally bounded metric space, we use the same approach to give upper bounds on misclassification probability for classifiers with decision boundaries that are far from the training examples.

Learning the kernel matrix with semidefinite programming

Kernel-based learning algorithms work by embedding the data into a Euclidean space, and then searching for linear relations among the embedded data points. The embedding is performed implicitly, by specifying the inner products between each pair of points in the embedding space. This information is contained in the so-called kernel matrix, a symmetric and positive semidefinite matrix that encodes the relative positions of all points. Specifying this matrix amounts to specifying the geometry of the embedding space and inducing a notion of similarity in the input space - classical model selection problems in machine learning. In this paper we show how the kernel matrix can be learned from data via semidefinite programming (SDP) techniques. When applied to a kernel matrix associated with both training and test data this gives a powerful transductive algorithm -using the labeled part of the data one can learn an embedding also for the unlabeled part. The similarity between test points is inferred from training points and their labels. Importantly, these learning problems are convex, so we obtain a method for learning both the model class and the function without local minima. Furthermore, this approach leads directly to a convex method for learning the 2-norm soft margin parameter in support vector machines, solving an important open problem.

Multitask learning with expert advice

We consider the problem of prediction with expert advice in the setting where a forecaster is presented with several online prediction tasks. Instead of competing against the best expert separately on each task, we assume the tasks are related, and thus we expect that a few experts will perform well on the entire set of tasks. That is, our forecaster would like, on each task, to compete against the best expert chosen from a small set of experts. While we describe the “ideal” algorithm and its performance bound, we show that the computation required for this algorithm is as hard as computation of a matrix permanent. We present an efficient algorithm based on mixing priors, and prove a bound that is nearly as good for the sequential task presentation case. We also consider a harder case where the task may change arbitrarily from round to round, and we develop an efficient approximate randomized algorithm based on Markov chain Monte Carlo techniques.

Classification with a reject option using a hinge loss

We consider the problem of binary classification where the classifier can, for a particular cost, choose not to classify an observation. Just as in the conventional classification problem, minimization of the sample average of the cost is a difficult optimization problem. As an alternative, we propose the optimization of a certain convex loss function φ, analogous to the hinge loss used in support vector machines (SVMs). Its convexity ensures that the sample average of this surrogate loss can be efficiently minimized. We study its statistical properties. We show that minimizing the expected surrogate loss—the φ-risk—also minimizes the risk. We also study the rate at which the φ-risk approaches its minimum value. We show that fast rates are possible when the conditional probability P(Y=1|X) is unlikely to be close to certain critical values.

Multitask learning with expert advice

We consider the problem of prediction with expert advice in the setting where a forecaster is presented with several online prediction tasks. Instead of competing against the best expert separately on each task, we assume the tasks are related, and thus we expect that a few experts will perform well on the entire set of tasks. That is, our forecaster would like, on each task, to compete against the best expert chosen from a small set of experts. While we describe the "ideal" algorithm and its performance bound, we show that the computation required for this algorithm is as hard as computation of a matrix permanent. We present an efficient algorithm based on mixing priors, and prove a bound that is nearly as good for the sequential task presentation case. We also consider a harder case where the task may change arbitrarily from round to round, and we develop an efficient approximate randomized algorithm based on Markov chain Monte Carlo techniques.

Navigating, recognizing and describing urban spaces with vision and lasers

In this paper we describe a body of work aimed at extending the reach of mobile navigation and mapping. We describe how running topological and metric mapping and pose estimation processes concurrently, using vision and laser ranging, has produced a full six-degree-of-freedom outdoor navigation system. It is capable of producing intricate three-dimensional maps over many kilometers and in real time. We consider issues concerning the intrinsic quality of the built maps and describe our progress towards adding semantic labels to maps via scene de-construction and labeling. We show how our choices of representation, inference methods and use of both topological and metric techniques naturally allow us to fuse maps built from multiple sessions with no need for manual frame alignment or data association.

Aerial SLAM with a single camera using visual expectation

Micro aerial vehicles (MAVs) are a rapidly growing area of research and development in robotics. For autonomous robot operations, localization has typically been calculated using GPS, external camera arrays, or onboard range or vision sensing. In cluttered indoor or outdoor environments, onboard sensing is the only viable option. In this paper we present an appearance-based approach to visual SLAM on a flying MAV using only low quality vision. Our approach consists of a visual place recognition algorithm that operates on 1000 pixel images, a lightweight visual odometry algorithm, and a visual expectation algorithm that improves the recall of place sequences and the precision with which they are recalled as the robot flies along a similar path. Using data gathered from outdoor datasets, we show that the system is able to perform visual recognition with low quality, intermittent visual sensory data. By combining the visual algorithms with the RatSLAM system, we also demonstrate how the algorithms enable successful SLAM.

Preparation and characterisation of tri-calcium phosphate scaffolds with tunnel-like macro-pores for bone tissue engineering

Calcium Phosphate ceramics have been widely used in tissue engineering due to their excellent biocompatibility and biodegradability. In the physiological environment, they are able to gradually degrade, absorbed and promote bone growth. Ultimately, they are capable of replacing damaged bone with new tissue. However, their low mechanical properties limit calcium phosphate ceramics in load-bearing applications. To obtain sufficient mechanical properties as well as high biocompatibility is one of the main focuses in biomaterials research. Therefore, the current project focuses on the preparation and characterization of porous tri-calcium phosphate (TCP) ceramic scaffolds. Hydroxapatite (HA) was used as the raw material, and normal calcium phosphate bioglass was added to adjust the ratio between calcium and phosphate. It was found that when 20% bioglass was added to HA and sintered at 1400oC for 3 hours, the TCP scaffold was obtained and this was confirmed by X-ray diffraction (XRD) analysis. Test results have shown that by applying this method, TCP scaffolds have significantly higher compressive strength (9.98MPa) than those made via TCP powder (<3MPa). Moreover, in order to further increase the compressive strength of TCP scaffolds, the samples were then coated with bioglass. For normal bioglass coated TCP scaffold, compressive strength was 16.69±0.5MPa; the compressive strength for single layer mesoporous bioglass coated scaffolds was 15.03±0.63MPa. In addition, this project has also concentrated on sizes and shapes effects; it was found that the cylinder scaffolds have more mechanical property than the club ones. In addition, this project performed cell culture within scaffold to assess biocompatibility. The cells were well distributed in the scaffold, and the cytotoxicity test was performed by 3-(4,5)-dimethylthiahiazo(-z-y1)-3,5-di- phenytetrazoliumromide (MTT) assay. The Alkaline Phosphatase (Alp) activity of human bone marrow mesenchymal stem cell system (hBMSCs) seeded on scaffold expressed higher in vitro than that in the positive control groups in osteogenic medium, which indicated that the scaffolds were both osteoconductive and osteoinductive, showing potential value in bone tissue engineering.

Advanced Computational Intelligence System for inverse aeronautical design optimisation

Abstract—Computational Intelligence Systems (CIS) is one of advanced softwares. CIS has been important position for solving single-objective / reverse / inverse and multi-objective design problems in engineering. The paper hybridise a CIS for optimisation with the concept of Nash-Equilibrium as an optimisation pre-conditioner to accelerate the optimisation process. The hybridised CIS (Hybrid Intelligence System) coupled to the Finite Element Analysis (FEA) tool and one type of Computer Aided Design(CAD) system; GiD is applied to solve an inverse engineering design problem; reconstruction of High Lift Systems (HLS). Numerical results obtained by the hybridised CIS are compared to the results obtained by the original CIS. The benefits of using the concept of Nash-Equilibrium are clearly demonstrated in terms of solution accuracy and optimisation efficiency.

Cost efficiency v quality service : using CHAT as a tool for understanding change and transformation in work practices

This chapter provides an analysis of feedback from key stakeholders, collected as part of a research project, on the problems and tensions evident in the collective work practices of learning advisers employed in learning assistance services at an Australian metropolitan university (Peach, 2003). The term 'learning assistance' is used in the Australian higher education sector generally to refer to student support services that include assistance with academic writing and other study skills. The aim of the study was to help learning advisers and other key stakeholders develop a better understanding of the work activity with a view to using this understanding to generate improvements in service provision. Over twenty problems and associated tensions were identified through stakeholder feedback however the focus of this chapter is the analysis of tensions related to a cluster of problems referred to as cost-efficiency versus quality service. Theoretical modelling derived from the tools made available through cultural historical activity theory and expansive visibilsation (Engestrom and Miettinen, 1999) and excerpts from data are used to illustrate how different understandings of the purpose of learning assistance services impacts on the work practices of learning advisers and creates problems and tensions in relation to the type of service available (including use of technology),level of service available, and learning adviser workload.

Social Procurement: Promoting the sustainability of NPOs through the transformation of economic, social and cultural capital

Social procurement provides a key source of income for the Third Sector, and is vital for the sustainability of many nonprofit organisations. Social procurement involves the exchange of economic capital from one organisation, typically government (although for-profit and non-profit organisations can also purchase), with a nonprofit organisations in order to deliver other forms of. It is this transformation of economic capital into other forms of capital (cultural, human, social) in the social procurement process, which is the focus of this paper. Four case studies, which are representative of the four main types of social procurement, will be examined in order to trace how economic capital is transformed into other types of capital in each of these cases. In so doing, the paper will advance our understanding of social procurement theoretically, and lead to a wider discussion about the role of social procurement in ensuring the sustainability of nonprofit organisations, and the civil societies in which they operate.

Atomistic exploration of deformation properties of copper nanowires with pre-existing defects

Based on the embedded atom method (EAM) and molecular dynamics (MD) method, in this paper, the tensile deformation properties of Cu nanowires (NWs) with different pre-existing defects, including single surface defects, surface bi-defects and single internal defects, are systematically studied. In-depth deformation mechanisms of NWs with pre-existing defects are also explored. It is found that Young's modulus is insensitive to different pre-existing defects, but yield strength shows an obvious decrease. Defects are observed influencing greatly on NWs' tensile deformation mechanisms, and playing a role of dislocation sources. Besides of the traditional deformation process dominated by the nucleation and propagation of partial dislocations, the generations of twins, grain boundaries, fivefold deformation twins, hexagonal close-packed (HCP) structure and phase transformation from face-centred cubic (FCC) structure to HCP structure have been triggered by pre-existing defects. It is found that surface defect intends to induce larger influence to yield strength than internal defect. Most importantly, the defect that lies on slip planes exerts larger influence than other defects. As expected, it is also found that the more or longer of the defect, the bigger influence will be induced.