Evaluation of spectral and texture features for object-based vegetation species classification using Support Vector Machines

The use of appropriate features to characterize an output class or object is critical for all classification problems. This paper evaluates the capability of several spectral and texture features for object-based vegetation classification at the species level using airborne high resolution multispectral imagery. Image-objects as the basic classification unit were generated through image segmentation. Statistical moments extracted from original spectral bands and vegetation index image are used as feature descriptors for image objects (i.e. tree crowns). Several state-of-art texture descriptors such as Gray-Level Co-Occurrence Matrix (GLCM), Local Binary Patterns (LBP) and its extensions are also extracted for comparison purpose. Support Vector Machine (SVM) is employed for classification in the object-feature space. The experimental results showed that incorporating spectral vegetation indices can improve the classification accuracy and obtained better results than in original spectral bands, and using moments of Ratio Vegetation Index obtained the highest average classification accuracy in our experiment. The experiments also indicate that the spectral moment features also outperform or can at least compare with the state-of-art texture descriptors in terms of classification accuracy.

Aesthetic tensions : evaluating outcomes for practice-led research and industry

This paper explores principles of contemporary aesthetics to suggest a basis for determining qualitative outcomes of artistic works in two contexts: the arts industry and the academy setting of practice-led research. Commonly articulated measures of quality—creativity and innovation—are questioned as mere rhetoric if not framed in specific ways in the two discrete settings. The paper also interrogates generally held assumptions that a longer time to develop work and greater periods of self-reflexivity will produce higher calibre artistic outcomes. The unease produced by apparent differences in qualitative outcomes between art works created in an industry setting and those created through practice-led research is analysed through three interconnected framing devices: intention, contextual parameters and criteria for evaluation, in conjunction with the relationships between the art work, the artist and the audience/viewer/listener. Common and differentiated criteria in the two contexts are explored, leading to the conclusion that innovation is more likely to be revealed in the end product in an industry context whereas in practice-led research it may be in the methodological processes of creating the work. While identifying and acknowledging that the two contexts encourage and produce distinctive qualitative artistic outcomes, both of value to the arts and the academy, the paper recommends ways in which closer formal liaison between industry artists and practice-led artists and supervisors might occur in order to ensure ongoing mutual influence and relevance.

Evaluation of accessibility for knowledge-based cities

Purpose: The purpose of the paper is to develop a framework for evaluation of accessibility for knowledge based cities. ----- ----- Design/methodology/approach: This approach notifies common mistakes and problems in accessibility assessment for knowledge cities. ----- ----- Originality/value: Accessibility plays a key role in transport sustainability and recognizes the crucial links between transport and sustainable goals like air quality, environmental resource consumption & social equity. In knowledge cities, accessibility has significant effects on quality of life and social equity by improving the mobility of people and goods. Accessibility also influences patterns of growth and economic health by providing access to land. Accessibility is not only one of the components of knowledge cities but also affects other elements of knowledge cities directly or indirectly. ----- ----- Practical implications: The outcomes of the application will be helpful for developing particular methodologies for evaluating knowledge cities. On other words, this methodology attempts to develop an assessment procedure for examining accessibility of knowledge-based cities.

Evaluation of on-road driving in people with hemianopia and quadrantanopia

OBJECTIVE: To examine whether some drivers with hemianopia or quadrantanopia display safe driving skills on the road compared with drivers with normal visual fields. ---------- METHOD: An occupational therapist evaluated 22 people with hemianopia, 8 with quadrantanopia, and 30 with normal vision for driving skills during naturalistic driving using six rating scales. ---------- RESULTS: Of drivers with normal vision, >90% drove flawlessly or had minor errors. Although drivers with hemianopia were more likely to receive poorer ratings for all skills, 59.1%–81.8% performed with no or minor errors. A skill commonly problematic for them was lane keeping (40.9%). Of 8 drivers with quadrantanopia, 7 (87.5%) exhibited no or minor errors. ---------- CONCLUSION: This study of people with hemianopia or quadrantanopia with no lateral spatial neglect highlights the need to provide individual opportunities for on-road driving evaluation under natural traffic conditions if a person is motivated to return to driving after brain injury.

A regional construction R&D evaluation system for China

Expenditure on R&D in the China construction industry has been relatively low in comparison with many developed countries for a number of years – a situation considered to be a major barrier to the industry’s competitiveness in general and unsatisfactory industry development of the 31 regions involved. A major problem with this is the lack of a sufficiently sophisticated method of objectively evaluating R&D activity in what are quite complex circumstances considering the size and regional differences that exist in this part of the world. A regional construction R&D evaluation system (RCRES) is presented aimed at rectifying the situation. This is based on 12 indicators drawn from the Chinese Government’s R&D Inventory of Resources in consultation with a small group of experts in the field, and further factor analysed into three groups. From this, the required evaluation is obtained by a simple formula. Examination of the results provides a ranking list of the R&D performance of each of the 31 regions, indicating a general disproportion between coastal and inland regions and highlighting regions receiving special emphasis or currently lacking in development. The understanding on this is vital for the future of China’s construction industry.

Ontology-based image annotation

With regard to the long-standing problem of the semantic gap between low-level image features and high-level human knowledge, the image retrieval community has recently shifted its emphasis from low-level features analysis to high-level image semantics extrac- tion. User studies reveal that users tend to seek information using high-level semantics. Therefore, image semantics extraction is of great importance to content-based image retrieval because it allows the users to freely express what images they want. Semantic content annotation is the basis for semantic content retrieval. The aim of image anno- tation is to automatically obtain keywords that can be used to represent the content of images. The major research challenges in image semantic annotation are: what is the basic unit of semantic representation? how can the semantic unit be linked to high-level image knowledge? how can the contextual information be stored and utilized for image annotation? In this thesis, the Semantic Web technology (i.e. ontology) is introduced to the image semantic annotation problem. Semantic Web, the next generation web, aims at mak- ing the content of whatever type of media not only understandable to humans but also to machines. Due to the large amounts of multimedia data prevalent on the Web, re- searchers and industries are beginning to pay more attention to the Multimedia Semantic Web. The Semantic Web technology provides a new opportunity for multimedia-based applications, but the research in this area is still in its infancy. Whether ontology can be used to improve image annotation and how to best use ontology in semantic repre- sentation and extraction is still a worth-while investigation. This thesis deals with the problem of image semantic annotation using ontology and machine learning techniques in four phases as below. 1) Salient object extraction. A salient object servers as the basic unit in image semantic extraction as it captures the common visual property of the objects. Image segmen- tation is often used as the �rst step for detecting salient objects, but most segmenta- tion algorithms often fail to generate meaningful regions due to over-segmentation and under-segmentation. We develop a new salient object detection algorithm by combining multiple homogeneity criteria in a region merging framework. 2) Ontology construction. Since real-world objects tend to exist in a context within their environment, contextual information has been increasingly used for improving object recognition. In the ontology construction phase, visual-contextual ontologies are built from a large set of fully segmented and annotated images. The ontologies are composed of several types of concepts (i.e. mid-level and high-level concepts), and domain contextual knowledge. The visual-contextual ontologies stand as a user-friendly interface between low-level features and high-level concepts. 3) Image objects annotation. In this phase, each object is labelled with a mid-level concept in ontologies. First, a set of candidate labels are obtained by training Support Vectors Machines with features extracted from salient objects. After that, contextual knowledge contained in ontologies is used to obtain the �nal labels by removing the ambiguity concepts. 4) Scene semantic annotation. The scene semantic extraction phase is to get the scene type by using both mid-level concepts and domain contextual knowledge in ontologies. Domain contextual knowledge is used to create scene con�guration that describes which objects co-exist with which scene type more frequently. The scene con�guration is represented in a probabilistic graph model, and probabilistic inference is employed to calculate the scene type given an annotated image. To evaluate the proposed methods, a series of experiments have been conducted in a large set of fully annotated outdoor scene images. These include a subset of the Corel database, a subset of the LabelMe dataset, the evaluation dataset of localized semantics in images, the spatial context evaluation dataset, and the segmented and annotated IAPR TC-12 benchmark.

Visual field size criteria for mobility rehabilitation referral

Purpose. To investigate evidence-based visual field size criteria for referral of low-vision (LV) patients for mobility rehabilitation. Methods. One hundred and nine participants with LV and 41 age-matched participants with normal sight (NS) were recruited. The LV group was heterogeneous with diverse causes of visual impairment. We measured binocular kinetic visual fields with the Humphrey Field Analyzer and mobility performance on an obstacle-rich, indoor course. Mobility was assessed as percent preferred walking speed (PPWS) and number of obstacle-contact errors. The weighted kappa coefficient of association (κr) was used to discriminate LV participants with both unsafe and inefficient mobility from those with adequate mobility on the basis of their visual field size for the full sample and for subgroups according to type of visual field loss and whether or not the participants had previously received orientation and mobility training. Results. LV participants with both PPWS <38% and errors >6 on our course were classified as having inadequate (inefficient and unsafe) mobility compared with NS participants. Mobility appeared to be first compromised when the visual field was less than about 1.2 steradians (sr; solid angle of a circular visual field of about 70° diameter). Visual fields <0.23 and 0.63 sr (31 to 52° diameter) discriminated patients with at-risk mobility for the full sample and across the two subgroups. A visual field of 0.05 sr (15° diameter) discriminated those with critical mobility. Conclusions. Our study suggests that: practitioners should be alert to potential mobility difficulties when the visual field is less than about 1.2 sr (70° diameter); assessment for mobility rehabilitation may be warranted when the visual field is constricted to about 0.23 to 0.63 sr (31 to 52° diameter) depending on the nature of their visual field loss and previous history (at risk); and mobility rehabilitation should be conducted before the visual field is constricted to 0.05 sr (15° diameter; critical).

Talking the talk : oracy demands in first year university assessment tasks

With more constructivist approaches to learning in higher education and more value on teamwork skills, students’ oracy (speaking and listening) features more prominently in curriculum, pedagogy and assessment. The paper reports on a study of two first-year Australian university courses in disciplines with explicit industry orientations and high proportions of international students. Drawing on classroom observations and interviews with the lecturers, this paper investigates their pedagogical designs on oracy and the oracy demands of their assessment tasks. The study found that talk-based assessment tasks (a group project and a group oral presentation) featured in both courses but the two courses treated students’ oracy differently: as product or process. The contrast between the two assessment designs explicates issues around EAL student needs, authentic links to industry, the provenance of criteria used to assess performance, perceptions about the relevance of talk and the ‘hidden assessment’ of oracy.

Can proteoglycan change in articular cartilage be detected by ultrasound evaluation?

This paper assesses the capacity of high-frequency ultrasonic waves for detecting changes in the proteoglycan (PG) content of articular cartilage. 50 cartilage-on-bone samples were exposed to ultrasonic waves via an ultrasound transducer at a frequency of 20MHz. Histology and ImageJ processing were conducted to determine the PG content of the specimen. The ratios of the reflected signals from both the surface and the osteochondral junction (OCJ) were determined from the experimental data. The initial results show an inconsistency in the capacity of ultrasound to distinguish samples with severe proteoglycan loss (i.e. >90% PG loss) from the normal intact sample. This lack of clear distinction was also demonstrated at for samples with less than 60% depletion, while there is a clear differentiation between the normal intact sample and those with 55-70% PG loss.

Numerical evaluation of pollutant dispersion at a toll plaza based on system dynamics and Computational Fluid Dynamics models

The health of tollbooth workers is seriously threatened by long-term exposure to polluted air from vehicle exhausts. Using traffic data collected at a toll plaza, vehicle movements were simulated by a system dynamics model with different traffic volumes and toll collection procedures. This allowed the average travel time of vehicles to be calculated. A three-dimension Computational Fluid Dynamics (CFD) model was used with a k–ε turbulence model to simulate pollutant dispersion at the toll plaza for different traffic volumes and toll collection procedures. It was shown that pollutant concentration around tollbooths increases as traffic volume increases. Whether traffic volume is low or high (1500 vehicles/h or 2500 vehicles/h), pollutant concentration decreases if electronic toll collection (ETC) is adopted. In addition, pollutant concentration around tollbooths decreases as the proportion of ETC-equipped vehicles increases. However, if the proportion of ETC-equipped vehicles is very low and the traffic volume is not heavy, then pollutant concentration increases as the number of ETC lanes increases.

Improving the performance of model-order selection criteria by partial-model selection search

The traditional searching method for model-order selection in linear regression is a nested full-parameters-set searching procedure over the desired orders, which we call full-model order selection. On the other hand, a method for model-selection searches for the best sub-model within each order. In this paper, we propose using the model-selection searching method for model-order selection, which we call partial-model order selection. We show by simulations that the proposed searching method gives better accuracies than the traditional one, especially for low signal-to-noise ratios over a wide range of model-order selection criteria (both information theoretic based and bootstrap-based). Also, we show that for some models the performance of the bootstrap-based criterion improves significantly by using the proposed partial-model selection searching method. Index Terms— Model order estimation, model selection, information theoretic criteria, bootstrap 1. INTRODUCTION Several model-order selection criteria can be applied to find the optimal order. Some of the more commonly used information theoretic-based procedures include Akaike’s information criterion (AIC) [1], corrected Akaike (AICc) [2], minimum description length (MDL) [3], normalized maximum likelihood (NML) [4], Hannan-Quinn criterion (HQC) [5], conditional model-order estimation (CME) [6], and the efficient detection criterion (EDC) [7]. From a practical point of view, it is difficult to decide which model order selection criterion to use. Many of them perform reasonably well when the signal-to-noise ratio (SNR) is high. The discrepancies in their performance, however, become more evident when the SNR is low. In those situations, the performance of the given technique is not only determined by the model structure (say a polynomial trend versus a Fourier series) but, more importantly, by the relative values of the parameters within the model. This makes the comparison between the model-order selection algorithms difficult as within the same model with a given order one could find an example for which one of the methods performs favourably well or fails [6, 8]. Our aim is to improve the performance of the model order selection criteria in cases where the SNR is low by considering a model-selection searching procedure that takes into account not only the full-model order search but also a partial model order search within the given model order. Understandably, the improvement in the performance of the model order estimation is at the expense of additional computational complexity.

The evaluation of qualitative methods selection in the field of design and emotion

The aim of this paper is to aid researchers in selecting appropriate qualitative methods in order to develop and improve future studies in the field of emotional design. These include observations, think-aloud protocols, questionnaires, diaries and interviews. Based on the authors’ experiences, it is proposed that the methods under review can be successfully used for collecting data on emotional responses to evaluate user product relationships. This paper reviews the methods; discusses the suitability, advantages and challenges in relation to design and emotion studies. Furthermore, the paper outlines the potential impact of technology on the application of these methods, discusses the implications of these methods for emotion research and concludes with recommendations for future work in this area.

Evidence of disagreement between patient-perceived change and conventional longitudinal evaluation of change in health-related quality of life among older adults

Objective: To identify agreement levels between conventional longitudinal evaluation of change (post–pre) and patient-perceived change (post–then test) in health-related quality of life. Design: A prospective cohort investigation with two assessment points (baseline and six-month follow-up) was implemented. Setting: Community rehabilitation setting. Subjects: Frail older adults accessing community-based rehabilitation services. Intervention: Nil as part of this investigation. Main measures: Conventional longitudinal change in health-related quality of life was considered the difference between standard EQ-5D assessments completed at baseline and follow-up. To evaluate patient-perceived change a ‘then test’ was also completed at the follow-up assessment. This required participants to report (from their current perspective) how they believe their health-related quality of life was at baseline (using the EQ-5D). Patient-perceived change was considered the difference between ‘then test’ and standard follow-up EQ-5D assessments. Results: The mean (SD) age of participants was 78.8 (7.3). Of the 70 participants 62 (89%) of data sets were complete and included in analysis. Agreement between conventional (post–pre) and patient-perceived (post–then test) change was low to moderate (EQ-5D utility intraclass correlation coefficient (ICC)¼0.41, EQ-5D visual analogue scale (VAS) ICC¼0.21). Neither approach inferred greater change than the other (utility P¼0.925, VAS P¼0.506). Mean (95% confidence interval (CI)) conventional change in EQ-5D utility and VAS were 0.140 (0.045,0.236) and 8.8 (3.3,14.3) respectively, while patient-perceived change was 0.147 (0.055,0.238) and 6.4 (1.7,11.1) respectively. Conclusions: Substantial disagreement exists between conventional longitudinal evaluation of change in health-related quality of life and patient-perceived change in health-related quality of life (as measured using a then test) within individuals.

Pattern-Based Evaluation of Scientific Workflow Management Systems

In recent years several scientific Workflow Management Systems (WfMSs) have been developed with the aim to automate large scale scientific experiments. As yet, many offerings have been developed, but none of them has been promoted as an accepted standard. In this paper we propose a pattern-based evaluation of three among the most widely used scientific WfMSs: Kepler, Taverna and Triana. The aim is to compare them with traditional business WfMSs, emphasizing the strengths and deficiencies of both systems. Moreover, a set of new patterns is defined from the analysis of the three considered systems.