Classification of lidar bare-earth points,buildings, vegetation,and small objects based on region growing and angular classifier

In recent years, light detection and ranging (lidar) systems have been intensively used in different urban applications such as map updating, communication analysis, virtual city modelling, risk assessment, and monitoring. A prerequisite to enhance lidar data content is to differentiate ground (bare earth) points that yield digital terrain models and off-terrain points in order to classify urban objects and vegetation. The increasing demand for a fast and efficient algorithm to extract three-dimensional urban features was the motive behind this work. A new combined approach to extract bare-earth points is proposed, and a novel methodology to automatically classify airborne laser data into different objects in an urban area is presented. In addition, a new concept of angular classification is introduced to differentiate buildings from vegetation and other small objects. The new angular classifier analyses the distribution of bare-earth points around unclassified point clusters to determine whether a cluster can be classified either as building or as vegetation. The experimental results confirm the high accuracy achieved to automatically classify urban objects in flat complex areas.     

Change detection in coral reef communities using Ikonos satellite sensor imagery and historic aerial photographs

For decades, aerial photographs have been the only source of very high spatial resolution data for coral reef researchers. With the launch of the Ikonos satellite in 1999, imagery with a 4 m spatial resolution in multispectral mode can now be combined with historical aerial photographs for change detection. We demonstrate this potential by combining two aerial photographs (1981 and 1992) and an Ikonos image (2000) to detect change in the coral reef communities for Carysfort Reef, Florida, USA. The results show a loss of 'coral-dominated' bottom from 52% (1981) to 16% (1992) to finally 6% (2000), a trend similar to in situ observations.     

Comparison of pixel‐based and object‐oriented image classification approaches—a case study in a coal fire area,Wuda, Inner Mongolia,China

Pixel‐based and object‐oriented classifications were tested for land‐cover mapping in a coal fire area. In pixel‐based classification a supervised Maximum Likelihood Classification (MLC) algorithm was utilized; in object‐oriented classification, a region‐growing multi‐resolution segmentation and a soft nearest neighbour classifier were used. The classification data was an ASTER image and the typical area extent of most land‐cover classes was greater than the image pixels (15 m). Classification results were compared in order to evaluate the suitability of the two classification techniques. The comparison was undertaken in a statistically rigorous way to provide an objective basis for comment and interpretation. Considering consistency, the same set of ground data was used for both classification results for accuracy assessment. Using the object‐oriented classification, the overall accuracy was higher than the accuracy obtained using the pixel‐based classification by 36.77%, and the user’s and producer’s accuracy of almost all the classes were also improved. In particular, the accuracy of (potential) surface coal fire areas mapping showed a marked increase. The potential surface coal fire areas were defined as areas covered by coal piles and coal wastes (dust), which are prone to be on fire, and in this context, indicated by the two land‐cover types ‘coal’ and ‘coal dust’. Taking into account the same test sites utilized, McNemar’s test was used to evaluate the statistical significance of the difference between the two methods. The differences in accuracy expressed in terms of proportions of correctly allocated pixels were statistically significant at the 0.1% level, which means that the thematic mapping result using object‐oriented image analysis approach gave a much higher accuracy than that obtained using the pixel‐based approach..     

Evolutionary computing in recommender systems: a review of recent research

One of the main current applications of intelligent systems is recommender systems (RS). RS can help users to find relevant items in huge information spaces in a personalized way. Several techniques have been investigated for the development of RS. One of them is evolutionary computational (EC) techniques, which is an emerging trend with various application areas. The increasing interest in using EC for web personalization, information retrieval and RS fostered the publication of survey papers on the subject. However, these surveys have analyzed only a small number of publications, around ten. This study provides a comprehensive review of more than 65 research publications focusing on five aspects we consider relevant for such: the recommendation technique used, the datasets and the evaluation methods adopted in their experimental parts, the baselines employed in the experimental comparison of proposed approaches and the reproducibility of the reported experiments. At the end of this review, we discuss negative and positive aspects of these papers, as well as point out opportunities, challenges and possible future research directions. To the best of our knowledge, this review is the most comprehensive review of various approaches using EC in RS. Thus, we believe this review will be a relevant material for researchers interested in EC and RS.     

Robust GPI Control of a New Parallel Rehabilitation Robot of Lower Extremities

International Journal of Control, Automation and Systems - In this paper, we propose a new robot for lower limbs rehabilitation by using a parallel structure. The goal of this robot is not only to...     

Ranking Pages by Topology and Popularity within Web Sites

We compare two link analysis ranking methods of web pages in a site. The first, called Site Rank, is an adaptation of PageRank to the granularity of a web site and the second, called Popularity Rank, is based on the frequencies of user clicks on the outlinks in a page that are captured by navigation sessions of users through the web site. We ran experiments on artificially created web sites of different sizes and on two real data sets, employing the relative entropy to compare the distributions of the two ranking methods. For the real data sets we also employ a nonparametric measure, called Spearman's footrule, which we use to compare the top-ten web pages ranked by the two methods. Our main result is that the distributions of the Popularity Rank and Site Rank are surprisingly close to each other, implying that the topology of a web site is very instrumental in guiding users through the site. Thus, in practice, the Site Rank provides a reasonable first order approximation of the aggregate behaviour of users within a web site given by the Popularity Rank.     

Measuring and improving the quality of development processes based on usability and accessibility

Universal Access in the Information Society - Measurement of both usability and accessibility is an important concern in software development today. However, while a great amount of attention has...     

Pattern classification with mixtures of weighted least-squares support vector machine experts

Support Vector Machine (SVM) classifiers are high-performance classification models devised to comply with the structural risk minimization principle and to properly exploit the kernel artifice of nonlinearly mapping input data into high-dimensional feature spaces toward the automatic construction of better discriminating linear decision boundaries. Among several SVM variants, Least-Squares SVMs (LS-SVMs) have gained increased attention recently due mainly to their computationally attractive properties coming as the direct result of applying a modified formulation that makes use of a sum-squared-error cost function jointly with equality, instead of inequality, constraints. In this work, we present a flexible hybrid approach aimed at augmenting the proficiency of LS-SVM classifiers with regard to accuracy/generalization as well as to hyperparameter calibration issues. Such approach, named as Mixtures of Weighted Least-Squares Support Vector Machine Experts, centers around the fusion of the weighted variant of LS-SVMs with Mixtures of Experts models. After the formal characterization of the novel learning framework, simulation results obtained with respect to both binary and multiclass pattern classification problems are reported, ratifying the suitability of the novel hybrid approach in improving the performance issues considered.     

Icon identification in context: the changing role of icon characteristics with user experience

OBJECTIVE: This research examined the relative importance of icon characteristics in determining the speed and accuracy of icon identification. BACKGROUND: Studies to date have focused on the role of one or two icon characteristics when users first experience an icon set. This means that little is known about the relative importance of icon characteristics or how the role of icon characteristics might change as users gain experience with icons. METHODS: Thirty participants carried out an icon identification task over a long series of trials to simulate learning through experience. Icon characteristics investigated included semantic distance, concreteness, familiarity, and visual complexity. RESULTS: Icon characteristics were major determinants of performance, accounting for up to 69% of the variance observed in performance. However, the importance of icon characteristics changed with experience: Semantic distance is crucial initially while icon-function relationships are learned, but familiarity is important later because it has lasting effects on access to long-term memory representations. CONCLUSION: These findings suggest that icon concreteness may not be of primary importance when identifying icons and that semantic distance and familiarity may be more important. APPLICATION: Designers need to take into account icon characteristics other than concreteness when creating icons, particularly semantic distance and familiarity. The precise importance of the latter characteristics will vary depending on whether icons are rarely encountered or frequently used.     

Vascular proteomics

The characterization of patients with acute coronary syndromes (ACS) at the molecular and cellular levels provides a novel vision for understanding the pathological and clinical expression of the disease. Recent advances in proteomic technologies permit the evaluation of systematic changes in protein expression in many biological systems and have been extensively applied to cardiovascular diseases (CVD). The cardiovascular system is in permanent intimate contact with blood, making blood-based biomarker discovery a particularly worthwhile approach. Thus, proteomics can potentially yield novel biomarkers reflecting CVD, establish earlier detection strategies, and monitor response to therapy. Here we review the different proteomic strategies used in the study of atherosclerosis and the novel proteins differentially expressed and secreted by atherosclerotic lesions which constitute novel potential biomarkers (HSP-27, Cathepsin D). Special attention is paid to MS-Imaging of atheroma plaque and the generation, for the first time, of 2-D images of lipids, showing the distribution of these molecules in the different areas of the atherosclerotic lesions. In addition new potential biomarkers have been identified in plasma (amyloid A1α, transtherytin), circulating cells (protein profile in monocytes from ACS patients) and individual cells constituents of atheroma plaques (endothelial, VSMC, macrophages) which provide novel insights into vascular pathophysiology.