Scalable Skin Lesion Multi-Classification Recognition System

Skin lesion recognition is an important challenge in the medical field. In this paper, we have implemented an intelligent classification system based on convolutional neural network. First of all, this system can classify whether the input image is a dermascopic image with an accuracy of 99%. And then diagnose the dermoscopic image and the non-skin mirror image separately. Due to the limitation of the data, we can only realize the recognition of vitiligo by non-skin mirror. We propose a vitiligo recognition based on the probability average of three structurally identical CNN models. The method is more efficient and robust than the traditional RGB color space-based image recognition method. For the dermoscopic classification model, we were able to classify 7 skin lesions, use weighted optimization to overcome the unbalanced data set, and greatly improve the sensitivity of the model by means of model fusion. The optimization and expansion of the system depend on the increase of database.     

Analysis of Underlay Cognitive Radio Networks Based on Interference Cancellation Mechanism

In this paper, we investigate the performance of secondary transmission scheme based on Markov ON-OFF state of primary users in Underlay cognitive radio networks. We propose flexible secondary cooperative transmission schemewith interference cancellation technique according to the ON-OFF status of primary transmitter. For maximal ratio combining (MRC) at destination, we have derived exact closed-form expressions of the outage probability in different situations. The numerical simulation results also reveal that the proposed scheme improve the secondary transmission performance compared with traditional mechanism in terms of secondary outage probability and energy efficiency.     

Learning about learning: patterns of sharing of research knowledge among Education,Border, and Cognitive Science fields

This study explores the patterns of exchange of research knowledge among Education Research, Cognitive Science, and what we call “Border Fields.” We analyze a set of 32,121 articles from 177 selected journals, drawn from five sample years between 1994 and 2014. We profile the references that those articles cite, and the papers that cite them. We characterize connections among the fields in sources indexed by Web of Science (WoS) (e.g., peer-reviewed journal articles and proceedings), and connections in sources that are not (e.g., conference talks, chapters, books, and reports). We note five findings—first, over time the percentage of Education Research papers that extensively cite Cognitive Science has increased, but the reverse is not true. Second, a high percentage of Border Field papers extensively cite and are cited by the other fields. Border Field authors’ most cited papers overlap those most cited by Education Research and Cognitive Science. There are fewer commonalities between Educational research and Cognitive Science most cited papers. This is consistent with Border Fields being a bridge between fields. Third, over time the Border Fields have moved closer to Education Research than to Cognitive Science, and their publications increasingly cite, and are cited by, other Border Field publications. Fourth, Education Research is especially strongly represented in the literature published outside those WoS-indexed publications. Fifth, the rough patterns observed among these three fields when using a more restricted dataset drawn from the WoS are similar to those observed with the dataset lying outside the WoS, but Education Research shows a far heavier influence than would be indicated by looking at WoS records alone.

     

Co-Evolution in the Successful Learning of Backgammon Strategy

Following Tesauro's work on TD-Gammon, we used a 4,000 parameter feedforward neural network to develop a competitive backgammon evaluation function. Play proceeds by a roll of the dice, application of the network to all legal moves, and selection of the position with the highest evaluation. However, no backpropagation, reinforcement or temporal difference learning methods were employed. Instead we apply simple hillclimbing in a relative fitness environment. We start with an initial champion of all zero weights and proceed simply by playing the current champion network against a slightly mutated challenger and changing weights if the challenger wins. Surprisingly, this worked rather well. We investigate how the peculiar dynamics of this domain enabled a previously discarded weak method to succeed, by preventing suboptimal equilibria in a meta-game of self-learning.     

Winds of change – Predicting water-based recreationists' support and opposition for offshore wind energy development in the Great Lakes

This study examined the factors influencing water-based recreationists' perceptions of support and opposition towards off-shore wind energy development (OWD) on Lake Erie. Much of the proposed or future Lake Erie OWD infrastructure may either be within or adjacent to public lands, waters, and protected areas, raising concerns about the potential environmental and social impacts upon recreation stakeholders. The limited body of OWD research within the United States has suggested there are numerous factors that may influence overall perceptions of support and opposition such as political orientation and beliefs in climate change. Moreover, recent research has proposed that the perceived recreation impact of OWD may be the most important predictor of support and opposition. This study confirmed this premise and found the perceived recreation impact of OWD to be the strongest predictor of support. Results of a multiple linear regression suggested that political orientation (β?=?0.135), beliefs in the anthropogenic causation of climate change (β?=?0.207), beliefs in the occurrence of climate change (β?=?0.213), and the perceived recreation impact of OWD among water-based recreationists (β?=?0.439) were significant predictors of support for OWD on Lake Erie (R²?=?0.46). Study findings corroborated previous research which suggested that regional climate change beliefs and political attitudes may influence support for OWD. From a policy and management standpoint, study results highlight the importance of assessing and communicating recreation experience and use impacts when planning, developing, and managing OWD and related decisions in the United States.     

Integrating affective learning into intelligent tutoring systems

Affectivity has influence in learning face-to-face environments and improves some aspects in students, such as motivation. For that reason, it is important to integrate affectivity elements into virtual environments. We propose a conceptual model that suggests which elements of tutor, student and dialogue should be integrated and implemented into learning systems. We design an ontology guided by methontology, and apply a mathematical evaluation (OntoQA) to determine the richness of the proposed model. The mathematical evaluation states that the proposed model has relationship richness and horizontal nature. We developed a software application implementing the conceptual model in order to prove its effectivity to generate students’ motivation. The findings suggest that the implemented affective learning ontology impacts positively the motivation in students with low academic performance, in female students and in engineering students.     

Multi‐Modal Perception for Selective Rendering

A major challenge in generating high‐fidelity virtual environments (VEs) is to be able to provide realism at interactive rates. The high‐fidelity simulation of light and sound is still unachievable in real time as such physical accuracy is very computationally demanding. Only recently has visual perception been used in high‐fidelity rendering to improve performance by a series of novel exploitations; to render parts of the scene that are not currently being attended to by the viewer at a much lower quality without the difference being perceived. This paper investigates the effect spatialized directional sound has on the visual attention of a user towards rendered images. These perceptual artefacts are utilized in selective rendering pipelines via the use of multi‐modal maps. The multi‐modal maps are tested through psychophysical experiments to examine their applicability to selective rendering algorithms, with a series of fixed cost rendering functions, and are found to perform significantly better than only using image saliency maps that are naively applied to multi‐modal VEs.     

Area‐Preserving Parameterizations for Spherical Ellipses

We present new methods for uniformly sampling the solid angle subtended by a disk. To achieve this, we devise two novel area‐preserving mappings from the unit square [0,1]² to a spherical ellipse (i.e. the projection of the disk onto the unit sphere). These mappings allow for low‐variance stratified sampling of direct illumination from disk‐shaped light sources. We discuss how to efficiently incorporate our methods into a production renderer and demonstrate the quality of our maps, showing significantly lower variance than previous work.     

Interaction and Outcomes in Collaborative Storytelling Systems: a Framework,a Field Study,and a Model

In the last decades, advances in interactive information technologies have facilitated collaborative fiction writing, which has become widespread and large-scale. This paper proposes a framework to analyze collaborative storytelling systems, made of a set of parameters divided into six conceptual areas. Four of them relate to the systems and two (process and output) to the results of the collaboration. Through this framework we can study more precisely these different factors of the systems, their interplay, and how they impact the creators’ performance. We also present a controlled extended-duration field study on collaborative storytelling, and we use this framework to comparatively analyze these observations and other relevant experiences in the field of co-creation of shared narrative spaces. As a result, we propose a human-information interaction model for collaborative narrative systems, intended to better support co-creation and address the barriers of this kind of systems turning them into new opportunities for collaboration.