International Journal of Semantic Computing

Rapid urbanization has brought about an influx of people to cities, tipping the scale between urban and rural living. Population predictions estimate that 64% of the global population will reside in cities by 2050. To meet the growing resource needs, improve management, reduce complexities, and eliminate unnecessary costs while enhancing the quality of life of citizens, cities are increasingly exploring open innovation frameworks and smart city initiatives that target priority areas including transportation, sustainability, and security. The size and heterogeneity of urban centers impede progress of technological innovations for smart cities. We propose a Smart Stadium as a living laboratory to balance both size and heterogeneity so that smart city solutions and Internet of Things (IoT) technologies may be deployed and tested within an environment small enough to practically trial but large and diverse enough to evaluate scalability and efficacy. The Smart Stadium for Smart Living initiative brings together multiple institutions and partners including Arizona State University (ASU), Dublin City University (DCU), Intel Corporation, and Gaelic Athletic Association (GAA), to turn ASU’s Sun Devil Stadium and Ireland’s Croke Park Stadium into twinned smart stadia to investigate IoT and smart city technologies and applications.

Learning to hash is receiving increasing research attention due to its effectiveness in addressing the large-scale similarity search problem. Most of the existing hashing algorithms are focused on learning hash functions in the form of numeric quantization of some projected feature space. In this work, we propose a novel hash learning method that encodes features’ relative ordering instead of quantizing their numeric values in a set of low-dimensional ranking subspaces. We formulate the ranking-based hash learning problem as the optimization of a continuous probabilistic error function using softmax approximation and present an efficient learning algorithm to solve the problem. As a generalization of Winner-Take-All (WTA) hashing, the proposed algorithm naturally enjoys the numeric stability benefits of rank correlation measures while being optimized to achieve high precision with very compact code. Additionally, the proposed method can also be easily extended to nonlinear kernel spaces to discover ranking structures that can not be revealed in linear subspaces. We demonstrate through extensive experiments that the proposed method can achive competitive performances as compared to a number of state-of-the-art hashing methods.

Video scene detection is the task of dividing a video into semantic sections. To perform this fundamental task, we propose a novel and effective method for temporal grouping of scenes using an arbitrary set of features computed from the video. We formulate the task of video scene detection as a generic optimization problem to optimally group shots into scenes, and propose an efficient procedure for solving the optimization problem based on a novel dynamic programming scheme. This unique formulation directly results in a temporally consistent segmentation, and has the advantage of being parameter-free, making it applicable across various domains. We provide detailed experimental results, showing that our algorithm outperforms current state-of-the-art methods. To assess the comprehensiveness of this method even further, we present experimental results testing different types of modalities and their applicability in this formulation.

In the past decades, we have witnessed an explosion of multimedia data, especially with the development of social media websites and blooming popularity of smart devices. As a result, multimedia semantic concept mining and retrieval whose objective is to mine useful information from the large amount of multimedia data including texts, images, and videos has become more and more important. The huge amount of multimedia data and the semantic gap between low-level features and high-level semantic concepts have made it even more challenging. To address these challenges, the correlations among the classes can provide important context cues to help bridge the semantic gap. Meanwhile, many real-world datasets do not have uniform class distributions while the minority instances actually represent the concept of interests, like frauds in transactions, intrusions in network security, and unusual events in surveillance. Despite extensive research efforts, imbalanced concept retrieval remains one of the most challenging research problems in multimedia data mining. Different from existing frameworks regarding concept correlations among labels, this paper presents a novel concept correlation analysis model using the correlation between the retrieval scores and labels. Experimental results on the TRECVID benchmark datasets demonstrate that the proposed framework can enhance imbalanced concept mining and retrieval even with trivial scores from the minority class.

When it comes to design and editing, complex ontologies have much in common with large and complex software systems. The ontology editor presented in this article adapts two solution approaches from software engineering to the task of ontology editing following the rationale that similar problems can be tackled with similar solutions. The first of the approaches is aspect orientation which allows to look at a problem from different perspectives and editing each perspective separately even with different names for one and the same entity. The article describes this approach’s theoretical foundations as well as the data model required for its implementation. The second approach is an auto-completion-like feature that checks whether editing steps on the ABox level are consistent with rules modeled on the TBox level and the ontology in general. The editor also features a visual language that is designed to facilitate editing OWL Lite based ontologies.