1,721,371 research outputs found
Predicting Traffic Congestion in Presence of Planned Special Events
No full textThe recent availability of datasets on transportation networks with high spatial and temporal resolution is enabling new research activities in the fields of Territorial Intelligence and Smart Cities. Within these domains, in this paper we focus on the problem of predicting traffic congestion in
urban environments caused by attendees leaving a Planned Special Events (PSE), such as a soccer game or a concert. The proposed approach consists of two steps. In the first one, we use the K-Nearest Neighbor algorithm to predict congestions within the vicinity of the venue (e.g. a Stadion) based on the knowledge from past observed events. In the second step, we identify the road segments that are likely to show congestion due to PSEs and map our prediction to these road segments. To visualize the traffic trends and congestion behavior we learned and to allow Domain Experts to evaluate the situation we also provide a Google Earth-based GUI. The proposed solution has been experimentally proven to outperform current state of the art solutions by about 35% and thus it can successfully serve to reliably predict congestions due to PSEs
Scalable Processing of Massive Traffic Datasets
No full textThe availability of new massive datasets about traffic, coming from Smart Sensor Networks composed of Vehicles, Mobile Phones and other GPS-equipped devices, is enabling the development of novel Intelligent Applications for Mobility. Among these, a hot and recent research topic is to discover vehicular traffic patterns from these datasets, to provide better mobility predictions. Nevertheless, from a practical stance, there are many technological challenges limiting the applicability of these solutions on the market. Especially the scalability and performance of such systems raise major concerns, given the massive amount of spatio-temporal data to be processed. The current industrial solution is to impose constraints and/or simplifications on both the spatial component of the data and on the employed learning algorithms.
This has the drawback that not all the potential information is exploited. To overcome this problem, in this chapter we present a scalable architecture aimed at exploit the computational and storage capabilities of the Cloud. Special emphasis is posed on the analysis of the underlying data models we defined to handle massive dataset for providing vehicular traffic predictions. This solution is actually being evaluated in an industrial context
Self-Organized Learning Networks for Lifelong Learning: RTD Programme 2003-2008
No full textPresentation for the research group of Prof. Dr. Wolfgang Nejdl. Hannover, November 24th 200
Using the X3D Language for Adaptive Manipulation of 3D Web Content
No full textWeb sites that include 3D content, i.e. Web sites where users navigate and interact (at least partially) through a 3D graphical interface, are increasingly employed in different domains, such as tutoring and training, tourism, e-commerce and scientific visualization. However, while a substantial body of literature and software tools is available about making 2D Web sites adaptive, very little has been published on the problem of personalizing 3D Web content and interaction. In this paper, we describe how we are exploiting a recently proposed 3D Web technology, i.e. the X3D (eXtensible 3D) language, for adaptive manipulation of 3D Web content
The graph structure in the web - analyzed on different aggregation levels
Get PDFKnowledge about the general graph structure of theWorldWideWeb is important for understanding the social mechanisms that govern its growth, for designing ranking methods, for devising better crawling algorithms, and for creating accurate models of its structure. In this paper, we analyze a large web graph. The graph was extracted from a large publicly accessible web crawl that was gathered by the Common Crawl Foundation in 2012. The graph covers over 3:5 billion web pages and 128:7 billion hyperlinks. We analyze and compare, among other features, degree distributions, connectivity, average distances, and the structure of weakly/strongly connected components. We conduct our analysis on three different levels of aggregation: page, host, and pay-level domain (PLD) (one “dot level” above public suffixes). Our analysis shows that, as evidenced by previous research (Serrano et al., 2007), some of the features previously observed by Broder et al., 2000 are very dependent on artifacts of the crawling process, whereas other appear to be more structural. We confirm the existence of a giant strongly connected component; we however find, as observed by other researchers (Donato et al., 2005; Boldi et al., 2002; Baeza-Yates and Poblete, 2003), very different proportions of nodes that can reach or that can be reached from the giant component, suggesting that the “bow-tie structure” as described by Broder et al. is strongly dependent on the crawling process, and to the best of our current knowledge is not a structural property of the Web. More importantly, statistical testing and visual inspection of size-rank plots show that the distributions of indegree, outdegree and sizes of strongly connected components of the page and host graph are not power laws, contrarily to what was previously reported for much smaller crawls, although they might be heavy tailed. If we aggregate at pay-level domain, however, a power law emerges. We also provide for the first time accurate measurement of distance-based features, using recently introduced algorithms that scale to the size of our crawl (Boldi and Vigna, 2013)
Characterizing the country-wide adoption and evolution of the Jodel messaging app in Saudi Arabia
No full text
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
- …
