Search results

Ship route prediction (SRP) is a quite complicated task, which enables the determination of the next position of a ship after a given period of time, given its current position. This paper aims to describe a study, which compares five families of multiclass classification algorithms to perform SRP.

Tested algorithm families include: Naive Bayes (NB), nearest neighbors, decision trees, linear algorithms and extension from binary. A common structure for all the algorithm families was implemented and adapted to the specific case, according to the test to be done. The tests were done on one month of real data extracted from automatic identification system messages, collected around the island of Malta.

Experiments show that K-nearest neighbors and decision trees algorithms outperform all the other algorithms. Experiments also demonstrate that linear algorithms and NB have a very poor performance.

This study is limited to the area surrounding Malta. Thus, findings cannot be generalized to every context. However, the methodology presented is general and can help other researchers in this area to choose appropriate methods for their problems.

The results of this study can be exploited by applications for maritime surveillance to build decision support systems to monitor and predict ship routes in a given area. For example, to protect the marine environment, the use of SRP techniques could be used to protect areas at risk such as marine protected areas, from illegal fishing.

The paper proposes a solid methodology to perform tests on SRP, based on a series of important machine learning algorithms for the prediction.

This paper aims to describe Tourpedia, a website about tourism, built on open data provided by official government agencies. Tourpedia provides data under a public license.

Tourpedia is built upon a modular architecture, which allows a developer to add a new source of data easily. This is achieved through a simple mapping language, namely, Tourpedia mapping language, which maps the original open data set model to the Tourpedia data model.

Tourpedia contains more than 70.000 accommodations, downloaded from open data provided by Italian, French and Spanish regions.

Tourpedia presents some limitations. First, extracted data are not homogeneous and often they are incomplete or wrong. Second, Tourpedia contains only accommodations. Finally, at the moment Tourpedia covers only some Italian, French and Spanish regions.

The most important implication of Tourpedia concerns the construction of a single access point for all Italian, French and Spanish open data about accommodations. In addition, a simple mechanism for the integration of new sources of open data is defined.

The current version of Tourpedia opens also the road to three new possible social scenarios. First, Tourpedia could be transformed into an open source of updated information about tourism. Second, Tourpedia could be empowered to support tours, which include some tourist attractions and/or events and suggest the nearest accommodations. Finally, Tourpedia may help tourists to discover unknown places.

Tourpedia constitutes an access point for data sets providers, application developers and tourists because it provides a unique website.

本论文介绍了Tourpedia, 一种以政府提供的开放数据为基础建立的旅游网站。Tourpedia通过公共执照来提供数据。

Tourpedia采用模块型结构建设而成, 方便开放商增加新数据源。这种设计通过简单映射语言, 即Tourpedia Mapping Language（TML）, 使得原开放数据模型映射到Tourpedia Data Model（TDM）。

Tourpedia包含70,000多家住宿服务, 可从意大利、法国、和西班牙国家区域提供的开放数据中下载。

Tourpedia有一些限制。首先, 其数据并非均质而且很多情况下不完整或者错误。第二, Tourpedia只包含住宿业数据。最后, 目前Tourpedia只包含一些意大利、法国、和西班牙国家区域的数据。

Tourpedia最重要的实践启示就是其通过单一信息渠道以涵盖所有意大利、法国、和西班牙国家区域关于住宿业的开放数据。此外, 新源开放数据的整合机制简单。

当前Tourpedia版本展开了三种社会场景的可能。首先, Tourpedia可以被改造成更新版的旅游信息开放数据源。第二, Tourpedia可以被用来支撑旅游活动, 包括提供一些游客景点和/或活动和就近住宿信息等。最后, Tourpedia可以帮助游客探索未知旅游目的地。

Tourpedia是一个独特的网站, 作为数据源, 为数据提供者、应用程序开发者、和游客提供便利。