Information Fusion and Intelligent Geographic Information Systems (IF&IGIS'17)

The major purpose of this paper is to discuss two phenomena: (1) geographic information systems (GIS) and (2) space. The discussion is from a computer science point-of-view. As it is well known, every point in GIS can be presented in 1D, 2D, 3D or nD dimension. If we take a look on linear algebra, we can find definitions of “space” and “subspace.” Therefore, the major point of our discussion is to determine space and subspace in GIS and to introduce some measures for dynamic space borders and other properties that can be calculated by different methods. The complexity of the proposed paper arrives from an original complexity of space definition and because of the fact that it is used in abstract algebra, philosophy, and GIS paradigms together.

This article presents important challenges and progress toward the management of data regarding the maritime domain for supporting analysis tasks. The article introduces our objectives for big data–analysis tasks, thus motivating our efforts toward advanced data-management solutions for mobility data in the maritime domain. The article introduces data sources to support specific maritime situation–awareness scenarios that are addressed in the datAcron [The datAcron project has received funding from the European Union’s Horizon 2020 research and innovation program under grant agreement No 687591 (http://​datacron-project.​eu).] project, presents the overall infrastructure designed for managing and exploiting data for analysis tasks, and presents a representation framework for integrating data from different sources revolving around the notion of semantic trajectories: the datAcron ontology.

This paper deals with data structures within GIS. Continuous phenomena are usually represented by raster structures for simplicity reasons. With such structures, spatial repartitions of the data are not easily interpretable. Moreover, in an overlapping/clustering context, these structures remove the links between the data and the algorithms. We propose a vector representation of such data based on non-regular multi-ring polygons. The structure requires multi-part nested polygons and new set operations. We present the formalism based on belief theory and uncertainty reasoning. We also detail the implementation of the structures and the set operations. The structures and the set operations are illustrated in the context of forest classification having diffuse transitions.

In spatial and urban sciences, it is customary to partition study areas into sub-areas—so-called regions, zones, neighborhoods, or communities—to carry out analyses of the spatial patterns and processes of socio-spatial phenomena. The purposeful delineation of these sub-areas is critical because of the potential biases associated with MAUP and UGCoP. If one agrees to characterize these sub-areas based on their homogeneity on a certain attribute, these homogeneous areas (patches) can be detected by data-driven algorithms. This study aims to evaluate the effectiveness and performance of five popular spatial clustering and regionalization algorithms (AZP, ARISeL, max-p-regions, AMOEBA, and SOM) for detecting attribute-based homogeneous patches of different sizes, shapes, and those with homogeneous values. The evaluation follows a quasi-experimental approach: It is based on 68 simulated data sets where the true distribution of patches is known and focuses purely on the capability of algorithms to successfully detect patches rather than computational costs. It is the most comprehensive assessment to-date thanks to a systematic control of various conditions so that a true baseline is available for comparison purposes. Among the tested algorithms, SOM and AMOEBA were found to perform very well in detecting patches of different sizes, different shapes, including those with holes, and different homogeneous values.

With the continuous development of maritime-hardware systems, intelligent decision making in port transport becomes increasingly more important. There are three types of waterways in China, which is specific about one-way waterways, two-way waterways, and compound waterways. Modelling of vessel-scheduling optimization in ports aims at giving a concrete contribution to efficient, safe, and environmentally friendly maritime transport. The model will service to innovative the e-navigational shipping industry, which can lay the groundwork for a future vessel traffic service (VTS). These studies assess the effects of channel and berth resources to improve the operation efficiency of ports using a multi-objective vessel scheduling–optimization model. Taking the minimum total scheduling and waiting times of vessels, the model was established based on these waterways by considering safety, efficiency, and fairness. To solve the proposed model, a multi-objective genetic algorithm (MOGA) was used in this paper. Compared with the first-come, first-served (FCFS) scheduling method, the capacity-conversion times of vessels entering and leaving a port and the total scheduling time are decreased efficiently. These works contribute to improving the safety and optimization of ship scheduling catering to the intelligence trends of future maritime service portfolios (MSP).

The Northern Sea Route along the Arctic coast of Russia offers a good alternative to the Suez Canal (due to the huge reduction in distance from Western Europe to East Asia) or Panama Canal and can also be used for supporting oil and gas industry in the Arctic. However, navigation in the Arctic seas is sufficiently complicated by extreme climate and ice conditions and the general lack of the marine infrastructure throughout the Arctic Ocean. This chapter presents an approach to vessel-route planning in the Arctic seas by means of special system, intelligent GIS. Ontology, expert subsystem, and some other Artificial-Intelligence technologies are proposed as basic ones for the system implementation. The application of the technique is illustrated by way of case study of situational route planning for a vessel navigating along the Northern Sea Route.

INFORMATION for various monitoring systems usually comes from heterogeneous sources such as AIS, radars, Internet, etc. However, not all sources can be considered equally reliable; furthermore, the quality of transmitted data also differs. It has been deemed necessary to solve the problem of ranking sources according to their credibility based on expert information and a randomised aggregated indices method (RIAM).

Regarding aiming at multiple mobile objects in a complex water traffic–navigation environment, the chapter puts forward a route-planning method based on the complexity map. First, a Complexity Map was established according to the theory of complexity measurement. Then, combined with the A* algorithm, the actual cost was modified by making use of the distribution of the complexity values. Meanwhile, to reduce the distance of the whole voyage and avoid the local minimum in the process of path-finding, the Euclidean distance from the current point to the target was set to estimate heuristic cost. In addition, by using the standardization method, the value of complexity and distance became dimensionless. Finally, considering the ship dimensions, a channel-boundary constraint was added. The experimental results show that in the case of satisfying the ship dimensions, the best path is close to the shortest route and avoids all the high complex areas.

In the present research, we are concerned with the problem of forecasting marine radar-visibility zones under various meteorological conditions. The existing widespread models describing the electromagnetic wave propagation around the Earth, such as AREPS and PETOOL, demonstrate the presence of some weak points in their conceptions. The method of calibration and verification of the models, which contain artificial unknown parameters, was elaborated to obtain the desired accuracy in calculations of the electromagnetic field.

The article describes the algorithm component of universal an Earth remote-sensing data (RDS) system. A comparative analysis of algorithms that are used to solve problems related to all stages of analysis—preliminary processing, selection of informative elements, description of informative elements, and classification of descriptions as well as their interfaces—is proposed. Data structures to store raw data and intermediate calculations are discussed. Theoretical results are confirmed with computer experiments and practical realization in an RSD-analysis system. The structure of the developed universal RSD-analysis system and an example of scenarios for the analysis of real data is considered.

This chapter regards the main features of an efficiency evaluation of bi-static and multi-static active sonar systems on the basis of modeling and visualization of the expected surveillance zones. Assessment of the impact of information-support quality of geographic information systems on the accuracy of calculation of the expected surveillance zones for bi-static and multi-static active sonars under various hydrological and acoustic conditions for various models of the inhomogeneous marine medium is performed.

Modern measuring and control instruments allow to describe the environmental properties that influence the search efforts using monitoring tools. These tools apply for the search of alarmed objects in the interest of navigation security and detecting objects of maritime activities. The scientific literature describes only the problem of the search-effort distribution when the observer’ possibilities do not depend on their location and direction of the search object. The interesting case is when changing environmental conditions define unique conditions of object detection at the each point of the search area. In this case, all objects of the search operation are represented as geospatial objects, and the search effort distribution is provided by GIS support. This chapter discusses the following areas of GIS support: attributes of geospatial-object generation; manipulation of geospatial data for problem solving of search-effort distribution; and graphical interpretation of initial, intermediate, and final data of problem solving.

We investigate community structures in disaggregated cargo flows that are part of the global maritime trade. Individual origin–destination flows of containerized cargo on the hinterland-side of the global maritime trade collectively form a complex and large-scale network. We use community-detection algorithms to identify natural communities that exist in such highly asymmetric networks. The analysis compares the structures that are identified in two geographic regions: China and Europe. We trace shipments by their trajectory patterns considering domestic movement, cross-country movement, and trans-shipments. Then we use the Infomap and Walktrap algorithms to detect structural equivalence between shipments from hinterland cities to port cities. Data consist of individual flows of containerized trade bound for the United States in October 2006. We draw conclusions on the relative performance of the two algorithms on asymmetric data networks, on the effects of the geographic context and type of flows on their performance, and on the spatial integrity of community structures and the impact of market contestability on the semantics of detected communities.

In this chapter, capabilities of the simulation modeling methods based on modern informational technology are considered in order to help increase decision validity, efficiency of organization, and functioning of monitoring systems and of sea environmental control. The necessity and possibility of application of such informational technologies as geoinformational technologies and expert systems in the modeling structure is determined. It is demonstrated that application of an information technology complex allows to significantly expand the modeling capabilities of processes control and monitoring while taking into account the solution to harmonization problem as well as the integration and fusion of data as a part of simulation modeling problems.

Floating-car data (FCD) are never perfectly accurate due to various noises. To make FCD available, we propose a novel spatio-temporal particle filter ST-PF for FCD pre-processing. First we analyze the causes of errors and the shortcomings of previous studies. Second, we introduce the spatio-temporal constraints into the modeling of ST-PF. We also devise a novel iterating strategy for the recurrence of particle filtering based on sequential-importance sampling (SIS). We further design a series of experiments and compare the performances with that of other four traditional filters, namely, the mean filter, the median filter, the Kalman filter, and the original particle filter. The final results show ST-PF is much more effective for noise reduction and improvement of map-matching performance and shows a promising direction for FCD pre-processing.

There has been a growing need for the use of information and decision-making systems in evacuation planning as a part of emergency management in order to reduce as, many losses as possible. To minimize damage, an accurate and effective evacuation plan that gives more than one evacuation path considering the changing road conditions in minimal time is imperative. The use of Geographic Information Systems (GIS), Decision-Support Systems (DSS), and shortest-path algorithms as a solution for this problem is the subject of this chapter. A framework for providing preparedness and response plans after an emergency event occurs is proposed. The plan provided by the proposed framework includes a calculated degree of hazard posed by that event (three emergency models are incorporated), the radius of affected area (a spatial overlay to draw a buffer zone is conducted), identification of all safe destinations, and the best alternative paths for evacuation from inside the buffer zone to safe destinations based on the dynamic road conditions displayed on the map. To identify all of the safe destinations and obtain the best alternatives, a graph theory–based model is proposed based on a developed algorithm to get everyone the closest safe destinations. Dijkstra’s algorithm is executed from a single source inside the buffer to all identified safe destinations resulting in the minimum travel time path and other alternative paths displayed on the map. To evaluate the proposed framework, a GIS-based evacuation-planning (G-BEP) prototype is implemented. The prototype is tested with different emergency types, different variables, and different street maps. The prototype is also found to respond differently based on the dynamic road conditions.

A complete and accurate geographic dataset is critical for relevant analysis and decision-making. This chapter proposes a four-step geographic data-conflation system: preprocessing, automatic conflation, evaluation, and manual adjustments. The automatic-conflation component uses an optimization approach to find matched features and a rubber-sheeting approach to complete spatial transformation. This system was tested using two bikeway datasets in Los Angeles County, California, from an authoritative source (Los Angeles County Metropolitan Transportation Authority) and an open source (OpenStreetMap). While bikeways that are already in both datasets are improved in terms of positional accuracy and attribute completeness, the conflated bikeway dataset also integrates complementary data in either of the input datasets. Experiments demonstrate the advantages of using crowd-sourced data to improve official bikeway data, which is important for building and maintaining high-quality bicycle-infrastructure datasets. The framework described in this chapter can be adapted to conflate other types of data themes.

The use of intelligent geographical information systems in the tourism industry allows for providing access to information about attractions during a tourist’s trip. Navigation is a main concern for tourists. Attractions can be located far away from the tourist’s current location, and the tourist usually reaches a desired attraction with the use of available transportation modes: on foot, by personal car, or on public transport. The present work describes a service for an intelligent mobile-tourist guide (TAIS) that supports routing between attractions using transportation modes inside the city. The tourist context is considered during the routing process. The service has been tested over the transport network of St. Petersburg, which is a Russian megalopolis with population of >5 million people.

Geo-information systems are widely applied in modern humanities. Such research studies are based on the use of geo-information technologies’ universal functionality; however, there is an objective shortage of the specialized GIS-analysis tools intended for historic, ethnographic, and other research. Geo-chronological tracking gives us an example of the methodological and technological analysis tool specifically developed for solving a given class of historical problems. This chapter is dedicated to the analysis of the principle capabilities and specifics of such a GIS tool.