Discovering Regularity Patterns of Mobility Practices Through Mobile Phone Data

The chapter addresses the issue of analyzing and mapping mobility practices by using different kinds of mobile phone network data that provide geo-located information on mobile phone activity at a high spatial and temporal resolution. The authors present and discuss major findings and drawbacks based on an application carried out on the Milan urban region (Lombardy, Northern Italy) and suggest possible implications for policies.

Environmental Monitoring Based on the Wireless Sensor Networking Technology

This chapter investigates real-life environmental monitoring applications based on wireless sensor networks (WSNs). Wireless sensor networking is an emerging technology, which has been adopted by many scientific fields in order to accurately and effectively monitor climate phenomena such as air pollution, destruction phenomena, etc. It has also been widely used in agriculture as well as in horticulture for field monitoring. In this chapter, the authors provide a critical overview of the basic components existing WSN deployments use. They also categorize these deployments, 111 in total, into five different field categories in order to provide a general view of the technologies used, the conditions under which the deployments were conducted, and much more. Then, five easy-to-use guides are provided discussing basic considerations for deploying WSNs in each of these fields. In order to showcase the usefulness of consulting the resulted guides, the authors consider representative application scenarios for each of these field deployments.

Discriminating Biomass and Nitrogen Status in Wheat Crop by Spectral Reflectance Using ANN Algorithms

Precision agriculture has the goal of reducing cost which is difficult when it is related to fertilizer application. Nitrogen (N) is the nutrient absorbed in greater amounts by crops and the N fertilizer application presents significant costs. The use of spectral reflectance sensors has been studied to identify the nutritional status of crops and prescribe varying N rates. This study aimed to contribute to the determination of a model to discriminating biomass and nitrogen status in wheat through two sensors, GreenSeeker and Crop Circle, using the resilient propagation and backpropagation artificial neural networks algorithms. As a result, a strong correlation to the sensor readings with the aboveground biomass production and N extraction by plants was detected. For both algorithms a satisfactory model for estimating wheat dry biomass production was established. The best backpropagation and resilient propagation models defined showed better performance for the GreenSeeker and Crop Circle sensors, respectively.

Processing and Visualizing Floating Car Data for Human-Centered Traffic and Environment Applications

In the era of the internet of things and big data, modern cars have become mobile electronic systems or computers on wheels. Car sensors record a multitude of car- and traffic-related data as well as environmental parameters outside the vehicle. The data recorded are spatio-temporal by nature (floating car data) and can thus be classified as geodata. Their geospatial potential is, however, not fully exploited so far. In this chapter, the authors present an approach to collect, process, and visualize floating car data for traffic- and environment-related applications. It is demonstrated that cartographic visualization, in particular, is an effective means to make the enormous stocks of machine-recorded data available to human perception, exploration, and analysis.

Could NoSQL Replace Relational Databases in FMIS?

FMIS (farm management information systems) is the computational tool responsible to process data to get information that improves farmers' decision support. The data manipulated in FMIS is originated from diverse sources, stored, and read whenever necessary without subsequent modifications, thus dismissing the necessity of complex data storage systems such as offered by the relational model. Due to its capability to handle with high performance, a large amount of unstructured data and to reduce the complexity of applications, the NoSQL data storage model, a convenient alternative to relational model, recently gained a lot of attention in the information systems market. This way, this chapter discusses how NoSQL models could improve the FMIS architecture and performance when used as data storage. Some works that have already benefited from NoSQL model adoption are reviewed and convenient use cases where both data storage models could be well used in FMIS's architecture are advised and discussed.

Mental Informatics and Agricultural Issues

This chapter presents an approach to understanding the importance of connected aspects of a topic, such as the relevance of issues for global change or for sustainable agriculture. The approach, Mind Genomics, identifies a specific topic, creates a battery of related questions which in concert “tell a story,” requires the researcher to provides several alternative answers to those questions, and then tests the answers as combinations, as vignettes. Respondents rate the vignettes on judgmental attributes, such as the degree to which the respondent “agrees” with the story being told by the vignette, or the emotion that the respondent feels when reading the vignette. The analysis of such data shows the impact of each of the answers, the “communication elements,” as a drive of “agreement with the values of the respondent,” and the linkage of each element to a set of emotions. Mind Genomics provides a new tool to understand responses to agricultural issues, creating in its wake the possibility of a new “mental informatics.”

New Design Approach to Handle Spatial Vagueness in Spatial OLAP Datacubes

Spatial OLAP (SOLAP) technologies are dedicated to multidimensional analysis of large volumes of (spatial) data. Spatal data are subject to different types of uncertainty, in particular spatial vagueness. Although several researches propose new models to cope with spatial vagueness, their integration in SOLAP systems is still in an embryonic state. Also, analyzing multidimensional data with metadata brought by the exploitation of the new models can be too complex and demanding for decision makers. To help reduce spatial vagueness consequences on the exactness of SOLAP analysis queries, the authors present a new approach for designing SOLAP datacubes based on end-users' tolerance to the risks of misinterpretation of fact data. An experimentation of the new approach on agri-environmental data is also proposed.

InWaterSense

A shift in the water monitoring approach from traditional grab sampling to novel wireless sensors is gaining in popularity not only among researchers but also in the market. These latest technologies readily enable numerous advantageous monitoring arrangements like remote, continuous, real-time, and spatially dense and broad in coverage measurements, and identification of long-term trends of parameters of interest. Thus, a WSN system is implemented in a river in Kosovo as part of the InWaterSense project to monitor its water quality parameters. It is one of the first state-of-the-art technology demonstration systems of its kind in the domain of water monitoring in developing countries like Kosovo. Water quality datasets are transmitted at pre-programmed intervals from sensing stations deployed in the river to the server at university via the GPRS network. Data is then made available through a portal to different target groups (policymakers, water experts, and citizens). Moreover, the InWaterSense system behaves intelligently like staying in line with water quality regulatory standards.

Introducing Activity-Based Costing in Farm Management

Recent research indicates that farm managers do not rely on adequate informative support in their decision-making processes. The authors propose a model of a farm management information system which integrates the activity-based costing approach. In describing the design and development of the “FarmBO” system, the authors provide a detailed functional requirement definition and the description of a working system prototype. The solution is designed to show the impact of general costs on the different crops, allocating them on the basis of the production cycle complexity. It includes a report section directly linked to the database which provides crop balance sheets and simulations in terms of what-if analyses. The system allows farm managers to 1) analyze deviations between budgeted and actual costs, 2) compare crop balance sheets across different years, and 3) perform sensitivity analyses. The authors account for prototype validation in two farms and discuss results and possible developments.

Semantic Web-Based Agricultural Information Integration

A huge volume of information is available in the worldwide web. However, the demand is on relevant information rather than available information, which are often heterogeneous and distributed. Agriculture is one such domain, which includes information like soil, crops, weather, etc. under one roof. This information is in different representations and structures (e.g., weather). This scenario leads to a challenge of how to integrate the available and heterogeneous agricultural information to deliver better production. As the information on the web is syntactically structured, the need is to provide semantic linkage. The semantic web supports the existing web to easily process and interpret information. In this chapter, a semantic-based agricultural information system (AIS) is proposed that addresses heterogeneity issues among weather systems and integrates information like soil, weather, crop, and fertilizers. AIS helps the farmers regarding the type of crop/soil, crop/climate, fertilizer applications, diseases, and prevention methods using effective retrieval of information from integrated systems.