Search results for "Data modeling"
showing 10 items of 112 documents
Wi-Dia: Data-Driven Wireless Diagnostic Using Context Recognition
2018
The recent densification of Wi-Fi networks is exacerbating the effects of well-known pathologies including hidden nodes and flow starvation. This paper provides an automatic diagnostic tool for detecting the source roots of performance impairments by recognizing the wireless operating context. Our tool for Wi-Fi diagnostic, named Wi-Dia, exploits machine learning methods and uses features related to network topology and channel utilization, without impact on regular network operations and working in real-time. Real-time per-link Wi-Fi diagnosis enables recovering actions for context-specific treatments. Wi-Dia classifier recognizes different classes of interference; it is jointly trained us…
WSNs for structural health monitoring of historical buildings
2009
Monitoring structural health of historical heritage buildings may be a daunting task for civil engineers due to the lack of a pre-existing model for the building stability, and to the presence of strict constraints on monitoring device deployment. This paper reports on the experience maturated during a project regarding the design and implementation of an innovative technological framework for monitoring critical structures in Sicily, Italy. The usage of wireless sensor networks allows for a pervasive observation over the sites of interest in order to minimize the potential damages that natural phenomena may cause to architectural or engineering works. Moreover, the system provides real-tim…
Active Learning Methods for Efficient Hybrid Biophysical Variable Retrieval
2016
Kernel-based machine learning regression algorithms (MLRAs) are potentially powerful methods for being implemented into operational biophysical variable retrieval schemes. However, they face difficulties in coping with large training data sets. With the increasing amount of optical remote sensing data made available for analysis and the possibility of using a large amount of simulated data from radiative transfer models (RTMs) to train kernel MLRAs, efficient data reduction techniques will need to be implemented. Active learning (AL) methods enable to select the most informative samples in a data set. This letter introduces six AL methods for achieving optimized biophysical variable estimat…
Toward a Collective Agenda on AI for Earth Science Data Analysis
2021
In the last years we have witnessed the fields of geosciences and remote sensing and artificial intelligence to become closer. Thanks to both the massive availability of observational data, improved simulations, and algorithmic advances, these disciplines have found common objectives and challenges to advance the modeling and understanding of the Earth system. Despite such great opportunities, we also observed a worrying tendency to remain in disciplinary comfort zones applying recent advances from artificial intelligence on well resolved remote sensing problems. Here we take a position on research directions where we think the interface between these fields will have the most impact and be…
AMUN: An Object Oriented Model For Cooperative Spatial Information Systems
1997
International audience; The diversity of spatial information systems promote the need to integrate heterogeneous spatial or geographic information systems (GIS) in a cooperative environment. We present an on going research project, called ISIS (Interoperable Spatial Information System), which aims to build an environment to support interoperability of GIS by interconnecting spatial data repositories and spatial processing resources. Our solution combines techniques from traditional interoperable information systems, spatial data modeling and distributed object oriented databases. While object oriented data modeling impact has been studied in spatial databases, research in model for distribu…
Incompleteness in Conceptual Data Modelling
2013
Although conceptual data modelers can ”get creative” when designing entities and relationships to meet business requirements, they are highly constrained by the business rules which determine the details of how the entities and relationships combine. Typically, there is a delay in realising which business rules might be relevant and a further delay in obtaining an authoritative statement of these rules. We identify circumstances under which viable database designs can be constructed from conceptual data models which are incomplete in the sense that they lack this “infrastructural” detail normally obtained from the business rules. As such detail becomes available, our approach allows the con…
Pruning Incremental Linear Model Trees with Approximate Lookahead
2014
Incremental linear model trees with approximate lookahead are fast, but produce overly large trees. This is due to non-optimal splitting decisions boosted by a possibly unlimited number of examples obtained from a data source. To keep the processing speed high and the tree complexity low, appropriate incremental pruning techniques are needed. In this paper, we introduce a pruning technique for the class of incremental linear model trees with approximate lookahead on stationary data sources. Experimental results show that the advantage of approximate lookahead in terms of processing speed can be further improved by producing much smaller and consequently more explanatory, less memory consumi…
On Metadata Support for Integrating Evolving Heterogeneous Data Sources
2019
With the emergence of big data technologies, the problem of structure evolution of integrated heterogeneous data sources has become extremely topical due to dynamic and diverse nature of big data. To solve the big data evolution problem, we propose an architecture that allows to store and process structured and unstructured data at different levels of detail, analyze them using OLAP capabilities and semi-automatically manage changes in requirements and data expansion. In this paper, we concentrate on the metadata essential for the operation of the proposed architecture. We propose a metadata model to describe schemata and supplementary properties of data sets extracted from sources and tran…
Heterogeneous Database Browsing in WWW Based on Meta Model of Data Sources
2001
This paper describes a development principle and technique for a simple universal multiple database browser. The browser operates by getting information from metamodel of data sources and actual data from legacy data sources. Every element such as entity, field, and relation is mapped to some component of HTML page with appropriate structure and layout. Many templates of information layouts can be created allowing to dynamical changing of HTML page to acceptable user interface. The wrappers are used to provide browser with actual data and to act as mediators between data sources and browser. This approach allows to quickly describing new data sources, creating wrappers, making modifications…
The integration of information technologies in the knowledge based organizations
2016
Relations between the users' expertise, complexity of tasks to be solved by knowledge-based organizations and mission of smart information systems, is a multi-dimensional structure that should provide the necessary conceptual framework of sustainable integrated smart development. The users of smart information systems face a variety of problems, such as: system access, data recovery, identifying and retrieving a specific document and its contents, and difficulties associated with understanding and interpreting of the used system on stages and methods following to be used, respectively problems on understanding the meaning of information provided. Using smart information systems and smart da…