H2020Индивидуална стипендия2020–2022

MALOT · Managing Mobility Data Quality for Location of Things

„Хоризонт 2020“ — Действия „Мария Склодовска-Кюри“

Период: 2020-04-15 → 2022-07-28
Финансиране от ЕС: 219 312 €
Участници: 1
Схема: MSCA-IF

Линиите свързват координатора с партньорите.

Накратко на български

Данните за местоположение от мрежи от свързани устройства, като тези в транспортните системи, се анализират за подобряване на качеството им. Това помага за по-ефективно управление на логистиката, сигурността и градското планиране.

Този кратък обзор е генериран от изкуствен интелект

Кратко обяснение, генерирано от езиков модел по текста на CORDIS. Оригиналът е по-долу.

Резултати накратко

Managing Mobility Data Quality for Location of Things

As an instance of the Internet of Things (IoT), Location of Things (LoT) represents a paradigm that connects and integrates various location sensing “things” for smart location-based services at scale. In guaranteeing user experiences, location-based services pose strict requirements on the quality of mobility data generated from LoT. However, LoT consists of massive amount of decentralized, dynamic, and heterogeneous computing nodes, making existing data quality management approaches inapplicable. In particular, many approaches assume stand-alone data systems or simplex data systems with homogeneous distributed nodes; many approaches consider neither heterogeneous data sources nor data of different qualities in computations; and many other approaches neglect the optimization of the task assignment among dynamic and heterogeneous computing nodes. The LoT has been widely spread around Europe and the world, and it forms an open and interconnected ecology that greatly expands the application potential of fundamental social services like transportation planning, logistics, and security control. However, these downstream services can truly exert their social value only when resolved is the problem of how to manage the data quality efficiently and effectively under a decentralized, dynamic, and heterogeneous architecture. Given the aforementioned problem, this project aims for a collection of modular techniques that can be adaptive to the decentralized, dynamic, and heterogeneous LoT environment for evaluating and improving mobility data quality. The project objectives are listed as follows. - We aim to design reliable methodology for continuously modeling mobility data quality for dynamic and heterogeneous computing nodes in a decentralized architecture. - We aim to devise efficient and effective decentralized algorithms for enhancing the quality of heterogeneous mobility data generated by LoT nodes. - We aim to propose an efficient and cost-effective mechanism to continuously coordinate multiple data quality management processes on heterogeneous LoT nodes.

Текст от CORDIS, на английски · Данни: CORDIS, © Европейски съюз

Цел на проекта

Location of Things (LoT) is an Internet of Things paradigm for mobility analytics. In LoT, massive mobility data is being gathered, processed and transmitted among heterogeneous data nodes in a decentralized architecture. Traditional centralized data quality management techniques cannot cope with such characteristics of LoT, making the management of data quality for LoT a prominent challenge. In the project MALOT, the researcher aims at designing a set of new techniques that are particularly adaptive to the decentralized and heterogeneous LoT architecture for assessing and enhancing mobility data quality. Specifically, the research actions of MALOT include (1) a core model for assessing mobility data quality at decentralized and dynamic data nodes; (2) effective quality-aware data enhancement algorithms to handle the heterogeneity and inconsistency of LoT mobility data; (3) a mechanism for scheduling quality management tasks among relevant nodes in an efficiency-optimal fashion. With the research actions dedicated to decentralized modelling, heterogeneous data integration, and mobile task planning, MALOT will firmly strengthen the researcher's scientific skills and innovative competences. Through many inter-sectoral training and communication activities planned for the project, the researcher will have great opportunities to diversify his skillsets and enhance his future career prospects. A two-way knowledge transfer is guaranteed since MALOT combines the researcher's expertise in mobility analytics and the participating organizations' expertise in big data management and decentralized information systems. Committed to the mobility data quality management for IoT-like architecture, MALOT is not only expected to benefit the academic development of the host and the researcher but will contribute to Europe's IoT innovation and applications.

Оригинален текст от CORDIS (на английски).

Участници

AALBORG UNIVERSITET · AalborgКоординаторДания