دانلود رایگان مقاله انگلیسی یک چارچوب جدید تجزیه و تحلیل کلان داده ها برای شهرهای هوشمند - الزویر 2018

Abstract

The emergence of smart cities aims at mitigating the challenges raised due to the continuous urbanization development and increasing population density in cities. To face these challenges, governments and decision makers undertake smart city projects targeting sustainable economic growth and better quality of life for both inhabitants and visitors. Information and Communication Technology (ICT) is a key enabling technology for city smartening. However, ICT artifacts and applications yield massive volumes of data known as big data. Extracting insights and hidden correlations from big data is a growing trend in information systems to provide better services to citizens and support the decision making processes. However, to extract valuable insights for developing city level smart information services, the generated datasets from various city domains need to be integrated and analyzed. This process usually referred to as big data analytics or big data value chain. Surveying the literature reveals an increasing interest in harnessing big data analytics applications in general and in the area of smart cities in particular. Yet, comprehensive discussions on the essential characteristics of big data analytics frameworks fitting smart cities requirements are still needed. This paper presents a novel big data analytics framework for smart cities called “Smart City Data Analytics Panel – SCDAP”. The design of SCDAP is based on answering the following research questions: what are the characteristics of big data analytics frameworks applied in smart cities in literature and what are the essential design principles that should guide the design of big data analytics frameworks have to serve smart cities purposes? In answering these questions, we adopted a systematic literature review on big data analytics frameworks in smart cities. The proposed framework introduces new functionalities to big data analytics frameworks represented in data model management and aggregation. The value of the proposed framework is discussed in comparison to traditional knowledge discovery approaches.

8. SCDAP Limitation and Future Research Directions

Although the proposed framework SCDAP presents new functionalities to big data analytics frameworks for smart city applications, the main feature of this architecture is limited to Apache Hadoop suite as an underlying data storage and management layer. Separation between SCDAP functionalities and the underlying data storage and management layer will add enhance the generality of SCDAP and its ability to deal with many other platforms. However, recommended future research directions involve the following points:

 Develop efficient model persistence, retrieval and ensemble algorithms.

 Develop efficient, powerful and friendly end-used interfaces involving multi-model visualization and OLAP style tools.

 Enable export/import of smart city analytical data models functionality to/from other analytical frameworks (e.g. knowledge exchange).

 Defining smart city performance measures (Key Performance Indicators - KPIs) in which analytics frameworks can be evaluated.