@Article{10798587.2017.1290328,
AUTHOR = {Samia Allaoua Chelloug, Mohamed A. El-Zawawy},
TITLE = {Middleware for Internet of Things: Survey and Challenges},
JOURNAL = {Intelligent Automation \& Soft Computing},
VOLUME = {24},
YEAR = {2018},
NUMBER = {2},
PAGES = {309--318},
URL = {http://www.techscience.com/iasc/v24n2/39757},
ISSN = {2326-005X},
ABSTRACT = {The Internet of things (IoT) applications span many potential fields. Furthermore, smart homes, smart 
cities, smart vehicular networks, and healthcare are very attractive and intelligent applications. In 
most of these applications, the system consists of smart objects that are equipped by sensors and 
Radio Frequency Identification (RFID) and may rely on other technological computing and paradigm 
solutions such as M2 M (machine to machine) computing, Wifi, Wimax, LTE, cloud computing, etc. Thus, 
the IoT vision foresees that we can shift from traditional sensor networks to pervasive systems, which 
deliver intelligent automation by running services on objects. Actually, a significant attention has been 
given to designing a middleware that supports many features; heterogeneity, mobility, scalability, 
multiplicity, and security. This papers reviews the-state-of-the-art techniques for IoT middleware 
systems and reveals an interesting classification for these systems into service and agent-oriented 
systems. Therefore two visions have emerged to provide the IoT middleware systems: Via designing 
the middleware for IoT system as an eco-system of services or as an eco-system of agents. The most 
common feature of the two approaches is the ability to overcome heterogeneity issues. However, 
the agent approach provides context awareness and intelligent elements. The review presented in 
this paper includes a detailed comparison between the IoT middleware approaches. The paper also 
explores challenges that form directions for future research on IoT middleware systems. Some of the 
challenges arise, because some crucial features are not provided (or at most partially provided) by the 
existing middleware systems, while others have not been yet tackled by current research in IoT.},
DOI = {10.1080/10798587.2017.1290328}
}