The use of machine learning (ML) in smart building applications is reviewed in this article. We split existing solutions into two main classes: occupant-centric versus energy/devices-centric. The first class groups solutions that use ML for aspects related to the occupants, including (1) occupancy estimation and identification, (2) activity recognition, and (3) estimating preferences and behavior. The second class groups solutions that use ML to estimate aspects related either to energy or devices. They are divided into three categories: (1) energy profiling and demand estimation, (2) appliances profiling and fault detection, and (3) inference on sensors. Solutions in each category are presented, discussed, and compared; open perspectives and research trends are discussed as well. Compared to related state-of-the-art survey papers, the contribution herein is to provide a comprehensive and holistic review from the ML perspectives rather than architectural and technical aspects of existing building management systems. This is by considering all types of ML tools, buildings, and several categories of applications, and by structuring the taxonomy accordingly. The article ends with a summary discussion of the presented works, with focus on lessons learned, challenges, open and future directions of research in this field.

The performance of wireless sensor networks (WSN) is affected by the lossy communication medium, application diversity, dense deployment, limited processing power and storage capacity, frequent topology change. All these limitations provide significant and unique design challenges to data transport control in wireless sensor networks. An effective transport protocol should consider reliable message delivery, energy-efficiency, quality of service and congestion control. The latter is vital for achieving a high throughput and a long network lifetime. Despite the huge number of protocols proposed in the literature, congestion control in WSN remains challenging. A review and taxonomy of the state-of-the-art protocols from the literature up to 2013 is provided in this paper. First, depending on the control policy, the protocols are divided into resource control vs. traffic control. Traffic control protocols are either reactive or preventive (avoiding). Reactive solutions are classified following the reaction scale, while preventive solutions are split up into buffer limitation vs. interference control. Resource control protocols are classified according to the type of resource to be tuned.

The use of a low-power wake-up radio in wireless sensor networks is considered in this paper, where relevant medium access control solutions are studied. A variety of asynchronous wake-up MAC protocols have been proposed in the literature, which take advantage of integrating a second radio to the main one for waking it up. However, a complete and a comprehensive survey particularly on these protocols is missing in the literature. This paper aims at filling this gap, proposing a relevant taxonomy, and providing deep analysis and discussions. From both perspectives of energy efficiency and latency reduction, as well as their operation principles, state-of-the-art wake-up MAC protocols are grouped into three main categories: (1) duty cycled wake-up MAC protocols; (2) non-cycled wake-up protocols; and (3) path reservation wake-up protocols. The first category includes two subcategories: (1) static wake-up protocols versus (2) traffic adaptive wake-up protocols. Non-cycled wake-up MAC protocols are again divided into two classes: (1) always-on wake-up protocol and (2) radio-triggered wake-up protocols. The latter is in turn split into two subclasses: (1) passive wake-up MAC protocols versus (2) ultra low power active wake-up MAC protocols. Two schemes could be identified for the last category, (1) broadcast based wake-up versus (2) addressing based wake-up. All these classes are discussed and analyzed in this paper, and canonical protocols are investigated following the proposed taxonomy.

With the constant increasing of vehicular traffic around the world, especially in urban areas, existing traffic management solutions become inefficient. This can be clearly seen in our life through persistent traffic jam and rising number of accidents. Wireless sensor networks (WSN) based intelligent transportation systems (ITS) have emerged as a cost effective technology that bear a pivotal potential to overcome these difficulties. This technology enables a new broad range of smart city applications around urban sensing including traffic safety, traffic congestion control, road state monitoring, vehicular warning services, and parking management.This manuscript gives a comprehensive review on WSN based ITS solutions. The main contribution of this paper is to classify current WSNs based ITS projects from the application perspective, with discussions on the fulfillment of the application requirements