The proliferation of wireless localization technologies provides a promising future for serving human beings in indoor scenarios. Their applications include real-time tracking, activity recognition, health care, navigation, emergence detection, and target-of-interest monitoring, among others. Additionally, indoor localization technologies address the inefficiency of GPS (Global Positioning System) inside buildings. Since people spend most of their time in indoor environments, indoor tracking service is in great public demand. Based on this observation, this paper aims to provide a better understanding of state-of-the-art technologies and stimulate new research efforts in this field. For these purposes, existing localization technologies that can be used for tracking individuals in indoor environments are reviewed, along with some further discussions.
Wireless sensor/actuator networks (WSANs) are emerging rapidly as a new generation of sensor networks. Despite intensive research in wireless sensor networks (WSNs), limited work has been found in the open literature in the field of WSANs. In particular, quality-of-service (QoS) management in WSANs remains an important issue yet to be investigated. As an attempt in this direction, this paper develops a fuzzy logic control based QoS management (FLC-QM) scheme for WSANs with constrained resources and in dynamic and unpredictable environments. Taking advantage of the feedback control technology, this scheme deals with the impact of unpredictable changes in traffic load on the QoS of WSANs. It utilizes a fuzzy logic controller inside each source sensor node to adapt sampling period to the deadline miss ratio associated with data transmission from the sensor to the actuator. The deadline miss ratio is maintained at a pre-determined desired level so that the required QoS can be achieved. The FLC-QM has the advantages of generality, scalability, and simplicity. Simulation results show that the FLC-QM can provide WSANs with QoS support.
Wireless control systems (WCSs) often have to operate in dynamic environments where the network traffic load may vary unpredictably over time. The sampling in sensors is conventionally time triggered with fixed periods. In this context, only worse-than-possible quality of control (QoC) can be achieved when the network is underloaded, while overloaded conditions may significantly degrade the QoC, even causing system instability. This is particularly true when the bandwidth of the wireless network is limited and shared by multiple control loops. To address these problems, a flexible time-triggered sampling scheme is presented in this work. Smart sensors are used to facilitate dynamic adjustment of sampling periods, which enhances the flexibility and resource efficiency of the system based on time-triggered sampling. Feedback control technology is exploited for adapting sampling periods in a periodic manner. The deadline miss ratio in each control loop is maintained at/around a desired level, regardless of workload variations. Simulation results show that the proposed sampling scheme is able to deal with dynamic and unpredictable variations in network traffic load. Compared to conventional time-triggered sampling, it leads to much better QoC in WCSs operating in dynamic environments.
Network representation learning (NRL) is an effective graph analytics technique and promotes users to deeply understand the hidden characteristics of graph data. It has been successfully applied in many real-world tasks related to network science, such as social network data processing, biological information processing, and recommender systems. Deep Learning is a powerful tool to learn data features. However, it is non-trivial to generalize deep learning to graph-structured data since it is different from the regular data such as pictures having spatial information and sounds having temporal information. Recently, researchers proposed many deep learning-based methods in the area of NRL. In this survey, we investigate classical NRL from traditional feature learning method to the deep learning-based model, analyze relationships between them, and summarize the latest progress. Finally, we discuss open issues considering NRL and point out the future directions in this field.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.