Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

Artificial neural networks

Digital processing of speech signals

Wireless sensor network (WSN) has emerged as one of the most promising technologies for the future. This has been enabled by advances in technology and availability of small, inexpensive, and smart sensors resulting in cost effective and easily deployable WSNs. However, researchers must address a variety of challenges to facilitate the widespread deployment of WSN technology in real-world domains. In this survey, we give an overview of wireless sensor networks and their application domains including the challenges that should be addressed in order to push the technology further. Then we review the recent technologies and testbeds for WSNs. Finally, we identify several open research issues that need to be investigated in future.

Our survey is different from existing surveys in that we focus on recent developments in wireless sensor network technologies. We review the leading research projects, standards and technologies, and platforms. Moreover, we highlight a recent phenomenon in WSN research that is to explore synergy between sensor networks and other technologies and explain how this can help sensor networks achieve their full potential. This paper intends to help new researchers entering the domain of WSNs by providing a comprehensive survey on recent developments.

Wireless sensor networks: a survey on recent developments and potential synergies

Space-air-ground integrated network (SAGIN), as an integration of satellite systems, aerial networks, and terrestrial communications, has been becoming an emerging architecture and attracted intensive research interest during the past years. Besides bringing significant benefits for various practical services and applications, SAGIN is also facing many unprecedented challenges due to its specific characteristics, such as heterogeneity, self-organization, and time-variability. Compared to traditional ground or satellite networks, SAGIN is affected by the limited and unbalanced network resources in all three network segments, so that it is difficult to obtain the best performances for traffic delivery. Therefore, the system integration, protocol optimization, resource management, and allocation in SAGIN is of great significance. To the best of our knowledge, we are the first to present the state-of-the-art of the SAGIN since existing survey papers focused on either only one single network segment in space or air, or the integration of space-ground, neglecting the integration of all the three network segments. In light of this, we present in this paper a comprehensive review of recent research works concerning SAGIN from network design and resource allocation to performance analysis and optimization. After discussing several existing network architectures, we also point out some technology challenges and future directions.

Space-Air-Ground Integrated Network: A Survey

Consider a discrete source producing a sequence of message letters from a finite alphabet. A single-letter distortion measure is given by a non-negative matrix (d ij ). The entryd ij measures the ?cost? or ?distortion? if letteriis reproduced at the receiver as letterj. The average distortion of a communications system (source-coder-noisy channel-decoder) is taken to bed= ? i.j P ij d ij whereP ij is the probability ofibeing reproduced asj. It is shown that there is a functionR(d) that measures the ?equivalent rate? of the source for a given level of distortion. For coding purposes where a leveldof distortion can be tolerated, the source acts like one with information rateR(d). Methods are given for calculatingR(d), and various properties discussed. Finally, generalizations to ergodic sources, to continuous sources, and to distortion measures involving blocks of letters are developed. In this paper a study is made of the problem of coding a discrete source of information, given afidelity criterionor ameasure of the distortionof the final recovered message at the receiving point relative to the actual transmitted message. In a particular case there might be a certain tolerable level of distortion as determined by this measure. It is desired to so encode the information that the maximum possible signaling rate is obtained without exceeding the tolerable distortion level. This work is an expansion and detailed elaboration of ideas presented earlier [1], with particular reference to the discrete case. We shall show that for a wide class of distortion measures and discrete sources of information there exists a functionR(d) (depending on the particular distortion measure and source) which measures, in a sense, the equivalent rateRof the source (in bits per letter produced) whendis the allowed distortion level. Methods will be given for evaluatingR(d) explicitly in certain simple cases and for evaluatingR(d) by a limiting process in more complex cases. The basic results are roughly that it is impossible to signal at a rate faster thanC/R(d) (source letters per second) over a memoryless channel of capacityC(bits per second) with a distortion measure less than or equal tod. On the other hand, by sufficiently long block codes it is possible to approach as closely as desired the rateC/R(d) with distortion leveld. Finally, some particular examples, using error probability per letter of message and other simple distortion measures, are worked out in detail.

Coding Theorems for a Discrete Source With a Fidelity CriterionInstitute of Radio Engineers, International Convention Record, vol. 7, 1959.

The integration of satellite communications into 5G ecosystem is pivotal to boost enhanced mobile broadband (eMBB) services in highly dynamic scenarios and in areas not optimally supported by terrestrial infrastructures. Given the heterogeneity of the networks involved, network slicing is key networking paradigm to ensure different grades of quality of service (QoS) based on the users’ and verticals’ requirements. In this light, this paper proposes an optimisation framework able to exploit the available resources allocated to the defined network slices so as to meet the diverse QoS/QoE requirements exposed by the network actors. Resource allocation schemes built upon neural network algorithms are validated through extensive simulation campaigns that have shown the superiority of the proposed concepts with respect to other solution candidates available from the literature.

QoS Optimisation of eMBB Services in Converged 5G-Satellite Networks

In this paper, a numerical study devoted to evaluate the application of a microwave imaging method for brain stroke detection is described. First of all, suitable operating conditions for the imaging system are defined by solving the forward electromagnetic scattering problem with respect to simplified configurations and analyzing the interactions between an illuminating electromagnetic wave at microwave frequencies and the biological tissues inside the head. Then, preliminary inversion results are obtained by applying an imaging procedure based on an iterative Gauss-Newton scheme to a realistic model of the human head. The proposed imaging algorithm is able to deal with the nonlinear and ill-posed problem associated to the integral equations describing the inverse scattering problem. The aim of the inversion procedure is related to the determination of the presence of a hemorrhagic brain stroke by retrieving the distributions of the dielectric parameters of the human tissues inside a slice of the head model.

A numerical study concerning brain stroke detection by microwave imaging systems

In view of the dense and complex space network topologies envisioned for the future, the management of congestion control is a prominent issue that deserves a particular attention. Given the challenging peculiarities of interplanetary environments, this paper focuses on the advantages offered by storage-based routing and on potentials of implementing Random Early Detection (RED) and Explicit Congestion Notification (ECN) mechanisms within the Delay Tolerant Network (DTN) architecture. In this light, solutions relying upon the aforementioned concepts have been designed and tested. Preliminary results show that combination of RED and ECN schemes with network-selection strategies for storage-based routing is really promising and outperforms other solutions in terms of reliability, network resource utilisation and power consumption.

Combined Congestion Control and Link Selection Strategies for Delay Tolerant Interplanetary Networks

In this paper a performance comparison of a probabilistic Gaussian-Kernel fingerprint-based indoor positioning method over different smartphones, is presented. The work aims at highlighting the positioning accuracy, the robustness and the consistency of the method by testing it over two different smartphone platforms (i.e., Nokia N95 and Samsung Galaxy S II), within a given area. In more detail, three different variants of the probabilistic approach have been tested: Nearest Neighbor (NN), K-Nearest Neighbor (K-NN) and K Weighted-Nearest Neighbor (KW-NN). Numerical experiments, carried out in an area of around 80 [m2], have shown that the probabilistic fingerprint provides good position accuracy (less than 1.20 [m] of error) for both devices and also robustness when the signal strength acquisitions are reduced. Finally, the similarity of results provided by the two smartphones leads to assert that the probabilistic approach is also consistent with respect to the device employed in the experiments.

Igor Bisio

Papers

QoS Optimisation of eMBB Services in Converged 5G-Satellite Networks

A numerical study concerning brain stroke detection by microwave imaging systems

Combined Congestion Control and Link Selection Strategies for Delay Tolerant Interplanetary Networks

Performance comparison of a probabilistic fingerprint-based indoor positioning system over different smartphones

Performance evaluation of bandwidth allocation methods in a geostationary satellite channel in the presence of internet traffic