Graph recursive least squares filter for topology inference in causal data processes

In this paper, we introduce the concept of recursive least squares graph filters for online topology inference in data networks that are modelled as Causal Graph Processes (CGP). A Causal Graph Process (CGP) is an auto regressive process in the time series associated to different variables, and whose coefficients are the so-called graph filters, which are matrix polynomials with different orders of the graph adjacency matrix. Given the time series of data at different variables, the goal is to estimate these graph filters, hence the associated underlying adjacency matrix. Previously proposed algorithms have focused on a batch approach, assuming implicitly stationarity of the CGP. We propose…

Forecasting Aquaponic Systems Behaviour With Recurrent Neural Networks Models

Aquaponic systems provide a reliable solution to grow vegetables while cultivating fish (or other aquatic organisms) in a controlled environment. The main advantage of these systems compared with traditional soil-based agriculture and aquaculture installations is the ability to produce fish and vegetables with low water consumption. Aquaponics requires a robust control system capable of optimizing fish and plant growth while ensuring a safe operation. To support the control system, this work explores the design process of Deep Learning models based on Recurrent Neural Networks to forecast one hour of pH values in small-scale industrial Aquaponics. This implementation guides us through the m…

Adaptive consensus-based distributed detection in WSN with unreliable links

Event detection is a crucial tasks in wireless sensor networks. The importance of a fast response makes distributed strategies, where nodes exchange information just with their one-hop neighbors to reach local decisions, more adequate than schemes where all nodes send observations to a central entity. Distributed detectors are usually based on average consensus, where all nodes iteratively communicate to asymptotically agree on a final result. In a realistic scenario, communications are subject to random failures, which impacts the performance of the consensus. We propose an alternative detector, which adapts to the statistical properties of the consensus and compensate deviations from the …

Online Non-linear Topology Identification from Graph-connected Time Series

Estimating the unknown causal dependencies among graph-connected time series plays an important role in many applications, such as sensor network analysis, signal processing over cyber-physical systems, and finance engineering. Inference of such causal dependencies, often know as topology identification, is not well studied for non-linear non-stationary systems, and most of the existing methods are batch-based which are not capable of handling streaming sensor signals. In this paper, we propose an online kernel-based algorithm for topology estimation of non-linear vector autoregressive time series by solving a sparse online optimization framework using the composite objective mirror descent…

Location-Free Spectrum Cartography

Spectrum cartography constructs maps of metrics such as channel gain or received signal power across a geographic area of interest using spatially distributed sensor measurements. Applications of these maps include network planning, interference coordination, power control, localization, and cognitive radios to name a few. Since existing spectrum cartography techniques require accurate estimates of the sensor locations, their performance is drastically impaired by multipath affecting the positioning pilot signals, as occurs in indoor or dense urban scenarios. To overcome such a limitation, this paper introduces a novel paradigm for spectrum cartography, where estimation of spectral maps rel…

Reaction-diffusion on dynamic inhibition areas: A bio-inspired link scheduling algorithm

We present the Dynamic Inhibition Areas Reaction-Diffusion (DIA-RD) algorithm, a distributed medium access control protocol that globally maximizes the spatial reusability (number of simultaneous transmissions per unit area) of wireless sensor networks. This algorithm is able, in consequence, to minimize the number of time slots needed to schedule the set of demanded links, making it very efficient to solve the Shortest Link Schedule problem. DIA-RD combines accurate interference management, provided by the use of dynamic inhibition areas based on the physical interference model; and global intelligent behavior, provided by the bio-inspired technique known as Reaction-Diffusion. This techni…

Experimental validation for spectrum cartography using adaptive multi-kernels

This paper validates the functionality of an algorithm for spectrum cartography, generating a radio environment map (REM) using adaptive radial basis functions (RBF) based on a limited number of measurements. The power at all locations is estimated as a linear combination of different RBFs without assuming any prior information about either power spectral densities (PSD) of the transmitters or their locations. The RBFs are represented as centroids at optimized locations, using machine learning to jointly optimize their positions, weights and Gaussian decaying parameters. Optimization is performed using expectation maximization with a least squares loss function and a quadratic regularizer. …

Consensus-Based Distributed State Estimation of Biofilm in Reverse Osmosis Membranes by WSNs

The appearance of biofilm has become a serious problem in many reverse osmosis based systems such as the ones found in water treatment and desalination plants. In these systems, the use of traditional techniques such as pretreatment or dozing biocides are not effective when the biofilm reaches an irreversible attachment phase. In this work, we present a framework for the use of a WSN as an estimator of the biofilm evolution in a reverse osmosis membrane so that effective solutions can be applied before the irreversible phase is attained. This design is addressed in a complete distributed and decentralized fashion, and subject to realistic constraints where cooperation between nodes is perfo…

A greedy perturbation approach to accelerating consensus algorithms and reducing its power consumption

The average consensus is part of a family of algorithms that are able to compute global statistics by only using local data. This capability makes these algorithms interesting for applications in which these distributed philosophy is necessary. However, its iterative nature usually leads to a large power consumption due to the repetitive communications among the iterations. This drawback highlights the necessity of minimizing the power consumption until consensus is reached. In this work, we propose a greedy approach to perturbing the connectivity graph, in order to improve the convergence time of the consensus algorithm while keeping bounded the power consumption per iteration step. These …

Design and implementation of a long-range low-power wake-up radio and customized DC-MAC protocol for LoRaWAN

In this paper, we present the design and implementation of a long-rage wake-up radio (WuR) and customized duty cycled (DC) MAC protocol for wireless IoT devices. The WuRx achieves a sensivity of −70 dBm by consuming just 0.032 mA, thereby optimizing the energy consumption of battery powered long-range wireless IoT devices. Reducing the power consumption of these devices minimizes the overall costs when deployed in large scale.

Efficient image compression using directionlets

Directionlets are built as basis functions of critically sampled perfect-reconstruction transforms with directional vanishing moments imposed along different directions. We combine the directionlets with the space-frequency quantization (SFQ) image compression method, originally based on the standard two-dimensional wavelet transform. We show that our new compression method outperforms the standard SFQ as well as the state-of-the-art image compression methods, such as SPIHT and JPEG-2000, in terms of the quality of compressed images, especially in a low-rate compression regime. We also show that the order of computational complexity remains the same, as compared to the complexity of the sta…

Distributed Clustering Algorithm for Spatial Field Reconstruction in Wireless Sensor Networks

En este trabajo, consideramos el problema de la estimación espacial distribuida para la reconstrucción del campo radio en redes de sensores inalámbricos. Para estimar el campo, se utiliza una técnica geoestadística llamada kriging. La estimación espacial centralizada con un gran número de sensores conllevan un elevado coste computacional y gasto de energía. Presentamos un novedoso algoritmo de clustering distribuido para estimar mapas de interferencia espacial, que son esenciales para las operaciones y la gestión de las futuras redes inalámbricas. En este algoritmo, los clústeres de sensores se forman de forma adaptativa mediante la minimización de la varianza de kriging. El cálculo del sem…

Cross-Layer MAC Protocol for Unbiased Average Consensus Under Random Interference

Wireless Sensor Networks have been revealed as a powerful technology to solve many different problems through sensor nodes cooperation. One important cooperative process is the so-called average gossip algorithm, which constitutes a building block to perform many inference tasks in an efficient and distributed manner. From the theoretical designs proposed in most previous work, this algorithm requires instantaneous symmetric links in order to reach average consensus. However, in a realistic scenario wireless communications are subject to interferences and other environmental factors, which results in random instantaneous topologies that are, in general, asymmetric. Consequently, the estimat…

Graph Filtering of Time-Varying Signals over Asymmetric Wireless Sensor Networks

In many applications involving wireless sensor networks (WSNs), the observed data can be modeled as signals defined over graphs. As a consequence, an increasing interest has been witnessed to develop new methods to analyze graph signals, leading to the emergence of the field of Graph Signal Processing. One of the most important processing tools in this field is graph filters, which can be easily implemented distributedly over networks by means of cooperation among the nodes. Most of previous works related to graph filters assume the same connection probability in both link directions when transmitting an information between two neighboring nodes. This assumption is not realistic in practice…

Joint Topology and Radio Resource Optimization for Device-to-Device Based Mobile Social Networks

In this paper, we consider a joint topology and radio resource optimization for device-to-device (D2D) based mobile social networks. The considered social network is an interest based which is modeled as a d -intersection binomial random graph. The Radio network is also modeled as a random graph where an edge between any two distinct nodes is activated with a certain probability that is equivalent to the probability of exceeding a certain signal to interference ratio for that link. The entire network is then modeled as an intersection graph between the social and radio induced graphs. Thereafter, network topology is optimized such that enabled social edges satisfy certain network connectivi…

Fast Distributed Subspace Projection via Graph Filters

A significant number of linear inference problems in wireless sensor networks can be solved by projecting the observed signal onto a given subspace. Decentralized approaches avoid the need for performing such an operation at a central processor, thereby reducing congestion and increasing the robustness and the scalability of the network. Unfortunately, existing decentralized approaches either confine themselves to a reduced family of subspace projection tasks or need an infinite number of iterations to obtain the exact projection. To remedy these limitations, this paper develops a framework for computing a wide class of subspace projections in a decentralized fashion by relying on the notio…

Energy Efficient Consensus Over Directed Graphs

Consensus algorithms are iterative methods that represent a basic building block to achieve superior functionalities in increasingly complex sensor networks by facilitating the implementation of many signal-processing tasks in a distributed manner. Due to the heterogeneity of the devices, which may present very different capabilities (e.g. energy supply, transmission range), the energy often becomes a scarce resource and the communications turn into directed. To maximize the network lifetime, a magnitude that in this work measures the number of consensus processes that can be executed before the first node in the network runs out of battery, we propose a topology optimization methodology fo…

Analog Multiple Description Joint Source-Channel Coding Based on Lattice Scaling

Joint source-channel coding schemes based on analog mappings for point-to-point channels have recently gained attention for their simplicity and low delay. In this paper, these schemes are extended either to scenarios with or without side information at the decoders to transmit multiple descriptions of a Gaussian source over independent parallel channels. They are based on a lattice scaling approach together with bandwidth reduction analog mappings adapted for this multiple description scenario. The rationale behind lattice scaling is to improve performance through bandwidth expansion. Another important contribution of this paper is the proof of the separation theorem for the communication …

Localization-Free Power Cartography

Author's accepted manuscript (postprint). © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. Spectrum cartography constructs maps of metrics such as channel gain or received signal power across a geographic area of interest using measurements of spatially distributed sensors. Applications of these maps include network planning, interference coordination, power con…

Online topology estimation for vector autoregressive processes in data networks

An important problem in data sciences pertains to inferring causal interactions among a collection of time series. Upon modeling these as a vector autoregressive (VAR) process, this paper deals with estimating the model parameters to identify the underlying causality graph. To exploit the sparse connectivity of causality graphs, the proposed estimators minimize a group-Lasso regularized functional. To cope with real-time applications, big data setups, and possibly time-varying topologies, two online algorithms are presented to recover the sparse coefficients when observations are received sequentially. The proposed algorithms are inspired by the classic recursive least squares (RLS) algorit…

Optimal gossip algorithm for distributed consensus SVM training in wireless sensor networks

In this paper, we consider the distributed training of a SVM using measurements collected by the nodes of aWireless Sensor Network in order to achieve global consensus with the minimum possible inter-node communications for data exchange. We derive a novel mathematical characterization for the optimal selection of partial information that neighboring sensors should exchange in order to achieve consensus in the network. We provide a selection function which ranks the training vectors in order of importance in the learning process. The amount of information exchange can vary, based on an appropriately chosen threshold value of this selection function, providing a desired trade-off between cla…

Fast Decentralized Linear Functions Over Edge Fluctuating Graphs

Implementing linear transformations is a key task in the decentralized signal processing framework, which performs learning tasks on data sets distributed over multi-node networks. That kind of network can be represented by a graph. Recently, some decentralized methods have been proposed to compute linear transformations by leveraging the notion of graph shift operator, which captures the local structure of the graph. However, existing approaches have some drawbacks such as considering some special instances of linear transformations, or reducing the family of transformations by assuming that a shift matrix is given such that a subset of its eigenvectors spans the subspace of interest. In c…

Distributed Pseudo-Gossip Algorithm and Finite-Length Computational Codes for Efficient In-Network Subspace Projection

In this paper, we design a practical power-efficient algorithm for Wireless Sensor Networks (WSN) in order to obtain, in a distributed manner, the projection of an observed sampled spatial field on a subspace of lower dimension. This is an important problem that is motivated in various applications where there are well defined subspaces of interest (e.g., spectral maps in cognitive radios). As opposed to traditional Gossip Algorithms used for subspace projection, where separation of channel coding and computation is assumed, our algorithm combines binary finite-length Computational Coding and a novel gossip-like protocol with certain communication rules, achieving important savings in conve…

Power-constrained sensor selection and routing for cooperative detection in cognitive radios

Given a spectrum-sensing network, a set of active nodes jointly aggregate sensed data at a preset frequency-band and simultaneously route this information to an arbitrarily chosen querying node through a power-constrained multi-hop path. Locally, each sensor node is assumed to be an energy-based detector. This work focuses on deriving algorithms that jointly optimize sensor selection and cooperative detection from which a power-efficient route to the querying node can be established, and then, a tree routing structure spanning the chosen nodes is constructed under a power budget constraint. Sensor information is sequentially aggregated along this optimized routing structure up to the queryi…

Non-convex power allocation games in MIMO cognitive radio networks

Consideramos un escenario de reparto del espectro, basado en la detección, en una red de radio cognitiva MIMO donde el objetivo general es maximizar el rendimiento total de cada usuario de radio cognitiva optimizando conjuntamente la operación de detección y la asignación de potencia en todos los canales, bajo una restricción de interferencia para los usuarios primarios. Los problemas de optimización resultantes conducen a un juego no convexo, que presenta un nuevo desafío a la hora de analizar los equilibrios de este juego. Con el fin de hacer frente a la no convexidad del juego, utilizamos un nuevo concepto relajado de equilibrio, el equilibrio cuasi-Nash (QNE). Se demuestran las condicio…

Energy Efficient Consensus Over Complex Networks

The need to extract large amounts of information from the environment to have precise situation awareness and then react appropriately to certain events has led to the emergence of complex and heterogeneous sensor networks. In this context, where the sensor nodes are usually powered by batteries, the design of new methods to make inference processes efficient in terms of energy consumption is necessary. One of these processes, which is present in many distributed tasks performed by these complex networks, is the consensus process. This is the basis for certain tracking algorithms in monitoring and control applications. To improve the energy efficiency of this process, in this paper we propo…

Accurate Graph Filtering in Wireless Sensor Networks

Wireless sensor networks (WSNs) are considered as a major technology enabling the Internet of Things (IoT) paradigm. The recent emerging Graph Signal Processing field can also contribute to enabling the IoT by providing key tools, such as graph filters, for processing the data associated with the sensor devices. Graph filters can be performed over WSNs in a distributed manner by means of a certain number of communication exchanges among the nodes. But, WSNs are often affected by interferences and noise, which leads to view these networks as directed, random and time-varying graph topologies. Most of existing works neglect this problem by considering an unrealistic assumption that claims the…

Online Edge Flow Imputation on Networks

Author's accepted manuscript © 2022 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. An online algorithm for missing data imputation for networks with signals defined on the edges is presented. Leveraging the prior knowledge intrinsic to real-world networks, we propose a bi-level optimization scheme that exploits the causal dependencies and the flow conservation, respe…

Joint Graph Learning and Signal Recovery via Kalman Filter for Multivariate Auto-Regressive Processes

In this paper, an adaptive Kalman filter algorithm is proposed for simultaneous graph topology learning and graph signal recovery from noisy time series. Each time series corresponds to one node of the graph and underlying graph edges express the causality among nodes. We assume that graph signals are generated via a multivariate auto-regressive processes (MAR), generated by an innovation noise and graph weight matrices. Then we relate the state transition matrix of Kalman filter to the graph weight matrices since both of them can play the role of signal propagation and transition. Our proposed Kalman filter for MAR processes, called KF-MAR, runs three main steps; prediction, update, and le…

Cyber-Physical Systems for Smart Water Networks: A Review

Author's accepted manuscript. There is a growing demand to equip Smart Water Networks (SWN) with advanced sensing and computation capabilities in order to detect anomalies and apply autonomous event-triggered control. Cyber-Physical Systems (CPSs) have emerged as an important research area capable of intelligently sensing the state of SWN and reacting autonomously in scenarios of unexpected crisis development. Through computational algorithms, CPSs can integrate physical components of SWN, such as sensors and actuators, and provide technological frameworks for data analytics, pertinent decision making, and control. The development of CPSs in SWN requires the collaboration of diverse scienti…

Channel Gain Cartography via Mixture of Experts

In order to estimate the channel gain (CG) between the locations of an arbitrary transceiver pair across a geographic area of interest, CG maps can be constructed from spatially distributed sensor measurements. Most approaches to build such spectrum maps are location-based, meaning that the input variable to the estimating function is a pair of spatial locations. The performance of such maps depends critically on the ability of the sensors to determine their positions, which may be drastically impaired if the positioning pilot signals are affected by multi-path channels. An alternative location-free approach was recently proposed for spectrum power maps, where the input variable to the maps…

Link scheduling in sensor networks for asymmetric average consensus

Wireless Sensor Networks constitute a recent technology where the nodes cooperate to obtain, in a totally distributed way, certain function of the sensed data. One example is the average consensus algorithm, which allows every node to converge to the global average. However, this algorithm presents two major drawbacks in practice. The first one is that instantaneous symmetric links are required, which are hard to ensure in practice because of the presence of wireless interferences. The second one is that all the nodes are required to communicate with all of their local neighbors in every iteration, which can lead to an unbounded delay. In order to solve these issues, we propose a novel link…

Design of Asymmetric Shift Operators for Efficient Decentralized Subspace Projection

A large number of applications in decentralized signal processing includes projecting a vector of noisy observations onto a subspace dictated by prior information about the field being monitored. Accomplishing such a task in a centralized fashion in networks is prone to a number of issues such as large power consumption, congestion at certain nodes and suffers from robustness issues against possible node failures. Decentralized subspace projection is an alternative method to address those issues. Recently, it has been shown that graph filters (GFs) can be implemented to perform decentralized subspace projection. However, most of the existing methods have focused on designing GFs for symmetr…

Low‐complexity detection for uplink massive MIMO SCMA systems

Paid Open Access UNIT agreement

Space-Frequency Quantization for Image Compression With Directionlets

The standard separable 2-D wavelet transform (WT) has recently achieved a great success in image processing because it provides a sparse representation of smooth images. However, it fails to efficiently capture 1-D discontinuities, like edges or contours. These features, being elongated and characterized by geometrical regularity along different directions, intersect and generate many large magnitude wavelet coefficients. Since contours are very important elements in the visual perception of images, to provide a good visual quality of compressed images, it is fundamental to preserve good reconstruction of these directional features. In our previous work, we proposed a construction of critic…

Fast Decentralized Linear Functions via Successive Graph Shift Operators

Decentralized signal processing performs learning tasks on data distributed over a multi-node network which can be represented by a graph. Implementing linear transformations emerges as a key task in a number of applications of decentralized signal processing. Recently, some decentralized methods have been proposed to accomplish that task by leveraging the notion of graph shift operator, which captures the local structure of the graph. However, existing approaches have some drawbacks such as considering special instances of linear transformations, or reducing the family of transformations by assuming that a shift matrix is given such that a subset of its eigenvectors spans the subspace of i…

Design and implementation of a long-range low-power wake-up radio for IoT devices

In this paper, we present the design and implementation of an on-demand wake-up radio (WuR) for long-range wireless IoT devices to reduce the power consumption, thereby increasing the life time of the devices. A custom narrow-band (NB) low noise amplifier is designed and implemented for WuR. The low-noise amplifier achieves a gain of 31 dB at 1 mA current consumption from a 6 V power supply. The WuR achieves a sensivity of -80 dBm by consuming just 1 mA, thereby optimizing the energy consumption of battery powered long-range IoT devices, hence reducing the power consumption and overall costs when deployed in large scale.

Online Topology Identification from Vector Autoregressive Time Series

Causality graphs are routinely estimated in social sciences, natural sciences, and engineering due to their capacity to efficiently represent the spatiotemporal structure of multivariate data sets in a format amenable for human interpretation, forecasting, and anomaly detection. A popular approach to mathematically formalize causality is based on vector autoregressive (VAR) models and constitutes an alternative to the well-known, yet usually intractable, Granger causality. Relying on such a VAR causality notion, this paper develops two algorithms with complementary benefits to track time-varying causality graphs in an online fashion. Their constant complexity per update also renders these a…

Field estimation in wireless sensor networks using distributed kriging

In this paper, we tackle the problem of spatial interpolation for distributed estimation in Wireless Sensor Networks by using a geostatistical technique called kriging. We present a novel Distributed Iterative Kriging Algorithm (DIKA) which is composed of two main phases. First, the spatial dependence of the field is exploited by calculating semivariograms in an iterative way. Second, the kriging system of equations is solved by an initial set of nodes in a distributed manner, providing some initial interpolation weights to each node. In our algorithm, the estimation accuracy can be improved by iteratively adding new nodes and updating appropriately the weights, which leads to a reduction i…

Reliable Underlay D2D Communications over Multiple Transmit Antenna Framework

Robust beamforming is an efficient technique to guarantee the desired receiver performance in the presence of erroneous channel state information (CSI). However, the application of robust beamforming in underlay device-to-device (D2D) communication still requires further investigation. In this paper, we investigate resource allocation problem for underlay D2D communications by considering multiple antennas at the base station (BS) and at the transmitters of D2D pairs. The proposed design problem aims at maximizing the aggregate rate of all D2D pairs and cellular users (CUs) in downlink spectrum. In addition, our objective is augmented to achieve a fair allocation of resources across the D2D…

Quasi-nash equilibria for non-convex distributed power allocation games in cognitive radios

In this paper, we consider a sensing-based spectrum sharing scenario in cognitive radio networks where the overall objective is to maximize the sum-rate of each cognitive radio user by optimizing jointly both the detection operation based on sensing and the power allocation, taking into account the influence of the sensing accuracy and the interference limitation to the primary users. The resulting optimization problem for each cognitive user is non-convex, thus leading to a non-convex game, which presents a new challenge when analyzing the equilibria of this game where each cognitive user represents a player. In order to deal with the non-convexity of the game, we use a new relaxed equilib…

Distributed Resource Allocation in Underlay Multicast D2D Communications

Multicast device-to-device communications operating underlay with cellular networks is a spectral efficient technique for disseminating data to nearby receivers. However, due to the critical challenge of having an intelligent interference coordination between multicast groups along with the cellular network, it is necessary to judiciously perform resource allocation for the combined network. In this work, we present a framework for a joint channel and power allocation strategy to maximize the sum rate of the combined network while guaranteeing minimum rate to individual groups and cellular users. The objective function is augmented by an austerity function that penalizes excessive assignmen…

Reliable Multicast D2D Communication Over Multiple Channels in Underlay Cellular Networks

Multicast device-to-device (D2D) communications operating underlay with cellular networks is a spectral efficient technique for disseminating data to the nearby receivers. However, due to critical challenges such as, mitigating mutual interference and unavailability of perfect channel state information (CSI), the resource allocation to multicast groups needs significant attention. In this work, we present a framework for joint channel assignment and power allocation strategy to maximize the sum rate of the combined network. The proposed framework allows access of multiple channels to the multicast groups, thus improving the achievable rate of the individual groups. Furthermore, fairness in …

Quantization in Graph Convolutional Neural Networks

Implementation of a two stage fully-blind self-adapted spectrum sensing algorithm

In this paper, an experimental validation of a combined two-stage detector called 2EMC is carried out. The detector is proposed in [1]. The 2EMC is composed of energy detector as a primary stage and maximum-minimum eigenvalue detector as a secondary stage. The 2EMC outperforms the two individual detectors in terms of the probability of detection for the same probability of false alarm. Regarding the complexity measured in the sensing time, the 2EMC sensing time is bounded by the sensing times of the two individual detectors. 2EMC incorporates noise estimation that is used by the energy detector, which makes it fully-blind and self-adapted detector. The noise estimator performance is express…

Power allocation optimization in OFDM-based cognitive radios based on sensing information

Owing to the non-zero probability of the missed detection and false alarm of active primary transmission, a certain degree of performance degradation of the primary user (PU) from cognitive radio users (CRs) is unavoidable. In this paper, we consider OFDM-based communication systems and present efficient algorithms to maximize the total rate of the CR by optimizing jointly both the detection operation and the power allocation, taking into account the influence of the probabilities of missed detection and false alarm, namely, the sensing accuracy. The optimization problem can be formulated as a two-variable non-convex problem, which can be solved approximately by using an alternating directi…

Rotation-Invariant Texture Retrieval via Signature Alignment Based on Steerable Sub-Gaussian Modeling

This paper addresses the construction of a novel efficient rotation-invariant texture retrieval method that is based on the alignment in angle of signatures obtained via a steerable sub-Gaussian model. In our proposed scheme, we first construct a steerable multivariate sub-Gaussian model, where the fractional lower-order moments of a given image are associated with those of its rotated versions. The feature extraction step consists of estimating the so-called covariations between the orientation subbands of the corresponding steerable pyramid at the same or at adjacent decomposition levels and building an appropriate signature that can be rotated directly without the need of rotating the im…

Topology design to increase network lifetime in WSN for graph filtering in consensus processes

Graph filters, which are considered as the workhorses of graph signal analysis in the emerging field of signal processing on graphs, are useful for many applications such as distributed estimation in wireless sensor networks. Many of these tasks are based on basic distributed operators such as consensus, which are carried out by sensor devices under limited energy supply. To cope with the energy constraints, this paper focuses on designing the network topology in order to maximize the network lifetime and reduce the energy consumption when applying graph filters. The problem is a complex combinatorial problem and in this work, we propose two efficient heuristic algorithms for solving it. We…

Graph Filtering with Quantization over Random Time-varying Graphs

Distributed graph filters can be implemented over wireless sensor networks by means of cooperation and exchanges among nodes. However, in practice, the performance of such graph filters is deeply affected by the quantization errors that are accumulated when the messages are transmitted. The latter is paramount to overcome the limitations in terms of bandwidth and computation capabilities in sensor nodes. In addition to quantization errors, distributed graph filters are also affected by random packet losses due to interferences and background noise, leading to the degradation of the performance in terms of the filtering accuracy. In this work, we consider the problem of designing graph filte…

Wireless sensor network for Spectrum Cartography based on Kriging interpolation

Dynamic spectrum access with Cognitive Radio (CR) network is a promising approach to increase the efficiency of spectrum usage. To allow the optimization of resource allocation and transmission adaptation techniques, each CR terminal needs to acquire awareness of the state of the time-frequency-location varying radio spectrum. In this paper we present a Spectrum Cartography (SC) approach where CR terminals are supported by a fixed wireless sensor network (WSN) to estimate and update the Power Spectral Density (PSD) over the area of interest. The wireless sensors collaborate to estimate the spatial distribution of the received power at a given frequency using either a centralized or a distri…

Ensuring High Performance of Consensus-Based Estimation by Lifetime Maximization in WSNs

The estimation of a parameter corrupted by noise is a common tasks in wireless sensor networks, where the deployed nodes cooperate in order to improve their own inaccurate observations. This cooperation usually involves successive data exchanges and local information updates until a global consensus value is reached. The quality of the final estimator depends on the amount of collected observations, hence the number of active nodes. Moreover, the inherent iterative nature of the consensus process involves a certain energy consumption. Since the devices composing the network are usually battery powered, nodes becoming inactive due to battery depletion emerges as a serious problem. In this wo…

Non-parametric spectrum cartography using adaptive radial basis functions

This paper presents a framework for spectrum cartography based on the use of adaptive Gaussian radial basis functions (RBF) centered around a specific number of centroid locations, which are determined, jointly with the other RBF parameters, by the available measurement values at given sensor locations in a specific geographical area. The spectrum map is constructed non-parametrically as no prior knowledge about the transmitters is assumed. The received signal power at each location (over a given bandwidth and time period) is estimated as a weighted contribution from different RBF, in such a way that the both RBF parameters and the weights are jointly optimized using an alternating minimiza…

Random Feature Approximation for Online Nonlinear Graph Topology Identification

Online topology estimation of graph-connected time series is challenging, especially since the causal dependencies in many real-world networks are nonlinear. In this paper, we propose a kernel-based algorithm for graph topology estimation. The algorithm uses a Fourier-based Random feature approximation to tackle the curse of dimensionality associated with the kernel representations. Exploiting the fact that the real-world networks often exhibit sparse topologies, we propose a group lasso based optimization framework, which is solve using an iterative composite objective mirror descent method, yielding an online algorithm with fixed computational complexity per iteration. The experiments con…

Consensus based distributed estimation of biomass concentration in reverse osmosis membranes

The correct estimation of biofilm formation in industrial environments, such as reverse osmosis plants, has become a topic of great interest. The occurrence of this natural process is the cause of huge economic losses due to a decrease of performance and maintenance costs in these plants. Current solutions based on water pretreatment or the dozing of biocides are not effective due to the lack of information about the state of the biofilm in the water system. In this work, we propose the use of a wireless sensor network that, based on the measurement of the biofilm thickness growth at the substratum of each sensor, estimates the biomass concentration within the biofilm, and, eventually, the …

Directionlets: Anisotropic Multidirectional representation with separable filtering

In spite of the success of the standard wavelet transform (WT) in image processing in recent years, the efficiency of its representation is limited by the spatial isotropy of its basis functions built in the horizontal and vertical directions. One-dimensional (1-D) discontinuities in images (edges and contours) that are very important elements in visual perception, intersect too many wavelet basis functions and lead to a nonsparse representation. To efficiently capture these anisotropic geometrical structures characterized by many more than the horizontal and vertical directions, a more complex multidirectional (M-DIR) and anisotropic transform is required. We present a new lattice-based pe…

Non-cooperative power allocation game with imperfect sensing information for cognitive radio

In this paper, we consider a sensing-based spectrum sharing scenario and present an efficient decentralized algorithm to maximize the total throughput of the cognitive radio users by optimizing jointly both the detection operation and the power allocation, taking into account the influence of the sensing accuracy. This optimization problem can be formulated as a distributed non-cooperative power allocation game, which can be solved by using an alternating direction optimization method. The transmit power budget of the cognitive radio users and the constraint related to the rate-loss of the primary user due to the interference are considered in the scheme. Finally, we use variational inequal…

Space-Frequency Quantization using Directionlets

In our previous work we proposed a construction of critically sampled perfect reconstruction transforms with directional vanishing moments (DVMs) imposed in the corresponding basis functions along different directions, called directionlets. Here, we combine the directionlets with the space-frequency quantization (SFQ) image compression method, originally based on the standard two-dimensional (2-D) wavelet transform (WT). We show that our new compression method outperforms the standard SFQ as well as the state-of-the-art compression methods, like SPIHT and JPEG-2000, in terms of the quality of compressed images, especially in a low-rate compression regime. We also show that the order of comp…

Adaptive Medium Access Control for Distributed Processing in Wireless Sensor Networks

Signal and information processing tasks over Wireless Sensor Networks can be successfully accomplished by means of a distributed implementation among the nodes. Existing distributed schemes are commonly based on iterative strategies that imply a huge demand of one-hop transmissions, which must be efficiently processed by the lower layers of the nodes. At the link layer, general purpose medium access (MAC) policies for wireless communications usually focus on avoiding collisions. These existing approaches result in a reduction of the number of simultaneous transmissions, and an underutilization of the channel as a consequence. This leads to a decrease in the performance of the distributed ta…

Stochastic Graph Filtering Under Asymmetric Links in Wireless Sensor Networks

Wireless sensor networks (WSN s) are often characterized by random and asymmetric packet losses due to the wireless medium, leading to network topologies that can be modeled as random, time-varying and directed graphs. Most of existing works related to graph filtering in the context of WSNs assume that the probability of delivering an information from one node to a neighbor node is the same as in the reverse direction. This assumption is not realistic due to the typical link asymmetry in WSNs caused by interferences and background noise. In this work, we analyze the problem of applying stochastic graph filtering over random time-varying asymmetric network topologies. We show that it is poss…

Adaptive Consensus-Based Distributed Kalman Filter for WSNs with Random Link Failures

Wireless Sensor Networks have emerged as a very powerful tool for the monitoring and control, over large areas, of diverse phenomena. One of the most appealing properties of these networks is their potentiality to perform complex tasks in a total distributed fashion, without requiring a central entity. In this scenario, where nodes are constrained to use only local information and communicate with one-hop neighbors, iterative consensus algorithms are extensively used due to their simplicity. In this work, we propose the design of a consensus-based distributed Kalman filter for state estimation, in a sensor network whose connections are subject to random failures. As a result of this unrelia…

Robust Transmit Beamforming for Underlay D2D Communications on Multiple Channels

Underlay device-to-device (D2D) communications lead to improvement in spectral efficiency by simultaneously allowing direct communication between the users and the existing cellular transmission. However, most works in resource allocation for D2D communication have considered single antenna transmission and with a focus on perfect channel state information (CSI). This work formulates a robust transmit beamforming design problem for maximizing the aggregate rate of all D2D pairs and cellular users (CUs). Assuming complex Gaussian distributed CSI error, our formulation guarantees probabilistically a signal to interference plus noise ratio (SINR) above a specified threshold. In addition, we al…

Radio measurements on a customized software defined radio module: A case study of energy detection spectrum sensing

In this paper, we developed a software defined radio (SDR) system for implementing energy detection spectrum sensing. The SDR module can be used for a wide range of applications. The use of the SDR module is motivated by its high interoperability, availability for relatively cheaper prices and being software independent. Energy detection for cognitive radios is chosen for its simplicity and popularity. However, it is chosen as a representative for a very wide range of measurements and algorithms that can be implemented in the SDR. We have used probabilities of detection and false alarm with the receiver operating characteristics (ROC) curves as performance metrics for the implemented energy…

Low-Rate Reduced Complexity Image Compression using Directionlets

The standard separable two-dimensional (2-D) wavelet transform (WT) has recently achieved a great success in image processing because it provides a sparse representation of smooth images. However, it fails to capture efficiently one-dimensional (1-D) discontinuities, like edges and contours, that are anisotropic and characterized by geometrical regularity along different directions. In our previous work, we proposed a construction of critically sampled perfect reconstruction anisotropic transform with directional vanishing moments (DVM) imposed in the corresponding basis functions, called directionlets. Here, we show that the computational complexity of our transform is comparable to the co…

Self-powered IoT Device based on Energy Harvesting for Remote Applications

In this paper, we present the design and prototype implementation of self-powered Internet of Things (IoT) device based on energy harvesting from a small solar panel of size 63mm x 63mm and 0.36W for remote applications. These IoT devices can be deployed in remote places within the range of a gateway. A complete proof of concept IoT device based on ambient energy harvesting is designed, prototyped and tested with super capacitors and Lithium cells in star topology. Based on the measurements, the IoT device can potentially last for one year with 55 seconds transmission interval with the fully charged 120mAh coin cell battery. On the other hand, a fully charged single 5F supercapacitor lasts …

Tracking of Quantized Signals Based on Online Kernel Regression

Kernel-based approaches have achieved noticeable success as non-parametric regression methods under the framework of stochastic optimization. However, most of the kernel-based methods in the literature are not suitable to track sequentially streamed quantized data samples from dynamic environments. This shortcoming occurs mainly for two reasons: first, their poor versatility in tracking variables that may change unpredictably over time, primarily because of their lack of flexibility when choosing a functional cost that best suits the associated regression problem; second, their indifference to the smoothness of the underlying physical signal generating those samples. This work introduces a …

Dynamic network identification from non-stationary vector autoregressive time series

Learning the dynamics of complex systems features a large number of applications in data science. Graph-based modeling and inference underpins the most prominent family of approaches to learn complex dynamics due to their ability to capture the intrinsic sparsity of direct interactions in such systems. They also provide the user with interpretable graphs that unveil behavioral patterns and changes. To cope with the time-varying nature of interactions, this paper develops an estimation criterion and a solver to learn the parameters of a time-varying vector autoregressive model supported on a network of time series. The notion of local breakpoint is proposed to accommodate changes at individu…

A Cluster based Sensor-Selection Scheme for Energy-Efficient Agriculture Sensor Networks

Improving the energy-efficiency of remotely deployed sensor nodes in agriculture wireless networks is very challenging due to a lack of access to energy grid. Network clustering and limiting the amount of sensor data are among the various methods to improve the lifetime of these sensor nodes. In this work, an optimal sensor-selection scheme is proposed to improve the Quality of Service in clustered agriculture networks. the proposed method selects a limited number of sensor nodes to be active in each cluster. It considers the estimator performance while selecting limited sensor nodes for environmental monitoring. the optimal sensor-selection process considers the information of remaining en…

Dynamic Regret Analysis for Online Tracking of Time-varying Structural Equation Model Topologies

Identifying dependencies among variables in a complex system is an important problem in network science. Structural equation models (SEM) have been used widely in many fields for topology inference, because they are tractable and incorporate exogenous influences in the model. Topology identification based on static SEM is useful in stationary environments; however, in many applications a time-varying underlying topology is sought. This paper presents an online algorithm to track sparse time-varying topologies in dynamic environments and most importantly, performs a detailed analysis on the performance guarantees. The tracking capability is characterized in terms of a bound on the dynamic re…

Sparse Image Representation by Directionlets

Despite the success of the standard wavelet transform (WT) in image processing in recent years, the efficiency and sparsity of its representation are limited by the spatial symmetry and separability of its basis functions built in the horizontal and vertical directions. One-dimensional discontinuities in images (edges or contours), which are important elements in visual perception, intersect too many wavelet basis functions and lead to a non-sparse representation. To capture efficiently these elongated structures characterized by geometrical regularity along different directions (not only the horizontal and vertical), a more complex multidirectional (M-DIR) and asymmetric transform is requi…

Data-Driven Pump Scheduling for Cost Minimization in Water Networks

Pumps consume a significant amount of energy in a water distribution network (WDN). With the emergence of dynamic energy cost, the pump scheduling as per user demand is a computationally challenging task. Computing the decision variables of pump scheduling relies over mixed integer optimization (MIO) formulations. However, MIO formulations are NP-hard in general and solving such problems is inefficient in terms of computation time and memory. Moreover, the computational complexity of solving such MIO formulations increases exponentially with the size of the WDN. As an alternative, we propose a data-driven approach to estimate the decision variables of pump scheduling using deep neural netwo…

Designing Asymmetric Shift Operators for Decentralized Subspace Projection

A large number of applications in wireless sensor networks include projecting a vector of noisy observations onto a subspace dictated by prior information about the field being monitored. In general, accomplishing such a task in a centralized fashion, entails a large power consumption, congestion at certain nodes, and suffers from robustness issues against possible node failures. Computing such projections in a decentralized fashion is an alternative solution that solves these issues. Recent works have shown that this task can be done via the so-called graph filters where only local inter-node communication is performed in a distributed manner using a graph shift operator. Existing methods …

Decentralized Subspace Projection for Asymmetric Sensor Networks

A large number of applications in Wireless Sensor Networks include projecting a vector of noisy observations onto a subspace dictated by prior information about the field being monitored. In general, accomplishing such a task in a centralized fashion, entails a large power consumption, congestion at certain nodes and suffers from robustness issues against possible node failures. Computing such projections in a decentralized fashion is an alternative solution that solves these issues. Recent works have shown that this task can be done via the so-called graph filters where only local inter-node communication is performed in a distributed manner using a graph shift operator. Most of the existi…

Spectrum cartography using adaptive radial basis functions: Experimental validation

In this paper, we experimentally validate the functionality of a developed algorithm for spectrum cartography using adaptive Gaussian radial basis functions (RBF). The RBF are strategically centered around representative centroid locations in a machine learning context. We assume no prior knowledge about neither the power spectral densities (PSD) of the transmitters nor their locations. Instead, the received signal power at each location is estimated as a linear combination of different RBFs. The weights of the RBFs, their Gaussian decaying parameters and locations are jointly optimized using expectation maximization with a least squares loss function and a quadratic regularizer. The perfor…

Topology design to reduce energy consumption of distributed graph filtering in WSN

The large number of nodes forming current sensor networks has made essential to introduce distributed mechanisms in many traditional applications. In the emerging field of graph signal processing, the distributed mechanism of information potentials constitutes a distributed graph filtering process that can be used to solve many different problems. An important limitation of this algorithm is that it is inherently iterative, which implies that the nodes incur in a repeated communication cost along the exchange periods of the filtering process. Since sensor nodes are battery powered and radio communications are one of the most energy demanding operations, in this work, we propose to redesign …

Online Hyperparameter Search Interleaved with Proximal Parameter Updates

There is a clear need for efficient hyperparameter optimization (HO) algorithms for statistical learning, since commonly applied search methods (such as grid search with N-fold cross-validation) are inefficient and/or approximate. Previously existing gradient-based HO algorithms that rely on the smoothness of the cost function cannot be applied in problems such as Lasso regression. In this contribution, we develop a HO method that relies on the structure of proximal gradient methods and does not require a smooth cost function. Such a method is applied to Leave-one-out (LOO)-validated Lasso and Group Lasso, and an online variant is proposed. Numerical experiments corroborate the convergence …

Message from the Workshop Chairs

Reliable Underlay Device-to-Device Communications on Multiple Channels

Device-to-device (D2D) communications provide a substantial increase in spectrum usage and efficiency by allowing nearby users to communicate directly without passing their packets through the base station (BS). In previous works, proper channel assignment and power allocation algorithms for sharing of channels between cellular users and D2D pairs, usually require exact knowledge of the channel-state-information (CSI). However, due to the non-stationary wireless environment and the need to limit the communication and computation overheads, obtaining perfect CSI in the D2D communication scenario is generally not possible. In this work, we propose a joint channel assignment and power allocati…

Self-Powered IoT Device for Indoor Applications

This paper presents a proof of concept for selfpowered Internet of Things (IoT) device, which is maintenance free and completely self-sustainable through energy harvesting. These IoT devices can be deployed in large scale and placed anywhere as long as they are in range of a gateway, and as long as there is sufficient light levels for the solar panel, such as indoor lights. A complete IoT device is designed, prototyped and tested. The IoT device can potentially last for more than 5 months (transmission interval of 30 seconds) on the coin cell battery (capacity of 120mAh) without any energy harvesting, sufficiently long for the dark seasons of the year. The sensor node contains ultra-low pow…

Design of SCMA Codebooks using Differential Evolution

Non-orthogonal multiple access (NOMA) is a promising technology which meets the demands of massive connectivity in future wireless networks. Sparse code multiple access (SCMA) is a popular code-domain NOMA technique. The effectiveness of SCMA comes from: (1) the multi-dimensional sparse codebooks offering high shaping gain and (2) sophisticated multi-user detection based on message passing algorithm (MPA). The codebooks of the users play the main role in determining the performance of SCMA system. This paper presents a framework to design the codebooks by taking into account the entire system including the SCMA encoder and the MPA-based detector. The symbol-error rate (SER) is considered as…

A reliable CSMA protocol for high performance broadcast communications in a WSN

Wireless Sensor Networks have been identified as a promising technology to efficiently perform distributed monitoring, tracking and control tasks. In order to accomplish them, since fast decisions are generally required, high values of throughput must be obtained. Additionally, a high packet reception rate is important to avoid wasting energy due to unsuccessful transmissions. These communication requirements are more easily satisfied by exploiting the broadcast nature of the wireless medium, which allows several simultaneous receptions through a unique node transmission. We propose a Medium Access Control protocol that ensures, simultaneously, high values of throughput and a high packet re…

Reducing the observation error in a WSN through a consensus-based subspace projection

An essential process in a Wireless Sensor Network is the noise mitigation of the measured data, by exploiting their spatial correlation. A widely used technique to achieve this reduction is to project the measured data into a proper subspace. We present a low complexity and distributed algorithm to perform this projection. Unlike other algorithms existing in the literature, which require the number of connections at every node to be larger than the dimension of the involved subspace, our algorithm does not require such dense network topologies for its applicability, making it suitable for a larger number of scenarios. Our proposed algorithm is based on the execution of several consensus pro…

DECENTRALIZED SUBSPACE PROJECTION IN LARGE NETWORKS

A great number of applications in wireless sensor networks involve projecting a vector of observations onto a subspace dictated by prior information. Accomplishing such a task in a centralized fashion entails great power consumption, congestion at certain nodes, and suffers from robustness issues. A sensible alternative is to compute such projections in a decentralized fashion. To this end, recent works proposed schemes based on graph filters, which compute projections exactly with a finite number of local exchanges among sensor nodes. However, existing methods to obtain these filters are confined to reduced families of projection matrices or small networks. This paper proposes a method tha…

JOINT TOPOLOGY LEARNING AND GRAPH SIGNAL RECOVERY VIA KALMAN FILTER IN CAUSAL DATA PROCESSES

In this paper, a joint graph-signal recovery approach is investigated when we have a set of noisy graph signals generated based on a causal graph process. By leveraging the Kalman filter framework, a three steps iterative algorithm is utilized to predict and update signal estimation as well as graph topology learning, called Topological Kalman Filter or TKF. Similar to the regular Kalman filter, we first predict the a posterior signal state based on the prior available data and then this prediction is updated and corrected based on the recently arrived measurement. But contrary to the conventional Kalman filter algorithm, we have no information of the transition matrix and hence we relate t…

Fast Graph Filters for Decentralized Subspace Projection

A number of inference problems with sensor networks involve projecting a measured signal onto a given subspace. In existing decentralized approaches, sensors communicate with their local neighbors to obtain a sequence of iterates that asymptotically converges to the desired projection. In contrast, the present paper develops methods that produce these projections in a finite and approximately minimal number of iterations. Building upon tools from graph signal processing, the problem is cast as the design of a graph filter which, in turn, is reduced to the design of a suitable graph shift operator. Exploiting the eigenstructure of the projection and shift matrices leads to an objective whose…