Modeling complex spatial and temporal correlations in the correlated time series data is indispensable for understanding the traffic dynamics and predicting the future status of an evolving traffic system. Recent works focus on designing complicated graph neural network architectures to capture shared patterns with the help of pre-defined graphs. In this paper, we argue that learning node-specific patterns is essential for traffic forecasting while the pre-defined graph is avoidable. To this end, we propose two adaptive modules for enhancing Graph Convolutional Network (GCN) with new capabilities: 1) a Node Adaptive Parameter Learning (NAPL) module to capture node-specific patterns; 2) a Data Adaptive Graph Generation (DAGG) module to infer the inter-dependencies among different traffic series automatically. We further propose an Adaptive Graph Convolutional Recurrent Network (AGCRN) to capture fine-grained spatial and temporal correlations in traffic series automatically based on the two modules and recurrent networks. Our experiments on two real-world traffic datasets show AGCRN outperforms state-of-the-art by a significant margin without pre-defined graphs about spatial connections.

Adaptive Graph Convolutional Recurrent Network for Traffic Forecasting

Cognitive radio technology has the potential to address the shortage of available radio spectrum by enabling dynamic spectrum access. Since its introduction, researchers have been working on enabling this innovative technology in managing the radio spectrum. As a result, this research field has been progressing at a rapid pace and significant advances have been made. To help researchers stay abreast of these advances, surveys and tutorial papers are strongly needed. Therefore, in this paper, we aimed to provide an in-depth survey on the most recent advances in spectrum sensing, covering its development from its inception to its current state and beyond. In addition, we highlight the efficiency and limitations of both narrowband and wideband spectrum sensing techniques as well as the challenges involved in their implementation. TV white spaces are also discussed in this paper as the first real application of cognitive radio. Last but by no means least, we discuss future research directions. This survey paper was designed in a way to help new researchers in the field to become familiar with the concepts of spectrum sensing, compressive sensing, and machine learning, all of which are the enabling technologies of the future networks, yet to help researchers further improve the efficiently of spectrum sensing.

https://www.mdpi.com/1424-8220/19/1/126/pdf/1

A Comprehensive Survey on Spectrum Sensing in Cognitive Radio Networks: Recent Advances, New Challenges, and Future Research Directions

Wireless networks with their ubiquitous applications have become an indispensable part of our daily lives. Wireless networks demand more and more spectral resources to support the ever increasing numbers of users. According to network engineers, the current spectrum crunch can be addressed with the introduction of cognitive radio networks (CRNs). In half-duplex (HD) CRNs, the secondary users (SUs) can either only sense the spectrum or transmit at a given time. This HD operation limits the SU throughput, because the SUs cannot transmit during the spectrum sensing. However, with the advances in self-interference suppression (SIS), full-duplex (FD) CRNs allow for simultaneous spectrum sensing and transmission on a given channel. This FD operation increases the throughput and reduces collisions as compared with HD-CRNs. In this paper, we present a comprehensive survey of FD-CRN communications. We cover the supporting network architectures and the various transmit and receive antenna designs. We classify the different SIS approaches in FD-CRNs. We survey the spectrum sensing approaches and security requirements for FD-CRNs. We also survey major advances in FD medium access control protocols as well as open issues, challenges, and future research directions to support the FD operation in CRNs.

Full-Duplex Communication in Cognitive Radio Networks: A Survey

Increasingly, human beings are sensors engaging directly with the mobile Internet. Individuals can now share real-time experiences at an unprecedented scale. Social Sensing: Building Reliable Systems on Unreliable Data looks at recent advances in the emerging field of social sensing, emphasizing the key problem faced by application designers: how to extract reliable information from data collected from largely unknown and possibly unreliable sources. The book explains how a myriad of societal applications can be derived from this massive amount of data collected and shared by average individuals. The title offers theoretical foundations to support emerging data-driven cyber-physical applications and touches on key issues such as privacy. The authors present solutions based on recent research and novel ideas that leverage techniques from cyber-physical systems, sensor networks, machine learning, data mining, and information fusion. Offers a unique interdisciplinary perspective bridging social networks, big data, cyber-physical systems, and reliability Presents novel theoretical foundations for assured social sensing and modeling humans as sensors Includes case studies and application examples based on real data sets Supplemental material includes sample datasets and fact-finding software that implements the main algorithms described in the book

Social Sensing: Building Reliable Systems on Unreliable Data

Widespread proliferation of wireless coverage has enabled culmination of number of advanced location-based services (LBS). Continuous tracking of accurate physical location is the foundation of these services, which is a challenging task especially indoors. Multitude of techniques and algorithms have been proposed for indoor positioning systems (IPS’s). However, accuracy, reliability, scalability and, adaptability to the environment still remain as challenges for widespread deployment. Especially, unpredictable radio propagation characteristics in vastly varying indoor environments plus access technology limitations contribute to these challenges. Machine learning (ML) approaches have been widely attempted recently to overcome these challenges with reasonable success. In this paper, we aim to provide a comprehensive survey of ML enabled localization techniques using most common wireless technologies. First, we provide a brief background on indoor localization techniques. Afterwards, we discuss various ML techniques (supervised and unsupervised) that could alleviate different challenges in indoor localization including Non-line-of-sight (NLOS) issue, device heterogeneity and environmental variations with reasonable complexity. The trade-offs among multitude of issues are discussed using numerous published results. We also discuss how the ML algorithms can be effectively used for fusing different technologies and algorithms to achieve a comprehensive IPS. In essence, this survey will serve as a reference material to acquire a detailed knowledge on recent development of machine learning for accurate indoor positioning.

/pdf/a-survey-of-machine-learning-for-indoor-positioning-3uqx28fbz2.pdf

A Survey of Machine Learning for Indoor Positioning

Multivariate time series forecasting has attracted wide attention in areas, such as system, traffic, and finance. The difficulty of the task lies in that traditional methods fail to capture complicated non-linear dependencies between time steps and between multiple time series. Recently, recurrent neural network and attention mechanism have been used to model periodic temporal patterns across multiple time steps. However, these models fit not well for time series with dynamic-period patterns or nonperiodic patterns. In this paper, we propose a dual self-attention network (DSANet) for highly efficient multivariate time series forecasting, especially for dynamic-period or nonperiodic series. DSANet completely dispenses with recurrence and utilizes two parallel convolutional components, called global temporal convolution and local temporal convolution, to capture complex mixtures of global and local temporal patterns. Moreover, DSANet employs a self-attention module to model dependencies between multiple series. To further improve the robustness, DSANet also integrates a traditional autoregressive linear model in parallel to the non-linear neural network. Experiments on real-world multivariate time series data show that the proposed model is effective and outperforms baselines.

DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting

We study cooperative spectrum sensing in cognitive radio networks (CRN) using machine learning techniques in this paper. A low-dimensional probability vector is proposed as the feature vector for machine learning based classification, instead of the N-dimensional energy vector in a CRN with a single primary user (PU) and N secondary users (SUs). This proposed method down-converts a high-dimensional feature vector to a constant two-dimensional feature vector for machine learning techniques while keeping the same spectrum sensing performance if not better. Due to its lower dimension, the probability vector based classification is capable of having a smaller training duration and a shorter classification time for testing vectors.

Machine learning techniques with probability vector for cooperative spectrum sensing in cognitive radio networks

While few-shot learning (FSL) aims for rapid generalization to new concepts with little supervision, self-supervised learning (SSL) constructs supervisory signals directly computed from unlabeled data. Exploiting the complementarity of these two manners, few-shot auxiliary learning has recently drawn much attention to deal with few labeled data. Previous works benefit from sharing inductive bias between the main task (FSL) and auxiliary tasks (SSL), where the shared parameters of tasks are optimized by minimizing a linear combination of task losses. However, it is challenging to select a proper weight to balance tasks and reduce task conflict. To handle the problem as a whole, we propose a novel approach named as Pareto self-supervised training (PSST) for FSL. PSST explicitly decomposes the few-shot auxiliary problem into multiple constrained multi-objective subproblems with different trade-off preferences, and here a preference region in which the main task achieves the best performance is identified. Then, an effective preferred Pareto exploration is proposed to find a set of optimal solutions in such a preference region. Extensive experiments on several public benchmark datasets validate the effectiveness of our approach by achieving state-of-the-art performance.

/pdf/pareto-self-supervised-training-for-few-shot-learning-5136w8uyhg.pdf

Pareto Self-Supervised Training for Few-Shot Learning

OFDM is proposed for time-based range estimation (TBRE) and analyzed with respect to its accuracy, both theoretically, in terms of its Cramer-Rao lower bound (CRLB), and practically, in terms of its maximum likelihood estimator (MLE). The CRLB for OFDM transmission is compared to that for pseudo-noise (PN) transmission, demonstrating a large performance gap in favour of OFDM. Moveover, the MLE for TBRE is compared to the commonly used MLE for channel estimation (CE), demonstrating a performance gap in favour of the MLE for TBRE. Finally, the CRLB for OFDM is compared to its corresponding MLE for TBRE, demonstrating a good agreement in performance except for the so-called ?threshold effect?, which is analyzed analytically in this letter.

OFDM Transmission for Time-Based Range Estimation

This paper studies the problem of learning message propagation strategies for graph neural networks (GNNs). One of the challenges for graph neural networks is that of defining the propagation strategy. For instance, the choices of propagation steps are often specialized to a single graph and are not personalized to different nodes. To compensate for this, in this paper, we present learning to propagate, a general learning framework that not only learns the GNN parameters for prediction but more importantly, can explicitly learn the interpretable and personalized propagate strategies for different nodes and various types of graphs. We introduce the optimal propagation steps as latent variables to help find the maximum-likelihood estimation of the GNN parameters in a variational Expectation- Maximization (VEM) framework. Extensive experiments on various types of graph benchmarks demonstrate that our proposed frame- work can significantly achieve better performance compared with the state-of-the-art methods, and can effectively learn personalized and interpretable propagate strategies of messages in GNNs.

Donglin Wang

Papers

DSANet: Dual Self-Attention Network for Multivariate Time Series Forecasting

Machine learning techniques with probability vector for cooperative spectrum sensing in cognitive radio networks

Pareto Self-Supervised Training for Few-Shot Learning

OFDM Transmission for Time-Based Range Estimation

Learning How to Propagate Messages in Graph Neural Networks