Search

In this paper, we present a framework for performing automatic analysis of Land Use Zones based on Location-Based Social Networks (LBSNs). We model city areas using a hierarchical structure of POIs extracted from foursquare. We encode such structures in kernel machines, e.g., Support Vector Machines, using a new Tree Kernel, i.e., the Hierarchical POI Kernel (HPK), which can take the importance of the individual POIs into account during the substructure matching. This way, HPK projects structures in the space of all their possible substructures such that each dimension corresponds to a semantic structural feature, weighted according to the discriminative power of POIs. We generated four different datasets for the following cities: Barcelona, Lisbon, Amsterdam and Milan, where we trained and tested our models. The results show that our approach largely outperforms previous work and standard baseline built on simple features, such as counts of different POIs. Finally, we apply a mining algorithm to extract the most relevant features (tree fragments) from the implicit TK space according to the weights the kernel machine assigned to them. Our approach can produce an explicit set of representative features that can be used to classify and characterize urban areas. [ABSTRACT FROM AUTHOR]

Power control is becoming increasingly essential for the fifth-generation (5G) and beyond systems. An example use-case, among others, is the unmanned-aerial-vehicle (UAV) communications where the nearly line-of-sight (LoS) radio channels may result in very low signal-to-interference-plus-noise ratios (SINRs). The authors in (Chiang et al., 2007) proposed to efficiently and reliably solve this kind of non-convex problem via a series of geometrical programmings (GPs) using condensation approximation. However, it is only applicable for a small-scale network with several communication pairs and practically infeasible with more (e.g., tens of) nodes to be jointly optimized. We therefore in this paper aim to provide new insights into this problem. By properly introducing auxiliary variables, the problem is transformed to an equivalent form which is simpler and more intuitive for condensation. A novel condensation method with linear complexity is also proposed based on the form. The enhancements make the GP-based power control feasible for both small- and especially large-scale networks that are common in 5G and beyond. The algorithm is verified via simulations. A preliminary case study of uplink UAV communications also shows the potential of the algorithm. [ABSTRACT FROM AUTHOR]

Automated machine learning (AutoML) seeks to automatically find so-called machine learning pipelines that maximize the prediction performance when being used to train a model on a given dataset. One of the main and yet open challenges in AutoMLis an effective use of computational resources: An AutoML process involves the evaluation of many candidate pipelines, which are costly but often ineffective because they are canceled due to a timeout. In this paper, we present an approach to predict the runtime of two-step machine learning pipelines with up to one pre-processor, which can be used to anticipate whether or not a pipeline will time out. Separate runtime models are trained offline for each algorithm that may be used in a pipeline, and an overall prediction is derived from these models. We empirically show that the approach increases successful evaluations made by an AutoML tool while preserving or even improving on the previously best solutions. [ABSTRACT FROM AUTHOR]

This paper presents a new method for selecting a patient specific forward model to compensate for anatomical variations in electrical impedance tomography (EIT) monitoring of neonates. The method uses a combination of shape sensors and absolute reconstruction. It takes advantage of a probabilistic approach which automatically selects the best estimated forward model fit from pre-stored library models. Absolute/static image reconstruction is performed as the core of the posterior probability calculations. The validity and reliability of the algorithm in detecting a suitable model in the presence of measurement noise is studied with simulated and measured data from 11 patients. The paper also demonstrates the potential improvements on the clinical parameters extracted from EIT images by considering a unique case study with a neonate patient undergoing computed tomography imaging as clinical indication prior to EIT monitoring. Two well-known image reconstruction techniques, namely GREIT and tSVD, are implemented to create the final tidal images. The impacts of appropriate model selection on the clinical extracted parameters such as center of ventilation and silent spaces are investigated. The results show significant improvements to the final reconstructed images and more importantly to the clinical EIT parameters extracted from the images that are crucial for decision-making and further interventions. [ABSTRACT FROM AUTHOR]

This paper is concerned with the forecasting aided state estimation (FASE) problem for power distribution networks (PDNs) subject to nonlinear measurements and limited communication resources. For the sake of using bandwidth more effectively, a special closed-loop event triggering condition is first designed with the hope to reduce unnecessary data transmission from the measurement side to the remote estimator. And an event-based robust filtering algorithm is proposed to improve the estimation performance of estimator with the nonlinear intermittent observations. In this algorithm, the measurement output function with high-order nonlinearity is reasonably reduced to a quadratic alternative form, in order to avoid the computation burden caused by the use of the second-order extended Kalman filter (SOEKF), the quadratic nonlinear function is further linearized by Taylor series with quadratic norm bound. Furthermore, an upper bound of the filtering error covariance containing some uncertainties (includes quadratic term and non-triggering errors) is derived and subsequently minimized at each time step. The desired filter gain is obtained by recursively solving a set of Riccati-like matrix equations, which is easy to implement via online computation. Finally, the effectiveness of the proposed algorithm is demonstrated using the standard IEEE 13-bus and 123-bus distribution test feeders with both phasor measurement unit (PMU) and conventional measurements. [ABSTRACT FROM AUTHOR]

This paper proposes a new decentralized data-driven load restoration (DDLR) scheme for transmission and distribution (TD) systems with high penetration of wind power. Robust DDLR models are constructed in order to handle uncertainties and ensure the feasibility of decentralized schemes. The Wasserstein metric is used to describe the ambiguity sets of probability distributions in order to build the complete DDLR model and realize computationally tractable formulation. A data-driven model-nested analytical target cascading (DATC) algorithm is developed to obtain the final load restoration result by iteratively solving small-scale mathematical models. The proposed DDLR scheme provides load restoration results with adjustable robustness, and performance efficiency is independent from the amount of data. The DDLR scheme makes full use of the available data while respecting information privacy requirements of independent operated systems, and ensures the feasibility of a decentralized load restoration strategy even in the worst-case condition. The effectiveness of the proposed method is validated using a small-scale TD system and a large-scale system with the IEEE 118-bus TS and thirty IEEE-33 DSs, showing high computational efficiency and superior restoration performance. [ABSTRACT FROM AUTHOR]

With the proliferation of distributed generators and energy storage systems, traditional passive consumers in power systems have been gradually evolving into the so-called “prosumers,” i.e., proactive consumers, which can both produce and consume power. To encourage energy exchange among prosumers, energy sharing is increasingly adopted, which is usually formulated as a generalized Nash game (GNG). In this paper, a distributed approach is proposed to seek the Generalized Nash equilibrium (GNE) of the energy sharing game. To this end, we first prove the strong monotonicity of the game. Then, the GNG is converted into an equivalent optimization problem. An algorithm based on Nesterov's methods is thereby devised to solve the equivalent problem and consequently find the GNE in a distributed manner. The convergence of the proposed algorithm is proved rigorously based on the nonexpansive operator theory. The performance of the algorithm is validated by experiments with three prosumers, and the scalability is tested by simulations using 1888 prosumers. [ABSTRACT FROM AUTHOR]

In this paper, a coupled interaction matrix is proposed to describe the interactions between line outages and the load shed at buses. The coupled interaction matrix is effectively estimated by the Expectation Maximization algorithm. A highly probabilistic coupled interaction model is further proposed to efficiently generate cascades with both line outages and the load shed based on the coupled interaction matrix and the distribution of initial outages. To mitigate cascading failures, critical links are identified based on the coupled interaction matrix by calculating a comprehensive severity index that considers the consequences of both line outages and the load shed. Simulation results on the IEEE 300-bus system verify the effectiveness of the proposed approach. The cascades generated from the coupled interaction model match the statistics of the original cascades very well. The identified critical links based on the comprehensive severity index enable a proper tradeoff between reducing line outages and reducing the load shed, leading to a better mitigation effect than only considering either line outages or the load shed. [ABSTRACT FROM AUTHOR]

With the introduction of massive renewable energy sources and storage devices, the traditional process of grid operation must be improved in order to be safe, reliable, fast responsive and cost efficient, and in this regard power flow solvers are indispensable. In this paper, we introduce an Interior Point-based (IP) Multi-Period AC Optimal Power Flow (MPOPF) solver for the integration of Stationary Energy Storage Systems (SESS) and Electric Vehicles (EV). The primary methodology is based on: 1) analytic and exact calculation of partial differential equations of the Lagrangian sub-problem, and 2) exploiting the sparse structure and pattern of the coefficient matrix of Newton-Raphson approach in the IP algorithm. Extensive results of the application of proposed methods on several benchmark test systems are presented and elaborated, where the advantages and disadvantages of different existing algorithms for the solution of MPOPF, from the standpoint of computational efficiency, are brought forward. We compare the computational performance of the proposed Schur-Complement algorithm with a direct sparse LU solver. The comparison is performed for two different applicational purposes: SESS and EV. The results suggest the substantial computational performance of Schur-Complement algorithm in comparison with that of a direct LU solver when the number of storage devices and optimisation horizon increase for both cases of SESS and EV. Also, some situations where computational performance is inferior are discussed. [ABSTRACT FROM AUTHOR]

Image quality assessment is a critical problem for image compression, which can be utilized as a guidance for image compression and codec evaluation. In this paper, we propose a full reference image quality assessment (IQA) algorithm to measure the perceptual quality of compressed images. The proposed IQA model utilizes a data-driven transform, multi-stage Karhunen-Loeve Transform (MS-KLT), as a feature extractor to decompose both reference and compressed images into feature domain, where the importance of feature distortions in different spectral components to human visual system (HVS) is easy to distinguish. Accordingly, an efficient weighting strategy is proposed to reflect the importance of feature distortions based on the energy of transformed coefficients. Considering HVS characteristics, weighted spatial masking effect is derived from both local and global perspectives. In addition, to avoid influences of random noises, a local adaptive low-pass filtering process is applied as a pre-processing operation. Extensive experimental results on popular datasets show that our proposed method correlates better with the subjective results compared with the state-of-the-art algorithms. Moreover, the proposed method behaves more robustly compared with existing methods, and achieves top-ranking performance on different IQA datasets. [ABSTRACT FROM AUTHOR]

This paper presents an overview of the geometric partitioning mode (GPM) algorithm that is a part of the most recent Versatile Video Coding (VVC) standard. The GPM algorithm aims to increase the partitioning precision of moving objects using non-rectangular and asymmetric rectangular partitions on top of the conventional rectangular block partitioning structure of VVC. Novel features of GPM contributing to the increase in coding efficiency and the reduction in encoder and decoder complexity are detailed and analyzed in this paper. Evaluated with VVC test model version 8.0 under the joint video experts team common test conditions, experimental results show that the presented GPM algorithm provides luma Bjøntegaard Delta rate reduction of 0.70% for random access and of 1.55% for low delay with B slices configurations, with roughly 3% to 5% additional encoding time and negligible decoder runtime change. Furthermore, as GPM provides more precise partitions for the boundaries of the moving objects, an improvement of visual quality is seen in GPM coded sequences. [ABSTRACT FROM AUTHOR]

This paper focuses on improving indoor Wi-Fi localization by mitigating the effect of fluctuation of received signal strength indication (RSSI). The RSSI data collected at each reference point is first transformed through translation and scaling. The BP (Back Propagation) neural network is then used to construct the ranging model using the transformed RSSI to determine the distances between the target point and each reference point. A genetic algorithm (GA) is developed to optimize the initial values of weights and biases of the BP neural network. For convenience, our proposed ranging model is denoted as GTBPD. A new localization algorithm is then proposed, which uses the GTBPD model and the sequential quadratic programming (SQP, an iterative nonlinear optimization algorithm), and the algorithm is denoted as GTBPD-LSQP for simplicity. Experiments were conducted in three areas of two different teaching buildings with complex environments. The performance of the proposed GTBPD-LSQP algorithm is evaluated and compared with four existing algorithms. The experimental results show that our proposed GTBPD-LSQP algorithm achieves significantly higher location accuracy than the four existing algorithms. [ABSTRACT FROM AUTHOR]

In this paper, an intelligent reflecting surface (IRS) is deployed to assist the terahertz (THz) communications. The sum-rate of user equipments (UEs) is maximized while guaranteeing the rate requirement of each UE. A block coordinate searching (BCS) algorithm is proposed to jointly optimize the IRS’s coordinates, phase shifts, THz sub-bands allocation and power control. Specifically, the relaxation with penalties based (RPB) algorithm is developed to obtain feasible coordinates of the IRS and guarantee the monotonicity of objective value. In addition, the IRS phase shifts are formulated as closed-form expressions with introduced pricing factors. Simulation results show that the proposed scheme can significantly enhance system performance. [ABSTRACT FROM AUTHOR]

In this paper, we consider a computation offloading problem in a three-tier network consisting of multiple mobile users (MUs), multiple edge clouds, and a central cloud. On this basis, we formulate a system Energy Time Cost ($ETC$) minimization problem by jointly optimizing the resource allocation, mobile-edge matching decision, and offloading decision. Due to the difficulty of directly solving the formulated problem, we decompose it and propose two offloading algorithms, namely Gale-Shapley based Minimum/Sequential Offloading Algorithm (GS-MOA/GS-SOA), to optimize offloading decisions by minimizing the system $ETC$ , in which the mobile-edge matching strategies based on the proposed Gale-Shapley based Mobile-Edge mAtching aLgorithm (GS-MEAL) and resource allocations are optimized iteratively. The simulations show the effectiveness of our proposed algorithm. [ABSTRACT FROM AUTHOR]

Infrared and visible image fusion (IVIF) expects to obtain images that retain thermal radiation information from infrared images and texture details from visible images. In this paper, a model-based convolutional neural network (CNN) model, referred to as Algorithm Unrolling Image Fusion (AUIF), is proposed to overcome the shortcomings of traditional CNN-based IVIF models. The proposed AUIF model starts with the iterative formulas of two traditional optimization models, which are established to accomplish two-scale decomposition, i.e., separating low-frequency base information and high-frequency detail information from source images. Then the algorithm unrolling is implemented where each iteration is mapped to a CNN layer and each optimization model is transformed into a trainable neural network. Compared with the general network architectures, the proposed framework combines the model-based prior information and is designed more reasonably. After the unrolling operation, our model contains two decomposers (encoders) and an additional reconstructor (decoder). In the training phase, this network is trained to reconstruct the input image. While in the test phase, the base (or detail) decomposed feature maps of infrared/visible images are merged respectively by an extra fusion layer, and then the decoder outputs the fusion image. Qualitative and quantitative comparisons demonstrate the superiority of our model, which can robustly generate fusion images containing highlight targets and legible details, exceeding the state-of-the-art methods. Furthermore, our network has fewer weights and faster speed. [ABSTRACT FROM AUTHOR]

Due to multi-layer encoding and Inter-layer prediction, Scalable High Efficiency Video Coding (SHVC) has extremely high coding complexity. It is very crucial to improve its coding speed so as to promote widespread and cost-effective SHVC applications. In this paper, we propose a new probability-based fast Intra prediction algorithm for spatial SHVC. More specifically, first, we integrate depth probabilities with textural based all-zero blocks and all-nonzero blocks through Lagrange Interpolation Polynomial (LIP) to derive thresholds to early skip unlikely depths and early terminate depth selection. Second, to early skip Intra mode prediction, we combine mode probabilities with Jarque-Bera test through LIP to test the residual coefficients of Inter-layer reference (ILR) mode. Third, we adopt the difference of Hadamard Costs (HCs) of horizontal, vertical and diagonal directional modes to predict candidate directional modes (DMs), and then exploit both the percentages of gradient amplitudes and HCs for DM early termination. Experimental results demonstrate that the proposed algorithm can achieve a speed up gain of more than 61% with 0.03% decrease in Bjøntegaard Delta Bit Rate on average. [ABSTRACT FROM AUTHOR]

This paper studies the joint estimation of channel fading and user activity for the uplink of a grant-free massive machine-type communication system. Comparing with previous studies, we consider more practical aspects of the system, including non-i.i.d. signature matrices, low-resolution quantization, and random users activated by an unknown sparse rate. A new estimation algorithm, termed hybrid decentralized generalized expectation consistent (HyDeGEC), is then derived based on a hybrid network that applies scalar message passing for the prior inference and vector message passing for the likelihood inference. This new algorithm outperforms many state-of-the-art techniques in terms of robustness (to non-i.i.d. signatures), complexity (in computation per iteration), and/or estimation accuracy (of the channel and the activity rate). The state evolution of the algorithm is also analyzed, which, as validated by simulations, can capture precisely the algorithm’s per-iteration behavior in MSE. Summing up, the algorithm we propose here is practically effective, computationally efficient, and theoretically analyzable. [ABSTRACT FROM AUTHOR]

Given a binary sequence with length $n$ , determining its minimal rational fraction representation (MRFR) has important applications in the design and cryptanalysis of stream ciphers. There are many studies of this problem since Klapper and Goresky first introduced an adaptive rational approximation algorithm with a time complexity of $O(n^{2}\log n\log \log n)$. In this paper, we revisit this problem by considering both adaptive and non-adaptive efficient algorithms. Compared with the state-of-art methods, we make several contributions to the problem of finding MRFR. Firstly, we find a general and precise recursive relationship between the minimal bases for two adjacent lattices generated by successive truncation sequences. This enables us to improve the currently fastest adaptive algorithm proposed by Li et al.. Secondly, by optimizing a time-consuming step of the well-known Lagrange reduction algorithm for 2-dimensional lattices, we obtain a non-adaptive, and yet practically faster MRFR-solving algorithm named global Euclidean algorithm. Thirdly, we identify theoretical flaws on some non-adaptive methods in the literature by counter-examples and correct the problems by designing modified Euclidean algorithm named partial Euclidean algorithm. Meanwhile, we further reduce the time complexity of existing algorithm from $O(n^{2})$ to $O(n\log ^{2}n\log \log n)$ by invoking the half-gcd algorithm. We also conduct a comprehensive experimental comparative analysis on the above algorithms to validate our theoretical analysis. [ABSTRACT FROM AUTHOR]

The Binary Iterative Hard Thresholding (BIHT) algorithm is a popular reconstruction method for one-bit compressed sensing due to its simplicity and fast empirical convergence. Despite considerable research on this algorithm, a theoretical understanding of the corresponding approximation error and convergence rate still remains an open problem. This paper shows that the normalized version of BIHT (NBIHT) achieves an approximation error rate optimal up to logarithmic factors. More precisely, using $m$ one-bit measurements of an $s$ -sparse vector $x$ , we prove that the approximation error of NBIHT is of order $O \left ({\frac{1 }{ m }}\right)$ up to logarithmic factors, which matches the information-theoretic lower bound $\Omega \left ({\frac{1 }{ m }}\right)$ proved by Jacques, Laska, Boufounos, and Baraniuk in 2013. To our knowledge, this is the first theoretical analysis of a BIHT-type algorithm that explains the optimal rate of error decay empirically observed in the literature. This also makes NBIHT the first provable computationally-efficient one-bit compressed sensing algorithm that breaks the inverse square-root error decay rate $O \left ({\frac{1 }{ m^{1/2} }}\right)\vphantom {{\left ({\frac{1 }{ m^{1/2} }}\right)}^{'}}$. [ABSTRACT FROM AUTHOR]

This paper presents the first network configuration verifier that provides fast all-pair reachability analysis of incremental configuration changes for network overlay data center networks (DCNs). Network overlay DCNs leverage distributed routing protocol on edge leaf switches to disseminate overlay routes and establish overlay tunnels. In addition, network overlay DCNs use access control lists, microsegmentation policy, policy-based routing and firewall policy to control east-west and north-south traffic. Although some incremental verification approaches have been proposed, they either do not support certain forwarding features of the network, or are not efficient. Our configuration verifier addresses these issues through the following components: 1) a port predicate based forwarding model that is general to support all features; 2) fine-grained association technique to index possibly affected reachable pairs by changed interfaces in the original network; and 3) required waypoint path computation that finds all reachable pairs related to changed interfaces in the new network. Based on these components, our verifier presents two incremental verification algorithms that are specially designed for different service update cases. Experiment results show that our incremental verification algorithms are accurate and fast. For all-pair reachability, our verifier performs change-impact analysis within 15s for networks with 200 leafs (4000 subnets and 16 million pairs), outperforming existing approaches by up to 10x. [ABSTRACT FROM AUTHOR]

Community detection is one of the fundamental tasks in graph mining, which aims to identify group assignment of nodes in a complex network. Recently, network embedding techniques have demonstrated their strong power in advancing the community detection task and achieve better performance than various traditional methods. Despite their empirical success, most of the existing algorithms directly leverage the observed coarse network structure for community detection. Therefore, they often lead to suboptimal performance as the observed connections fail to capture the essential tie strength information among nodes precisely and account for the impact of noisy links. In this paper, an optimal network structure for community detection is introduced to characterize the fine-grained tie strength information between connected nodes and alleviate the adverse effects of noisy links. To obtain an expressive node representation for community detection, we learn the optimal network structure and network embeddings in a joint framework, instead of using a two-stage approach to derive the node embeddings from the coarse network topology. In particular, we formulate the joint framework as an optimization problem and an alternating optimization algorithm is exploited to solve the proposed optimization problem. Additionally, theoretical analyses regarding the computational complexity and the convergence of the optimization algorithm are also provided. Extensive experiments on both synthetic and real-world networks demonstrate the effectiveness and superiority of the proposed framework. [ABSTRACT FROM AUTHOR]

The ability of an algorithm to extract power quality parameters on a low-end digital controller with constrained resources and computational capacity can promote comprehensive adoption of power quality control and monitoring infrastructure because of reduced cost and thus improve operational ability in a microgrid or distribution grid and support more in-depth integration of renewable energy. Since conventional harmonic extraction for single-phase grid mostly operate on Fourier transform, lock-in amplifier and their derivative algorithms, they demand large memory and computational power which are available with high-end application-specific processors, digital signal processors (DSPs) and field programmable gate arrays (FPGAs). In this paper, a computationally efficient harmonic extraction algorithm is proposed, which can be implemented on commercially available microcontrollers with ease, without compromising accuracy. A detailed theoretical analysis of the proposed method, along with various simulation and the experimental results are presented. Workarounds for minor implementation issues on digital controllers are discussed as well. [ABSTRACT FROM AUTHOR]

A fast and precise dynamic phasor estimation algorithm using an adaptive improved second order Levenberg–Marquadt algorithm under stressed and off-nominal frequency circumstances is proposed in this paper. The proposed algorithm ventures a faster quasi-second-order method and in addition, the learning rate is also made adaptive to speed up the convergence. Moreover, the projected estimator essentially filters harmonics, estimates transients in a signal during faults and effectually performs in complex modulated setting which is found commonly in a power system with distributed energy resources. Outcomes reveal that the estimation errors and the convergence time of the proposed approach is way below the minimum requirement of the IEEE C37.118.1 standard. Besides, due to its reduced complexity, the estimator has been successfully implemented on the field programmable gate array (FPGA) platform and has been verified on a practical microgrid scenario including photo voltaic systems. The performance during testing indicates that the proposed technique has potential ability to perform under stressed conditions conforming the accuracy and speed of response. [ABSTRACT FROM AUTHOR]

Temperature rising is an unavoidable effect on VLSI and has always been a critical issue in any system-on-chip – especially when targeting compute-intensive applications. This effect increases the delay in hardware accelerators, resulting in timing errors due to unsustainable clock frequency, whose impact must be carefully evaluated on design time to measure the performance degradation of the hardware accelerator. Further, a hardware operating at a higher temperature accelerates device aging, which incurs in more timing errors. This issue is usually addressed with the inclusion of timing guardbands that compensate for the deleterious effects of temperature, ensuring the hardware accelerator works within a reliable zone, i.e., without any timing errors caused by temperature effects at runtime. However, guardbands directly result in considerable performance and efficiency losses because the circuit will be clocked at a frequency lower than its full potential. Accelerators on edge devices often dismiss such guardbands to explore the full potential of the designed circuits, posing an enormous design challenge as this approach requires a careful evaluation of the impact of timing errors on the quality of the target applications. Many algorithms, such as in multimedia and machine learning applications, are capable of tolerating hardware errors. Yet, these algorithms have a dynamic behavior (i.e., closed-loop) where a timing error can be propagated, affecting subsequent steps. Measuring the degradation-induced errors in these applications is very challenging given that an accurate gate-level simulation to investigate degradation-induced timing errors needs to be coupled dynamically with a system-level simulator to unveil how induced errors in the underlying hardware ultimately impact the algorithm execution in the hardware accelerator. This is the first work to achieve this goal. State-of-the-art works have studied accelerators under timing-errors when removing (or narrowing) guardbands. However, their approach was suitable only for open-loop hardware accelerators which are entirely agnostic of complex interactions of the algorithms. Unlike prior work, this paper investigates temperature- and aging-induced timing-errors in the joint accelerator-algorithm interactions and their runtime impacts. Our framework investigates aging effects across the different layers starting from transistor physics all the way up to the algorithm layer. The hardware accelerator employed as a case study in this work is the sum of absolute differences (SAD), which is the most compute-intensive accelerator on commercial video encoder for mobile applications. Our results demonstrate the runtime behavior impacts of three advanced block-matching algorithms of the video encoder in a joint operation by a SAD accelerator under timing-errors induced by temperature and aging effects considering a 14nm FinFET technology. [ABSTRACT FROM AUTHOR]

In mobile edge computing, popular mobile applications, such as augmented reality, usually offload their tasks to resource-rich edge servers. The user experience can be considerably affected when many mobile users compete for the limited communication and computation resources. The key technical challenge in task offloading is to guarantee the Quality of Service (QoS) for such applications. Existing work on task offloading focus on deterministic QoS (delay) guarantee, which means that tasks have to complete before the given deadline with 100 percent. However, it is impractical to impose a deterministic QoS guarantee for tasks due to the high dynamics of the wireless environment when offloading to edge servers. In this paper, we focus on task offloading with statistical QoS guarantee (tasks are allowed to complete before a given deadline with a probability above the given threshold), which can further save more energy by loosing the QoS requirement. Specially, we first propose a statistical computation model and a statistical transmission model to quantify the correlation between the statistical QoS guarantee and task offloading strategy. Then, we formulate the task offloading problem as a mixed integer non-Linear programming problem with the statistical delay constraint. We transform the statistical delay constraint into the constraints on CPU cycle numbers and the delay exponent respectively. We propose an algorithm to provide the statistical QoS guarantee for tasks using convex optimization theory and Gibbs sampling method. Experiment results show that the proposed algorithm outperforms the three baselines. [ABSTRACT FROM AUTHOR]

Long-term evolution advanced (LTE-A) heterogeneous networks have been observed to offer reliable and service-differentiated communication, thereby enabling numerous mobile applications such as smart meters, remote sensors, and vehicular applications. This fact envisions the trend of Internet of Things (IoT) underlaying heterogeneous small cell networks. On this basis, this paper proposes an energy-efficient framework for such a scenario, where multitier heterogeneous small cell networks provide wireless connection and seamless coverage for mobile users and IoT nodes. In our proposed framework, an elastic cell-zooming algorithm based on the quality of service and traffic loads of end-users is performed by adaptively adjusting the transmission power of small cells in order to reduce energy consumption. In addition, aiming at the high energy efficiency of IoT underlaying small cell networks, a clustering-based IoT structure is used, where a SWIPT-CH selection algorithm is proposed to maximize the average residual energy of IoT nodes and to mitigate resource competition between IoT nodes and mobile users. Extensive simulations demonstrate that our proposed framework can significantly enhance the energy efficiency for IoT underlaying small cell networks with guaranteed outage probability. [ABSTRACT FROM AUTHOR]

Device-to-Device (D2D) communication with short communication distance is an efficient way to improve spectrum efficiency and mitigate interference. To realize the optimal resource configuration including wireless channel matching and power allocation, a distributed resource matching scheme is proposed based on deep reinforcement learning(DRL). The reward is defined as the difference of achieve rate of D2D users and the consumed power, which is limited by the Signal to Interference plus Noise Ratio (SINR) of the other cellular users on the current channel. The proposed algorithm maximizes the D2D throughput and energy efficiency in a distributed manner, without online coordination and message exchange between users. The considered resource allocation problem is formulated as a random non-cooperative game with multiple players (D2D pairs), where each player is a learning agent, whose task is to learn its best strategy based on locally observed information, multi-user communication resource matching algorithm is proposed based on a Double Deep Q-network (DDQN), where the total cellular throughput and user energy efficiency could converge to the Nash equilibrium (NE) under the mixed strategy. Simulation results show that the proposed algorithm can improve the communication rate and energy efficiency of each user by selecting the optimal strategy, and has better convergence performance compared with existing schemes. [ABSTRACT FROM AUTHOR]

Although we have seen a proliferation of algorithms for recommending visualizations, these algorithms are rarely compared with one another, making it difficult to ascertain which algorithm is best for a given visual analysis scenario. Though several formal frameworks have been proposed in response, we believe this issue persists because visualization recommendation algorithms are inadequately specified from an evaluation perspective. In this paper, we propose an evaluation-focused framework to contextualize and compare a broad range of visualization recommendation algorithms. We present the structure of our framework, where algorithms are specified using three components: (1) a graph representing the full space of possible visualization designs, (2) the method used to traverse the graph for potential candidates for recommendation, and (3) an oracle used to rank candidate designs. To demonstrate how our framework guides the formal comparison of algorithmic performance, we not only theoretically compare five existing representative recommendation algorithms, but also empirically compare four new algorithms generated based on our findings from the theoretical comparison. Our results show that these algorithms behave similarly in terms of user performance, highlighting the need for more rigorous formal comparisons of recommendation algorithms to further clarify their benefits in various analysis scenarios. [ABSTRACT FROM AUTHOR]

The use of a large-scale antenna array (LSAA) has become an important characteristic of multi-antenna communication systems to achieve beamforming gains such as in designing millimeter-wave (mmWave) systems to combat severe propagation losses. In such applications, each antenna element has to be driven by a radio frequency (RF) chain for the implementation of fully-digital beamformers, significantly increasing the hardware cost, complexity, and power consumption. Therefore, constant-modulus analog beamforming (CMAB) becomes a viable solution. In this paper, we consider the scaled analog beamforming (SAB) or constant-modulus analog beamforming (CMAB) architecture and design the system parameters by solving two variants of beampattern matching problem. In the first case, both the magnitude and phase of the beampattern are matched to the given desired beampattern whereas in the second case, only the magnitude of the beampattern is matched. Both the beampattern matching problems are cast as a variant of the constant-modulus least-squares (CLS) problem. We provide efficient algorithms based on the alternating majorization-minimization (AMM) framework that combines the alternating minimization and the MM frameworks and the conventional-cyclic coordinate descent (C-CCD) algorithms to solve the problem in each case. We also propose algorithms based on a new modified-CCD (M-CCD) based approach. For all the developed algorithms we prove convergence to a Karush-Kuhn-Tucker (KKT) point (or a stationary point). Numerical results demonstrate that the proposed algorithms converge faster than the state-of-the-art solutions. Among all the algorithms, the M-CCD-based algorithms have faster convergence when evaluated in terms of the number of iterations and the AMM-based algorithms offer lower complexity. [ABSTRACT FROM AUTHOR]

Weighted multi-view clustering (MVC) aims to combine the complementary information of multi-view data (such as image data with different types of features) in a weighted manner to obtain a consistent clustering result. However, when the cluster-wise weights across views are vastly different, most existing weighted MVC methods may fail to fully utilize the complementary information, because they are based on view-wise weight learning and can not learn the fine-grained cluster-wise weights. Additionally, extra parameters are needed for most of them to control the weight distribution sparsity or smoothness, which are hard to tune without prior knowledge. To address these issues, in this paper we propose a novel and effective Cluster-weighted mUlti-view infoRmation bottlEneck (CURE) clustering algorithm, which can automatically learn the cluster-wise weights to discover the discriminative clusters across multiple views and thus can enhance the clustering performance by properly exploiting the cluster-level complementary information. To learn the cluster-wise weights, we design a new weight learning scheme by exploring the relation between the mutual information of the joint distribution of a specific cluster (containing a group of data samples) and the weight of this cluster. Finally, a novel draw-and-merge method is presented to solve the optimization problem. Experimental results on various multi-view datasets show the superiority and effectiveness of our cluster-wise weighted CURE over several state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Despite major advancements in nonlinear programming (NLP) and convex relaxations, most system operators around the world still predominantly use some form of linear programming (LP) approximation of the AC power flow equations. This is largely due to LP technology's superior reliability and computational efficiency, especially in real-time market applications, security-constrained applications, and extensions involving integer variables, in addition to its ability to readily generate locational marginal prices (LMP) for market applications. In the aim of leveraging the advantages of LP while retaining the accuracy of NLP interior-point methods (IPMs), this paper proposes a sequential linear programming (SLP) approach consisting of a sequence of carefully constructed supporting hyperplanes and halfspaces. The algorithm is numerically demonstrated to converge on 138 test cases with up the 3375 buses to feasible high-quality solutions (i) without AC feasibility restoration (i.e., using LP solvers exclusively), (ii) in computation times generally within the same order of magnitude as those from a state-of-the-art NLP solver, and (iii) with robustness against the choice of starting point. In particular, the (relative) optimality gaps and the mean constraint violations are on average around $10^{-3}$ % and $10^{-7}$ , respectively, under a single parameter setting for all the 138 test cases. To the best of our knowledge, the proposed SLP approach is the first to use LP exclusively to reach feasible and high-quality solutions to the nonconvex AC OPF in a reliable way, which paves the way for system and market operators to keep using their LP solvers but now with the ability to accurately capture transmission losses, price reactive power (Q-LMP), and obtain more accurate LMP. [ABSTRACT FROM AUTHOR]

Smart textiles provide an opportunity to simultaneously record various electrophysiological signals, e.g., ECG, from the human body in a non-invasive and continuous manner. Accurate processing of ECG signals recorded using textile sensors is challenging due to the very low signal-to-noise ratio (SNR). Signal processing algorithms that can extract ECG signals out of textile-based electrode recordings, despite low SNR are needed. Presently, there are no textile ECG datasets available to develop, test and validate these algorithms. In this paper we attempted to model textile ECG signals by adding the textile sensor noise to open access ECG signals. We employed the linear predictive coding method to model different features of this noise. By approximating the linear predictive coding residual signals using Kernel Density Estimation, an artificial textile ECG noise signal was generated by filtering the residual signal with the linear predictive coding coefficients. The synthetic textile sensor noise was added to the MIT-BIH Arrhythmia Database (MITDB), thus creating Textile-like ECG dataset consisting of 108 trials (30 min each). Furthermore, a Python code for generating textile-like ECG signals with variable SNR was also made available online. Finally, to provide a benchmark for the performance of R-peak detection algorithms on textile ECG, the five common R-peak detection algorithms: Pan & Tompkins, improved Pan & Tompkins (in Biosppy), Hamilton, Engelse, and Khamis, were tested on textile-like MITDB. This work provides an approach to generating noisy textile ECG signals, and facilitating the development, testing, and evaluation of signal processing algorithms for textile ECGs. [ABSTRACT FROM AUTHOR]

In this paper, we describe a new algorithm to build a few sparse principal components from a given data matrix. Our approach does not explicitly create the covariance matrix of the data and can be viewed as an extension of the Kogbetliantz algorithm to build an approximate singular value decomposition for a few principal components. We show the performance of the proposed algorithm to recover sparse principal components on various datasets from the literature and perform dimensionality reduction for classification applications. [ABSTRACT FROM AUTHOR]

Benchmarking various metaheuristics and their new enhancements, strategies, and adaptation mechanisms has become standard in computational intelligence research. Recently, many challenges and issues regarding fair comparisons and recommendations toward good practices for benchmarking of metaheuristic algorithms, have been identified. This article is aimed at an important issues in metaheuristics design and benchmarking, which are boundary strategies or boundary control methods (BCMs). This work aims to investigate whether the choice of a BCM could significantly influence the performance of competitive algorithms. The experiments encompass the top three performing algorithms from IEEE CEC competitions 2017 and 2020 with six different BCMs. We provide extensive statistical analysis and rankings resulting in conclusions and recommendations for metaheuristics researchers and possibly also for the future direction of benchmark definitions. We conclude that the BCM should be considered another vital metaheuristics input variable for unambiguous reproducibility of results in benchmarking and for a better understanding of population dynamics, since the BCM setting could impact the optimization method performance. [ABSTRACT FROM AUTHOR]

Breakthroughs in unsupervised domain adaptation (uDA) can help in adapting models from a label-rich source domain to unlabeled target domains. Despite these advancements, there is a lack of research on how uDA algorithms, particularly those based on adversarial learning, can work in distributed settings. In real-world applications, target domains are often distributed across thousands of devices, and existing adversarial uDA algorithms – which are centralized in nature – cannot be applied in these settings. To solve this important problem, we introduce FRuDA: an end-to-end framework for distributed adversarial uDA. Through a careful analysis of the uDA literature, we identify the design goals for a distributed uDA system and propose two novel algorithms to increase adaptation accuracy and training efficiency of adversarial uDA in distributed settings. Our evaluation of FRuDA with five image and speech datasets show that it can boost target domain accuracy by up to 50% and improve the training efficiency of adversarial uDA by at least $11\times$ 11 × . [ABSTRACT FROM AUTHOR]

Medical image fusion technology integrates the contents of medical images of different modalities, thereby assisting users of medical images to better understand their meaning. However, the fusion of medical images corrupted by noise remains a challenge. To solve the existing problems in medical image fusion and denoising algorithms related to excessive blur, unclean denoising, gradient information loss, and color distortion, a novel medical image fusion and denoising algorithm is proposed. First, a new image layer decomposition model based on hybrid variation-sparse representation and weighted Schatten p-norm is proposed. The alternating direction method of multipliers is used to update the structure, detail layer dictionary, and detail layer coefficient map of the input image while denoising. Subsequently, appropriate fusion rules are employed for the structure layers and detail layer coefficient maps. Finally, the fused image is restored using the fused structure layer, detail layer dictionary, and detail layer coefficient maps. A large number of experiments confirm the superiority of the proposed algorithm over other algorithms. The proposed medical image fusion and denoising algorithm can effectively remove noise while retaining the gradient information without color distortion. [ABSTRACT FROM AUTHOR]

This paper presents a new single-source three-phase seven-level inverter with an inherent three-time voltage boosting capability for medium-voltage applications. The proposed topology is comprised of series connection of two switched-capacitor (SC) networks with an added half-bridge module per phase. Each of such integrated SC networks requires a single capacitor associated with three active power switches. The three-time voltage boosting feature of the proposed topology can reduce the dc-link voltage requirements by 50% in comparison to the traditional neutral point clamped (NPC), flying capacitors, active NPC (ANPC), hybrid clamped ANPC, and cascaded H-bridge topologies, and 75% to advanced ANPC topologies. It can also reduce the number of required switches and capacitors as well as their voltage stresses compared to those state-of-the-art topologies reported in the literature. By integrating “n” number of added SC networks in the proposed seven-level basic topology, the number of output voltage levels can be extended to 2n+3 per phase. A finite control set model predictive control algorithm is also derived to control the converter in both the active and reactive power exchanges modes without distorting the generated grid current quality. The capacitor voltage balancing is inherent in the proposed topology, and thus, there is no need for any additional voltage balancing circuit, which further reduces the control complexity. The performance of the proposed topology and its control algorithm are validated by several measurement results. [ABSTRACT FROM AUTHOR]

This paper proposes a direct speed and flux control system for Dual Stator Winding Induction Machines (DSWIMs) based on Super Twisting Sliding Mode Control (STSMC). The proposed nonlinear controller which has finite time convergence of error to zero, is designed such that the Lyapunov stability condition is satisfied. Furthermore, a novel torque-sharing algorithm is introduced for DSWIMs. This algorithm enables them to operate in a wide speed region, including zero speed, such that the required electromagnetic torque is supplied by two winding sets based on their power ratings. In addition, a Sliding Mode Control (SMC) based full order observer is proposed for DSWIMs. This observer, which is able to estimate the winding fluxes, flux angles and rotor speed with high-accuracy, guarantees the optimal flux condition. The functionality of the proposed sensor-less DSWIM drive scheme is evaluated through some experimental tests performed on a 3.3 kW DSP-based DSWIM drive system. The experimental results confirm the effectiveness of the proposed control method, torque sharing algorithm and the full order observer in various speed regions. [ABSTRACT FROM AUTHOR]

Deep learning methods have achieved attractive performance in dynamic MR cine imaging. However, most of these methods are driven only by the sparse prior of MR images, while the important low-rank (LR) prior of dynamic MR cine images is not explored, which may limit further improvements in dynamic MR reconstruction. In this paper, a learned singular value thresholding (Learned-SVT) operator is proposed to explore low-rank priors in dynamic MR imaging to obtain improved reconstruction results. In particular, we put forward a model-based unrolling sparse and low-rank network for dynamic MR imaging, dubbed as SLR-Net. SLR-Net is defined over a deep network flow graph, which is unrolled from the iterative procedures in the iterative shrinkage-thresholding algorithm (ISTA) for optimizing a sparse and LR-based dynamic MRI model. Experimental results on a single-coil scenario show that the proposed SLR-Net can further improve the state-of-the-art compressed sensing (CS) methods and sparsity-driven deep learning-based methods with strong robustness to different undersampling patterns, both qualitatively and quantitatively. Besides, SLR-Net has been extended to a multi-coil scenario, and achieved excellent reconstruction results compared with a sparsity-driven multi-coil deep learning-based method under a high acceleration. Prospective reconstruction results on an open real-time dataset further demonstrate the capability and flexibility of the proposed method on real-time scenarios. [ABSTRACT FROM AUTHOR]

Developmental dysplasia of the hip (DDH) is a common and serious disease in infants. Hip landmark detection plays a critical role in diagnosing the development of neonatal hip in the ultrasound image. However, the local confusion and the regional weakening make this task challenging. To solve these challenges, we explore the stable hip structure and the distinguishable local features to provide dependencies for hip landmark detection. In this paper, we propose a novel architecture named Dependency Mining ResNet (DM-ResNet), which investigates end-to-end dependency mining for more accurate and much faster hip landmark detection. First of all, we convert the landmark detection to the heatmap estimation by ResNet to build a strong baseline architecture for fast and accurate detection. Secondly, a dependency mining module is explored to mine the dependencies and leverage both the local and global information to decline the local confusion and strengthen the weakening region. Thirdly, we propose a simple but effective local voting algorithm (LVA) that seeks trade-off between long-range and short-range dependencies in the hip ultrasound image. Besides, a dataset with 2000 annotated hip ultrasound images is constructed in our work. It is the first public hip ultrasound dataset for open research. Experimental results show that our method achieves excellent precision in hip landmark detection (average point error of 0.719mm and successful detection rate within 1mm of 79.9%). [ABSTRACT FROM AUTHOR]

In mobile crowdsensing, it is a challenge to assign tasks to appropriate smartphones. Existing task allocation mechanisms mainly aim at optimizing the global system performance, while ignoring the personal preferences of individual crowdsensing tasks and smartphone users. Nevertheless, in an open crowdsensing system, a task assignment is prone to be unstable if smartphone users or tasks have incentives to deviate from the global assignment, and seek for alternative choices to improve their own utilities. Besides that, during task competition, the rational smartphone users might choose to adjust their payments after the first few failures, which however, brings new challenges in achieving the stability. To address these issues, this paper constructs a distributed many-to-many matching model to capture the interaction between crowdsensing tasks and smartphone users, taking into account the budget constraints of tasks. Then, we design a stable matching algorithm to allocate the tasks to the users, and determine their payments. We prove that the proposed algorithm achieves several desirable properties including individual rationality, stability, and convergency. It is also proved that the proposed scheme achieves at least half of the optimal system efficiency when each smartphone provides homogeneous service quality. Finally, simulation results confirm the effectiveness of the proposed scheme. [ABSTRACT FROM AUTHOR]

This paper presents a method for estimating the time of arrival (ToA) of long term evolution (LTE) signals received on multiple separate transmission bands by the same base station (BS) mast. By exploiting the overall bandwidth occupied by the different signals and the correlation between the corresponding channel impulse responses, a higher precision is achieved with respect to the usually adopted single-band approach whenever the time-correlation among the bands is sufficiently high. The ToA estimation is carried out by generalizing the space-alternating generalized expectation-maximization (SAGE) algorithm to the multi-band context, proving that the availability of multiple bands provides a reduced standard deviation for the estimated ToA, with a limited increase of the computational cost. The main analyzed issue consists in the management of the asynchrony between transmitters belonging to distinct cellular operators, which is addressed by developing a suitable method to combine the contributions provided by the different bands. The method is validated by simulations in dual- and tri-band scenarios, and is further applied to real dual-band signals measured through a portable setup and experimentally acquired from an LTE BS mast covering multiple cells. [ABSTRACT FROM AUTHOR]

Multipath TCP (MPTCP) is a promising solution that can provide high end-to-end throughput in fifth generation (5G) mobile networks. Many next-generation applications will require high throughput and low latency simultaneously, but the current MPTCP congestion control algorithms cannot reliably satisfy this requirement. In this paper, a novel MPTCP congestion control scheme named delay-equalized FAST (DEFT) is proposed to achieve high throughput and low end-to-end (E2E) delay in 5G networks. First, in order to achieve high throughput, DEFT includes a novel window control algorithm that shows fast responsiveness when the state of the millimeter-wave (mmWave) link changes from line-of-sight (LOS) to non-LOS (NLOS) and vice versa. Second, in order to achieve low E2E delay, DEFT includes a delay-equalizing algorithm which minimizes additional reordering delay in the receive buffer. The performance of DEFT was evaluated based on ns-3 simulation and was compared with wVegas, Balia, and delay-adapted LIA. Simulation results show that DEFT can provide a significant goodput gain and application-level E2E delay reduction for the range of interest. [ABSTRACT FROM AUTHOR]

This paper investigates the sub-channels and power allocation issue in the multi-carrier NOMA communication system. To maximize the sum rate of the system, we design a fast dynamic resource allocation (FDRA) algorithm. The algorithm can quickly identify the interference nodes with poor channel conditions, and reduces the search complexity of the algorithm. By jointly optimizing sub-carrier and power resource allocation, the proposed scheme can take full advantage of the channel capacity, and maximize the system performance while ensuring the quality of service (QoS) of each user. Simulation results show that when compared with the joint resource allocation (JRA) algorithm and the genetic algorithm (GA), the FDRA algorithm can achieve the best performance on the complexity and the sum rate of the system. Thus, the proposed algorithm can provide a fast and efficient resource allocation scheme for the downlink multi-carrier NOMA systems. [ABSTRACT FROM AUTHOR]

In this paper, we propose three new compressive sensing-based algorithms for channel estimation in millimeter wave hybrid MIMO systems over doubly (time and frequency) selective channels. Utilizing the basis expansion model (BEM) for effectively representing doubly selective channels, we first propose a BEM-based block orthogonal matching pursuit (BBOMP) algorithm, which can work with any training sequence structure. Next, we present the second algorithm to reduce the complexity of the BBOMP method by employing a special training sequence which results in a computationally efficient block sparse sensing matrix. Finally, in order to further decrease the computational complexity, we propose the third algorithm, where the channel estimation is split into two separate steps of tap detection and gain estimation. The proposed algorithms exploit the entire available training sequence to estimate all channel parameters, and can capture channel variations across the entire training frames without requiring a feedback channel. The Cramer-Rao lower bound and the computational complexity of the proposed algorithms are also addressed. Intensive computer simulations are conducted to evaluate the accuracy of the proposed approaches, showing that they can significantly improve the mean squared error performance compared with the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Federated learning (FL) as a promising edge-learning framework can effectively address the latency and privacy issues by featuring distributed learning at the devices and model aggregation in the central server. In order to enable efficient wireless data aggregation, over-the-air computation (AirComp) has recently attracted great attention. However, fading of wireless channels can produce aggregate distortions in an AirComp-based FL scheme. In this paper, we propose a modified federated averaging (FedAvg) algorithm by introducing the local learning rates and present the convergence analysis. To combat the distortion, the local learning rate is optimized to adapt the fading channel, which is termed as dynamic learning rate (DLR). We begin our discussion by considering multiple-input-single-output (MISO) scenario, since the underlying optimization problem is convex and has a closed-form solution. Our studies are extended to a more general multiple-input-multiple-output (MIMO) case and an iterative method is derived. We also present the asymptotic analysis and give a near-optimal and closed-form receive beamforming solution when the number of antennas approaches infinity. Extensive simulation results demonstrate the effectiveness of the proposed DLR scheme in reducing the aggregate distortion and guaranteeing the testing accuracy on the MNIST and CIFAR10 datasets. In addition, the asymptotic analysis and the close-form solution are verified through numerical simulations. [ABSTRACT FROM AUTHOR]

The proliferation of Internet-of-Things (IoT) devices and cloud-computing applications over siloed data centers is motivating renewed interest in the collaborative training of a shared model by multiple individual clients via federated learning (FL). To improve the communication efficiency of FL implementations in wireless systems, recent works have proposed compression and dimension reduction mechanisms, along with digital and analog transmission schemes that account for channel noise, fading, and interference. The prior art has mainly focused on star topologies consisting of distributed clients and a central server. In contrast, this paper studies FL over wireless device-to-device (D2D) networks by providing theoretical insights into the performance of digital and analog implementations of decentralized stochastic gradient descent (DSGD). First, we introduce generic digital and analog wireless implementations of communication-efficient DSGD algorithms, leveraging random linear coding (RLC) for compression and over-the-air computation (AirComp) for simultaneous analog transmissions. Next, under the assumptions of convexity and connectivity, we provide convergence bounds for both implementations. The results demonstrate the dependence of the optimality gap on the connectivity and on the signal-to-noise ratio (SNR) levels in the network. The analysis is corroborated by experiments on an image-classification task. [ABSTRACT FROM AUTHOR]

Federated learning (FL) involves training machine learning models over distributed edge nodes (i.e., workers) while facing three critical challenges, edge heterogeneity, Non-IID data and communication resource constraint. In the synchronous FL, the parameter server has to wait for the slowest workers, leading to significant waiting time due to edge heterogeneity. Though asynchronous FL can well tackle the edge heterogeneity, it requires frequent model transfers, resulting in massive communication resource consumption. Moreover, the different relative frequency of workers participating in asynchronous updating may seriously hurt training accuracy, especially on Non-IID data. In this paper, we propose a semi-asynchronous federated learning mechanism (FedSA), where the parameter server aggregates a certain number of local models by their arrival order in each round. We theoretically analyze the quantitative relationship between the convergence bound of FedSA and different factors, e.g., the number of participating workers in each round, the degree of data Non-IID and edge heterogeneity. Based on the convergence bound, we present an efficient algorithm to determine the number of participating workers to minimize the training completion time. To further improve the training accuracy on Non-IID data, FedSA deploys adaptive learning rates for workers by their relative participation frequency. We extend our proposed mechanism to the dynamic and multiple learning tasks scenarios. Experimental results on the testbed show that our proposed mechanism and algorithms address the three challenges more effectively than the state-of-the-art solutions. [ABSTRACT FROM AUTHOR]

Federated learning has emerged as a popular technique for distributing machine learning (ML) model training across the wireless edge. In this paper, we propose two timescale hybrid federated learning (TT-HF), a semi-decentralized learning architecture that combines the conventional device-to-server communication paradigm for federated learning with device-to-device (D2D) communications for model training. In TT-HF, during each global aggregation interval, devices (i) perform multiple stochastic gradient descent iterations on their individual datasets, and (ii) aperiodically engage in consensus procedure of their model parameters through cooperative, distributed D2D communications within local clusters. With a new general definition of gradient diversity, we formally study the convergence behavior of TT-HF, resulting in new convergence bounds for distributed ML. We leverage our convergence bounds to develop an adaptive control algorithm that tunes the step size, D2D communication rounds, and global aggregation period of TT-HF over time to target a sublinear convergence rate of $\mathcal {O}(1/t)$ while minimizing network resource utilization. Our subsequent experiments demonstrate that TT-HF significantly outperforms the current art in federated learning in terms of model accuracy and/or network energy consumption in different scenarios where local device datasets exhibit statistical heterogeneity. Finally, our numerical evaluations demonstrate robustness against outages caused by fading channels, as well favorable performance with non-convex loss functions. [ABSTRACT FROM AUTHOR]

In network optimization problems, from traffic engineering to network monitoring, the routing model is typically considered as something given and frozen. This paper is motivated by the fundamental question how the ability to change and optimize the routing model itself influences the efficiency at which communication networks can be operated. To this end, we identify two main dimensions of a routing model: consistency (of a single route) and coherence (of sets of routes). We present analytical results on the impact of the routing model on the achievable route diversity as well as on the runtime of solving optimization problems underlying different case studies. We also uncover that it can sometimes be beneficial to artificially restrict the routing model, to significantly reduce the computational complexity without negatively affecting the route diversity much. [ABSTRACT FROM AUTHOR]