Quantum Bayesian computation

Quantum Bayesian computation is an emerging field that levers the computational gains available from quantum computers. They promise to provide an exponential speed-up in Bayesian computation. Our article adds to the literature in three ways. First, we describe how quantum von Neumann measurement provides quantum versions of popular machine learning algorithms such as Markov chain Monte Carlo and deep learning that are fundamental to Bayesian learning. Second, we describe quantum data encoding methods needed to implement quantum machine learning including the counterparts to traditional feature extraction and kernel embeddings methods. Third, we show how quantum algorithms naturally calculate Bayesian quantities of interest such as posterior distributions and marginal likelihoods. Our goal then is to show how quantum algorithms solve statistical machine learning problems. On the theoretical side, we provide quantum versions of high dimensional regression, Gaussian processes and stochastic gradient descent. On the empirical side, we apply a quantum FFT algorithm to Chicago house price data. Finally, we conclude with directions for future research.     

Convergence Rate of Solutions to a Hyperbolic Equation with $p(x)$-Laplacian Operator and Non-Autonomous Damping

This paper concerns the convergence rate of solutions to a hyperbolic equation with $p(x)$-Laplacian operator and non-autonomous damping. We apply the Faedo-Galerkin method to establish the existence of global solutions, and then use some ideas from the study of second order dynamical system to get the strong convergence relationship between the global solutions and the steady solution. Some differential inequality arguments and a new Lyapunov functional are proved to show the explicit convergence rate of the trajectories.     

Terminal constrained robust hybrid iterative learning model predictive control for complex time-delayed batch processes

This work mainly addresses terminal constrained robust hybrid iterative learning model predictive control against time delay and uncertainties in a class of complex batch processes with input and output constraints. In this work, an equivalently novel extended two-dimensional switched system is first constructed to represent the process model by introducing state difference, output error and new relaxation variable information. Then, a hybrid predictive updating controller is proposed and an optimal performance index function including terminal constraints is designed. Under the condition that the switching signal meets certain conditions, the solvable problem of model predictive control is realized by Lyapunov stability theory. Meanwhile, the design scheme of controller parameters is also given. In addition, the robust constraint set is adopted to overcome the disadvantage that the traditional asymptotic stability cannot converge to the origin when it involves disturbances, such that the system state converges to the constraint set and meets its expected value. Finally, the effectiveness of the proposed algorithm is verified by controlling the speed and pressure parameters of the injection molding process.     

Chiral-Quantum-Optics-Based Supervised Learning

Based on the excellent control of single photons realized by atom-photon-chiral couplings,a novel quantum-optics scheme for supervised learning is proposed. The single-photon rotating and phase-shift operations, which can be controlled by another single photon, are realized by proper atom-photon-chiral couplings. Then, an algorithm to perform the supervised learning tasks, composed by integrating the realized gates, and implemented by the tunable gate parameters, is realized.     

基于PCAU-Net的快速多通道磁共振成像方法

多通道磁共振成像方法采用多个接收线圈同时欠采样k空间以加快成像速度,并基于后处理算法重建图像,但在较高加速因子时,其图像重建质量仍然较差．本文提出了一种基于PCAU-Net的快速多通道磁共振成像方法,将单通道实数U型卷积神经网络拓展到多通道复数卷积神经网络,设计了一种结构不对称的U型网络结构,通过在解码部分减小网络规模以降低模型的复杂度．PCAU-Net网络在跳跃连接前增加了1×1卷积,以实现跨通道信息交互．输入和输出之间利用残差连接为误差的反向传播提供捷径．实验结果表明,使用规则和随机采样模板,在不同加速因子时,相比常规的GRAPPA重建算法和SPIRiT重建方法,本文提出的PCAU-Net方法可高质量重建出磁共振复数图像,并且相比于PCU-Net方法,PCAU-Net减少了模型参数、缩短了训练时间．     

Robustness quantification method for network intrusion detection models

Deep learning techniques have been successfully applied to network intrusion detection tasks, but as in the case of autonomous driving and face recognition, the reliability of the system itself has become a pressing issue. Robustness is a key attribute to determine whether a deep learning system is secure and reliable, and we also choose to explore the security of intrusion detection models from a new perspective of robustness quantification. In this paper, we focus on the intrusion detection model based on long and short-term memory, and use a fine-grained linear approximation method to derive a more accurate robustness bound on the nonlinear activation function with tighter linear constraints. We can use this bound to quantitatively measure the robustness of the detection model and determine whether the model is susceptible to the influence of adversarial samples. In our experiments, we test networks with various structures on the MNIST dataset, and the results show that our proposed method can effectively deduce the robustness bounds of output elements, and has good scalability and applicability.     

Active learning for OPM in FMF systems

Optical performance monitoring (OPM) is essential to guarantee the robust and reliable operation of few-mode fiber (FMF)-based transmission. The available OPM methods including the analytical models such as the enhanced Gaussian noise model provide high accuracy along with high computational complexity which makes them improper for real-time implementations. As an alternative approach, machine learning (ML)-based OPM removes this barrier at the cost of leveraging a large training dataset. However, generating a field or synthetic dataset for FMF-based transmission is very hard and time-consuming. As a specific ML deployment, active learning (AL) is designed to work with a small training dataset, therefore, in this paper, we employ AL for OPM in FMF-based transmission. Results indicate that the proposed AL-based OPM can properly estimate the generalized signal-to-noise ratio by using a very small training dataset and achieve the root mean squared error similar to that obtained by working on large training datasets.     

Adaptive multimode transmission in wireless sensor networks with energy harvesting

Limited energy has always been an important factor restricting the development of wireless sensor networks. The unbalanced energy consumption of nodes will accelerate the death of some nodes. To solve the above problems, an adaptive routing algorithm for energy collection sensor networks based on distributed energy saving clustering (DEEC) is proposed. In each hop of data transmission, the optimal mode is adaptively selected from four transmission modes: single-hop cooperative, multi-hop cooperative, single-hop non-cooperative and multi-hop non-cooperative, so as to reduce and balance the energy consumption of nodes. The performance of the proposed adaptive multi-mode transmission method and several benchmark schemes are evaluated and compared by computer simulation, where a few performance metrics such as the network lifetime and throughput are adopted. The results show that, the proposed method can effectively reduce the energy consumption of the network and prolong the network lifetime; it is superior to various benchmark schemes.     

Enhancing network lifespan in wireless sensor networks using deep learning based Graph Neural Network

Inadequate energy of sensors is one of the most significant challenges in the development of a reliable wireless sensor network (WSN) that can withstand the demands of growing WSN applications. Implementing a sleep-wake scheduling scheme while assigning data collection and sensing chores to a dominant group of awake sensors while all other nodes are in a sleep state seems to be a potential way for preserving the energy of these sensor nodes. When the starting energy of the nodes changes from one node to another, this issue becomes more difficult to solve. The notion of a dominant set-in graph has been used in a variety of situations. The search for the smallest dominant set in a big graph might be time-consuming. Specifically, we address two issues: first, identifying the smallest possible dominant set, and second, extending the network lifespan by saving the energy of the sensors. To overcome the first problem, we design and develop a deep learning-based Graph Neural Network (DL-GNN). The GNN training method and back-propagation approach were used to train a GNN consisting of three networks such as transition network, bias network, and output network, to determine the minimal dominant set in the created graph. As a second step, we proposed a hybrid fixed-variant search (HFVS) method that considers minimal dominant sets as input and improves overall network lifespan by swapping nodes of minimal dominating sets. We prepared simulated networks with various network configurations and modeled different WSNs as undirected graphs. To get better convergence, the different values of state vector dimensions of the input vectors are investigated. When the state vector dimension is 3 or 4, minimum dominant set is recognized with high accuracy. The paper also presents comparative analyses between the proposed HFVS algorithm and other existing algorithms for extending network lifespan and discusses the trade-offs that exist between them. Lifespan of wireless sensor network, which is based on the dominant set method, is greatly increased by the techniques we have proposed.     

Unsupervised LoS/NLoS identification in mmWave communication using two-stage machine learning framework

Identification of line-of-sight (LoS)/ non-LoS (NLoS) condition in millimeter wave (mmWave) communication is important for localization and unobstructed transmission between a base station (BS) and a user. A sudden obstruction in a link between a BS and a user can result in poorly received signal strength or termination of communication. Channel features obtained by the estimation of channel state information (CSI) of a user at the BS can be used for identifying LoS/NLoS condition. With the assumption of labeled CSI, existing machine learning (ML) methods have achieved satisfactory performance for LoS/NLoS identification. However, in a real communication environment, labeled CSI is not available. In this paper, we propose a two-stage unsupervised ML based LoS/NLoS identification framework to address the lack of labeled data. We conduct experiments for the outdoor scenario by generating data from the NYUSIM simulator. We compare the performance of our method with the supervised deep neural network (SDNN) in terms of accuracy and receiver characteristic curves. The proposed framework can achieve an accuracy of 87.4% and it outperforms SDNN. Further, we compare the performance of our method with other state-of-the-art LoS/NLoS identification schemes in terms of accuracy, recall, precision, and F1-score.