Hematoxylin and Eosin (H&E) staining is a widely used sample preparation procedure for enhancing the saturation of tissue sections and the contrast between nuclei and cytoplasm in histology images for medical diagnostics. However, various factors, such as the differences in the reagents used, result in high variability in the colors of the stains actually recorded. This variability poses a challenge in achieving generalization for machine-learning based computer-aided diagnostic tools. To desensitize the learned models to stain variations, we propose the Generative Stain Augmentation Network (G-SAN) -- a GAN-based framework that augments a collection of cell images with simulated yet realistic stain variations. At its core, G-SAN uses a novel and highly computationally efficient Laplacian Pyramid (LP) based generator architecture, that is capable of disentangling stain from cell morphology. Through the task of patch classification and nucleus segmentation, we show that using G-SAN-augmented training data provides on average 15.7% improvement in F1 score and 7.3% improvement in panoptic quality, respectively. Our code is available at https://github.com/lifangda01/GSAN-Demo.
In this paper, we investigated the downlink transmission problem of a cognitive radio network (CRN) equipped with a novel transmissive reconfigurable intelligent surface (TRIS) transmitter. In order to achieve low power consumption and high-rate multi-streams communication, time-modulated arrays (TMA) is implemented and users access the network using rate splitting multiple access (RSMA). With such a network framework, a multi-objective optimization problem with joint design of the precoding matrix and the common stream rate is constructed to achieve higher energy efficiency (EE) and spectral efficiency (SE). Since the objective function is a non-convex fractional function, we proposed a joint optimization algorithm based on difference-of-convex (DC) programming and successive convex approximation (SCA). Numerical results show that under this framework the proposed algorithm can considerably improve and balance the EE and SE.
Deploying active reflecting elements at the intelligent reflecting surface (IRS) increases signal amplification capability but incurs higher power consumption. Therefore, it remains a challenging and open problem to determine the optimal number of active/passive elements for maximizing energy efficiency (EE). To answer this question, we consider a hybrid active-passive IRS (H-IRS) assisted wireless communication system, where the H-IRS consists of both active and passive reflecting elements.Specifically, we study the optimization of the number of active/passive elements at the H-IRS to maximize EE. To this end, we first derive the closed-form expression for a near-optimal solution under the line-of-sight (LoS) channel case and obtain its optimal solution under the Rayleigh fading channel case. Then, an efficient algorithm is employed to obtain a high-quality sub-optimal solution for the EE maximization under the general Rician channel case. Simulation results demonstrate the effectiveness of the H-IRS for maximizing EE under different Rician factors and IRS locations.
The cellular network coexisting with device-to-device (D2D) communications has been studied extensively. Reconfigurable intelligent surface (RIS) and non-orthogonal multiple access (NOMA) are promising technologies for the evolution of 5G, 6G and beyond. Besides, sparse code multiple access (SCMA) is considered suitable for next-generation wireless network in code-domain NOMA. In this paper, we consider the RIS-aided uplink SCMA cellular network simultaneously with D2D users. We formulate the optimization problem which aims to maximize the cellular sum-rate by jointly designing D2D users resource block (RB) association, the transmitted power for both cellular users and D2D users, and the phase shifts at the RIS. The power limitation and users communication requirements are considered. The problem is non-convex, and it is challenging to solve it directly. To handle this optimization problem, we propose an efficient iterative algorithm based on block coordinate descent (BCD) method. The original problem is decoupled into three subproblems to solve separately. Simulation results demonstrate that the proposed scheme can significantly improve the sum-rate performance over various schemes.
Network energy efficiency is a main pillar in the design and operation of wireless communication systems. In this paper, we investigate a dense radio access network (dense-RAN) capable of radiated power management at the base station (BS). Aiming to improve the long-term network energy efficiency, an optimization problem is formulated by collaboratively managing multi-BSs radiated power levels with constraints on the users traffic volume and achievable rate. Considering stochastic traffic arrivals at the users and time-varying network interference, we first formulate the problem as a Markov decision process (MDP) and then develop a novel deep reinforcement learning (DRL) framework based on the cloud-RAN operation scheme. To tackle the trade-off between complexity and performance, the overall optimization of multi-BSs energy efficiency with the multiplicative complexity constraint is modeled to achieve nearoptimal performance by using a deep Q-network (DQN). In DQN,each BS first maximizes its individual energy efficiency, and then cooperates with other BSs to maximize the overall multiBSs energy efficiency. Simulation results demonstrate that the proposed algorithm can converge faster and enjoy a network energy efficiency improvement by 5% and 10% compared with the benchmarks of the Q-learning and sleep schemes, respectively.
Multi-tier computing can enhance the task computation by multi-tier computing nodes. In this paper, we propose a cell-free massive multiple-input multiple-output (MIMO) aided computing system by deploying multi-tier computing nodes to improve the computation performance. At first, we investigate the computational latency and the total energy consumption for task computation, regarded as total cost. Then, we formulate a total cost minimization problem to design the bandwidth allocation and task allocation, while considering realistic heterogenous delay requirements of the computational tasks. Due to the binary task allocation variable, the formulated optimization problem is nonconvex. Therefore, we solve the bandwidth allocation and task allocation problem by decoupling the original optimization problem into bandwidth allocation and task allocation subproblems. As the bandwidth allocation problem is a convex optimization problem, we first determine the bandwidth allocation for given task allocation strategy, followed by conceiving the traditional convex optimization strategy to obtain the bandwidth allocation solution. Based on the asymptotic property of received signal-to-interference-plus-noise ratio (SINR) under the cell-free massive MIMO setting and bandwidth allocation solution, we formulate a dual problem to solve the task allocation subproblem by relaxing the binary constraint with Lagrange partial relaxation for heterogenous task delay requirements. At last, simulation results are provided to demonstrate that our proposed task offloading scheme performs better than the benchmark schemes, where the minimum-cost optimal offloading strategy for heterogeneous delay requirements of the computational tasks may be controlled by the asymptotic property of the received SINR in our proposed cell-free massive MIMO-aided multi-tier computing systems.
Federated learning (FL) enables distributed clients to collaboratively train a machine learning model without sharing raw data with each other. However, it suffers the leakage of private information from uploading models. In addition, as the model size grows, the training latency increases due to limited transmission bandwidth and the model performance degrades while using differential privacy (DP) protection. In this paper, we propose a gradient sparsification empowered FL framework over wireless channels, in order to improve training efficiency without sacrificing convergence performance. Specifically, we first design a random sparsification algorithm to retain a fraction of the gradient elements in each client's local training, thereby mitigating the performance degradation induced by DP and and reducing the number of transmission parameters over wireless channels. Then, we analyze the convergence bound of the proposed algorithm, by modeling a non-convex FL problem. Next, we formulate a time-sequential stochastic optimization problem for minimizing the developed convergence bound, under the constraints of transmit power, the average transmitting delay, as well as the client's DP requirement. Utilizing the Lyapunov drift-plus-penalty framework, we develop an analytical solution to the optimization problem. Extensive experiments have been implemented on three real life datasets to demonstrate the effectiveness of our proposed algorithm. We show that our proposed algorithms can fully exploit the interworking between communication and computation to outperform the baselines, i.e., random scheduling, round robin and delay-minimization algorithms.
Hierarchical Federated Learning (HFL) is a distributed machine learning paradigm tailored for multi-tiered computation architectures, which supports massive access of devices' models simultaneously. To enable efficient HFL, it is crucial to design suitable incentive mechanisms to ensure that devices actively participate in local training. However, there are few studies on incentive mechanism design for HFL. In this paper, we design two-level incentive mechanisms for the HFL with a two-tiered computing structure to encourage the participation of entities in each tier in the HFL training. In the lower-level game, we propose a coalition formation game to joint optimize the edge association and bandwidth allocation problem, and obtain efficient coalition partitions by the proposed preference rule, which can be proven to be stable by exact potential game. In the upper-level game, we design the Stackelberg game algorithm, which not only determines the optimal number of edge aggregations for edge servers to maximize their utility, but also optimize the unit reward provided for the edge aggregation performance to ensure the interests of cloud servers. Furthermore, numerical results indicate that the proposed algorithms can achieve better performance than the benchmark schemes.
Massive access has been challenging for the fifth generation (5G) and beyond since the abundance of devices causes communication overload to skyrocket. In an uplink massive access scenario, device traffic is sporadic in any given coherence time. Thus, channels across the antennas of each device exhibit correlation, which can be characterized by the row sparse channel matrix structure. In this work, we develop a bilinear generalized approximate message passing (BiGAMP) algorithm based on the row sparse channel matrix structure. This algorithm can jointly detect device activities, estimate channels, and detect signals in massive multiple-input multiple-output (MIMO) systems by alternating updates between channel matrices and signal matrices. The signal observation provides additional information for performance improvement compared to the existing algorithms. We further analyze state evolution (SE) to measure the performance of the proposed algorithm and characterize the convergence condition for SE. Moreover, we perform theoretical analysis on the error probability of device activity detection, the mean square error of channel estimation, and the symbol error rate of signal detection. The numerical results demonstrate the superiority of the proposed algorithm over the state-of-the-art methods in DADCE-SD, and the numerical results are relatively close to the theoretical analysis results.
In this letter, we investigate a novel quadrature spatial scattering modulation (QSSM) transmission technique based on millimeter wave (mmWave) systems, in which the transmitter generates two orthogonal beams targeting candidate scatterers in the channel to carry the real and imaginary parts of the conventional signal, respectively. Meanwhile, the maximum likelihood (ML) detector is adopted at the receiver to recover the received beams and signals. Based on the ML detector, we derive the closed-form average bit error probability (ABEP) expression of the QSSM scheme. Furthermore, we evaluate the asymptotic ABEP expression of the proposed scheme. Monte Carlo simulations verify the exactness and tightness of the derivation results. It is shown that the ABEP performance of QSSM is better than that of traditional spatial scattering modulation.