The decimation of high-frequency (HF) features during exhaustive low-dose computed tomography(LDCT) denoising introduces structural deformation. This paper addresses the aforementioned issue by introducing a GAN frame...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
The decimation of high-frequency (HF) features during exhaustive low-dose computed tomography(LDCT) denoising introduces structural deformation. This paper addresses the aforementioned issue by introducing a GAN framework that provides novel adversarial training via discriminators in the wavelet and spatial domains. The wavelet-domain discriminator forces the generator to gain knowledge of the HF features via HF wavelet details (LH, HL, HH) and minimizes structural distortion. The generator network uses a spatial-domain discriminator to preserve local and global pixel correlations without altering the low-frequency (LF) features. Furthermore, we develop a generator network using a novel stationary wavelet-based residual block (SWTRB), which adaptively integrates spatial and frequency-domain information. In addition, we propose a wavelet-domain objective function on HF components, further improving the diagnostic quality of CT images. The experimental results demonstrate that the proposed method outperforms several state-of-the-art techniques on publicly available datasets, including "2016 NIH-AAPM-Mayo Clinic LDCT " and "Low-dose CT image and projection."
Unsupervised multi-view outlier detection has garnered increasing attention in recent years, yet existing methods face persistent challenges. Many approaches rely predominantly on first-order neighborhood information,...
详细信息
ISBN:
(数字)9798350368741
ISBN:
(纸本)9798350368758
Unsupervised multi-view outlier detection has garnered increasing attention in recent years, yet existing methods face persistent challenges. Many approaches rely predominantly on first-order neighborhood information, overlooking the richer insights offered by higher-order structures, which can degrade detection accuracy. Additionally, some methods suffer from outlier domination in their objective functions, leading to suboptimal performance. Integrating information effectively across multiple views also remains a significant hurdle. To address these challenges, we propose a novel Multi-View Outlier Detection method based on Optimal Graph Filtering (MODGF). Our approach detects outliers using a high-order graph filtering mechanism, ensuring consistency between feature and neighborhood spaces by sharing filtering parameters. Furthermore, we incorporate the Corr-entropy Induced Metric (CIM) to refine the objective function and introduce an efficient scoring strategy for enhanced detection reliability. Extensive experimental results demonstrate that our method is both stable and efficient across scenarios. The code is available at https://***/criticcc/MODGF.
This article investigates the feasibility of using a dual-cantilever atomic force microscope for imaging the electrical properties of a sample below the surface. Principles from macro-scale electrical resistive tomogr...
详细信息
ISBN:
(数字)9798331533892
ISBN:
(纸本)9798331533908
This article investigates the feasibility of using a dual-cantilever atomic force microscope for imaging the electrical properties of a sample below the surface. Principles from macro-scale electrical resistive tomography are adapted to utilize measurements from a dual-probe atomic force microscope. A deep-learning method is employed to perform the inversion process and construct the tomography. Simulation results demonstrate that electrical resistive tomography is possible at the nanometre scale but improvements to the inversion algorithms are needed before moving to experimental applications.
The entanglement distribution problem over quantum networks has been widely studied, with the objective of maximizing network throughput, that is, the number of entanglements distributed for all user pairs. However, m...
详细信息
ISBN:
(数字)9798350368369
ISBN:
(纸本)9798350368376
The entanglement distribution problem over quantum networks has been widely studied, with the objective of maximizing network throughput, that is, the number of entanglements distributed for all user pairs. However, most of the existing works only focus on throughput maximization while neglecting fairness considerations. In this paper, we first characterize the fairness of an entanglement distribution scheme by introducing a fairness factor based on Element-Wise Inequalities, referred to as EWI-fairness. The EWI-fairness requires that the entanglement distribution rate of each user pair exceeds a certain threshold, ensuring the fair distribution. Second, we enforce fairness guarantees into two existing distribution methods, Temporal Multiplexing Distribution (TMD) and Flow Multiplexing Distribution (FMD). Our theoretical analysis reveals that FMD-based scheme outperforms TMD-based scheme. Therefore, we focus on optimizing FMD-based scheme. Third, we formulate the fair entanglement distribution problem as a linear programming problem, where fairness requirements serve as constraints, aiming to identify the optimal FMD-based scheme with the highest throughput. Simulation results demonstrate that the optimized FMD-based scheme achieves a higher throughput compared to existing schemes under identical fairness requirements.
Maximizing energy efficiency (EE) in Multiple-Input Single-Output (MISO) downlink networks employing Quadrature Rate-Splitting Multiple Access (Q-RSMA) is a challenging task due to the non-convex optimization problem ...
详细信息
ISBN:
(数字)9798331507022
ISBN:
(纸本)9798331507039
Maximizing energy efficiency (EE) in Multiple-Input Single-Output (MISO) downlink networks employing Quadrature Rate-Splitting Multiple Access (Q-RSMA) is a challenging task due to the non-convex optimization problem involving power allocations, beamforming vectors, and rate allocations under multiple constraints. In this paper, we propose a Deep Reinforcement Learning (DRL) framework based on the Deep Deterministic Policy Gradient (DDPG) algorithm to maximize EE. We handle the minimum rate constraints by formulating the rate allocation as a linear programming (LP) problem, which allows for a computationally efficient solution. The beamforming vector normalization is clarified to ensure the unit norm constraints are satisfied. Simulation results demonstrate the effectiveness of the proposed approach in achieving high EE while satisfying all system constraints.
Regenerative braking improves the energy efficiency of railway transportation by converting the kinetic energy into the electrical energy. In this paper, linear programming (LP) is applied to search for the train brak...
详细信息
Regenerative braking improves the energy efficiency of railway transportation by converting the kinetic energy into the electrical energy. In this paper, linear programming (LP) is applied to search for the train braking trajectory with the maximum Regenerative Braking Energy (RBE). LP takes the advantages of simplicity in modelling, efficiency in computation, flexibility in applications. Compared with the previously proposed model in [1], the proposed LP optimisation model takes into account the speed limit constraints during the braking operation. Four case studies have been performed with different speed limits and initial braking speeds. While the maximum allowed braking time takes a key role for the RBE recovery, a threshold exists when the impact of maximum allowed braking time starts to become negligible. It has been demonstrated in this paper that LP is a robust and effective method to locate the optimal braking trajectory with the maximum RBE. The results of the optimisation are of significant interest for urban transportation systems where the regenerative braking is frequently applied. Future work of this paper is to investigate the optimisation of RBE in a more complicated scenario where the gradients are present and the motoring operation of train is allowed.
This paper aims to study a new form of facility layout problem, in which the building has already been constructed and the specific room layout inside has been determined. Unlike the traditional facility layout proble...
详细信息
This paper aims to study a new form of facility layout problem, in which the building has already been constructed and the specific room layout inside has been determined. Unlike the traditional facility layout problem, what we take into account is how to assign a certain number of rooms to a given number of departments with the purpose of maximizing the utilization rate of the rooms. This is equivalent to minimizing the total difference value between the extra area of different departments after satisfying their required area, thus reducing the space waste. To solve this special combinatorial optimization problem, we develop a Mixed-Integer linear programming (MILP) model. The model is solved using commercial software CPLEX12.6. Computational results on several randomly generated instances demonstrate the effectiveness of the proposed approach.
With the proposal of dual-carbon policy, it is especially important to improve the economy and stability of microgrid while how to reduce the carbon emission of the system. To this end, this paper firstly constructs a...
详细信息
ISBN:
(数字)9798331521950
ISBN:
(纸本)9798331521967
With the proposal of dual-carbon policy, it is especially important to improve the economy and stability of microgrid while how to reduce the carbon emission of the system. To this end, this paper firstly constructs an electric-hydrogen hybrid energy storage system and proposes an electric-hydrogen hybrid storage stepwise control strategy. Finally, the system economy, energy utilization, load loss rate and carbon emissions are normalized to obtain the weighted integrated objective function under the minimum of each energy storage capacity. The results show that compared with the traditional electrochemical energy storage method, the electric-hydrogen hybrid storage significantly improves the stability of the system and reduces the carbon emission under the premise of close economy.
We develop a cooperative decode-and-forward strategy of distributed Source-Relay network coding for a three-node relay model, in which Relay and Source both send their own messages to Destination. First, we present a ...
详细信息
We develop a cooperative decode-and-forward strategy of distributed Source-Relay network coding for a three-node relay model, in which Relay and Source both send their own messages to Destination. First, we present a cooperative communication protocol to achieve decode-and-forward capacity by leveraging transmit rates between Source and Relay and designing distributed Source-Relay network coding accordingly. After-wards, multi-dimension Low-density parity-check (LDPC) code is constructed as a layered structure, where Source LDPC, Relay LDPC, and network LDPC code are organically integrated to realize a distributed design. Our design randomly embeds network-coded message into the layered structure as effective extra checks offering side information for both Source and Relay. Based on derivation of the algebraic relationship between constituent codes, a good multi-dimension LDPC code profile is generated. Meanwhile, network coding complexity maintains linear to the block length. The coding scheme is demonstrated to approach decode-and-forward capacity and still provides effective spatial diversity.
This study presents a set-based method to estimate unknown parameters of continuous-time structured nonlinear systems under uncertainties. Sets containing the parameters are found by using data sets and structures of ...
详细信息
This study presents a set-based method to estimate unknown parameters of continuous-time structured nonlinear systems under uncertainties. Sets containing the parameters are found by using data sets and structures of the systems. Such estimation is challenging because the uncertainties are caused by disturbances, data noises, and partially unknown dynamics. In addition, the estimation for continuous-time nonlinear systems faces nonlinear problems that are difficult to address. To overcome these issues, the proposed set-based method solves linear programming (LP) problems iteratively instead of the nonlinear problems. The inequalities in the LP are derived such that they are consistent with the true parameters, using the boundedness of the uncertainties. A theoretical analysis guarantees that solving the iterative LP gives sets containing the true parameters.
暂无评论