Explicit Abnormality Extraction for Unsupervised Motion Artifact Reduction in Magnetic Resonance Imaging.

Motion artifacts compromise the quality of magnetic resonance imaging (MRI) and pose challenges to achieving diagnostic outcomes and image-guided therapies. In recent years, supervised deep learning approaches have emerged as successful solutions for motion artifact reduction (MAR). One disadvantage of these methods is their dependency on acquiring paired sets of motion artifact-corrupted (MA-corrupted) and motion artifact-free (MA-free) MR images for training purposes. Obtaining such image pairs is difficult and therefore limits the application of supervised training. In this paper, we propose a novel UNsupervised Abnormality Extraction Network (UNAEN) to alleviate this problem. Our network is capable of working with unpaired MA-corrupted and MA-free images. It converts the MA-corrupted images to MA-reduced images by extracting abnormalities from the MA-corrupted images using a proposed artifact extractor, which intercepts the residual artifact maps from the MA-corrupted MR images explicitly, and a reconstructor to restore the original input from the MA-reduced images. The performance of UNAEN was assessed by experimenting with various publicly available MRI datasets and comparing them with state-of-the-art methods. The quantitative evaluation demonstrates the superiority of UNAEN over alternative MAR methods and visually exhibits fewer residual artifacts. Our results substantiate the potential of UNAEN as a promising solution applicable in real-world clinical environments, with the capability to enhance diagnostic accuracy and facilitate image-guided therapies. Our codes are publicly available at https://github.com/YuSheng-Zhou/UNAEN.

Jamming precoding in AF relay-aided PLC systems with multiple eavessdroppers.

Enhancing information security has become increasingly significant in the digital age. This paper investigates the concept of physical layer security (PLS) within a relay-aided power line communication (PLC) system operating over a multiple-input multiple-output (MIMO) channel based on MK model. Specifically, we examine the transmission of confidential signals between a source and a distant destination while accounting for the presence of multiple eavesdroppers, both colluding and non-colluding. We propose a two-phase jamming scheme that leverages a full-duplex (FD) amplify-and-forward (AF) relay to address this challenge. Our primary objective is to maximize the secrecy rate, which necessitates the optimization of the jamming precoding and transmitting precoding matrices at both the source and the relay while adhering to transmit power constraints. We present a formulation of this problem and demonstrate that it can be efficiently solved using an effective block coordinate descent (BCD) algorithm. Simulation results are conducted to validate the convergence and performance of the proposed algorithm. These findings confirm the effectiveness of our approach. Furthermore, the numerical analysis reveals that our proposed algorithm surpasses traditional schemes that lack jamming to achieve higher secrecy rates. As a result, the proposed algorithm offers the benefit of guaranteeing secure communications in a realistic channel model, even in scenarios involving colluding eavesdroppers.

The role of directed cycles in a directed neural network.

This paper investigates the dynamics of a directed acyclic neural network by edge adding control. We find that the local stability and Hopf bifurcation of the controlled network only depend on the size and intersection of directed cycles, instead of the number and position of the added edges. More specifically, if there is no cycle in the controlled network, the local dynamics of the network will remain unchanged and Hopf bifurcation will not occur even if the number of added edges is sufficient. However, if there exist cycles, then the network may undergo Hopf bifurcation. Our results show that the cycle structure is a necessary condition for the generation of Hopf bifurcation, and the bifurcation threshold is determined by the number, size, and intersection of cycles. Numerical experiments are provided to support the validity of the theory.

An ADMM-LSTM framework for short-term load forecasting.

Accurate short-term load forecasting (STLF) is crucial for maintaining reliable and efficient operations within power systems. With the continuous increase in volume and variety of energy data provided by renewables, electric vehicles and other sources, long short-term memory (LSTM) has emerged as an attractive approach for STLF due to its superiorities in extracting the dynamic temporal information. However, traditional LSTM training methods rely on stochastic gradient methods that have several limitations. This paper presents an innovative LSTM optimization framework via the alternating direction method of multipliers (ADMM) for STLF, dubbed ADMM-LSTM. Explicitly, we train the LSTM network distributedly by the ADMM algorithm. More specifically, we introduce a novel approach to update the parameters in the ADMM-LSTM framework, using a backward-forward order, significantly reducing computational time. Additionally, within the proposed framework, the solution to each subproblem is achieved by utilizing either the proximal point algorithm or local linear approximation, preventing the need for supplementary numerical solvers. This approach confers several advantages, including avoiding issues associated with exploding or vanishing gradients, thanks to the inherent gradient-free characteristics of ADMM-LSTM. Furthermore, we offer a comprehensive theoretical analysis that elucidates the convergence properties inherent to the ADMM-LSTM framework. This analysis provides a deeper understanding of the algorithm's convergence behavior. Lastly, the efficacy of our method is substantiated through a series of experiments conducted on two publicly available datasets. The experimental results demonstrate the superior performance of our approach when compared to existing methods.

The SAITS epidemic spreading model and its combinational optimal suppression control.

In this paper, an SAITS epidemic model based on a single layer static network is proposed and investigated. This model considers a combinational suppression control strategy to suppress the spread of epidemics, which includes transferring more individuals to compartments with low infection rate and with high recovery rate. The basic reproduction number of this model is calculated and the disease-free and endemic equilibrium points are discussed. An optimal control problem is formulated to minimize the number of infections with limited resources. The suppression control strategy is investigated and a general expression for the optimal solution is given based on the Pontryagin's principle of extreme value. The validity of the theoretical results is verified by numerical simulations and Monte Carlo simulations.

Automated periodontitis bone loss diagnosis in panoramic radiographs using a bespoke two-stage detector.

Periodontitis is a serious oral disease that can lead to severe conditions such as bone loss and teeth falling out if left untreated. Diagnosis of radiographic bone loss (RBL) is critical for the staging and treatment of periodontitis. Unfortunately, the RBL diagnosis by examining the panoramic radiographs is time-consuming. The demand for automated image analysis is urgent. However, existing deep learning methods have limited performances in diagnosis accuracy and have certain difficulties in implementation. Hence, we propose a novel two-stage periodontitis detection convolutional neural network (PDCNN), where we optimize the detector with an anchor-free encoding that allows fast and accurate prediction. We also introduce a proposal-connection module in our detector that excludes less relevant regions of interests (ROIs), making the network focus on more relevant ROIs to improve detection accuracy. Furthermore, we introduced a large-scale, high-resolution panoramic radiograph dataset that captures various complex cases with professional periodontitis annotations. Experiments on our panoramic-image dataset show that the proposed approach achieved an RBL classification accuracy of 0.762. This result shows that our approach outperforms state-of-the-art detectors such as Faster R-CNN and YOLO-v4. We can conclude that the proposed method successfully improves the RBL detection performance. The dataset and our code have been released on GitHub. (https://github.com/PuckBlink/PDCNN).

Robust Iterative Distributed Minimum Total MSE Algorithm for Secure Communications in the Internet of Things Using Relays.

In this article, we first investigate secure communications for a two-hop interference channel relay system with imperfect channel estimation in the wireless Internet of Things (IoT), where K source-destination pairs communicate simultaneously when an eavesdropper exists. We jointly conceive source, relay and destination matrices upon minimizing total mean-squared error (MSE) of all legitimate destinations while keeping the MSE at eavesdropper above a given threshold. We illuminate that the design of the source, relay and destination matrices is subject to both transmit power constraints and secrecy requirements. More specifically, we propose an efficient robust iterative distributed algorithm to simplify the process of the joint design for optimal source, relay and destination matrices. Furthermore, the convergence of the iterative distributed algorithm is described. Additionally, the performances of our proposed algorithm, such as its secrecy rate and MSE, are characterized in the form of simulation results. The simulation results reveal that the proposed algorithm is superior to the traditional approach. As a benefit, secure communications can be ensured by using the proposed algorithm for the multiple input multiple output (MIMO) interference relay IoT network in the presence of an eavesdropper.