The approach of factor-graphs (FGs) is applied in the context of power control and user pairing in Device-to-Device (D2D) communications as an effective underlay concept in wireless cellular networks. D2D communications can increase the spectral efficiency of wireless cellular networks by establishing a direct link between devices with limited help from the evolved node base stations (eNBs). A well-designed user pairing and power allocation scheme with low complexity can remarkably improve the system's performance. In this paper, a simple and distributed FG based approach is utilized for power control and user pairing implementation in an underlay cellular network with D2D communications. A max-min criterion is proposed to maximize the minimum rate of all active users in the network, including the cellular and multiple D2D co-channel links in the uplink direction. An associated message-passing (MP) algorithm is presented to distributedly solve the resultant NP-hard maximization problem, with a guaranteed convergence compared to game theoretic and Q-learning based methods. The complexity and convergence of the proposed method is analyzed and numerical results confirm that the proposed scheme outperforms alternative algorithms in terms of complexity, while keeping the sum-rate of users nearly the same as centralized counterpart methods.
In device-to-device (D2D) communications, D2D users establish a direct link by utilizing the cellular users' spectrum to increase the network spectral efficiency. However, due to the higher priority of cellular users, interference imposed by D2D users to cellular ones should be controlled by channel and power allocation algorithms. Due to the unknown distribution of dynamic channel parameters, learning-based resource allocation algorithms work more efficient than classic optimization methods. In this paper, the problem of the joint channel and power allocation for D2D users in realistic scenarios is formulated as an interactive learning problem, where the channel state information of selected channels is unknown to the decision center and learned during the allocation process. In order to achieve the maximum reward function by choosing an action (channel and power level) for each D2D pair, a recency-based Q-learning method is introduced to find the best channel-power for each D2D pair. The proposed method is shown to achieve logarithmic regret function asymptotically, which makes it an order optimal policy, and it converges to the stable equilibrium solution. The simulation results confirm that the proposed method achieves better responses in terms of network sum rate and fairness criterion in comparison with conventional learning methods and random allocation.
In cognitive radio networks, secondary users utilize idle parts of primary users' spectrum in order to achieve more spectrum efficiency. However, due to the fact that sensing more than one channel at every sensing opportunity is difficult, the spectrum selection by the secondary users is a serious challenge in real senarios. In this paper, the problem of spectrum sensing and selection in a cognitive radio system is modeled as a multi-armed multi-player bandit problem. Unlike to the other works in this area, we have considered a bursty type traffic for primary users and by introducing a forgetting factor to the involved past successful transmissions in the bandit model, it is shown that the average successful transmission rate is increased. Simulation results show that successful transmission rate in our algorithm is 10% better than that of random spectrum sensing.
Acute respiratory distress syndrome (ARDS) is a life-threatening condition with mortality rates between 30-50%. Althoughin vitromodels replicate some aspects of ARDS, small and large animal models remain the primary research tools due to the multifactorial nature of the disease. When using these animal models, histology serves as the gold standard method to confirm lung injury and exclude other diagnoses as high-resolution chest images are often not feasible. Semi-quantitative scoring performed by independent observers is the most common form of histologic analysis in pre-clinical animal models of ARDS. Despite progress in standardizing analysis procedures, objectively comparing histological injuries remains challenging, even for highly-trained pathologists. Standardized scoring simplifies the task and allows better comparisons between research groups and across different injury models, but it is time-consuming, and interobserver variability remains a significant concern. Convolutional neural networks (CNNs), which have emerged as a key tool in image analysis, could automate this process, potentially enabling faster and more reproducible analysis. Here we explored the reproducibility of human standardized scoring for an animal model of ARDS and its suitability for training CNNs for automated scoring at the whole slide level. We found large variations between human scorers, even for pre-clinical experts and board-certified pathologies in evaluating ARDS animal models. We demonstrate that CNNs (VGG16, EfficientNetB4) are suitable for automated scoring and achieve up to 83% F1-score and 78% accuracy. Thus, CNNs for histopathological classification of acute lung injury could help reduce human variability and eliminate a time-consuming manual research task with acceptable performance.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.