Online reinforcement learning for adaptive interference coordination

https://journals.lww.com/ajg/Fulltext/9900/Reduced_Adenoma_Miss_Rate_With_9_Minute_vs.545.aspx

Reduced Adenoma Miss Rate With 9-Minute vs 6-Minute Withdrawal Times for Screening Colonoscopy: A Multicenter Randomized Tandem Trial

In order to maximize energy efficiency in heterogeneous networks (HetNets), a turbo Q-Learning (TQL) combined with multistage decision process and tabular Q-Learning is proposed to optimize the resource configuration. For the large dimensions of action space, the problem of energy efficiency optimization is designed as a multistage decision process in this paper, according to the resource allocation of optimization objectives, the initial problem is divided into several subproblems which are solved by tabular Q-Learning, and the traditional exponential increasing size of action space is decomposed into linear increase. By iterating the solutions of subproblems, the initial problem is solved. The simple stability analysis of the algorithm is given in this paper. As to the large dimension of state space, we use a deep neural network (DNN) to classify states where the optimization policy of novel Q-Learning is set to label samples. Thus far, the dimensions of action and state space have been solved. The simulation results show that our approach is convergent, improves the convergence speed by 60% while maintaining almost the same energy efficiency and having the characteristics of system adjustment.

https://www.mdpi.com/1099-4300/22/9/957/pdf

A Turbo Q-Learning (TQL) for Energy Efficiency Optimization in Heterogeneous Networks.

In order to comprehensively improve the performance of edge users in heterogeneous cellular networks and the fairness of network users, a downlink interference coordination optimization strategy in heterogeneous cellular networks with non-orthogonal multiple access (NOMA) based on the cell range expansion (CRE) and the almost blank subframe (ABS) technology is proposed. Different from the traditional interference coordination strategy, a NOMA user pairing scheme combined with ABS technology and a dynamic NOMA power allocation scheme are designed to maximize the network fairness based on the optimized throughput of the edge users. The simulation results show that the proposed optimization strategy can balance the performance of network users more effectively to improve the throughput of edge users and network fairness than other NOMA user pairing and power allocation algorithms without the complexity being increased.

/pdf/research-on-interference-coordination-optimization-strategy-3oy9n970.pdf

Research on Interference Coordination Optimization Strategy for User Fairness in NOMA Heterogeneous Networks

The rapid growth of Internet of Things (IoT) dramatically increases power consumption of wireless devices. Simultaneous wireless information and power transfer (SWIPT) is a promising solution for sustainable operation of IoT devices. In this paper, we study energy efficiency (EE) in SWIPT-based distributed antenna system (DAS), where power splitting (PS) is applied at IoT devices to coordinate the energy harvesting (EH) and information decoding (ID) processes by varying transmit power of distributed antenna (DA) ports and PS ratios of IoT devices. In the case of single IoT device, we find the optimal closed-form solution by deriving some useful properties based on Karush-Kuhn-Tucker (KKT) conditions and the solution is no need for numerical iterations. For the case of multiple IoT devices, we propose an efficient suboptimal algorithm to solve the EE maximization problem. Simulation results show that the proposed schemes achieve better EE performance compared with other benchmark schemes in both single and multiple IoT devices cases.

Energy-Efficient SWIPT in IoT Distributed Antenna Systems

To solve the problem of load imbalance and system interference in heterogeneous networks (HetNets), an energy efficiency (EE) optimized strategy based on enhanced intercell interference coordination (eICIC) technology is proposed. The optimization of the EE of the system is established by taking into account four components which are the connection between the users and base stations (BSs), almost blank subframe (ABS) ratio, resource allocation in the frequency domain, and the power transmission of the macro BSs (MBSs). In our optimized strategy, the user’s optimal BS connection status are determined according to the overall EE change of the system, and the allocation of subframes and resource blocks of the MBSs both in the time domain and frequency domain are optimized, respectively. We use the Gauss–Seidel method to iteratively solve the optimization problem. Simulation results show that the optimized strategy outperforms other solutions in terms of EE and user fairness in average. The proposed optimization strategy increases the system EE by 24.2% and 19.1%, respectively, when compared with the maximal reference signal received power (MAX-RSRP) and the low power-ABS (LP-ABS) strategies. The Jain fairness index of our proposed optimization strategy is averagely increased by 33.8% and 23.4%, respectively. In addition, the proposed strategy can further improve the user satisfaction and the performance in the system.

Energy Efficiency Optimization Based on eICIC for Wireless Heterogeneous Networks

Colorectal sessile serrated lesion detection using linked color imaging: A multicenter, parallel randomized controlled trial.

Inflammation, apoptosis and oxidative stress contribute to the development of severe acute pancreatitis-associated acute lung injury (SAP-ALI). Currently, there is no curative treatment for SAP-ALI in the clinic. This study investigated the potential therapeutic role and mechanisms of colchicine in a rat model of SAP-ALI.Male Sprague-Dawley rats were randomized and administrated intragastrically with vehicle saline or colchicine (0.5 mg/kg/day) for seven days, followed by injecting sodium taurocholate to induce SAP-ALI. Together with a healthy control group of rats, their pancreatic and lung tissues and plasma samples were collected for histology, enzyme-linked immunosorbent assay (ELISA), immunoblot, immunohistochemistry, and immunofluorescence.Compared with the sham controls, the SAP group of rats with vehicle saline treatment displayed severe damages, inflammation with many neutrophil and macrophage infiltrates in pancreatic and lung tissues, accompanied by elevated levels of plasma interleukin-1β (IL-1β), IL-6 and tumor necrosis factor (TNF)-α, which were significantly mitigated in colchicine-treated SAP + COL group of rats. Furthermore, colchicine treatment significantly attenuated nuclear factor kappa-B (NF-κB)-p65, signal transducer and activator of transcription 3 (STAT3) and protein kinase B (AKT) phosphorylation, reduced inducible nitric oxide synthase (iNOS) and 4-Hydroxynonenal expression, ROS production and cell apoptosis by decreasing caspase-3 cleavage, Bax expression, but increasing Bcl-2, nuclear factor erythroid 2-related factor 2 (Nrf2) and heme oxygenase-1 (HO-1) expression in pancreatic and lung tissues, relative to the SAP group of rats.Colchicine treatment significantly mitigated the severity of SAP-ALI by inhibiting inflammation, oxidative stress and cell apoptosis in rats. 

Colchicine improves severe acute pancreatitis-induced acute lung injury by suppressing inflammation, apoptosis and oxidative stress in rats.

BACKGROUND AND STUDY AIMS
Previous studies have reported the effectiveness of narrow-band imaging (NBI) and linked-color imaging (LCI) in improving the detection of colorectal neoplasms. However, there has been no direct comparison between LCI and NBI in detecting colorectal sessile serrated lesions (SSLs). The present study aims to compare the effectiveness of detecting colorectal SSLs between LCI and NBI.


PATIENTS AND METHODS
A prospective, parallel, randomized controlled trial was conducted. The participants were randomly assigned to the LCI arm and NBI arm. The primary endpoint was the SSL detection rate (SDR).


RESULTS
A total of 406 patients were involved, with 204 patients in the LCI arm and 202 patients in the NBI arm. The total polyp detection rate, adenoma detection rate and SDR was 54.2%, 38.7%, and 10.8%, respectively. The SDR had no significant difference between the LCI arm and the NBI arm (12.3% vs 9.4%, P = 0.356). The differences in the detection rate and the per-patient number of polyps, adenomas, diminutive lesions and flat lesions between LCI and NBI also had no statistical significance. Multivariate analysis showed that LCI or NBI was not an independent factor associated with SDR, whereas Boston Bowel Preparation Scale (OR: 1.346, 95% CI: 1.031-1.758, P = 0.029), withdrawal time (OR: 1.125, 95% CI: 1.003-1.261, P = 0.044) and operator experience (OR: 3.730, 95% CI: 1.672-8.322, P = 0.001) were independent factors associated with SDR.


CONCLUSIONS
LCI and NBI is comparable for SSL detection, as well as for polyps and adenomas detection.

Lei Li

Papers

Energy Efficiency Optimization Based on eICIC for Wireless Heterogeneous Networks

Colorectal sessile serrated lesion detection using linked color imaging: A multicenter, parallel randomized controlled trial.

A Turbo Q-Learning (TQL) for Energy Efficiency Optimization in Heterogeneous Networks.

Colchicine improves severe acute pancreatitis-induced acute lung injury by suppressing inflammation, apoptosis and oxidative stress in rats.

Colorectal sessile serrated lesion detection using linked-color imaging versus narrow-band imaging: a parallel randomized controlled trial