Application of Recurrent Neural Networks for Adaptive Selection of Parameters of Error-correcting Code in Telemetry Data Transmission Systems

2021 ◽  
Author(s):  
Ilya Bogachev ◽  
Alexey Levenets ◽  
En Un Chye
Keyword(s):  
Neural Networks ◽  
Recurrent Neural Networks ◽  
Data Transmission ◽  
Error Correcting Code ◽  
Telemetry Data ◽  
Transmission Systems ◽  
Adaptive Selection ◽  
Selection Of

scholarly journals SIMULATION OF DATA TRANSMISSION SYSTEM WITH ADAPTIVE SELECTION OF AN ERROR-CORRECTING CODE BASED ON COMMUNICATION CHANNEL STATE ASSESS-MENT

2020 ◽  
Vol 4 ◽  
pp. 17-24
Author(s):  
I.V. Kochetova ◽  
◽  
A.V. Levenets ◽  
Keyword(s):  
Data Transmission ◽  
Communication Channel ◽  
Error Correcting Code ◽  
Feedback Channel ◽  
Channel State ◽  
Adaptive Selection ◽  
Transmission Equipment ◽  
Simulated System ◽  
Data Transmission System ◽  
Selection Of

The article proposes a simulation model of an adaptive system for transmitting discrete messages, in which information about the state of the communication channel is used to set the parameters of an error-correcting code, which makes it possible to operate the bandwidth of the communication channel and optimize the performance of data transmission equipment. An assessment of the efficiency of cer-tain error-correcting coding methods in a simulated system with respect to the value Eb/No is carried out. The model makes it possible to estimate such parameters as the weight of transmitted messages, the number of repeated messages through the feedback channel for a given value of Eb/No.

scholarly journals A New Hyper-Parameter Optimization Method for Power Load Forecast Based on Recurrent Neural Networks

Algorithms ◽  
2021 ◽  
Vol 14 (6) ◽  
pp. 163
Author(s):  
Yaru Li ◽  
Yulai Zhang ◽  
Yongping Cai
Keyword(s):  
Neural Networks ◽  
Parameter Optimization ◽  
Recurrent Neural Networks ◽  
Critical Role ◽  
Optimization Method ◽  
Bayesian Optimization ◽  
Power Load ◽  
Gradient Calculation ◽  
Truncated Newton ◽  
Selection Of

The selection of the hyper-parameters plays a critical role in the task of prediction based on the recurrent neural networks (RNN). Traditionally, the hyper-parameters of the machine learning models are selected by simulations as well as human experiences. In recent years, multiple algorithms based on Bayesian optimization (BO) are developed to determine the optimal values of the hyper-parameters. In most of these methods, gradients are required to be calculated. In this work, the particle swarm optimization (PSO) is used under the BO framework to develop a new method for hyper-parameter optimization. The proposed algorithm (BO-PSO) is free of gradient calculation and the particles can be optimized in parallel naturally. So the computational complexity can be effectively reduced which means better hyper-parameters can be obtained under the same amount of calculation. Experiments are done on real world power load data,where the proposed method outperforms the existing state-of-the-art algorithms,BO with limit-BFGS-bound (BO-L-BFGS-B) and BO with truncated-newton (BO-TNC),in terms of the prediction accuracy. The errors of the prediction result in different models show that BO-PSO is an effective hyper-parameter optimization method.

scholarly journals Approximation of phenol concentration using novel hybrid computational intelligence methods

2014 ◽  
Vol 24 (1) ◽  
pp. 165-181 ◽  
Author(s):  
Pawel Plawiak ◽  
Ryszard Tadeusiewicz
Keyword(s):  
Neural Networks ◽  
Genetic Algorithms ◽  
Computational Intelligence ◽  
Recurrent Neural Networks ◽  
Phenol Concentration ◽  
Neural Systems ◽  
Feed Forward ◽  
Computational Intelligence Methods ◽  
Lm Algorithm ◽  
Selection Of

Abstract This paper presents two innovative evolutionary-neural systems based on feed-forward and recurrent neural networks used for quantitative analysis. These systems have been applied for approximation of phenol concentration. Their performance was compared against the conventional methods of artificial intelligence (artificial neural networks, fuzzy logic and genetic algorithms). The proposed systems are a combination of data preprocessing methods, genetic algorithms and the Levenberg-Marquardt (LM) algorithm used for learning feed forward and recurrent neural networks. The initial weights and biases of neural networks chosen by the use of a genetic algorithm are then tuned with an LM algorithm. The evaluation is made on the basis of accuracy and complexity criteria. The main advantage of proposed systems is the elimination of random selection of the network weights and biases, resulting in increased efficiency of the systems.

scholarly journals Training of technical personnel of tactical data LINK

2018 ◽  
Vol 48 (1) ◽  
pp. 559-573
Author(s):  
Artur Chmarowski ◽  
Władysław Melnarowicz
Keyword(s):  
Training Program ◽  
Data Transmission ◽  
Level Of Service ◽  
Data Link ◽  
Transmission Systems ◽  
Technical Personnel ◽  
Modular Training ◽  
Tactical Data Link ◽  
Selection Of

Abstract An important area in the process of using and servicing tactical data transmission systems LINK-16 is a system of training operators and technicians. The article presents the results of research related to the modelling and implementation of a modular training program for technical personnel. There were determined ranges of qualification requirements for technical personnel TDL, for the first and second level of service and the possibility of flexible selection of expansion modules for the development of specific skills depending on the destination job.

Sign in / Sign up

Export Citation Format

Share Document