AN EXAMPLE OF NEURAL NETWORK USAGE FOR ASSIGNING A MODULATION-CODE SCHEME TO A 5G BASE STATION SCHEDULER

2021 ◽  
Keyword(s):  
Neural Network ◽  
Base Station ◽  
Code Scheme ◽  
Network Usage ◽  
Modulation Code

scholarly journals Optimising Performance for NB-IoT UE Devices through Data Driven Models

2021 ◽  
Vol 10 (1) ◽  
pp. 21
Author(s):  
Omar Nassef ◽  
Toktam Mahmoodi ◽  
Foivos Michelinakis ◽  
Kashif Mahmood ◽  
Ahmed Elmokashfi
Keyword(s):  
Neural Network ◽  
Reinforcement Learning ◽  
Gradient Descent ◽  
Deep Neural Network ◽  
Narrow Band ◽  
Learning Algorithm ◽  
Base Station ◽  
User Equipment ◽  
Data Driven ◽  
Superior Performance

This paper presents a data driven framework for performance optimisation of Narrow-Band IoT user equipment. The proposed framework is an edge micro-service that suggests one-time configurations to user equipment communicating with a base station. Suggested configurations are delivered from a Configuration Advocate, to improve energy consumption, delay, throughput or a combination of those metrics, depending on the user-end device and the application. Reinforcement learning utilising gradient descent and genetic algorithm is adopted synchronously with machine and deep learning algorithms to predict the environmental states and suggest an optimal configuration. The results highlight the adaptability of the Deep Neural Network in the prediction of intermediary environmental states, additionally the results present superior performance of the genetic reinforcement learning algorithm regarding its performance optimisation.

scholarly journals Research on Distributed 5G Signal Coverage Detection Algorithm Based on PSO-BP-Kriging

Sensors ◽  
2018 ◽  
Vol 18 (12) ◽  
pp. 4390
Author(s):  
Tingli Xiang ◽  
Hongjun Wang
Keyword(s):  
Neural Network ◽  
Communication Network ◽  
Mobile Communication ◽  
Detection Algorithm ◽  
Base Station ◽  
Distributed Sensor ◽  
Mobile Communication Network ◽  
The Neural Network ◽  
Signal Coverage ◽  
5G Mobile Communication

In order to overcome the limitations of traditional road test methods in 5G mobile communication network signal coverage detection, a signal coverage detection algorithm based on distributed sensor network for 5G mobile communication network is proposed. First, the received signal strength of the communication base station is collected and pre-processed by randomly deploying distributed sensor nodes. Then, the neural network objective function is modified by using the variogram function, and the initial weight coefficient of the neural network is optimized by using the improved particle swarm optimization algorithm. Next, the trained network model is used to interpolate the perceptual blind zone. Finally, the sensor node sampling data and the interpolation estimation result are combined to generate an effective coverage of the 5G mobile communication network signal. Simulation results indicate that the proposed algorithm can detect the real situation of 5G mobile communication network signal coverage better than other algorithms, and has certain feasibility and application prospects.

Resource Allocation in Orthogonal Frequency Division Multiple Access-Long Term Evaluation: Neural Network

2019 ◽  
Vol 16 (12) ◽  
pp. 5026-5031
Author(s):  
Kethavath Narender ◽  
C. Puttamadappa
Keyword(s):  
Neural Network ◽  
Resource Allocation ◽  
Communication Systems ◽  
Multiple Access ◽  
Large Scale ◽  
Cuckoo Search ◽  
Base Station ◽  
Frequency Division ◽  
Term Evaluation

Symmetrical Frequency Division Multiple Access (OFDMA) is utilized in the higher rate Wireless Communication Systems (WCSs). In the correspondence framework, a fem to cell is a little cell in building Base Station (BS), which devours less power, short range, and works in a minimal effort. The fem to cell has little separation among sender and recipient that give higher flag quality. In spite of the favorable position in fem to cell systems, there win critical difficulties in Interference Management. Specifically, impedance between the macro cell and fem to cell turns into the fundamental issue in OFDMA-Long Term Evaluation (OFDMA-LTE) framework. In this paper, the Neural Network and Hybrid Bee Colony and Cuckoo Search based Resource Allocation (NN-HBCCS-RA) in OFDMA-LTE framework is presented. The ideal power esteems are refreshed to dispense every one of the clients in the fem to cell and large scale cell. The NN-HBCCS strategy accomplished low Signal to Interference Noise Ratio (SINR), otherworldly proficiency and high throughput contrasted with customary techniques.

ART-2 neural network usage to determine moment of slag discharge during steel teeming process

2017 ◽  
Author(s):  
Y. I. Eremenko ◽  
D. A. Poleshchenko ◽  
A. I. Glushchenko ◽  
Yu. A. Tsygankov ◽  
Yu. A. Kovriznich
Keyword(s):  
Neural Network ◽  
Network Usage

scholarly journals ATRIAL FIBRILLATION DETECTION ON ELECTROCARDIOGRAMS WITH CONVOLUTIONAL NEURAL NETWORKS

2019 ◽  
Vol 9 (4) ◽  
pp. 69-73
Author(s):  
Viktor Kifer ◽  
Natalia Zagorodna ◽  
Olena Hevko
Keyword(s):  
Neural Network ◽  
Atrial Fibrillation ◽  
Sinus Rhythm ◽  
Deep Neural Network ◽  
Normal Sinus Rhythm ◽  
Normal Sinus ◽  
Noisy Signals ◽  
Network Usage ◽  
Model Training

In this paper, we present our research which confirms the suitability of the convolutional neural network usage for the classification of single-lead ECG recordings. The proposed method was designed for classifying normal sinus rhythm, atrial fibrillation (AF), non-AF related other abnormal heart rhythms and noisy signals. The method combines manually selected features with the features learned by the deep neural network. The Physionet Challenge 2017 dataset of over 8500 ECG recordings was used for the model training and validation. The trained model reaches an average F1-score 0.71 in classifying normal sinus rhythm, AF and other rhythms respectively.

scholarly journals A RADIAL BASIS NEURAL NETWORK CONTROLLER TO SOLVE CONGESTION IN WIRELESS SENSOR NETWORKS

2018 ◽  
Vol 44 (1) ◽  
pp. 40-48
Author(s):  
Maab Hussain
Keyword(s):  
Neural Network ◽  
Shortest Path ◽  
Base Station ◽  
Wireless Sensor ◽  
Network Congestion ◽  
Time Data ◽  
Radial Basis Neural Network ◽  
Memory Space ◽  
Neural Network Controller ◽  
Radial Basis

In multihop networks, such as the Internet and the Mobile Ad-hoc Networks, routing is one of the most importantissues that has an important effect on the network’s performance. This work explores the possibility of using the shortest path routingin wireless sensor network . An ideal routing algorithm should combat to find an perfect path for data that transmitted within anexact time. First an overview of shortest path algorithm is given. Then a congestion estimation algorithm based on multilayerperceptron neural networks (MLP-NNs) with sigmoid activation function, (Radial Basis Neural Network Congestion Controller(RBNNCC) )as a controller at the memory space of the base station node. The trained network model was used to estimate trafficcongestion along the selected route. A comparison study between the network with and without controller in terms of: trafficreceived to the base station, execution time, data lost, and memory utilization . The result clearly shows the effectiveness of RadialBasis Neural Network Congestion Controller (RBNNCC) in traffic congestion prediction and control.

scholarly journals Advanced modulation coding schemes for an optical transceiver systems–based OWC communication channel model

2021 ◽  
Vol 10 (2) ◽  
pp. 767-775
Author(s):  
Hazem M. El-Hageen ◽  
Aadel M. Alatwi ◽  
Ahmed Nabih Zaki Rashed
Keyword(s):  
Communication Channel ◽  
Channel Model ◽  
Power Level ◽  
Q Factor ◽  
Code Scheme ◽  
Optical Wireless ◽  
Coding Schemes ◽  
Modulation Coding ◽  
Received Power ◽  
Modulation Code

This paper examines advanced modulation coding schemes for an optical transceiver systems–based optical wireless communication (OWC) channel model. These modulation techniquesinclude On-Off keying and return to zero (RZ)/non–return to zero (NRZ) coding. The signal power level against time and frequency spectral variations are measured. The max. Q factor and min. bit error rate (BER) are estimated and clarified for each modulation code scheme by using an optisystem simulation model. Transmission bit rates of up to 40 Gb/s can be achieved for possible distances up to 500 km with acceptable Q factor. The received power and max. Q factor are measured and clarified with OWC distance variations. The On-Off keying modulation code scheme resulted in better performance than the other modulation code schemes did.

scholarly journals MPDHD-A Handover Decision Scheme for Seamless Connectivity in Wireless Network

2020 ◽  
Vol 9 (9) ◽  
pp. 524-528
Keyword(s):  
Neural Network ◽  
Wireless Network ◽  
Intelligent System ◽  
Fuzzy Model ◽  
Base Station ◽  
Handover Decision ◽  
Novel Technologies ◽  
Multiple Parameters ◽  
Seamless Connectivity ◽  
Increasing Demand

Handover is one of the major concerns arising in wireless network due to increasing demand of services by the customers. Different studies have been performed to attain a seamless handover. Researchers are implementing novel technologies so that efficient decision can be made to maintain effective communication. Multilayer feed forward artificial neural network has been implemented in a recent study in which Received Signal strength indicator (RSSI), monetary cost, Data rate and Velocity of mobile users in the network are taken into account for handover decision in wireless network. Due to several limitations of this technique, a novel method- Multiple parameters dependent Handover decision (MPDHD) is presented in which Sugeno fuzzy model is amalgamated with neural network to form an intelligent system. In the system, neural network is trained by the fuzzy model which reduced the complexity of the existing work. Also along with the parameters used in existing work, a new user metric-Load is introduced to check the availability of the base station with minimum load of users connected to it. The simulation of the proposed work is carried out in the MATLAB environment. From, the experimental results, it is concluded that MPDHD is better than existing approaches and reduced the handover probability in the network.

About Heating Plants Control System Developing on Basis of Neural Network Usage for PID-Regulator Parameters Optimization

2014 ◽  
Vol 682 ◽  
pp. 80-86 ◽  
Author(s):  
Yuri Eremenko ◽  
Dmitry Poleshchenko ◽  
Anton Glushchenko
Keyword(s):  
Neural Network ◽  
Control System ◽  
Parameters Optimization ◽  
Rule Base ◽  
Adaptive Control System ◽  
Neural Network Learning ◽  
Network Learning ◽  
Furnace Control ◽  
Network Usage ◽  
Control Modeling

An adaptive control system implementation is described. Such system is based on a neural network, used for online PID-regulator coefficients tuning. The backpropagation online training method is used. It is modified by adding a rule base. It contains conditions on choosing neural network learning rate. PID-regulator with neural tuner and conventional PID-regulator were used as regulators during the process of heating furnace control modeling. Such experiments were made for different loading furnace modes and setpoint schedules. The 11% economy of time on setpoint schedule realizing was achieved with the help of proposed neural tuner..

Sign in / Sign up

Export Citation Format

Share Document