Метод прогнозирования состояния радиоканала 4G и 5G

2019 ◽  
Author(s):  
A.V. Pestryakov ◽  
A.S. Konstantinov
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
Comparative Analysis ◽  
Channel Model ◽  
Radio Channel ◽  
Learning Algorithms ◽  
Base Station ◽  
Coding Scheme ◽  
Lstm Network ◽  
Short Time

The paper presents a developed framework based on several neural networks for predicting the state of a radio channel in order to select the best modulation and coding scheme on the base station, taking into account the fading in the radio channel. Comparative analysis of the efficiency of modern architectures in the prediction of time series is carried out. Neural Long Short Time Memory (LSTM) network is defined as a framework core. The learning algorithms of the architectures under consideration are investigated. The choice of the radio channel model is justified. The framework efficiency is evaluated. Представлен разработанный на основе нескольких нейронных сетей фреймворк для прогнозирования состояния радиоканала с целью выбора наилучшей модуляционно-кодовой схемы на стороне базовой станции (с учетом замираний в нисходящей линии связи). Проведен сравнительный анализ эффективности современных архитектур при прогнозировании временных рядов и определена нейронная сеть LSTM в качестве ядра фреймворка. Исследованы алгоритмы обучения рассма- триваемых архитектур. Обоснован выбор модели радиоканала, параметров и проведена оценка эффективности фреймворка.

scholarly journals Rainfall prediction: A comparative analysis of modern machine learning algorithms for time-series forecasting

2021 ◽  
pp. 100204
Author(s):  
Ari Yair Barrera-Animas ◽  
Lukumon Oladayo Oyedele ◽  
Muhammad Bilal ◽  
Taofeek Dolapo Akinosho ◽  
Juan Manuel Davila Delgado ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Comparative Analysis ◽  
Learning Algorithms ◽  
Time Series Forecasting ◽  
Machine Learning Algorithms ◽  
Rainfall Prediction ◽  
Modern Machine

Predicting drug-target affinity based on recurrent neural networks and graph convolutional neural networks

2021 ◽  
Vol 24 ◽  
Author(s):  
Qingyu Tian ◽  
Mao Ding ◽  
Hui Yang ◽  
Caibin Yue ◽  
Yue Zhong ◽  
...  
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Convolutional Neural Network ◽  
Drug Target ◽  
Channel Model ◽  
Search Space ◽  
Topological Features ◽  
Latent Features ◽  
Chemical Background

Background: Drug development requires a lot of money and time, and the outcome of the challenge is unknown. So, there is an urgent need for researchers to find a new approach that can reduce costs. Therefore, the identification of drug-target interactions (DTIs) has been a critical step in the early stages of drug discovery. These computational methods aim to narrow the search space for novel DTIs and to elucidate the functional background of drugs. Most of the methods developed so far use binary classification to predict the presence or absence of interactions between the drug and the target. However, it is more informative, but also more challenging, to predict the strength of the binding between a drug and its target. If the strength is not strong enough, such a DTI may not be useful. Hence, the development of methods to predict drug-target affinity (DTA) is of significant importance. Method: We have improved the Graph DTA model from a dual-channel model to a triple-channel model. We interpreted the target/protein sequences as time series and extracted their features using the LSTM network. For the drug, we considered both the molecular structure and the local chemical background, retaining the four variant networks used in Graph DTA to extract the topological features of the drug and capturing the local chemical background of the atoms in the drug by using BiGRU. Thus, we obtained the latent features of the target and two latent features of the drug. The connection of these three feature vectors is then input into a 2-layer FC network, and a valuable binding affinity is output. Result: We use the Davis and Kiba datasets, using 80% of the data for training and 20% of the data for validation. Our model shows better performance by comparing it with the experimental results of Graph DTA. Conclusion: In this paper, we altered the Graph DTA model to predict drug-target affinity. It represents the drug as a graph, and extracts the two-dimensional drug information using a graph convolutional neural network. Simultaneously, the drug and protein targets are represented as a word vector, and the convolutional neural network is used to extract the time series information of the drug and the target. We demonstrate that our improved method has better performance than the original method. In particular, our model has better performance in the evaluation of benchmark databases.

scholarly journals A Comparative Study of Predicting Customer Churn and Lifetime

2020 ◽  
Vol 26 (1) ◽  
pp. 1-6
Author(s):  
O. Adesua ◽  
◽  
P.A. Danquah ◽  
O.B Longe
Keyword(s):  
Neural Networks ◽  
Comparative Analysis ◽  
Mobile Station ◽  
Signal Strength ◽  
Base Station ◽  
Churn Prediction ◽  
Customer Base ◽  
Customer Churn ◽  
Customer Lifetime ◽  
Station Mobile

The problem to be investigated in this research is that of predicting customers who are at risk of leaving the company, a term called churn prediction in telecommunication. The aim of this research is to predict customer churn and further focus on creating customer lifetime profiles. These profiles will allow the company to fit their customer base into n categories and make a long estimation on when a customer is potentially going to terminate their service with the company. The research then proceeds to provide a comparative analysis of neural networks and survival analysis in their capabilities of predicting customer churn and lifetime. . Key words: GSM networks, Base station, Mobile station, Signal strength, GSM service provider

scholarly journals FINANCIAL FORECASTING USING NEURAL NETWORKS

2006 ◽  
Vol 1 ◽  
pp. 392
Author(s):  
A. Zorins
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Time Series ◽  
Comparative Analysis ◽  
Stock Exchange ◽  
Financial Time Series ◽  
Financial Forecasting ◽  
Neural Network Learning ◽  
Network Learning ◽  
Financial Time

This paper presents an application of neural networks to financial time-series forecasting. No additional indicators, but only the information contained in the sales time series was used to model and forecast stock exchange index. The forecasting is carried out by two different neural network learning algorithms – error backpropagation and Kohonen self-organising maps. The results are presented and their comparative analysis is performed in this article.

scholarly journals Uncertainty Quantification in Machine Learning Modeling for Multi-Step Time Series Forecasting: Example of Recurrent Neural Networks in Discharge Simulations

Water ◽  
2020 ◽  
Vol 12 (3) ◽  
pp. 912
Author(s):  
Tianyu Song ◽  
Wei Ding ◽  
Haixing Liu ◽  
Jian Wu ◽  
Huicheng Zhou ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Time Series ◽  
Uncertainty Quantification ◽  
Recurrent Neural Networks ◽  
Short Term Memory ◽  
Time Series Forecasting ◽  
Uncertainty Sources ◽  
Discharge Simulation ◽  
Lstm Network

As a revolutionary tool leading to substantial changes across many areas, Machine Learning (ML) techniques have obtained growing attention in the field of hydrology due to their potentials to forecast time series. Moreover, a subfield of ML, Deep Learning (DL) is more concerned with datasets, algorithms and layered structures. Despite numerous applications of novel ML/DL techniques in discharge simulation, the uncertainty involved in ML/DL modeling has not drawn much attention, although it is an important issue. In this study, a framework is proposed to quantify uncertainty contributions of the sample set, ML approach, ML architecture and their interactions to multi-step time-series forecasting based on the analysis of variance (ANOVA) theory. Then a discharge simulation, using Recurrent Neural Networks (RNNs), is taken as an example. Long Short-Term Memory (LSTM) network, a state-of-the-art DL approach, was selected due to its outstanding performance in time-series forecasting, and compared with simple RNN. Besides, novel discharge forecasting architecture is designed by combining the expertise of hydrology and stacked DL structure, and compared with conventional design. Taking hourly discharge simulations of Anhe (China) catchment as a case study, we constructed five sample sets, chose two RNN approaches and designed two ML architectures. The results indicate that none of the investigated uncertainty sources are negligible and the influence of uncertainty sources varies with lead-times and discharges. LSTM demonstrates its superiority in discharge simulations, and the ML architecture is as important as the ML approach. In addition, some of the uncertainty is attributable to interactions rather than individual modeling components. The proposed framework can both reveal uncertainty quantification in ML/DL modeling and provide references for ML approach evaluation and architecture design in discharge simulations. It indicates uncertainty quantification is an indispensable task for a successful application of ML/DL.

Ultra-short-term prediction of LOD using LSTM neural networks

2021 ◽  
Author(s):  
Junyang Gou ◽  
Mostafa Kiani Shahvandi ◽  
Roland Hohensinn ◽  
Benedikt Soja
Keyword(s):  
Time Series ◽  
Rapid Expansion ◽  
Short Term ◽  
Earth Orientation Parameters ◽  
Earth Orientation ◽  
The Earth ◽  
Space Geodetic Techniques ◽  
Lstm Network ◽  
Short Time ◽  
Orientation Parameters

<p>The Earth Orientation Parameters (EOP) are fundamentals of geodesy, connecting the terrestrial and celestial reference frames. The typical way to generate EOP of highest accuracy is combining different space geodetic techniques. Due to the time demand for processing data and combining different techniques, the combined EOP products often have latencies from several days to several weeks. However, real-time EOP are needed for multiple geodetic and geophysical applications, including precise navigation and operation of satellites. Predictions of EOP in ultra-short time can overcome the problem of latency of EOP products to a certain extent.</p><p>In 2010, the Earth Orientation Parameters Prediction Comparison Campaign (EOP PCC) collected predictions from 20 methods, which were mainly based on statistical approaches, and provided a combined solution. In recent years, more hybrid and machine learning methods have been introduced for EOP prediction.</p><p>The rapid expansion of computing power and data volume in recent years has made the application of deep learning in geodesy increasingly promising. In particular, the Long Short-Term Memory (LSTM) network, one of the most popular variations of Recurrent Neural Network (RNN), is promising for geodetic time series prediction. Thanks to the special structure of its cells, LSTM network can capture the non-linear structure between different time epochs in the time series. Therefore, it is suitable for EOP prediction problems.</p><p>In this study, we investigate the potential of using LSTM for the prediction of Length of Day (LOD). The LOD data from a combination of space geodetic techniques are first preprocessed in order to obtain residuals. For this step, we experiment with the application of Savitzky-Golay filters, Singular Spectrum Analysis and the Gauss Markov model. We then employ LSTM networks of different architectures and its variations such as bidirectional LSTM networks to predict the LOD residuals in ultra-short time. Furthermore, we study the impact of Atmospheric Angular Momentum (AAM) and its forecast data on the predictions. The performance of this method is compared with other results of EOP PCC in a hindcast experiment under the same conditions. In addition, we assess the performance of LOD predictions using longer time series than for the EOP PCC to consider improvements of EOP products over the last decade.</p>

Sign in / Sign up

Export Citation Format

Share Document