A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2020; you can also visit the original URL.
The file type is application/pdf
.
Filters
Deep Echo State Networks for Short-Term Traffic Forecasting: Performance Comparison and Statistical Assessment
[article]
2020
arXiv
pre-print
In short-term traffic forecasting, the goal is to accurately predict future values of a traffic parameter of interest occurring shortly after the prediction is queried. ...
In this work we elaborate on the performance of Deep Echo State Networks for this particular task. ...
FUNDAMENTALS OF ECHO STATE NETWORKS In general, RC models build upon the capability of Recursive Neural Networks (RNN) to perform well even when their constituent trainable parameters (weights) are not ...
arXiv:2004.08170v1
fatcat:kzep2sf5ffeh3jwa6fkw72m5dm
A Survey on Traffic Prediction Techniques Using Artificial Intelligence for Communication Networks
2021
Telecom
We then discuss machine learning and statistical techniques to predict future traffic and classify each into short-term or long-term applications. ...
Much research effort has been conducted to introduce intelligence into communication networks in order to enhance network performance. ...
[22] use an echo state network (ESN) and autoregressive integrated moving average (ARIMA) model to forecast mobile communication traffic series. ...
doi:10.3390/telecom2040029
fatcat:5o3d27bp35cf7kl626sbkmrsh4
Applications of Recurrent Neural Networks in Environmental Factor Forecasting: A Review
2018
Neural Computation
When predicting the future probability of events using time series, recurrent neural networks (RNNs) are an effective tool that have the learning ability of feedforward neural networks and expand their ...
We present the structure, processing flow, and advantages of RNNs and analyze the applications of various RNNs in time series forecasting. ...
An, Song, and Zhao (2011) used a model for traffic flow forecasting based on echo state neural networks (ESNs). ...
doi:10.1162/neco_a_01134
pmid:30216144
fatcat:3rcnrh7u4fefdl4ie4kafypjne
Survey on Deep Fuzzy Systems in regression applications: a view on interpretability
[article]
2022
arXiv
pre-print
Fuzzy logic systems (FLS) are inherently interpretable models, well known in the literature, capable of using nonlinear representations for complex systems through linguistic terms with membership degrees ...
This paper aims to investigate the state-of-the-art on existing methodologies that combine DL and FLS, namely deep fuzzy systems, to address regression problems, configuring a topic that is currently not ...
granulation with Stacked Autoencoder Traffic flow prediction No T - [197] Fuzzy seasonal long short-term Wind power forecasting No O - memory network [199] Long Short-Term Memory model Wind speed forecasting ...
arXiv:2209.04230v1
fatcat:mvwyqrhb3nerndnedlq4ccidku
KeyMemoryRNN: A Flexible Prediction Framework for Spatiotemporal Prediction Networks
2021
IEEE Access
In other words, the network tends to be more optimize short-term forecast results, which makes it difficult for the network to learn the correlation between long-term states via gradient descent. ...
Spatiotemporal sequence data correspond to the sequence data with spatiotemporal correlations, such as precipitation radar echo data, traffic flows data or other video data. ...
doi:10.1109/access.2021.3114215
fatcat:6ebijvogcrhuzg575rumyvrtma
A Novel Hybrid Model for Predicting Traffic Flow via Improved Ensemble Learning Combined with Deep Belief Networks
2021
Mathematical Problems in Engineering
Accurate and efficient short-term traffic state forecasting is a significant issue in ITS. ...
., artificial neural network, long short-term memory neural network, and DBN), the ELM-IBF model reveals better performance in forecasting single-step-ahead traffic volume and speed. ...
neural network [30] , fuzzy neural network [31] , echo state neural network [32] , radial basis function neural network (RBFNN) [33] , and recurrent neural network (RNN) [34] . ...
doi:10.1155/2021/7328056
fatcat:3w3x5m7pejfpfn7str2ztbhl6e
PredRNN: A Recurrent Neural Network for Spatiotemporal Predictive Learning
[article]
2022
arXiv
pre-print
Concretely, besides the original memory cell of LSTM, this network is featured by a zigzag memory flow that propagates in both bottom-up and top-down directions across all layers, enabling the learned ...
We further propose a new curriculum learning strategy to force PredRNN to learn long-term dynamics from context frames, which can be generalized to most sequence-to-sequence models. ...
of long-term and short-term dynamics. ...
arXiv:2103.09504v4
fatcat:al5ij37d3nhj7nynglu7rod5k4
Quantitative Short-Term Precipitation Model Using Multimodal Data Fusion Based on a Cross-Attention Mechanism
2022
Remote Sensing
Firstly, the radar feature encoder comprises a shallow convolution neural network and a stacked convolutional long short term memory network (ConvLSTM), which is used to extract the spatio-temporal features ...
of radar-echo data. ...
of short-term precipitation through external neural networks. ...
doi:10.3390/rs14225839
fatcat:ibd3so3hifcuhdiic2u2f7hqiy
Chaotic Time Series Forecasting Approaches Using Machine Learning Techniques: A Review
2022
Symmetry
This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY ...
In [50] , the authors developed the self-organizing Takagi and Sugeno-type FNN model for predicting the short-term traffic flow. ...
short-term electrical energy demand. ...
doi:10.3390/sym14050955
dblp:journals/symmetry/RamadeviB22
fatcat:3oa3go7rdzdurjl4yxcivjsbf4
Short-Term Traffic Flow Forecasting: An Experimental Comparison of Time-Series Analysis and Supervised Learning
2013
IEEE transactions on intelligent transportation systems (Print)
The literature on short-term traffic flow forecasting has undergone great development recently. ...
First, we review existing approaches to short-term traffic flow forecasting methods under the common view of probabilistic graphical models, presenting an extensive experimental comparison, which proposes ...
UNIFIED VIEW FOR SHORT-TERM TRAFFIC FORECASTING METHODS USING GRAPHICAL MODELS The literature on short-term traffic forecasting covers a broad spectrum of research areas including statistics, control systems ...
doi:10.1109/tits.2013.2247040
fatcat:xjvxfgjmsjf6jdtkc3i7lhhoma
MSDM v1.0: A machine learning model for precipitation nowcasting over eastern China using multisource data
2021
Geoscientific Model Development
The developed multisource data model (MSDM) combines the optical flow, random forest, and convolutional neural network (CNN) algorithms. ...
The predicted radar echoes from the MSDM together with satellite data from the optical flow algorithm are recursively implemented in the MSDM to achieve a 120 min lead time. ...
From Table 1 , we notice that optical flow method achieves the best score when the lead time is 30 min, which shows its great advantage in short-term forecasting. ...
doi:10.5194/gmd-14-4019-2021
fatcat:n2xy3qcrzjbg5buffxchvosfwm
Spatiotemporal deep learning model for citywide air pollution interpolation and prediction
[article]
2019
arXiv
pre-print
In this paper, we propose the usage of Convolutional Long Short-Term Memory (ConvLSTM) model , a combination of Convolutional Neural Networks and Long Short-Term Memory, which automatically manipulates ...
Collecting as many of them could help us to forecast air pollution better. ...
Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) models CNN is one of the most successful Deep Learning algorithms, especially in image classification, object detection. ...
arXiv:1911.12919v1
fatcat:tjp3qmm3kbfnddny4s44wa3nhq
Approximation of regression-based fault minimization for network traffic
2020
TELKOMNIKA (Telecommunication Computing Electronics and Control)
The network traffic is computed from the traffic load (data and multimedia) of the computer network nodes via the Internet. ...
This research associates three distinct approaches for computer network traffic prediction. ...
The non-linear data analysis based on echo state network to forecast the data traffic is presented in [21] . ...
doi:10.12928/telkomnika.v18i4.13192
fatcat:24hpbc6fgjfylinga2ylrteaxa
Prediction of Tourist Flow Based on Deep Belief Network and Echo State Network
2019
Revue d'intelligence artificielle : Revue des Sciences et Technologies de l'Information
Next, the echo state network (ESN) was effectively fused with the DBN. The ESN was placed at the top layer of the tourist flow prediction model, serving as the logic regression layer. ...
The artificial neural network (ANN) has been widely adopted to predict nonlinear time series, but its shallow structure cannot effectively learn the features of high-dimensional tourist flow data. ...
The ESN boasts a very useful function called the short-term memory, because the numerous sparsely connected neurons in the reservoir can record the state of the network before operation. ...
doi:10.18280/ria.330403
fatcat:gp4lueewwzh7zdo6opg4v6utli
Congestion Prediction in Internet of Things Network using Temporal Convolutional Network A Centralized Approach
2022
Defence Science Journal
Hence, the network traffic flow estimation is important in IoT networks to predict congestion. ...
The unprecedented ballooning of network traffic flow, specifically, Internet of Things (IoT) network traffic, has big stressed of congestion on todays Internet. ...
Recurrent Neural networks (RNN) and Long Short Term Memory (LSTM) are the most common deep learning methods to analyze time-series data. ...
doi:10.14429/dsj.72.17447
fatcat:hy4mauznqrdcjatmr5euiwwc5q
« Previous
Showing results 1 — 15 out of 1,016 results