Trajectory prediction based on long short-term memory network and Kalman filter using hurricanes as an example

Qin, Wanting; Tang, Jun; Lu, Cong; Lao, Songyang

doi:10.1007/s10596-021-10037-2

Cited by 16 publications

(8 citation statements)

References 37 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…rough the training of historical trajectory data, the trajectory prediction model is obtained, so that early warning can be achieved [1,2]. In terms of health care, the use of an LSTM network to independently detect the contraction curve of an ECG or EMG signal, based on the predicted signal, provides a powerful assistant for medical staff to quickly diagnose and help patients recover [3][4][5].…”

Section: Introductionmentioning

confidence: 99%

An Algorithm for Time Prediction Signal Interference Detection Based on the LSTM-SVM Model

Xiao

Song

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Interference detection is an important part of the electronic defense system. It is difficult to detect interference with the traditional method of extracting characteristic parameters for interference generated at the same frequency as the original signal. Aiming at this special time-frequency overlapping interference signal, this paper proposes an interference detection algorithm based on the long short-term memory-support vector machines (LSTM-SVM) model. LSTM is used for the time series prediction of the received signal. The difference between the predicted signal and the received signal is used as the feature sample, and the SVM algorithm is used to classify the feature samples to obtain the recognition rate of whether the sample has interference. The LSTM-SVM model is compared with the gate recurrent unit-support vector machines (GRU-SVM) model, and the comparison results are visualized using a confusion matrix. The simulation results show that this LSTM-SVM model algorithm cannot only detect the existence of the interference signal but also can determine the specific position of the interference signal in the received waveform, and the detection performance is better than the GRU-SVM model.

show abstract

Section: Introductionmentioning

confidence: 99%

An Algorithm for Time Prediction Signal Interference Detection Based on the LSTM-SVM Model

Xiao

Song

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

show abstract

“…Using deep learning technology, a deep multimodal fusion and multitasking trajectory prediction model is proposed to predict the position of the typhoon [30].…”

Section: Deep Multimodal Fusion and Multitasking Trajectory Predictio...mentioning

confidence: 99%

A Deep Multimodal Fusion and Multitasking Trajectory Prediction Model for Typhoon Trajectory Prediction to Reduce Flight Scheduling Cancellation

Tang,

Qin,

Pan

et al. 2024

J. of Syst. Eng. Electron.

View full text Add to dashboard Cite

Natural events have had a significant impact on overall flight activity, and the aviation industry plays a vital role in helping society cope with the impact of these events. As one of the most impactful weather typhoon seasons appears and continues, airlines operating in threatened areas and passengers having travel plans during this time period will pay close attention to the development of tropical storms. This paper proposes a deep multimodal fusion and multitasking trajectory prediction model that can improve the reliability of typhoon trajectory prediction and reduce the quantity of flight scheduling cancellation. The deep multimodal fusion module is formed by deep fusion of the feature output by multiple submodal fusion modules, and the multitask generation module uses longitude and latitude as two related tasks for simultaneous prediction. With more dependable data accuracy, problems can be analysed rapidly and more efficiently, enabling better decision-making with a proactive versus reactive posture. When multiple modalities coexist, features can be extracted from them simultaneously to supplement each other's information. An actual case study, the typhoon Lichma that swept China in 2019, has demonstrated that the algorithm can effectively reduce the number of unnecessary flight cancellations compared to existing flight scheduling and assist the new generation of flight scheduling systems under extreme weather.

show abstract

“…Based on the findings in this paper, it is recommended that the deep learning models be applied in other jurisdictions for location prediction problems. The authors recommends combined algorithms be applied to trajectory datasets and the best selected as followed in this study instead of methods used in the works of [15], [17], [18], and [19] which applied only LSTM; [16] that applied only traditional RNNs, [23] that applied a hybrid architecture of CNN and LSTM; [22] applied BiLSTM ; [24] which adopted only the deep neural network (i.e., multilayer perceptron (MLP); and [7] that applied combined kNN and LSTM models for geographical location prediction. The authors also recommends the deep learning algorithms for geographical location prediction problems of not only Covid-19 patients but all other pandemic disease situations around the globe.…”

Section: Independent Variablesmentioning

confidence: 99%

“…To this end, Machine Learning (ML) approach was considered by researchers as a solution to this challenge. Authors such as [1], [15][16][17][18][19][20][21][22], [7] have studied and applied ML models in different ways for predicting geographical locations of moving objects. ML models are more efficient and effective in terms of accuracy, time saving, minimal use of computer resources, and so on.…”

Section: Related Workmentioning

confidence: 99%

Deep Learning Algorithms for predicting the geographical locations of Pandemic Disease Patients from Global Positioning System (GPS) Trajectory Datasets

Ugwoke

Udanor

Bakpo

2023

Preprint

View full text Add to dashboard Cite

Background and aim:The successful isolation of the Covid-19 virus in Wuhan, China in December 2019 provided empirical/scientific proof of the existence of the Covid 19 virus and marked the beginning of a pandemic of great proportions. Although localized and moderate at inception, the Covid-19 pandemic has proceeded to overwhelm the health authorities in several countries of the world. Concerted efforts to monitor the spread of the virus had been undertaken since the advent of the Covid-19 pandemic. The attempt to flatten the curve of the Covid-19 pandemic initially relied on contact tracing of persons who made contacts with infected persons. Presently, owing to the dynamics of the pandemic, scientists appear more preoccupied with the higher task of geographical location prediction of pandemic disease patients. Accordingly, the aim of this study is to carry out a comparative analysis of six deep learning algorithms for predicting the geographical locations of Covid-19 patients from Big GPS trajectory datasets. Method: The methodology for this study, proposes to design and apply selected deep learning algorithms for predicting the location of infected Covid-19 patients under monitoring. Among the deep learning algorithms include Recurrent Neural networks (RNN), Long-Short Term Memory (LSTM), Bidirectional LSTM (BiLSTM), Convolutional Neural Networks (CNN), Gated Recurrent Unit (GRU), Multilayer perceptron (MLP). The distinctive quality of the models is efficiency and effectiveness with regards to time saving, minimal use of computer resources, smart design, and development. Result: The result of this study showed that with application of the above mentioned deep learning models, it is possible to predict the location of infected Covid-19 patients. Thus, the predictive ability of these models is not in doubt. The GRU algorithm outperformed the other algorithms (i.e., RNN, LSTM, BiLSTM, CNN, and MLP) based on Key Performance Indicators (KPIs) metrics applied such as Mean Absolute Error (MAE), Mean Squared Error (MSE), Mean Absolute Percentage Error (MAPE), and Root Mean Squared Logarithmic Error (RMSLE) using uniform geographical location data. The result further revealed that location prediction of Covid-19 patients is more optimally executed using the deep learning models. Based on the findings in this paper, it is recommended that the deep learning models be applied in other jurisdictions for location prediction problems. Conclusion: The result of this study recommends the deep learning models for location prediction problems of not only Covid-19 patients but all other pandemic disease situations around the globe.

show abstract

Trajectory prediction based on long short-term memory network and Kalman filter using hurricanes as an example

Cited by 16 publications

References 37 publications

An Algorithm for Time Prediction Signal Interference Detection Based on the LSTM-SVM Model

An Algorithm for Time Prediction Signal Interference Detection Based on the LSTM-SVM Model

A Deep Multimodal Fusion and Multitasking Trajectory Prediction Model for Typhoon Trajectory Prediction to Reduce Flight Scheduling Cancellation

Deep Learning Algorithms for predicting the geographical locations of Pandemic Disease Patients from Global Positioning System (GPS) Trajectory Datasets

Contact Info

Product

Resources

About