scholarly journals Joint Geoeffectiveness and Arrival Time Prediction of CMEs by a Unified Deep Learning Framework

2021 ◽  
Vol 13 (9) ◽  
pp. 1738
Author(s):  
Huiyuan Fu ◽  
Yuchao Zheng ◽  
Yudong Ye ◽  
Xueshang Feng ◽  
Chaoxu Liu ◽  
...  
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Arrival Time ◽  
Optical Observations ◽  
Feature Maps ◽  
Feature Map ◽  
Learning Framework ◽  
Time Prediction ◽  
Arrival Time Prediction ◽  
Better Than

Fast and accurate prediction of the geoeffectiveness of coronal mass ejections (CMEs) and the arrival time of the geoeffective CMEs is urgent, to reduce the harm caused by CMEs. In this paper, we present a new deep learning framework based on time series of satellites’ optical observations that can give both the geoeffectiveness and the arrival time prediction of the CME events. It is the first time combining these two demands in a unified deep learning framework with no requirement of manually feature selection and get results immediately. The only input of the deep learning framework is the time series images from synchronized solar white-light and EUV observations. Our framework first uses the deep residual network embedded with the attention mechanism to extract feature maps for each observation image, then fuses the feature map of each image by the feature map fusion module and determines the geoeffectiveness of CME events. For the geoeffective CME events, we further predict its arrival time by the deep residual regression network based on group convolution. In order to train and evaluate our proposed framework, we collect 2400 partial-/full-halo CME events and its corresponding images from 1996 to 2018. The F1 score and Accuracy of the geoeffectiveness prediction can reach 0.270% and 75.1%, respectively, and the mean absolute error of the arrival time prediction is only 5.8 h, which are both significantly better than well-known deep learning methods and can be comparable to, or even better than, the best performance of traditional methods.

scholarly journals INTEGRATION OF EXPONENTIAL SMOOTHING WITH STATE SPACE FORMULATION FOR BUS TRAVEL TIME AND ARRIVAL TIME PREDICTION

Transport ◽  
2015 ◽  
Vol 32 (4) ◽  
pp. 358-367 ◽  
Author(s):  
Selvaraj Vasantha Kumar ◽  
Krishna Chaitanya Dogiparthi ◽  
Lelitha Vanajakshi ◽  
Shankar Coimbatore Subramanian
Keyword(s):  
Time Series ◽  
State Space ◽  
Travel Time ◽  
Kalman Filtering ◽  
Arrival Time ◽  
Arima Models ◽  
Time Prediction ◽  
Space Formulation ◽  
Arrival Time Prediction ◽  
Bus Travel Time

In recent years, the problem of bus travel time prediction is becoming more important for applications such as informing passengers regarding the expected bus arrival time in order to make public transit more attractive to the urban commuters. One of the popular techniques reported for such prediction is the use of time series analysis. Most of the studies on the application of time series techniques for bus arrival time prediction used Box-Jenkins AutoRegressive Integrated Moving Average (ARIMA) models, which are presently not suited for real time implementation. This is mainly due to the necessity and dependence of ARIMA models on a time series modelling software to execute. Moreover, the ARIMA model building process is time consuming, making it difficult to use for real-time implementations. Alternatively, Exponential Smoothing (ES) methods can be used, as they are easy to understand and implement when compared to ARIMA models. The present study is an attempt in this direction, where the basic equation of ES is used, as the state equation with Kalman filtering to recursively update the travel time estimate as the new observation becomes available. The proposed algorithm of state space formulation of ES with Kalman filtering for bus travel time and arrival time prediction was field tested using 105 actual bus trips data along a particular bus route from Chennai, India. The results are promising and a comparison of the proposed algorithm with ES alone without state space formulation and Kalman filtering has also been performed. An information system based on a webpage for real-time display of bus arrival times has been designed and developed using the proposed algorithm.

Bus Arrival Time Modeling Based on Auckland Data

2019 ◽  
Vol 2673 (6) ◽  
pp. 1-9 ◽  
Author(s):  
Prakash Ranjitkar ◽  
Li-Sian Tey ◽  
Enakshi Chakravorty ◽  
Kirsten L. Hurley
Keyword(s):  
Time Series ◽  
Arrival Time ◽  
Gene Expression Programming ◽  
Time Prediction ◽  
Time Modeling ◽  
Regression Techniques ◽  
Artificial Neural ◽  
Arrival Time Prediction ◽  
Bus Arrival Time Prediction ◽  
Bus Travel Time

Inaccurate bus arrival time predictions are counterproductive to changing transport habits and promoting public transport use. This research sought to improve the bus passenger experience in terms of bus arrival time prediction by investigating various time series and regression-based techniques suitable for bus arrival time modeling. The models developed in the current study included: random walk with drift, multivariate linear regression, decision tree, artificial neural networks, and gene expression programming models. Historic automatic vehicle location and passenger flow data obtained for four bus routes spanning Auckland city, in both travel directions, were used as model inputs. Specifically, 10 independent variables were incorporated in the regression models, with distance between bus stops being the most significant predictor for bus travel time. Research results indicated that time series models outperformed regression techniques, with the time series artificial neural network being the most successful of the seven models developed. Moreover, the alternative models all performed significantly better than the prediction engine currently utilized by an Auckland bus company for arrival time prediction. However, these results require corroboration with manually collected field data, on account of the quality concerns afflicting the raw data reported by the transport company.

scholarly journals A Deep Learning-Based Approach for Train Arrival Time Prediction

2021 ◽  
pp. 213-222
Author(s):  
Bas Jacob Buijse ◽  
Vahideh Reshadat ◽  
Oscar Willem Enzing
Keyword(s):  
Deep Learning ◽  
Arrival Time ◽  
Time Prediction ◽  
Arrival Time Prediction

scholarly journals A Lightweight Fusion Distillation Network for Image Deblurring and Deraining

Sensors ◽  
2021 ◽  
Vol 21 (16) ◽  
pp. 5312
Author(s):  
Yanni Zhang ◽  
Yiming Liu ◽  
Qiang Li ◽  
Jianzhong Wang ◽  
Miao Qi ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Deblurring ◽  
Image Features ◽  
Image Feature ◽  
Model Complexity ◽  
Small Scale ◽  
Feature Maps ◽  
Learning Framework ◽  
Channel Information ◽  
Scale Spaces

Recently, deep learning-based image deblurring and deraining have been well developed. However, most of these methods fail to distill the useful features. What is more, exploiting the detailed image features in a deep learning framework always requires a mass of parameters, which inevitably makes the network suffer from a high computational burden. We propose a lightweight fusion distillation network (LFDN) for image deblurring and deraining to solve the above problems. The proposed LFDN is designed as an encoder–decoder architecture. In the encoding stage, the image feature is reduced to various small-scale spaces for multi-scale information extraction and fusion without much information loss. Then, a feature distillation normalization block is designed at the beginning of the decoding stage, which enables the network to distill and screen valuable channel information of feature maps continuously. Besides, an information fusion strategy between distillation modules and feature channels is also carried out by the attention mechanism. By fusing different information in the proposed approach, our network can achieve state-of-the-art image deblurring and deraining results with a smaller number of parameters and outperform the existing methods in model complexity.

scholarly journals ResBCDU-Net: A Deep Learning Framework for Lung CT Image Segmentation

Sensors ◽  
2021 ◽  
Vol 21 (1) ◽  
pp. 268
Author(s):  
Yeganeh Jalali ◽  
Mansoor Fateh ◽  
Mohsen Rezvani ◽  
Vahid Abolghasemi ◽  
Mohammad Hossein Anisi
Keyword(s):  
Image Segmentation ◽  
Deep Learning ◽  
Ct Images ◽  
Medical Image Segmentation ◽  
Great Success ◽  
Morphological Operations ◽  
Ct Image ◽  
Feature Maps ◽  
Learning Framework ◽  
Lung Ct

Lung CT image segmentation is a key process in many applications such as lung cancer detection. It is considered a challenging problem due to existing similar image densities in the pulmonary structures, different types of scanners, and scanning protocols. Most of the current semi-automatic segmentation methods rely on human factors therefore it might suffer from lack of accuracy. Another shortcoming of these methods is their high false-positive rate. In recent years, several approaches, based on a deep learning framework, have been effectively applied in medical image segmentation. Among existing deep neural networks, the U-Net has provided great success in this field. In this paper, we propose a deep neural network architecture to perform an automatic lung CT image segmentation process. In the proposed method, several extensive preprocessing techniques are applied to raw CT images. Then, ground truths corresponding to these images are extracted via some morphological operations and manual reforms. Finally, all the prepared images with the corresponding ground truth are fed into a modified U-Net in which the encoder is replaced with a pre-trained ResNet-34 network (referred to as Res BCDU-Net). In the architecture, we employ BConvLSTM (Bidirectional Convolutional Long Short-term Memory)as an advanced integrator module instead of simple traditional concatenators. This is to merge the extracted feature maps of the corresponding contracting path into the previous expansion of the up-convolutional layer. Finally, a densely connected convolutional layer is utilized for the contracting path. The results of our extensive experiments on lung CT images (LIDC-IDRI database) confirm the effectiveness of the proposed method where a dice coefficient index of 97.31% is achieved.

Sign in / Sign up

Export Citation Format

Share Document