Long Short-Term Memory Neural Network Applied to Train Dynamic Model and Speed Prediction

Li, Zhen; Tang, Tao; Gao, Chunhai

doi:10.3390/a12080173

Cited by 17 publications

(8 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Third, generally RNN-based models (i.e., BI-GRU, HA-GRU, and HARNN) have worse performance compared to the other ones. This is because an EHR is a long sequence, which easily gives rise to vanishing gradient problems with RNN-based models [22]. This also suggests that sequence information for words is not as important as it is in natural language models [39].…”

Section: Results and Analysis 51 Overall Performance (Rq1)mentioning

confidence: 99%

Coding Electronic Health Records with Adversarial Reinforcement Path Generation

Wang

Ren

Chen

et al. 2020

Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

Electronic Health Record (EHR) coding is the task of assigning one or more International Classification of Diseases (ICD) codes to every EHR. Most previous work either ignores the hierarchical nature of the ICD codes or only focuses on parent-child relations. Moreover, existing EHR coding methods predict ICD codes from the leaf level with the greatest ICD number and the most fine-grained categories, which makes it difficult for models to make correct decisions. In order to address these problems, we model EHR coding as a path generation task. For this approach, we need to address two main challenges: (1) How to model relations between EHR and ICD codes, and relations between ICD codes? (2) How to evaluate the quality of generated ICD paths in order to obtain a signal that can be used to supervise the learning? We propose a coarse-tofine ICD path generation framework, named Reinforcement Path Generation Network (RPGNet), that implements EHR coding with a Path Generator (PG) and a Path Discriminator (PD). We address challenge (1) by introducing a Path Message Passing (PMP) module in the PG to encode three types of relation: between EHRs and ICD codes, between parent-child ICD codes, and between sibling ICD codes. To address challenge (2), we propose a PD component that estimates the reward for each ICD code in a generated path. RPGNet is trained with Reinforcement Learning (RL) in an adversarial manner. Experiments on the MIMIC-III benchmark dataset show that RPGNet significantly outperforms state-of-the-art methods in terms of micro-averaged F1 and micro-averaged AUC. CCS CONCEPTS• Information systems → Content analysis and feature selection; • Applied computing → Health care information systems; • Computing methodologies → Adversarial learning; Reinforcement learning.

show abstract

Section: Results and Analysis 51 Overall Performance (Rq1)mentioning

confidence: 99%

Coding Electronic Health Records with Adversarial Reinforcement Path Generation

Wang

Ren

Chen

et al. 2020

Proceedings of the 43rd International ACM SIGIR Conference on Research and Development in Information Retrieval

View full text Add to dashboard Cite

show abstract

“…The abstract process of biological neurons can process information for activation functions. ANN is a linear element of non-linear relationship, has more complex logic, and has better performance in motion simulation and non-linear problems [20,21]. Calculate the MSE corresponding to each interval, denoted by…”

Section: B Optimization Of Lstmmentioning

confidence: 99%

Mathematical Model of Yield Forecast Based on Long and Short-Term Memory Image Neural Network

2024

View full text Add to dashboard Cite

Yield prediction has always been the focus of stock investors' attention in stock investment. This research uses the virtual stock scene constructed by VR technology to explore the mathematical model of return rate prediction. First, neural nodes, activation functions and output functions are designed under the LSTM framework, and a recurrent neural network that can handle long-term sequences is constructed. Use VR technology to simulate stock data and extract key frames from the image sequence. Aiming at the timing of key curve nodes, this study uses a long and short-term memory neural network that is good at processing time series data to classify curve trends, and realizes the identification of abnormal fluctuations in virtual scenes of stock images. Then, according to the existing probability control asset allocation theory, the index of investment allocation is adjusted from the entire time series to a dynamic time series. According to the stock price decomposition of EEMD, the EEMD-LSTM model is constructed to predict the stock market price. Use EEMD to decompose the original sequence to obtain IMF and trend items containing various timescale characteristics. Then, the LSTM neural network is used to predict and analyze each rate of return, and the analysis software Python is used to process and count the predicted results. At the same time, retrospective restrictions are regarded as riskier assets. Finally, the investment is made under conditions that do not allow shorting in the VR simulation scenario. The accuracy of the calculation is more than 70% except for the Shanghai and Shenzhen 300 Index reaching 66%. The research results show that in the case of different stock price forecasts, the prediction ability of LSTM neural network has been greatly improved compared with that of support vector machine, which fully reflects the advantages of LSTM in time series prediction.

show abstract

“…(1) Driving from high speed limit zone to low speed limit zone (2) Maintain constant speed at the next low speed limit…”

Section: Coast Interval X 1 •mentioning

confidence: 99%

“…With the popularization of the Automatic Train Operation (ATO) system, the automation of train operation has been achieved. However, the performance of the algorithm in ATO system is not good enough, and it can be further improved [2]. Inaccuracy and high energy consumption seriously affect the quality of train operation.…”

Section: Introductionmentioning

confidence: 99%

Energy-Efficient Speed Profile Optimization and Sliding Mode Speed Tracking for Metros

et al. 2020

View full text Add to dashboard Cite

Nowadays, most metro vehicles are equipped with an automatic train operation (ATO) system, and the speed control method, combining cruise speed planning and proportional-integral-derivative (PID) control, is widely used. The automation is achieved, and the energy-efficient can be improved. This paper presents an improved artificial bee colony algorithm for speed profile optimization with coast mode and an adaptive terminal sliding mode method for speed tracking. Specifically, a multi-objective optimization model is established, which considers energy consumption, comfortableness, and punctuality. Then, a novel artificial bee colony algorithm named regional reinforcement artificial bee colony (RR-ABC) is designed, to search the optimal speed profile with coast mode, in which some improvements are made to speed up convergence and to avoid local optimal solutions. For speed-tracking control, the adaptive terminal sliding mode controller (ATSMC) is used to improve the speed error, robustness, and energy saving. In addition, a disturbance observer (DOB) is designed to improve the anti-interference ability of the system and further improve the robustness and anti-disturbance, which are also conducive to speed error and energy saving. Finally, the line and train data of the Qingdao Metro Line 6 are used for simulation, which proves the effectiveness of the study. Specific to the energy saving rate, and compared with normal algorithms, RR-ABC with coast mode is approximately 9.55%, and ATSMC+DOB is 7.58%.

show abstract

Long Short-Term Memory Neural Network Applied to Train Dynamic Model and Speed Prediction

Cited by 17 publications

References 50 publications

Coding Electronic Health Records with Adversarial Reinforcement Path Generation

Coding Electronic Health Records with Adversarial Reinforcement Path Generation

Mathematical Model of Yield Forecast Based on Long and Short-Term Memory Image Neural Network

Energy-Efficient Speed Profile Optimization and Sliding Mode Speed Tracking for Metros

Contact Info

Product

Resources

About