Hybrid of deep recurrent network and long short term memory for rear-end collision detection in fog based internet of vehicles

Almutairi, Mubarak; Almutairi, Khalid; Chiroma, Haruna

doi:10.1016/j.eswa.2022.119033

Cited by 16 publications

(7 citation statements)

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Drawing on the attention mechanism of the human brain, the model is focused on more important feature information, and a larger weight ratio is assigned to it during model training. For relatively unimportant information, smaller weights are assigned to reduce sensitivity to secondary information, thereby improving the models data processing ability when the models computing power is limited 29 . And in LSTM, attention mechanism weighting based on different features in temporal information can improve the correlation of neural network predictions.…”

Section: Methodsmentioning

confidence: 99%

See 1 more Smart Citation

PM2.5 concentration prediction based on EEMD-ALSTM

Liu,

Ji,

Wang

2024

Sci Rep

View full text Add to dashboard Cite

The concentration prediction of PM2.5 plays a vital role in controlling the air and improving the environment. This paper proposes a prediction model (namely EEMD-ALSTM) based on Ensemble Empirical Mode Decomposition (EEMD), Attention Mechanism and Long Short-Term Memory network (LSTM). Through the combination of decomposition and LSTM, attention mechanism is introduced to realize the prediction of PM2.5 concentration. The advantage of EEMD-ALSTM model is that it decomposes and combines the original data using the method of ensemble empirical mode decomposition, reduces the high nonlinearity of the original data, and Specially reintroduction the attention mechanism, which enhances the extraction and retention of data features by the model. Through experimental comparison, it was found that the EEMD-ALSTM model reduced its MAE and RMSE by about 15% while maintaining the same R2 correlation coefficient, and the stability of the model in the prediction process was also improved significantly.

show abstract

Section: Methodsmentioning

confidence: 99%

“…3. www.nature.com/scientificreports/ data processing ability when the models computing power is limited 29 . And in LSTM, attention mechanism weighting based on different features in temporal information can improve the correlation of neural network predictions.…”

Section: Methodsmentioning

confidence: 99%

PM2.5 concentration prediction based on EEMD-ALSTM

Liu,

Ji,

Wang

2024

Sci Rep

View full text Add to dashboard Cite

show abstract

“…Collision detection is also called intersection test or contact test [7][8], the usual way of detection is to find out the intersecting objects by constructing the geometric mechanism of the model [9][10], due to the complexity of the shape of the parts involved, in order to do the collision detection more accurately, in this paper, we will select the AABB bounding box, enclosing sphere, and the capsule body bounding box as the geometric structure body. Taking the capsule body as an example, the column region is represented as shown in equation ( 1):…”

Section: Bounding Box Selectionmentioning

confidence: 99%

Design and experimentation of virtual assembly system based on candy packing machine

Xiao,

Yan,

Dong

2024

Fourth International Conference on Mechanical Engineering, Intelligent Manufacturing, and Automation Technology (MEMAT 2023)

View full text Add to dashboard Cite

Aiming at the complexity of the assembly process of the candy pushing mechanism of the BZ350 candy packaging machine and other problems, this paper develops a virtual assembly system based on the BZ350 candy packaging machine. Through SolidWorks to establish a three-dimensional model, with Yixinghe engine and Visual Studio as the system development environment, using the augmented reality device HTC VIVE rich means of human-computer interaction, to realize a set of manual assembly of the virtual assembly system. The experiment shows that: the virtual assembly system reproduces the assembly process and assembly path of the BZ350 candy packaging machine, scores the assembly results as well as saves them, and the time required to complete an assembly experiment of twisted parts is about 9 minutes. The system has good immersion and interactivity, which effectively improves the quality and efficiency of product assembly, and the practical application effect is remarkable, providing users with an intuitive sense of the scene and a new product design mode.

show abstract

“…LSTM is meant to solve the challenges faced by RNNs with the help of gates that manage the flow of sequences at the current state and output of the current sequence [49]. The idea of LSTM is that it maintains the state of the memory for a long time due to the The mathematical description of an ANN can be understood by Equation (1) [46].…”

Section: Basic Concepts Of the Algorithms Used In This Studymentioning

confidence: 99%

“…Figure 2 shows a representation of the LSTM model and its mathematical formulation can be found in [52]. LSTM has advantages over other deep learning algorithms: it learns data behavior better than RNNs from any predetermined value [49] and generally requires a minimum number of hyperparameters for fine tuning [53].…”

Section: Basic Concepts Of the Algorithms Used In This Studymentioning

confidence: 99%

Comparative Analysis of the Implementation of Support Vector Machines and Long Short-Term Memory Artificial Neural Networks in Municipal Solid Waste Management Models in Megacities

Meza

Yepes

Rodrigo-Ilarri

et al. 2023

IJERPH

View full text Add to dashboard Cite

The development of methodologies to support decision-making in municipal solid waste (MSW) management processes is of great interest for municipal administrations. Artificial intelligence (AI) techniques provide multiple tools for designing algorithms to objectively analyze data while creating highly precise models. Support vector machines and neuronal networks are formed by AI applications offering optimization solutions at different managing stages. In this paper, an implementation and comparison of the results obtained by two AI methods on a solid waste management problem is shown. Support vector machine (SVM) and long short-term memory (LSTM) network techniques have been used. The implementation of LSTM took into account different configurations, temporal filtering and annual calculations of solid waste collection periods. Results show that the SVM method properly fits selected data and yields consistent regression curves, even with very limited training data, leading to more accurate results than those obtained by the LSTM method.

show abstract

Hybrid of deep recurrent network and long short term memory for rear-end collision detection in fog based internet of vehicles

Cited by 16 publications

References 25 publications

PM2.5 concentration prediction based on EEMD-ALSTM

PM2.5 concentration prediction based on EEMD-ALSTM

Design and experimentation of virtual assembly system based on candy packing machine

Comparative Analysis of the Implementation of Support Vector Machines and Long Short-Term Memory Artificial Neural Networks in Municipal Solid Waste Management Models in Megacities

Contact Info

Product

Resources

About