Traffic Flow Prediction Based on Stack AutoEncoder and Long Short-Term Memory Network

Tian, Yu; Wei, Chenchen; Xu, Dongwei

doi:10.1109/auteee50969.2020.9315723

Cited by 6 publications

(8 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The reduction in the number of neurons in each layer starts from the input layer and is followed by the mirroring of the layers at the center, known as the bottleneck, to build the autoencoder’s decoding section. An AE aims to constrict the input into a lower-dimensional code and reconstruct the new representation’s output to obtain the initial picture [ 8 , 30 , 31 ]. Like the multilayer perceptron, the AE framework consists of NN with one or two hidden layers.…”

Section: Methodsmentioning

confidence: 99%

“…Compressing the input vectors into lower dimensions increases the learning efficiency [ 7 ]. AE’s input and output layers should contain the same number of neurons [ 8 , 9 ] because the AE aims to initialize the latent layer parameters that will reconstruct the multidimensional input data [ 31 ].…”

Section: Methodsmentioning

confidence: 99%

“…The authors in [ 8 ] proposed using an improved stacked autoencoder (SAE) model based on a deep learning network to refine traffic flow prediction performed by the Intelligent Transport System (ITS). This model improved the traffic flow forecasting accuracy to easily control the traffic with high-dynamic change and various noises in the real world.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Enhancing Safety and Efficiency in Firefighting Operations via Deep Learning and Temperature Forecasting Modeling in Autonomous Unit

Ishola

Valles

2023

Sensors

View full text Add to dashboard Cite

Firefighters face numerous challenges when entering burning structures to rescue trapped victims, assess the conditions of a residential structure, and extinguish the fire as quickly as possible. These challenges include extreme temperatures, smoke, toxic gases, explosions, and falling objects, which can hinder their efficiency and pose risks to their safety. Accurate information and data about the burning site can help firefighters make informed decisions about their duties and determine when it is safe to enter and evacuate, reducing the likelihood of casualties. This research presents unsupervised deep learning (DL) to classify the danger levels at a burning site and an autoregressive integrated moving average (ARIMA) prediction model to forecast temperature changes using the extrapolation of a random forest regressor. The DL classifier algorithms provide the chief firefighter with an awareness of the danger levels in the burning compartment. The prediction models forecast the rise in temperature from a height ranging from 0.6 m to 2.6 m and the changes in temperature over time at an altitude of 2.6 m. Predicting the temperature at this altitude is critical as the temperature increases faster with height, and elevated temperatures can weaken the building’s structural material. We also investigated a new classification method using an unsupervised DL autoencoder artificial neural network (AE-ANN). The prediction data analytical approach included using the autoregressive integrated moving average (ARIMA) with random forest regression implementation. The proposed AE-ANN model, with an accuracy score of 0.869, did not perform as well compared to previous work, with an accuracy of 0.989, at achieving high accuracy scores for the classification task using the same dataset. However, the random forest regressor and our ARIMA models are analyzed and evaluated in this work, while other research has not utilized this dataset, even though it is open-sourced. However, the ARIMA model demonstrated remarkable predictions of the trends of temperature changes in a burning site. The proposed research aims to classify fire sites into dangerous levels and predict temperature progression using deep learning and predictive modeling techniques. This research’s main contribution is using a random forest regressor and autoregressive integrated moving average models to predict temperature trends in burning sites. This research demonstrates the potential of using deep learning and predictive modeling to enhance firefighter safety and decision-making processes.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Enhancing Safety and Efficiency in Firefighting Operations via Deep Learning and Temperature Forecasting Modeling in Autonomous Unit

Ishola

Valles

2023

Sensors

View full text Add to dashboard Cite

show abstract

“…An LSTM, equipped with memory cells and gating functions, models longterm dependencies and resolves vanishing gradients, offering significant advantages in time series prediction [10]. It has been widely applied in fields such as stock prediction in financial markets and short-term traffic flow prediction [11][12][13][14]. Nevertheless, standard LSTM neural networks encounter problems in time series prediction, such as a high time consumption and complexity [15].…”

Section: Related Workmentioning

confidence: 99%

Prediction of Parking Space Availability Using Improved MAT-LSTM Network

Zhang,

Shang,

Yan

et al. 2024

IJGI

View full text Add to dashboard Cite

The prediction of parking space availability plays a crucial role in information systems providing parking guidance. However, controversy persists regarding the efficiency and accuracy of mainstream time series prediction methods, such as convolutional neural networks (CNNs) and recurrent neural networks (RNNs). In this study, a comparison was made between a temporal convolutional network (TCN) based on CNNs and a long short-term memory (LSTM) network based on RNNs to determine an appropriate baseline for predicting parking space availability. Subsequently, a multi-head attention (MAT) mechanism was incorporated into an LSTM network, attempting to improve its accuracy. Experiments were conducted on three real and two synthetic datasets. The results indicated that the TCN achieved the fastest convergence, whereas the MAT-LSTM method provided the highest average accuracy, namely 0.0330 and 1.102 × 10−6, on the real and synthetic datasets, respectively. Furthermore, the improved MAT-LSTM model accomplished an increase of up to 48% in accuracy compared with the classic LSTM model. Consequently, we concluded that RNN-based networks are better suited for predicting long-time series. In particular, the MAT-LSTM method proposed in this study holds higher application value for predicting parking space availability with a higher accuracy.

show abstract

“…In [181], the authors used LSTM to build a short-term traffic flow prediction model based on the driving data of private cars and minibusses. In [182], the LSTM is not only used to extract time-series information but also is combined with stack auto-encoder to extract spatial information in traffic data, thereby achieving more accurate traffic flow prediction.…”

Section: ) Intelligent Transportation Systems (Its)mentioning

confidence: 99%

Compacting Deep Neural Networks for Internet of Things: Methods and Applications

Zhang

Ying

Dai

et al. 2021

IEEE Internet Things J.

View full text Add to dashboard Cite

Deep Neural Networks (DNNs) have shown great success in completing complex tasks. However, DNNs inevitably bring high computational cost and storage consumption due to the complexity of hierarchical structures, thereby hindering their wide deployment in Internet-of-Things (IoT) devices, which have limited computational capability and storage capacity. Therefore, it is a necessity to investigate the technologies to compact DNNs. Despite tremendous advances in compacting DNNs, few surveys summarize compacting-DNNs technologies, especially for IoT applications. Hence, this paper presents a comprehensive study on compacting-DNNs technologies. We categorize compacting-DNNs technologies into three major types: 1) network model compression, 2) Knowledge Distillation (KD), 3) modification of network structures. We also elaborate on the diversity of these approaches and make side-by-side comparisons. Moreover, we discuss the applications of compacted DNNs in various IoT applications and outline future directions.

show abstract

Traffic Flow Prediction Based on Stack AutoEncoder and Long Short-Term Memory Network

Cited by 6 publications

References 11 publications

Enhancing Safety and Efficiency in Firefighting Operations via Deep Learning and Temperature Forecasting Modeling in Autonomous Unit

Enhancing Safety and Efficiency in Firefighting Operations via Deep Learning and Temperature Forecasting Modeling in Autonomous Unit

Prediction of Parking Space Availability Using Improved MAT-LSTM Network

Compacting Deep Neural Networks for Internet of Things: Methods and Applications

Contact Info

Product

Resources

About