A Hybrid Method for Traffic Incident Detection Using Random Forest-Recursive Feature Elimination and Long Short-Term Memory Network With Bayesian Optimization Algorithm

Shang, Qiang; Feng, Linlin; Gao, Song

doi:10.1109/access.2020.3047340

Cited by 22 publications

(11 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…[27] to detect different types of early-stage cancers through critical lncRNAs proposes a next-generation deep learning algorithm Concrete Autoencoder (CAE) comparing its results with alternative methods such as LASSO, RF, and SVM-RFE, indicating that obtained an accuracy of 93%. [28] proposes a hybrid method consisting of a random forest recursive feature elimination algorithm (RF-RFE), a long and short-term memory (LSTM), and a Bayesian optimization algorithm, for the automatic detection of incidents in all fields of intelligent transport systems, achieving an accuracy of 98.07%. To validate the learning styles [29] proposes a new approach using machine learning techniques and eye-tracking using three classification algorithms: SVM, Naive Bayes, and Logistic Regression, but previously using SVM-RFE as a feature selection method, indicating that achieved the best results with Naive Bayes and SVM-RFE with an accuracy of 71%.…”

Section: Description and Analysis Of The Resultsmentioning

confidence: 99%

Selection of Characteristics by Hybrid Method: RFE, Ridge, Lasso, and Bayesian for the Power Forecast for a Photovoltaic System

et al. 2021

View full text Add to dashboard Cite

Currently, the generation of alternative energy from solar radiation with photovoltaic systems is growing, its efficiency depends on internal variables such as powers, voltages, currents; as well as external variables such as temperatures, irradiance, and load. To maximize performance, this research focused on the application of regularization techniques in a multiparametric linear regression model to predict the active power levels of a photovoltaic system from 14 variables that model the system under study. These variables affect the prediction to some degree, but some of them do not have so much preponderance in the final forecast, so it is convenient to eliminate them so that the processing cost and time are reduced. For this, we propose a hybrid selection method: first we apply the elimination of Recursive Feature Elimination (RFE) within the selection of subsets and then to the obtained results we apply the following contraction regularization methods: Lasso, Ridge and Bayesian Ridge; then the results were validated demonstrating linearity, normality of the error terms, without autocorrelation and homoscedasticity. All four prediction models had an accuracy greater than 99.97%. Training time was reduced by 71% and 36% for RFE-Ridge and RFE-OLS respectively. The variables eliminated with RFE were Total Energy, Daily Energy, and Irradiance, while the variable eliminated by Lasso was: "Frequency". In all cases we see that the root mean square errors were reduced for RFE. Lasso by 0.15% while for RFE-Bayesian Ridge by 0.06%.

show abstract

Section: Description and Analysis Of The Resultsmentioning

confidence: 99%

Selection of Characteristics by Hybrid Method: RFE, Ridge, Lasso, and Bayesian for the Power Forecast for a Photovoltaic System

et al. 2021

View full text Add to dashboard Cite

show abstract

“…Experiments are conducted using real data. Compared with several advanced AID methods, this method has achieved good performance in almost all evaluation indexes [23].…”

Section: Machine Learningmentioning

confidence: 99%

“…For Problem 2: Previous algorithms only rely on three traffic parameters of traffic volume, speed and occupancy to study, and then there are algorithms to combine the three traffic parameters to get new variables, such as California algorithm. Shang [23] and Jiang [22] added the prediction variables to the initial variable set. Li fully considered the real-time nature of traffic incident, and established a relatively comprehensive initial variable set with the traffic parameters five minutes before the incident as new variables [21].…”

Section: Ensemble Learningmentioning

confidence: 99%

Automated Traffic Incident Detection: Coping With Imbalanced and Small Datasets

Xie

Shang

2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

Automatic incident detection (AID) has always been one of the focus issues in the field of transportation. However, due to the contingency and randomness of traffic incident, traffic incident samples are scarce and far less than non-incident samples. Therefore, unlike other scenarios using largescale deep networks, traffic incident detection tackle at small and imbalanced sample size. Imbalanced, small sample data sets, inappropriate and incomplete initial variable sets make the AID model insensitive to incident samples, resulting in unsatisfactory model performance (low detection rate or high false alarm rate). Therefore, a hybrid AID method (SASYNO-RF-RSKNN) is proposed using self-adaptive synthetic oversampling, random forest and random subspace k nearest neighbor. First, the spatial-temporal and real-time characteristics of traffic stream are used for the selection of appropriate initial variables to construct a relatively complete set of initial variables. Second, the SASYNO oversampling method is used to expand the original imbalanced sample database, so that the number of minority class samples is consistent with the number of most class samples. Then, feature variables are selected from the initial variables using the RF algorithm. Finally, the RSKNN ensemble algorithm with feature variables as input is employed to detect traffic incident. In addition, six indexes are used to evaluate model performance, including accuracy (ACC), false alarm rate (FAR), detection rate (DR), precision, Matthews correlation coefficient (MCC) and F1-score. Simultaneously, we also designed horizontal and vertical contrast experiments, and the experimental results show that SASYNO-RF-RSKNN model has superior performance. It is worth mentioning that experiments are implemented on two real-world datasets. Most indexes of the proposed model are the best compared with other five excellent machine learning algorithms. On the whole, the proposed model has a dependable and high-performance for traffic incident detection.

show abstract

“…Te machine learning-based approaches use encrypted trafc statistical features to build models and summarize trafc features to distinguish trafc categories. Traditional machine learning algorithms include C4.5 decision tree (DT) [5], Naive Bayes (NB) [6], K-means [7], support vector machine (SVM) [8], and random forest (RF) [9]. Approaches based on traditional machine learning [10][11][12] make up for rule-based approaches' defciencies and have greatly improved classifcation accuracy.…”

Section: Malicious Encrypted Trafc Detectionmentioning

confidence: 99%

A Few-Shot Malicious Encrypted Traffic Detection Approach Based on Model-Agnostic Meta-Learning

Wang

et al. 2023

Security and Communication Networks

View full text Add to dashboard Cite

Existing malicious encrypted traffic detection approaches need to be trained with many samples to achieve effective detection of a specified class of encrypted traffic data. With the rapid development of encryption technology, various new types of encrypted traffic are emerging and difficult to label. Therefore, it is an urgent problem to train a deep learning model using only a small number of samples to detect new classes of malicious encrypted traffic. This paper proposes a few-shot malicious encrypted traffic detection (FMETD) approach based on model-agnostic meta-learning (MAML), integrating feature selection and classification into an end-to-end framework. The FMETD approach first converts the raw traffic data into two-dimensional grayscale images. Then, FMETD trains a deep learning model (2D-CNN) using the MAML, which is to learn an optimal set of model initialization parameters for the model from a set of classification tasks consisting of grayscale images. The model with this set of parameters can detect new classes of maliciously encrypted traffic data efficiently with a few samples by a few iterations steps. The experimental results show that the FMETD approach has 99.8% accuracy for two-class classification encrypted traffic and 98.5% average accuracy for multi-classification. When the number of grayscale images of each class in the support set and validation set is reduced to 20, the accuracy of our approach to multi-class classification is 97.9% for new classes of traffic.

show abstract

A Hybrid Method for Traffic Incident Detection Using Random Forest-Recursive Feature Elimination and Long Short-Term Memory Network With Bayesian Optimization Algorithm

Cited by 22 publications

References 45 publications

Selection of Characteristics by Hybrid Method: RFE, Ridge, Lasso, and Bayesian for the Power Forecast for a Photovoltaic System

Selection of Characteristics by Hybrid Method: RFE, Ridge, Lasso, and Bayesian for the Power Forecast for a Photovoltaic System

Automated Traffic Incident Detection: Coping With Imbalanced and Small Datasets

A Few-Shot Malicious Encrypted Traffic Detection Approach Based on Model-Agnostic Meta-Learning

Contact Info

Product

Resources

About