Kernel PCA for road traffic data non‐linear feature extraction

Wang, Yongdong; Xu, Dongwei; Peng, Peng; Liu, Yi; Zhang, Guijun; Xue-mei, Xiao

doi:10.1049/iet-its.2018.5215

“…PCA is a widely used data-driven method that performs well on data feature extraction tasks and is often applied for process monitoring in industrial practice [ 31 , 32 , 33 , 34 , 35 ]. However, this method often ignores the local structure underlying data, resulting in the loss of potential information from such structures.…”

Section: Process Monitoring Based On Dlppcamentioning

confidence: 99%

Fault Monitoring Based on the VLSW-MADF Test and DLPPCA for Multimodal Processes

Wang

¹

,

Wang

²

,

Tong

³

et al. 2023

Sensors

View full text Add to dashboard Cite

Actual industrial processes often exhibit multimodal characteristics, and their data exhibit complex features, such as being dynamic, nonlinear, multimodal, and strongly coupled. Although many modeling approaches for process fault monitoring have been proposed in academia, due to the complexity of industrial data, challenges remain. Based on the concept of multimodal modeling, this paper proposes a multimodal process monitoring method based on the variable-length sliding window-mean augmented Dickey–Fuller (VLSW-MADF) test and dynamic locality-preserving principal component analysis (DLPPCA). In the offline stage, considering the fluctuation characteristics of data, the trend variables of data are extracted and input into VLSW-MADF for modal identification, and different modalities are modeled separately using DLPPCA. In the online monitoring phase, the previous moment’s historical modal information is fully utilized, and modal identification is performed only when necessary to reduce computational cost. Finally, the proposed method is validated to be accurate and effective for modal identification, modeling, and online monitoring of multimodal processes in TE simulation and actual plant data. The proposed method improves the fault detection rate of multimodal process fault monitoring by about 14% compared to the classical DPCA method.

show abstract

“…Therefore, the proposed GDFE-DRPNL framework employs the Gaussian distributive feature embedding technique to reduce dimension during the indoor floor-planning process. For effective feature extraction in the proposed work and to enhance the performance of the Gaussian distribution function, the Kernel Principal Component Analysis concept [17] is applied.…”

Section: Gaussian Distributive Feature Embedding Technique (Dimensionality Reduction)mentioning

confidence: 99%

A Machine-Learning Framework to Improve Wi-Fi Based Indoorpositioning

Pichaimani¹,

Manjula²

2022

Intelligent Automation &Amp; Soft Computing

View full text Add to dashboard Cite

The indoor positioning system comprises portable wireless devices that aid in finding the location of people or objects within the buildings. Identification of the items is through the capacity level of the signal received from various access points (i.e., Wi-Fi routers). The positioning of the devices utilizing some algorithms has drawn more attention from the researchers. Yet, the designed algorithm still has problems for accurate floor planning. So, the accuracy of position estimation with minimum error is made possible by introducing Gaussian Distributive Feature Embedding based Deep Recurrent Perceptive Neural Learning (GDFE-DRPNL), a novel framework. Novel features from the dataset are through two processing stages dimensionality reduction and position estimation. Initially, the essential elements selection using the Gaussian Distributive Feature Embedding technique is the novel framework. The feature reduction process aims to reduce the time consumption and overhead for estimating the location of various devices. In the next stage, employ Deep Recurrent multilayer Perceptive Neural Learning to evaluate the device position with dimensionality reduced features. The proposed Deep-learning approach accurately learns the quality and the signal strength data with multiple layers by applying Deming Regressive Trilateral Positioning Model. As a result, the GDFE-DRPNL framework increases the positioning accuracy and minimizes the error rate. The experimental assessments with various factors such as positioning accuracy minimized by 70% and 60%, computation time minimized by 45% and 55% as well as overhead by 11% and 23% compared with PFRL and two-dimensional localization algorithm. Through the experiment and after analyzing the data, verify that the proposed GDFE-DRPNL algorithm in this paper is better than the previous methods.

show abstract

“…Video images often have high dimensionality and contain complex and redundant information. To recognize the traffic states timely and effectively, attempts have been conducted to reduce the dimensionality of video images, thereby performing image pattern recognition based on the dimension-reduced data in [13]. Encoders, which are nonlinear and unsupervised neural network models that include an input layer, a hidden layer, and an output layer, can effectively reduce the dimensionality of video image data and realize image classification in [14].…”

Section: Introductionmentioning

confidence: 99%

Automatic Traffic State Recognition Based on Video Features Extracted by an Autoencoder

Cai

¹

,

Jing

²

,

Peng

³

et al. 2022

Mathematical Problems in Engineering

3

0

View full text Add to dashboard Cite

Video surveillance has become an important measure of urban traffic monitoring and control. However, due to the complex and diverse video scenes, traffic data extraction from original videos is a sophisticated and difficult task, and corresponding algorithms are of high complexity and calculation cost. To reduce the algorithm complexity and subsequent computation cost, this study proposed an autoencoder model which effectively reduces the video dimension by optimizing structural parameters; thus several traffic recognition models can conduct image processing work based on dimension-reduced videos. Firstly, an optimal autoencoder model A ∗ with five hidden layers was constructed. Then, it was combined with a linear classifier, support vector machine, deep neural network, DNN linear classification method, and the k-means clustering method; thus, five traffic state recognition models were constructed: A ∗ -Linear, A ∗ -SVM, A ∗ -DNN, A ∗ -DNN_Linear, and A ∗ -k-means. Train and test results show that the accuracy rate and recall rate of A ∗ -linear, A ∗ -SVM, A ∗ -DNN, and A ∗ -DNN_Linear were 94.5%–97.1%, and the F1 score was 94.4%–97.1%; besides, the accuracy rate, recall rate, and F1 score of A ∗ -k-means were all approximately 95%, which suggests that the combination of the autoencoder A ∗ and common classification or clustering methods achieve good recognition performance. Comparison was also implemented among the five models proposed above and four CNN-based models such as AlexNet, LeNet, GoogLeNet, and VGG16, which shows that the five proposed modes achieve F1 scores of 94.4%–97.1%, while the four CNN-based models achieve F1 scores of 16.7%–94%, indicating that the proposed light weight design methods outperform more complex CNN-based models in traffic state recognition.

show abstract

Kernel PCA for road traffic data non‐linear feature extraction

Cited by 11 publications

References 19 publications

Fault Monitoring Based on the VLSW-MADF Test and DLPPCA for Multimodal Processes

Fault Monitoring Based on the VLSW-MADF Test and DLPPCA for Multimodal Processes

A Machine-Learning Framework to Improve Wi-Fi Based Indoorpositioning

Automatic Traffic State Recognition Based on Video Features Extracted by an Autoencoder

Contact Info

Product

Resources

About