Image encoding selection based on Pearson correlation coefficient for time series anomaly detection

Rahadian, Helmy; Bandong, Steven; Widyotriatmo, Augie; Joelianto, Endra

doi:10.1016/j.aej.2023.09.070

Cited by 31 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Common correlation methods, such as Pearson, Spearman, Kendall and maximal information coefficient (MIC), are widely used in data analysis [49][50][51][52][53][54][55]. Among these methods, MIC (Maximal Information Coefficient) offers several advantages, including universality, fairness and symmetry.…”

Section: Maximum Mutual Information Coefficient Methodsmentioning

confidence: 99%

Load Day-Ahead Automatic Generation Control Reserve Capacity Demand Prediction Based on the Attention-BiLSTM Network Model Optimized by Improved Whale Algorithm

Li,

Liang

et al. 2024

Energies

View full text Add to dashboard Cite

Load forecasting is a research hotspot in academia; in the context of new power systems, the prediction and determination of load reserve capacity is also important. In order to adapt to new forms of power systems, a day-ahead automatic generation control (AGC) reserve capacity demand prediction method based on the Fourier transform and the attention mechanism combined with a bidirectional long and short-term memory neural network model (Attention-BiLSTM) optimized by an improved whale optimization algorithm (IWOA) is proposed. Firstly, based on the response time, Fourier transform is used to refine the distinction between various types of load reserve demand, and the power of the AGC reserve band is calculated using Parseval’s theorem to obtain the reserve capacity demand sequence. The maximum mutual information coefficient method is used to explore the relevant influencing factors of the AGC reserve sequence concerning the data characteristics of the AGC reserve sequence. Then, the historical daily AGC reserve demand sequences with relevant features are input into the Attention-BiLSTM prediction model, and the improved whale algorithm is used to automatically find the optimal hyperparameters to obtain better prediction results. Finally, the arithmetic simulation results show that the model proposed in this paper has the best prediction performance with the upper (0.8810) and lower (0.6651) bounds of the coefficient of determination (R2) higher than the other models, and it has the smallest mean absolute percentage error (MAPE) and root mean square error (RMSE).

show abstract

Section: Maximum Mutual Information Coefficient Methodsmentioning

confidence: 99%

Load Day-Ahead Automatic Generation Control Reserve Capacity Demand Prediction Based on the Attention-BiLSTM Network Model Optimized by Improved Whale Algorithm

Li,

Liang

et al. 2024

Energies

View full text Add to dashboard Cite

show abstract

“…The Pearson correlation coefficient is defined as the covariance of two variables divided by the product of their standard deviations [19]. The formula is defined as follows:…”

Section: Pearson Correlation Analysismentioning

confidence: 99%

Development Characteristics and Reactivation Mechanism of a Large-Scale Ancient Landslide in Reservoir Area

Dai,

Jia,

Chen

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

The intricate geological conditions of reservoir banks render them highly susceptible to destabilization and damage from fluctuations in water levels. The study area, the Cheyipin section of the Huangdeng Hydroelectric Station, is characterized by numerous ancient landslides of varying scales and ages. In June 2019, during the reservoir filling process of the Huangdeng Hydroelectric Station, a large-scale reactivation of ancient landslides occurred in this area, posing severe threats to riverside infrastructure and human safety, including ground cracking, house cracking, foundation settlement, and road collapse. The reactivation mechanism of ancient landslides at reservoir banks is highly complex due to fluid dynamics. This study conducted field investigations in the Cheyipin landslide area, monitored surface and subsurface deformations using GNSS and inclinometers, and analyzed the distribution characteristics, destruction features, and reactivation mechanisms of the landslides through correlation analysis and numerical calculations. The results indicate that the instability pattern of the slopes manifests as traction-type sliding failure. The slopes do not slide along the ancient sliding surface but along a newly formed arcuate sliding surface, with the direct impact area mainly concentrated near the waterline. The stability of the slopes in this project is closely related to the reservoir water level. It can be assumed that the lowering of the reservoir water level triggered the reactivation of the ancient landslides in the Cheyipin section, while the influence of rainfall can be ignored. To prevent the reactivation of ancient landslides, attention should be focused on the changes in reservoir water level, avoiding rapid adjustments in water level during the initial lowering and final raising of the water level.

show abstract

“…RP is an image visualization method designed to examine m-dimensional phase space trajectories by illustrating the recurrence of data values in 2D [ 16 , 17 ]. When time-series data are provided as

, the m-dimensional phase space trajectory

can be expressed as Equation (1).…”

Section: Techniques Of Data Generation and Image Encodingmentioning

confidence: 99%

“… Two-dimensional images inherently contain more information than 1D data and possess visual characteristics, allowing for more diverse feature extraction and effective fault diagnosis when applied to CNN models [ 14 , 15 ]. Two-dimensional image-based fault detection enables quick and easy identification of various data characteristics without direct feature extraction, offering low time complexity and being well-suited for real-time, high-precision fault diagnosis [ 12 , 16 ]. …”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Fault Diagnosis Method for Human Coexistence Robots Based on Convolutional Neural Networks Using Time-Series Data Generation and Image Encoding

Choi,

Park,

et al. 2023

Sensors

View full text Add to dashboard Cite

This paper proposes fault diagnosis methods aimed at proactively preventing potential safety issues in robot systems, particularly human coexistence robots (HCRs) used in industrial environments. The data were collected from durability tests of the driving module for HCRs, gathering time-series vibration data until the module failed. In this study, to apply classification methods in the absence of post-failure data, the initial 50% of the collected data were designated as the normal section, and the data from the 10 h immediately preceding the failure were selected as the fault section. To generate additional data for the limited fault dataset, the Wasserstein generative adversarial networks with gradient penalty (WGAN-GP) model was utilized and residual connections were added to the generator to maintain the basic structure while preventing the loss of key features of the data. Considering that the performance of image encoding techniques varies depending on the dataset type, this study applied and compared five image encoding methods and four CNN models to facilitate the selection of the most suitable algorithm. The time-series data were converted into image data using image encoding techniques including recurrence plot, Gramian angular field, Markov transition field, spectrogram, and scalogram. These images were then applied to CNN models, including VGGNet, GoogleNet, ResNet, and DenseNet, to calculate the accuracy of fault diagnosis and compare the performance of each model. The experimental results demonstrated significant improvements in diagnostic accuracy when employing the WGAN-GP model to generate fault data, and among the image encoding techniques and convolutional neural network models, spectrogram and DenseNet exhibited superior performance, respectively.

show abstract

Image encoding selection based on Pearson correlation coefficient for time series anomaly detection

Cited by 31 publications

References 41 publications

Load Day-Ahead Automatic Generation Control Reserve Capacity Demand Prediction Based on the Attention-BiLSTM Network Model Optimized by Improved Whale Algorithm

Load Day-Ahead Automatic Generation Control Reserve Capacity Demand Prediction Based on the Attention-BiLSTM Network Model Optimized by Improved Whale Algorithm

Development Characteristics and Reactivation Mechanism of a Large-Scale Ancient Landslide in Reservoir Area

Fault Diagnosis Method for Human Coexistence Robots Based on Convolutional Neural Networks Using Time-Series Data Generation and Image Encoding

Contact Info

Product

Resources

About