A Deep Learning Anomaly Detection Framework for Satellite Telemetry with Fake Anomalies

Wang, Yakun; Gong, Jianglei; Zhang, Jie; Han, Xiaodong

doi:10.1155/2022/1676933

Cited by 12 publications

(5 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Anomaly detection is also an important task in telemetry data analysis. Wang et al [9] proposed a datadriven anomaly detection framework using the Deviation Divide Mean over Neighbors (DDMN) method and Long Short-Term Memory (LSTM) to develop a model with multivariable time-series data, and a Gaussian model to detect anomalies. With this experiment, they proved the superiority of DDMN compared with other unsupervised methods for fake anomaly detection and they demonstrate the effectiveness of LSTMs based on DDMN for anomaly detection [9].…”

Section: Machine Learningmentioning

confidence: 99%

“…Wang et al [9] proposed a datadriven anomaly detection framework using the Deviation Divide Mean over Neighbors (DDMN) method and Long Short-Term Memory (LSTM) to develop a model with multivariable time-series data, and a Gaussian model to detect anomalies. With this experiment, they proved the superiority of DDMN compared with other unsupervised methods for fake anomaly detection and they demonstrate the effectiveness of LSTMs based on DDMN for anomaly detection [9]. When a large data set with thousands of variables or attributes and samples or observations are used, we should consider performing the dimensionality reduction of the dataset.…”

Section: Machine Learningmentioning

confidence: 99%

See 1 more Smart Citation

The Application of Machine learning to Amazonia-1 satellite power subsystem telemetry prediction

Barbosa

Ferreira

Júnior

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

This article presents the data acquisition, exploratory data analysis, model training, evaluation, and use of hyperparameters in a machine learning model that will be used to predict telemetry data from the Amazonia-1 satellite. The Amazonia-1 satellite was launched in 2021, it uses the Multi-Mission Platform as a service module and has a Wide Field Imager imaging camera. Its power subsystem has 715 telemetries with distinct data types that will be used as dependent and independent variables. The amount of telemetry data generated daily is large, making manual analysis of this data unfeasible. The ensemble XGBoost machine learning algorithm is used to predict the values of the dependent variable D008 “Battery Module 1 Voltage” that belongs to the electric power subsystem. For the evaluation and performance Mean Absolute Error (MAE), Root Mean Square Error (RMSE), and R2 are used. The final learning model resulted in the coefficient of determination (R2) with 99.99%, MAE of 0.005749, and RMSE of 0.007727. After the cross-validation step, RMSE reached 0.006888. The execution time was 57 minutes and 32 seconds. Based on these numbers, we can consider that the machine learning model built reached a good result, especially when used with cross-validation.

show abstract

Section: Machine Learningmentioning

confidence: 99%

Section: Machine Learningmentioning

confidence: 99%

The Application of Machine learning to Amazonia-1 satellite power subsystem telemetry prediction

Barbosa

Ferreira

Júnior

2023

J. Phys.: Conf. Ser.

View full text Add to dashboard Cite

show abstract

“…The proposed method is more interpretable than other commonly used prediction models, and its general applicability was verified on two common datasets. It was proposed in [31] that errors in satellite remote sensing test data would lead to false anomalies. To solve this problem, the deviation divide mean over neighbors (DDMN) was used in this study to model multivariate time series data by using a long short-term memory network, effectively avoiding false positives.…”

Section: Related Researchmentioning

confidence: 99%

Satellite Network Security Routing Technology Based on Deep Learning and Trust Management

Liu,

Rong,

Jiang

et al. 2023

Sensors

View full text Add to dashboard Cite

The conventional trust model employed in satellite network security routing algorithms exhibits limited accuracy in detecting malicious nodes and lacks adaptability when confronted with unknown attacks. To address this challenge, this paper introduces a secure satellite network routing technology founded on deep learning and trust management. The approach embraces the concept of distributed trust management, resulting in all satellite nodes in this paper being equipped with trust management and anomaly detection modules for assessing the security of neighboring nodes. In a more detailed breakdown, this technology commences by preprocessing the communication behavior of satellite network nodes using D–S evidence theory, effectively mitigating interference factors encountered during the training of VAE modules. Following this preprocessing step, the trust vector, which has undergone prior processing, is input into the VAE module. Once the VAE module’s training is completed, the satellite network can assess safety factors by employing the safety module during the collection of trust evidence. Ultimately, these security factors can be integrated with the pheromone component within the ant colony algorithm to guide the ants in discovering pathways. Simulation results substantiate that the proposed satellite network secure routing algorithm effectively counters the impact of malicious nodes on data transmission within the network. When compared to the traditional trust management model of satellite network secure routing algorithms, the algorithm demonstrates enhancements in average end-to-end delay, packet loss rate, and throughput.

show abstract

“…Of the data samples, 0.15% were labeled anomalous by an expert and the rest were normal. The training dataset was preprocessed to remove errors in the data [42]. The detailed dataset statistics are summarized in Table 1.…”

Section: Iforest-based Error Evaluation and Anomaly Detectionmentioning

confidence: 99%

Unsupervised Anomaly Detection for Time Series Data of Spacecraft Using Multi-Task Learning

et al. 2022

Self Cite

View full text Add to dashboard Cite

Although in-orbit anomaly detection is extremely important to ensure spacecraft safety, the complex spatial-temporal correlation and sparsity of anomalies in the data pose significant challenges. This study proposes the new multi-task learning-based time series anomaly detection (MTAD) method, which captures the spatial-temporal correlation of the data to learn the generalized normal patterns and hence facilitates anomaly detection. First, four proxy tasks are implemented for feature extraction through joint learning: (1) Long short-term memory-based data prediction; (2) autoencoder-based latent representation learning and data reconstruction; (3) variational autoencoder-based latent representation learning and data reconstruction; and (4) joint latent representation-based data prediction. Proxy Tasks 1 and 4 capture the temporal correlation of the data by fusing the latent space, whereas Tasks 2 and 3 fully capture the spatial correlation of the data. The isolation forest algorithm then detects anomalies from the extracted features. Application to a real spacecraft dataset reveals the superiority of our method over existing techniques, and further ablation testing for each task proves the effectiveness of fusing multiple tasks. The proposed MTAD method demonstrates promising potential for effective in-orbit anomaly detection for spacecraft.

show abstract

A Deep Learning Anomaly Detection Framework for Satellite Telemetry with Fake Anomalies

Cited by 12 publications

References 30 publications

The Application of Machine learning to Amazonia-1 satellite power subsystem telemetry prediction

The Application of Machine learning to Amazonia-1 satellite power subsystem telemetry prediction

Satellite Network Security Routing Technology Based on Deep Learning and Trust Management

Unsupervised Anomaly Detection for Time Series Data of Spacecraft Using Multi-Task Learning

Contact Info

Product

Resources

About