An incremental clustering method for anomaly detection in flight data

Zhao, Weizun; Li, Lishuai; Alam, Sameer; Wang, Yanjun

doi:10.1016/j.trc.2021.103406

Cited by 24 publications

(7 citation statements)

References 36 publications

(28 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In addition, the horizontal axis depicts the distance from landing. By comparing the results from CMCA with those from NNID K-means, GMM, and DBSCAN [18,24], it is evident that CMCA can provide a more intuitive understanding of SMEs. To further illustrate the explainability of the results from CMCA, we use the pilots' operation during approach as an example.…”

Section: Explanation Analysis Of Cmca Resultsmentioning

confidence: 99%

“…To address these limitations, specific methods have been utilized to obtain natural clustering results to guide the adjustment of hyperparameters. In [24], a Bayesian Information Criterion (BIC) was used to determine the number of components in a Gaussian Mixture Model (GMM), and the DBSCAN method was then utilized to merge similar flights. The hyperparameters of DBSCAN were set according to the GMM test results.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Using Catalyst Mass-Based Clustering Analysis to Identify Adverse Events during Approach

et al. 2023

View full text Add to dashboard Cite

Discovering and mitigating potential risks in advance is essential for preventing aviation accidents on routine flights. Although anomaly detection-based explanation techniques have successfully uncovered potential risks for proactive flight safety management, explaining group-scale precursors using these methods is challenging due to the assumption that risky flights are significantly fewer in number than normal flights, as well as the reliance on non-domain knowledge for hyperparameter adjustment. To characterize the group-scale precursors more accurately, we propose a novel technique called Catalyst Mass-Based Clustering Analysis (CMCA), which employs a composite entropy-energy dissipation index during approach to evaluate the energy management performance. On this basis, an optimization objective is constructed to identify clusters exhibiting significant energy management differences during the approach phase. We successfully identify group-scale precursors with energy management issues by applying CMCA to a combination of minority-labeled and majority-unlabeled flights. Comparative experiments show that these precursors have energy levels that deviate from normal flights by 5.83% and 10.93%, respectively, 1000 ft above touchdown, demonstrating the effectiveness of our method. The analysis suggests that poor energy management awareness on the part of pilots could be responsible for these group-scale precursors. Notably, the results obtained using CMCA are comprehensible for Subject Matter Experts, making the method a valuable tool for proactive flight safety management.

show abstract

Section: Explanation Analysis Of Cmca Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Using Catalyst Mass-Based Clustering Analysis to Identify Adverse Events during Approach

et al. 2023

View full text Add to dashboard Cite

show abstract

“…e purpose is to identify exceptions without knowing the normative standard. Zhao et al [12] proposed an algorithm based on a Gaussian mixture model (GMM) that incrementally updates the clusters according to the data instead of reclustering and adapts to the new data through an expectation-maximization algorithm to handle dynamically changing data in flight data. Zeng et al [13] used a densitybased DBSCAN clustering method to detect aircraft onboard and controller data that deviate from the normal range.…”

Section: Machine Learning Methodsmentioning

confidence: 99%

Anomaly Detection in QAR Data Using VAE-LSTM with Multihead Self-Attention Mechanism

Rong

OuYang

Sun

2022

Mobile Information Systems

View full text Add to dashboard Cite

With the rapid development of the aviation industry, it is particularly important to ensure the safe flight of aircraft. How to find potential hazards in the process of aircraft flight has always been one of the important topics of civil aviation research. At present, the Quick Access Recorder (QAR) is the most widely used equipment to store the data recorded on aircraft. QAR data contain a lot of valuable and unexplored information, which records the true status of the aircraft in detail. Therefore, finding abnormal data from QAR data lays an important foundation for obtaining the cause of abnormality and providing a guarantee for flight. In this paper, in order to discover the abnormal information in the QAR data, we applied a VAE-LSTM model with a multihead self-attention mechanism. Compared to the VAE and LSTM models alone, our model performs much better in anomaly detection and prediction, detecting all types of anomalies. We conducted extensive experiments on real-world QAR data sets to prove the efficiency and accuracy of our proposed neural network model. The experimental results proved that our proposed model can outperform state-of-the-art models under different experimental settings.

show abstract

“…In the literature, a lot of studies have been done on the development of black box technology: black box search, 10,11 cyber security of aviation technology, 12,13 new approaches for black box design. [14][15][16][17] Over time, black box technologies have been developed and legal tightening has been made.…”

Section: Related Workmentioning

confidence: 99%

“…Also via this study, reason of accidents can be found and it can prevent future accidents. In Reference 15, a method has been proposed for making a backup of flight data. It is about the development of an incremental clustering method for anomaly detection with dynamically growing dataset.…”

Section: Related Workmentioning

confidence: 99%

BLOCKBOX: Blockchain based black box designing and modeling

Korkuc,

Aytas Korkmaz,

Genc

et al. 2024

Concurrency and Computation

View full text Add to dashboard Cite

SummaryWith the development of technology, data has become more accessible. The storage of critical and valuable information is getting harder and harder with the increase of cyber attacks and vulnerabilities of network and internet. The centralized storage of data causes security and privacy problems. As a remedy to these problems, blockchain has occurred. The reliability, transparency, integrity and confidentiality of the data have been increased with the blockchain technology. Blockchain maintains the immutability of the data with cryptographic hash algorithms. The data is kept in distributed structures with the consensus algorithms so that it is not lost. Projects and studies using blockchain technology have shown that data stored in centralized structures is not as reliable as data that is distributed and secured by cryptographic algorithms, smart contracts, and consensus. The data of flights, which is a critical data, has a great place in world transportation. The parameters inside the black boxes guide us on why the aircrafts have crashed: whether the responsibility belongs to the manufacturer, to the pilot, or to the aircraft technicians. In this way, the real reasons of the accident may be determined and measures can be taken for the accidents that may occur afterwards. In addition, the safe delivery of all black box data to the interested parties and its storage in a way that is immutable will not only benefit to the manufacturer's self‐development by processing the data, but also help flight companies to find optimum flight data. Both the flight companies and the manufacturer will be able to read the black box data, thus the suspicion of data manipulation will be eliminated and the data will become more transparent. In this study, a system is proposed in which an aircraft's black box data can be saved safely and securely with the help of blockchain technology.

show abstract

An incremental clustering method for anomaly detection in flight data

Cited by 24 publications

References 36 publications

Using Catalyst Mass-Based Clustering Analysis to Identify Adverse Events during Approach

Using Catalyst Mass-Based Clustering Analysis to Identify Adverse Events during Approach

Anomaly Detection in QAR Data Using VAE-LSTM with Multihead Self-Attention Mechanism

BLOCKBOX: Blockchain based black box designing and modeling

Contact Info

Product

Resources

About