Detection of Outlier in 3D Flow Velocity Collection in an Open-Channel Bend Using Various Data Mining Techniques

Vaghefi, Mohammad; Mahmoodi, Kumars; Akbari, Maryam

doi:10.1007/s40996-018-0131-2

Cited by 19 publications

(5 citation statements)

References 44 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…When measurements with gross errors, the measurement function can be expressed as: (15) where (16) According to the running system in figure 2 and the formula (11) of corrected measurements, it can be concluded that the residual r k of the system can be expressed as:…”

Section: B the Methods Of Gross Errors Detectionmentioning

confidence: 99%

“…There are also some scholars who propose various methods on how to detect and compensate for the measurement of gross errors. Vaghefi et al used six data mining methods to identify outliers in flow experiments, and verified the effects of various methods for detecting outliers [16]. Based on the mathematical model of the sun's trajectory, Xie et al used the traditional time-controlled algorithm to track the sun's trajectory, analyzed the main factors of the system tracking statics generated by the tracking device, and designed and designed a correctable tracking system for tracking biases.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Accurate Position Estimation of Mobile Robot Based on Cyber-Physical-Social Systems (CPSS)

et al. 2020

View full text Add to dashboard Cite

Section: B the Methods Of Gross Errors Detectionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Accurate Position Estimation of Mobile Robot Based on Cyber-Physical-Social Systems (CPSS)

et al. 2020

View full text Add to dashboard Cite

“…Te DCS-DAE is an improved feature extractor based on unsupervised learning [25,31,45], which can realize anomaly diagnosis using reconstruction error and boxplot [46,47] as well as achieve anomaly localization through the weighted K-nearest neighbor algorithm [48]. To improve the abnormal recognition ability of the DCS-DAE model in different structural scenarios, a domain-adaptive DCS-DAE model is proposed.…”

Section: Framework Of Model and Objective Functionmentioning

confidence: 99%

Unsupervised Domain Adaptation Damage Identification Approach of High Arch Dams after Earthquakes

Cao

Liang

Jian-yun

et al. 2023

Structural Control and Health Monitoring

View full text Add to dashboard Cite

In actual concrete arch dam engineering scenarios, the dynamic data obtained by the health monitoring system of an arch dam are incomplete. The data acquired typically depend on the state of the dam structure, that is, whether it is intact or incomplete. Besides, the future environmental loads of the structure are unpredictable. Thus, environmental noise is also uncertain. In practical engineering, the use of a damage identification model constructed based on incomplete information is problematic in scenarios with variable loads. Consequently, detecting the water level in actual arch dam projects after an earthquake and determining the impact of environmental uncertainty are necessary. Accordingly, this paper proposes a denoising contractive sparse deep autoencoder (DCS-DAE) model based on domain adaptation. The core idea of the proposed method is to constrain the data probability distribution of feature spaces in the source and target domains using maximum mean discrepancy. This fusion enables the DCS-DAE model to be capable of feature extraction. Moreover, it resolves the problem in which the objective function cannot be applied to other similar scenarios because of the lack of consistency constraints of feature spaces in the source and target domains. Four working conditions are designed to reproduce the uncertainty of structural modeling and the variability of water levels. The conditions are based on the postseismic water level detection requisites of dams in practical engineering. The results show that the proposed anomaly detection model enhances the generalization performance of the DCS-DAE in terms of feature design. Hence, the constructed model can “infer other things from one fact.” The results of this study are meaningful for the real-time cross-domain monitoring of structures under variable load conditions, providing a driving force to apply similar methods to practical arch dam projects.

show abstract

“…The subject of several professional publications is the identification of outliers and their evaluation, specifically their imaging using boxplots [30][31][32]. These methods are applied to data from natural, technical, as well as social sciences [33][34][35], including transportation, where subjects such as urban traffic [36,37] and the evaluation of psychological and physical parameters of drivers [38,39] are discussed.…”

Section: Literature Reviewmentioning

confidence: 99%

Improvement of Road Safety through Appropriate Cargo Securing Using Outliers

et al. 2021

View full text Add to dashboard Cite

The article focuses on evaluating a transportation experiment that intends to improve road safety by analyzing transport shocks that significantly affect the system of securing the load, vehicle, driver, and other aspects. Within Europe, improper or insufficient securing of loads causes up to 25% of all cargo vehicle accidents. Our transport experiment consists of eight rides of a Tatra truck. The measured values of shocks (acceleration coefficients) are statistically evaluated. Three hypotheses are established for these purposes. First, it is proven that the probability distributions of the shocks values differ statistically significantly among individual rides, namely in their shape and median value. Thus further statistical analyses are performed separately for the individual rides, axes, and the accelerometer locations. These analyses prove significant exceedances of the normatively set limits given by the EN 12195-1:2010 standard, which is potentially risky. Especially for the z axis and y axis, the set 20% limit was exceeded in 75.0% and 56.3% of cases, respectively. In the case of the x axis, the established 20% limit was practically not exceeded at all. The analysis of exceeding the permitted limits (the statistical evaluation of the second and third established hypothesis) is based on boxplots that graphically describe the individual rides, as well as on the found contaminated log-normal distribution of the values of the acceleration coefficients in the individual rides. The last hypothesis regarding exceeding the double value of the permitted limit is rejected. Methods of statistical comparison are used during data analysis. The probability distribution of acceleration coefficients is modeled using a contaminated log-normal distribution.

show abstract

Detection of Outlier in 3D Flow Velocity Collection in an Open-Channel Bend Using Various Data Mining Techniques

Cited by 19 publications

References 44 publications

Accurate Position Estimation of Mobile Robot Based on Cyber-Physical-Social Systems (CPSS)

Accurate Position Estimation of Mobile Robot Based on Cyber-Physical-Social Systems (CPSS)

Unsupervised Domain Adaptation Damage Identification Approach of High Arch Dams after Earthquakes

Improvement of Road Safety through Appropriate Cargo Securing Using Outliers

Contact Info

Product

Resources

About