Kantorovich Distance based Fault Detection Scheme: An Application to Wastewater Treatment Plant

Kini, K Ramakrishna; Madakyaru, Muddu

doi:10.1016/j.ifacol.2022.04.057

Cited by 3 publications

(4 citation statements)

References 16 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Another approach is to use a histogram-based method, where the time series are discretized into a finite number of bins, and the 2-Wasserstein distance is computed between the resulting histograms. The segmentation technique is utilized between the two distributions which enables to capture sensitive details in the data (Kini and Madakyaru, 2022). This feature enables the KD metric to enhance the detection of small magnitude anomalies.…”

Section: Kantorovich Distancementioning

confidence: 99%

A semi-supervised anomaly detection strategy for drunk driving detection: a feasibility study

Harrou,

Kini,

Madakyaru

et al. 2024

Front. Sens.

Self Cite

View full text Add to dashboard Cite

Drunk driving poses a significant threat to road safety, necessitating effective detection methods to enhance preventive measures and ensure the well-being of road users. Recognizing the critical importance of identifying drunk driving incidents for public safety, this paper introduces an effective semi-supervised anomaly detection strategy. The proposed strategy integrates three key elements: Independent Component Analysis (ICA), Kantorovitch distance (KD), and double Exponentially Weighted Moving Average (DEWMA). ICA is used to handle non-gaussian and multivariate data, while KD is used to measure the dissimilarity between normal and abnormal events based on ICA features. The DEWMA is applied to KD charting statistics to detect changes in data and uses a nonparametric threshold to improve sensitivity. The primary advantage of this approach is its ability to perform anomaly detection without requiring labeled data. The study also used XGBoost for the later calculation of the SHAP (SHapley Additive exPlanations) values to identify the most important variables for detecting drunk driving behavior. The approach was evaluated using publicly available data from gas and temperature sensors, as well as digital cameras. The results showed that the proposed approach achieved an F1-score of 98% in detecting the driver’s drunk status, outperforming conventional PCA-based and ICA-based methods.

show abstract

Section: Kantorovich Distancementioning

confidence: 99%

A semi-supervised anomaly detection strategy for drunk driving detection: a feasibility study

Harrou,

Kini,

Madakyaru

et al. 2024

Front. Sens.

Self Cite

View full text Add to dashboard Cite

show abstract

“…The cost of transportation is very minimum for distributions that are similar and maximum for dissimilar distributions and this is the basic idea behind the use of KD statistic in abnormality detection problems. For any two distributions C and D, the KD statistic can be computed using the following expression [11]:…”

Section: B Kantorovich Distancementioning

confidence: 99%

“…where 𝜇 𝑐 and 𝜇 𝑑 indicate means while Σ 𝑐 and Σ 𝑑 indicate covariance matrices. The KD statistic is computed between the two distributions using segmentation process which enables it to capture the sensitive details in both data that eventually aids in better detection ability sets [11]. This attractive feature has enabled it to be applied in anomaly identification problems.…”

Section: B Kantorovich Distancementioning

confidence: 99%

Automatic Detection of Unbalanced Sitting Postures in Wheelchairs Using Unlabeled Sensor Data

et al. 2022

Self Cite

View full text Add to dashboard Cite

This letter presents an effective data-driven anomaly detection scheme for automatically recognizing unbalanced sitting posture in a wheelchair using data from pressure sensors embedded in the wheelchair. Essentially, the designed approach merges the desirable features of the kernel principal components analysis (KPCA) as a feature extractor with the Kantorovich Distance (KD)-driven monitoring chart to detect abnormal sitting posture in a wheelchair. It is worth noting that this approach does not require labeled data and only employs normal events data to train the detection model, which makes it more appealing in practice. Specifically, we used the KPCA model to exploit its capacity to reduce the dimensionality of nonlinear data to obtain good detection. At the same time, the KD monitoring scheme is an efficient distribution-driven anomaly detection approach in multivariate data. Furthermore, a nonparametric decision threshold using kernel density estimation is adopted to extend the flexibility of the proposed approach. Publically available data has been used to verify the detection capacity of the proposed approach. The overall detection system proved promising, outperforming some commonly used monitoring methods.

show abstract

“…Supporting the safe and effective management of complex, nonlinear, time-varying, and regulated wastewater treatment processes, the provided model is of great practical value. Kini and Madakyaru (2022) Mihály, Simon-Várhelyi and Cristea ( 2022) investigated the design and training of ANN models for predicting energy and effluent quality indices with the intention of using them to accelerate the optimization of WWTPs to determine the optimal setpoint values for the nitrates and dissolved oxygen control loops. The measurements of WWTP influent and process variables were used to collect plant data for a period of 22 days, with a sample interval of 30 minutes.…”

Section: Fault Detection In Wastewater Treatment Plantmentioning

confidence: 99%

Machine Learning for Failure Detection in Bakery Industrial Effluents Treatment by Electrocoagulation

DA SILVA RIBEIRO

View full text Add to dashboard Cite

show abstract

Kantorovich Distance based Fault Detection Scheme: An Application to Wastewater Treatment Plant

Cited by 3 publications

References 16 publications

A semi-supervised anomaly detection strategy for drunk driving detection: a feasibility study

A semi-supervised anomaly detection strategy for drunk driving detection: a feasibility study

Automatic Detection of Unbalanced Sitting Postures in Wheelchairs Using Unlabeled Sensor Data

Machine Learning for Failure Detection in Bakery Industrial Effluents Treatment by Electrocoagulation

Contact Info

Product

Resources

About