Automated Detection and Classification of Infiltration in Sewer Pipes

Shehab, Tariq; Moselhi, Osama

doi:10.1061/(asce)1076-0342(2005)11:3(165)

Cited by 39 publications

(5 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…As for the machine learning approaches, multi-layer perceptron (MLP) has been commonly utilized for classifying multiple sewer defects [35][36][37]. Other techniques such as fuzzy logic [38,39] and finite element analysis [40] are also combined with MLP for defect classification.…”

Section: Conventional Computer Vison and Machine Learning Based Methodsmentioning

confidence: 99%

Automated sewer pipe defect tracking in CCTV videos based on defect detection and metric learning

Wang

Kumar

Cheng

2021

Automation in Construction

View full text Add to dashboard Cite

Section: Conventional Computer Vison and Machine Learning Based Methodsmentioning

confidence: 99%

Automated sewer pipe defect tracking in CCTV videos based on defect detection and metric learning

Wang

Kumar

Cheng

2021

Automation in Construction

View full text Add to dashboard Cite

“…Hybrid neural networks have also been used to analyze the image data collected by CCTVs (Moselhi et al, 1999;2000;Shehab et al,2005) to classify the defects present in drainage networks. However, to better combine the available data, the XGBoost algorithm, which is suitable for analyzing numerical data, needs to be used.…”

Section: Related Workmentioning

confidence: 99%

Drainage network flow anomaly classification based on XGBoost

2023

Global NEST: The International Journal

View full text Add to dashboard Cite

<p>Identifying and classifying anomalies in on-line monitoring systems of drainage systems is important to reduce urban water pollution. In the context of big data, the mini-batch K-means combined with the XGBoost drainage network abnormal flow identification and classification model is proposed to precisely identify and classify abnormalities that occur in real-time updates of online drainage network data while resolving problems with subjectivity and the lack of uniform standards for classification. First, using Mini Batch K-means, the unclassified drainage network data were sorted into four categories: normal drainage, sneaky drainage, rainwater and sewage mixing, and inflow and infiltration. Next, XGBoost performs data modeling to create a model for classification and identification of drainage flow anomalies. To increase the accuracy of the model, the features were ultimately chosen based on the ranking of the importance of the features, and the model parameters were established using grid search and cross-validation. The results showed that the XGBoost Drainage Network Anomaly Classification and Identification Model can accurately identify four drainage network situations with high classification accuracy and good performance. It was also validated through the application of data from the online system monitoring points in Changsha, China, in 2020.</p>

show abstract

“…Morphological methods have been applied individually or with other techniques like edge detection for feature extraction in many studies [47][48][49][50]. With the extracted features, machine learning classifiers such as neural network [51,52], support vector machine (SVM) [47,53,54], and random forest (RF) [55] are trained to detect the existence of defects or classify defect types. The multi-stage traditional workflow requires constructing features manually and adjusting classifier parameters specifically for a particular case [56].…”

Section: Automated Inspection Data Interpretationmentioning

confidence: 99%