Prediction and validation of alternative fillers used in micro surfacing mix-design using machine learning techniques

Gujar, Rajesh; Vakharia, Vinay

doi:10.1016/j.conbuildmat.2019.02.136

Cited by 32 publications

(5 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This support vector lies on the largest margin to find on optimal hyper plane. Optimal hyper plane separates data of one class from another class and classification result is obtained [26].…”

Section: Support Vector Machinementioning

confidence: 99%

See 1 more Smart Citation

Texture classification of machined surfaces using image processing and machine learning techniques

Patel¹,

Vakharia²,

Kiran³

2019

FME Transactions

Self Cite

View full text Add to dashboard Cite

The identification of surface texture images from machining surfaces using image processing techniques has been a prominent research area in the recent decades. The aim of this paper is to identify various machined surface texture images using machine learning techniques. Charge coupled device is used to capture images of machined components. Based on captured images, twelve statistical features are extracted and feature vector is formed. Grey Level Co-occurrence Matrix is used to extract statistical features from the machined surface images. Four Machine learning algorithms such as Random Forest, Support Vector Machine, Artificial Neural Network and J48 were utilized to characterize machined surfaces. Training and Tenfold cross validation process is utilized for identification of machined component images. It is found that Artificial Neural Network and Random forest give100 % training accuracy and 99% cross validation accuracy. Results obtained demonstrate the efficiency of proposed methodology, which is useful for identifying texture images.

show abstract

Section: Support Vector Machinementioning

confidence: 99%

“…A Neural network consists of various layers of interconnected nodes. The feature vector serves as an input to the algorithm via input layer which consists of at least one hidden layers where the real preparing of data is completed [26].…”

Section: Artificial Neural Networkmentioning

confidence: 99%

Texture classification of machined surfaces using image processing and machine learning techniques

Patel¹,

Vakharia²,

Kiran³

2019

FME Transactions

Self Cite

View full text Add to dashboard Cite

show abstract

“…Apaza et al 17 evaluated the skid and abrasion resistance of MS with iron ore aggregate using WTAT and LWT in conjunction with relevant specification requirements. Gujar and Vakharia 18 used the results of WTAT as an indicator to predict the performance of MS mixtures through machine learning techniques. Nascimento et al 19 tested the adhesion between MS and the original pavement at different temperatures from the point of view of interlayer bonding and concluded that MS are more susceptible to damage in high temperature areas.…”

Section: Introductionmentioning

confidence: 99%

Study of long‐term skid and wear resistance of waterborne epoxy resin‐SBR compound modified emulsified asphalt microsurfacing

Lu,

Zheng,

Gao

et al. 2023

J of Applied Polymer Sci

View full text Add to dashboard Cite

As an eco‐friendly technology for pavement preventive maintenance, microsurfacing (MS) has the potential properties of cost‐saving and excellent performance benefits in repairing distress. MS also improves the surface function, especially skid resistance, of old pavements that have gradually decayed under the coupled effects of long‐term environment and loads. Reasonable assessments of the long‐term skid and wear resistance of the MS can provide support for accurate decision‐making on preventive maintenance, which in turn reduces maintenance costs and saves maintenance costs, and ensures traffic safety. To evaluate the long‐term skid and wear resistance of MS in different natural and traffic environments, this paper investigated the change of British pendulum number (BPN), rutting depth, and mass loss rate of waterborne epoxy resin‐SBR compound emulsified asphalt micro‐surfacing (WER‐SBR MEAMS) under different environmental factors and traffic conditions based on the self‐developed accelerated loading abrasion instrument. The factors considered in the experiment include temperature, rainfall, UV radiation, speed, and load. The results showed that temperature and vehicle speed had a detrimental effect on the durability of WER‐SBR MEAMS, which was more pronounced after 10,000 wear loading cycles. Reducing immersion time and slowing down the aging rate can improve the durability of WER‐SBR MEAMS. Further, the influence degrees of different factors on the skid and wear resistance of MS were evaluated using the gray correlation method. From the results of the gray correlation analysis, the correlation coefficients between external variables and BPN, rutting depth, and mass loss rate are all greater than 0.8, which indicate that all the variables involved have relatively obvious and regular effects on the skid and wear resistance of WER‐SBR MEAMS.

show abstract

“…Moreover, a hybrid model using outputs of conventional machine learning models as inputs of ANN model has been developed by Asteris et al to predict concrete compressive strength [21]. In terms of concrete and cement research, ML has shown its unique effectiveness in diverse studies such as composite mix design optimization [22,23], property prediction [24,25] and pattern recognition [26,27]. Several studies have utilized ML such as ANNs and SVMs for simulating the carbonation process of concrete.…”

Section: Introductionmentioning

confidence: 99%

Development of hybrid machine learning-based carbonation models with weighting function

Chen

Lin

Sagoe‐Crentsil

et al. 2022

Construction and Building Materials

View full text Add to dashboard Cite

Prediction and validation of alternative fillers used in micro surfacing mix-design using machine learning techniques

Cited by 32 publications

References 13 publications

Texture classification of machined surfaces using image processing and machine learning techniques

Texture classification of machined surfaces using image processing and machine learning techniques

Study of long‐term skid and wear resistance of waterborne epoxy resin‐SBR compound modified emulsified asphalt microsurfacing

Development of hybrid machine learning-based carbonation models with weighting function

Contact Info

Product

Resources

About