• Land and Housing Review
• /
• v.12 no.3
• /
• pp.109-119
• /
• 2021

Global warming caused by greenhouse gas emissions has rapidly increased abnormal climate events and geotechnical engineering hazards in terms of their size and frequency accordingly. Biopolymer-based soil treatment (BPST) in geotechnical engineering has been implemented in recent years as an alternative to reducing carbon footprint. Furthermore, thermo-gelating biopolymers, including agar gum, gellan gum, and xanthan gum, are known to strengthen soils noticeably. However, an explicitly detailed evaluation of the correlation between the factors, that have a significant influence on the strengthening behavior of BPST, has not been explored yet. In this study, machine learning regression analysis was performed using the UCS (unconfined compressive strength) data for BPST tested in the laboratory to evaluate the factors influencing the strengthening behavior of gellan gum-treated soil mixtures. General linear regression, Ridge, and Lasso were used as linear regression methods; the key factors influencing the behavior of BPST were determined by RMSE (root mean squared error) and regression coefficient values. The results of the analysis showed that the concentration of biopolymer and the content of clay have the most significant influence on the strength of BPST.

• Asian-Australasian Journal of Animal Sciences
• /
• v.12 no.4
• /
• pp.537-543
• /
• 1999

Whole horse beans (Vicia faba cv. Alfred) (WHB) were pressure toasted at different temperatures of 100, 118 and $136^{\circ}C$ for 3, 7, 15 and 30 minutes in order to determine an optimal heating conditions to increase bypass starch (BPSt) as glucose source which is usually limiting nutrient in highly producing dairy cows in the Netherlands. Starch (St) Ruminal Degradative Kinetics and Fermentation Characteristics of (SRDC) of WHB were determined using in sacco technique in 4 lactating dairy cows fed 47% hay and 53% concentrate according to Dutch dairy cow requirements. Measured characteristics of St were soluble fraction (S), potentially degradable fraction (D) and rate of degradation (Kd) of insoluble but degradable fraction. Based on measured characteristics, percentage bypass starch (BPSt) was calculated according to the Dutch new feed evaluation system: the DVE/OEB system. Pressure toasting temperatures significantly affected starch gelatinization (p<0.01). Degradability of Starch in the rumen was highly reduced by pressure toasting (p<0.01). S varied from 58.2% in the raw WHB (RWHB as a control) to 19.6% in $136^{\circ}C/15min$. S was reduced rapidly with increasing time and temperature (p<0.01). D varied from 41.8% in RWHB to 80.5% in $136^{\circ}C/15min$. D fraction was enormously increased with increasing time and temperature (p<0.01). Kd varied from 4.9%h in RWHB to 3.4%/h in $136^{\circ}C/15min$. All these effects resulted in increasing %BPSt from 29.0% in RWHB to 53.1% in $136^{\circ}C/15min$. Therefore BPSt increased from 93.5 g/kg in RWHB to 173.5 g/kg in $136^{\circ}C/15min$. The effects of pressure toasting on %BPSt and BPSt seemed to be linear up to the highest values tested. Therefore no optimal pressure toasting conditions could be determined at this stage. But among 10 treatments, The treatment of $136^{\circ}C/15min$was the best with the highest BPSt content. It was concluded that pressure toasting was effective in shifting starch degradation from rumen to small intestine to increase bypass starch.

• Geomechanics and Engineering
• /
• v.36 no.4
• /
• pp.381-390
• /
• 2024

The introduction of bio-based materials has been recommended in the geotechnical engineering field to reduce environmental pollutants such as heavy metals and greenhouse gases. However, bio-treated soil methods face limitations in field application due to short research periods and insufficient verification of engineering performance, especially when compared to conventional materials like cement. Therefore, this study aimed to develop a machine learning model for predicting the unconfined compressive strength, a representative soil property, of biopolymer-based soil treatment (BPST). Four machine learning algorithms were compared to determine a suitable model, including linear regression (LR), support vector regression (SVR), random forest (RF), and neural network (NN). Except for LR, the SVR, RF, and NN algorithms exhibited high predictive performance with an R² value of 0.98 or higher. The permutation feature importance technique was used to identify the main factors affecting the strength enhancement of BPST. The results indicated that the unconfined compressive strength of BPST is affected by mean particle size, followed by biopolymer content and water content. With a reliable prediction model, the proposed model can present guidelines prior to laboratory testing and field application, thereby saving a significant amount of time and money.