• Computers and Concrete
• /
• 제32권3호
• /
• pp.327-337
• /
• 2023

Concrete is the most widely used building material, with various types including high- and ultra-high-strength, reinforced, normal, and lightweight concretes. However, accurately predicting concrete properties is challenging due to the geotechnical design code's requirement for specific characteristics. To overcome this issue, researchers have turned to new technologies like machine learning to develop proper methodologies for concrete specification. In this study, we propose a highly accurate deep learning-based predictive model to investigate the compressive strength (UCS) of lightweight concrete with natural aggregates (pumice). Our model was implemented on a database containing 249 experimental records and revealed that water, cement, water-cement ratio, fine-coarse aggregate, aggregate substitution rate, fine aggregate replacement, and superplasticizer are the most influential covariates on UCS. To validate our model, we trained and tested it on random subsets of the database, and its performance was evaluated using a confusion matrix and receiver operating characteristic (ROC) overall accuracy. The proposed model was compared with widely known machine learning methods such as MLP, SVM, and DT classifiers to assess its capability. In addition, the model was tested on 25 laboratory UCS tests to evaluate its predictability. Our findings showed that the proposed model achieved the highest accuracy (accuracy=0.97, precision=0.97) and the lowest error rate with a high learning rate (R2=0.914), as confirmed by ROC (AUC=0.971), which is higher than other classifiers. Therefore, the proposed method demonstrates a high level of performance and capability for UCS predictions.

• Geomechanics and Engineering
• /
• 제32권6호
• /
• pp.583-600
• /
• 2023

The resilient modulus (M_R) of various pavement materials plays a significant role in the pavement design by a mechanistic-empirical method. The M_R determination is done by experimental tests that need time and money, along with special experimental tools. The present paper suggested a novel hybridized extreme gradient boosting (XGB) structure for forecasting the M_R of modified base materials subject to wet-dry cycles. The models were created by various combinations of input variables called deep learning. Input variables consist of the number of W-D cycles (WDC), the ratio of free lime to SAF (CSAFR), the ratio of maximum dry density to the optimum moisture content (DMR), confining pressure (σ₃), and deviatoric stress (σ_d). Two XGB structures were produced for the estimation aims, where determinative variables were optimized by particle swarm optimization (PSO) and black widow optimization algorithm (BWOA). According to the results' description and outputs of Taylor diagram, M1 model with the combination of WDC, CSAFR, DMR, σ₃, and σ_d is recognized as the most suitable model, with R² and RMSE values of BWOA-XGB for model M1 equal to 0.9991 and 55.19 MPa, respectively. Interestingly, the lowest value of RMSE for literature was at 116.94 MPa, while this study could gain the extremely lower RMSE owned by BWOA-XGB model at 55.198 MPa. At last, the explanations indicate the BWO algorithm's capability in determining the optimal value of XGB determinative parameters in M_R prediction procedure.

• Computers and Concrete
• /
• 제32권2호
• /
• pp.149-163
• /
• 2023

One of the main design parameters traditionally utilized in projects of geotechnical engineering is the uniaxial compressive strength. The present paper employed three artificial intelligence methods, i.e., the stochastic fractal search (SFS), the multi-verse optimization (MVO), and the vortex search algorithm (VSA), in order to determine the compressive strength of concrete (CSC). For the same reason, 1030 concrete specimens were subjected to compressive strength tests. According to the obtained laboratory results, the fly ash, cement, water, slag, coarse aggregates, fine aggregates, and SP were subjected to tests as the input parameters of the model in order to decide the optimum input configuration for the estimation of the compressive strength. The performance was evaluated by employing three criteria, i.e., the root mean square error (RMSE), mean absolute error (MAE), and the determination coefficient (R²). The evaluation of the error criteria and the determination coefficient obtained from the above three techniques indicates that the SFS-MLP technique outperformed the MVO-MLP and VSA-MLP methods. The developed artificial neural network models exhibit higher amounts of errors and lower correlation coefficients in comparison with other models. Nonetheless, the use of the stochastic fractal search algorithm has resulted in considerable enhancement in precision and accuracy of the evaluations conducted through the artificial neural network and has enhanced its performance. According to the results, the utilized SFS-MLP technique showed a better performance in the estimation of the compressive strength of concrete (R²=0.99932 and 0.99942, and RMSE=0.32611 and 0.24922). The novelty of our study is the use of a large dataset composed of 1030 entries and optimization of the learning scheme of the neural prediction model via a data distribution of a 20:80 testing-to-training ratio.

• Asian-Australasian Journal of Animal Sciences
• /
• 제28권5호
• /
• pp.605-611
• /
• 2015

A synthetic strain of ducks (Anas platyrhynchos) was developed by introducing genes for long duration of fertility to be used as mother of mule ducklings and a seven-generation selection experiment was conducted to increase the number of fertile eggs after a single artificial insemination (AI) with pooled Muscovy semen. Reciprocal crossbreeding between Brown Tsaiya LRI-2 (with long duration of fertility) and Pekin L-201 (with white plumage mule ducklings) ducks produced the G0. Then G1 were intercrossed to produce G2 and so on for the following generations. Each female duck was inseminated 3 times, at 26, 29, and 32 weeks of age. The eggs were collected for 14 days from day 2 after AI. Individual data regarding the number of incubated eggs (Ie), the number of fertile eggs at candling at day 7 of incubation (F), the total number of dead embryos (M), the maximum duration of fertility (Dm) and the number of hatched mule ducklings (H) with plumage colour were recorded. The selection criterion was the breeding values of the best linear unbiased prediction animal model for F. The results show high percentage of exhibited heterosis in G2 for traits to improve (19.1% for F and 12.9% for H); F with a value of 5.92 (vs 3.74 in the Pekin L-201) was improved in the G2. Heritabilities were found to be low for Ie ($h^2=0.07{\pm}0.03$) and M ($h^2=0.07{\pm}0.01$), moderately low for Dm ($h^2=0.13{\pm}0.02$), of medium values for H ($h^2=0.20{\pm}0.03$) and F ($h^2=0.23{\pm}0.03$). High and favourable genetic correlations existed between F and Dm ($r_g=0.93$), between F and H ($r_g=0.97$) and between Dm and H ($r_g=0.90$). The selection experiment showed a positive trend for phenotypic values of F (6.38 fertile eggs in G10 of synthetic strain vs 5.59 eggs in G4, and 3.74 eggs in Pekin L-201), with correlated response for increasing H (5.73 ducklings in G10 vs 4.86 in G4, and 3.09 ducklings in Pekin L-201) and maximum duration of the fertile period without increasing the embryo mortality rate. The average predicted genetic response for F was 40% of genetic standard deviation per generation of selection. The mule ducklings' feather colour also was improved. It was concluded that this study provided results for a better understanding of the genetics of the duration of fertility traits in the common female duck bred for mule and that the selection of a synthetic strain was effective method of improvement.

• 대한토목학회논문집
• /
• 제35권1호
• /
• pp.173-185
• /
• 2015

본 연구는 통계적 분석기법을 통하여 부산시내에서 운영 중인 11개 터널에서 발생한 교통사고 456건을 대상으로 교통사고의 발생특성, 유형화 및 예측모델을 구축하였는바 다음과 같은 결론을 얻게 되었다. 교통사고 발생특성으로는 시간대별 터널 내 교통사고 08~18시 사이가 전체의 64.9%를 차지하고 있어 기존 도로의 45.8~46.1%에 비해 높게 나타났고, 사고유형별로는 차대차 사고가 대부분을 차지하고 있으며, 차량단독사고는 기존도로에 비해 다소 높게 나타났으며, 연령층별로는 21~40세의 구성비가 높았고, 제1당사자 차종별로는 화물차의 비중이 높았고, 운량별로는 맑은 날을 제외하고 비가 오는 날이 흐린 날 보다 더욱 높은 수치를 보였다. 교통사고 영향요인에 대하여 주성분분석을 실시한 결과, 제1주성분은 도로, 터널구조 및 교통류 관련요인이, 제2주성분은 조명시설 및 도로구조 관련요인이, 제3주성분은 대기상태 및 조명시설 관련요인이, 제4주성분은 인적 및 시계열 관련요인이, 제5주성분은 인적요인이, 제6주성분은 차량적 요인과 교통류 관련 요인이, 제7주성분은 기상요인으로 대별되었다. 교통사고 발생지점에 대하여 유형화를 실시한 결과, 최적 집단수는 5개로 구분지어 졌으며, 집단별로 수량화이론 1류를 적용하여 분석한 결과, 제1집단은 예측모델의 설명력이 낮은 반면 제4집단은 예측모델의 설명력이 중간정도, 제2, 제3, 제5집단은 높은 설명력을 가진 예측모델이 구축되었다. 예측모델의 편상관계수 절대 값이 0.2(약한 상관) 이상인 항목(주성분) 중에서 도로환경적 요인이 포함된 변수를 체크하여 분석한 결과, 주요 검토항목은 적절한 교통류 처리, 횡단구성(차로폭), 터널구조(터널길이), 도로선형, 환기시설, 조명시설로 요약되었다.

• 대한후두음성언어의학회지
• /
• 제21권1호
• /
• pp.37-41
• /
• 2010

Background and Objectives : Transient minor voice changes after thyroidectomy are not infrequent complaints even in cases without any evidence of recurrent laryngeal nerve damage. However, clinical course, diagnosis and management of such voice changes are not fully understood. This study aimed to evaluate the clinical characteristics of minor voice changes after thyroidectomy. We also tried to assess the significance and feasibility of superior laryngeal nerve monitoring and to find out the optimal evaluation tools for such voice changes after thyroidectomy. Materials and Method : Nine adult patients who received total thyroidectomy without evidence of recurrent laryngeal nerve injury were enrolled for this prospective study. Voice evaluations were performed preoperatively and 3 months postoperatively ; acoustic analyses including voice range profile, aerodynamic study, stroboscopic evaluation and subjective voice assessment with questionnaires. The external branch of superior laryngeal nerve was monitored by nerve stimulator after ligation of superior thyroidal vessels. Results: Four of nine patients complained their voice change at 3 months after the surgery. Three of them reported complete recovery of their voice at 6 months after the surgery. Acoustic analysis revealed significant decrease in their phonatory range especially with high tone loss. Questionnaires related to singing was more sensitive than previously well-known "voice handicap index". Stimulation of the superior laryngeal nerve was feasible in most of the cases (94.4%), but it failed to show any correlation with minor voice changes after thyroidectomy. Conclusion : Minor voice changes were not rare events during the first 6 month after thyroidectomy. Decrease in phonatory range with high tone loss and therefore, discomfort in singing was the most common finding. Superior laryngeal monitoring was feasible but it was not a sensitive tool for the prediction of minor voice change after thyroidectomy.