Search

This study aims to predict the migration time of toxic fumes induced by excavation blasting in underground mines. To reduce numerical simulation time and optimize ventilation design, several back propagation neural network (BPNN) models optimized by honey badger algorithm (HBA) with four chaos mapping (CM) functions (i.e., Chebyshev (Che) map, Circle (Cir) map, Logistic (Log) map, and Piecewise (Pie) map) are developed to predict the migration time. 125 simulations by the computational fluid dynamics (CFD) method are used to train and test the developed models. The determination coefficient (R2), the variance accounted for (VAF), the Willmott’s index (WI), the root mean square error (RMSE), the mean absolute percentage error (MAPE), and the sum of squares error (SSE) are utilized to evaluate the model performance. The evaluation results indicate that the CirHBA-BPNN model has achieved the most satisfactory performance by reaching the highest values of R2 (0.9945), WI (0.9986), VAF (99.4811%), and the lowest values of RMSE (15.7600), MAPE (0.0343) and SSE (6209.4), respectively. The wind velocity in roadway (Wv) is the most important feature for predicting the migration time of toxic fumes. Furthermore, the intrinsic response characteristic of the optimal model is implemented to enhance the model interpretability and provide reference for the relationship between features and migration time of toxic fumes in ventilation design.

Flexible damping technology considering aseismic materials and aseismic structures seems be a good solution for engineering structures. In this study, a constrained damping structure for underground tunnel lining, using a rubber-sand-concrete (RSC) as the aseismic material, is proposed. The aseismic performances of constrained damping structure were investigated by a series of hammer impact tests. The damping layer thickness and shape effects on the aseismic performance such as effective duration and acceleration amplitude of time-domain analysis, composite loss factor and damping ratio of the transfer function analysis, and total vibration level of octave spectrum analysis were discussed. The hammer impact tests revealed that the relationship between the aseismic performance and damping layer thickness was not linear, and that the hollow damping layer had a better aseismic performance than the flat damping layer one. The aseismic performances of constrained damping structure under different seismicity magnitudes and geological conditions were investigated. The effects of the peak ground acceleration (PGA) and tunnel overburden depth on the aseismic performances such as the maximum principal stress and equivalent plastic strain (PEEQ) were discussed. The numerical results show the constrained damping structure proposed in this paper has a good aseismic performance, with PGA in the range (0.2–1.2)g and tunnel overburden depth in the range of 0–300 m.

Study region: Nine representative cities in Shandong Province, northern China Study focus: The analytical stochastic approach is computationally-efficient in green roofs (GRs)’ hydrologic performances. However, use of rainfall event separation methods and the resulting rainfall statistic affect the accuracy of this approach. This study integrates a Kernel distribution estimation (KDE)-based rainfall event separation method with the analytical stochastic model (ASM) developed for GRs. The proposed approach was tested for 198 design cases of GRs with considering different soil types and depths at 9 cities in the Shandong Province, northern China. New hydrologic insights for the region: Poisson and Kolmogorov–Smirnov tests can be performed to obtain the available pairs of minimum interevent time and threshold rainfall event depth. The optimal pairs of MIET-vt can be further determined based on the standardized procedure by the KDE-based rainfall event separation and characterization approach. Exponential distributions fit well the observed frequency distributions of rainfall event characteristics of the study area. ASM results using rainfall statistics obtained from a KDE-based method agree very well with those obtained from continuous simulations. The proposed integration of KDE-based rainfall statistics and ASM is accurate and useful for the planning, design and assessment of green roofs in regions of northern China.

The technical challenges associated with deep underground space activities have become increasingly significant. Among these challenges, one major concern is the assessment of rockburst risks and the instability of rock masses. Extensive research has been conducted by numerous scholars to mitigate the risks and prevent occurrences of rockburst through various assessment methods. Rockburst incidents commonly occur during the excavation of hard rock in underground environments, posing severe threats to personnel safety, equipment integrity, and operational continuity. Thus, it is crucial to systematically document real cases of rockburst, allowing for a comprehensive understanding of the underlying mechanisms and triggering conditions. This understanding will contribute to the advancement of rockburst prediction and prevention methods. Proper selection of an appropriate rockburst assessment method is a fundamental aspect in underground operations. However, there is a limited number of studies that summarize and compare different prediction and prevention methods of rockburst. This paper aims to address this gap by analyzing global trends using CiteSpace software since 1990. It discusses rockburst classification and characteristics, comprehensively reviews research findings related to rockburst prediction, including empirical, simulation, mathematical modeling, and microseismic monitoring methods. Additionally, the paper presents a compilation of current rockburst prevention measures. Notably, the paper emphasizes the significance of control strategies, which provide key insights into the effective utilization of stored energy within rock. Finally, the paper concludes by suggesting six directions for implementing intelligent management techniques to mitigate hazards during underground operations and reduce the probability of rockburst incidents.

Hard rock pillar is one of the important structures in engineering design and excavation in underground mines. Accurate and convenient prediction of pillar stability is of great significance for underground space safety. This paper aims to develop hybrid support vector machine (SVM) models improved by three metaheuristic algorithms known as grey wolf optimizer (GWO), whale optimization algorithm (WOA) and sparrow search algorithm (SSA) for predicting the hard rock pillar stability. An integrated dataset containing 306 hard rock pillars was established to generate hybrid SVM models. Five parameters including pillar height, pillar width, ratio of pillar width to height, uniaxial compressive strength and pillar stress were set as input parameters. Two global indices, three local indices and the receiver operating characteristic (ROC) curve with the area under the ROC curve (AUC) were utilized to evaluate all hybrid models’ performance. The results confirmed that the SSA-SVM model is the best prediction model with the highest values of all global indices and local indices. Nevertheless, the performance of the SSA-SVM model for predicting the unstable pillar (AUC: 0.899) is not as good as those for stable (AUC: 0.975) and failed pillars (AUC: 0.990). To verify the effectiveness of the proposed models, 5 field cases were investigated in a metal mine and other 5 cases were collected from several published works. The validation results indicated that the SSA-SVM model obtained a considerable accuracy, which means that the combination of SVM and metaheuristic algorithms is a feasible approach to predict the pillar stability.

Borehole breakouts significantly influence drilling operations’ efficiency and economics. Accurate evaluation of breakout size (angle and depth) can enhance drilling strategies and hold potential for in situ stress magnitude inversion. In this study, borehole breakout size is approached as a complex nonlinear problem with multiple inputs and outputs. Three hybrid multi-output models, integrating commonly used machine learning algorithms (artificial neural networks ANN, random forests RF, and Boost) with the Walrus optimization algorithm (WAOA) optimization techniques, are developed. Input features are determined through literature research (friction angle, cohesion, rock modulus, Poisson’s ratio, mud pressure, borehole radius, in situ stress), and 501 related datasets are collected to construct the borehole breakout size dataset. Model performance is assessed using the Pearson Correlation Coefficient (R2), Mean Absolute Error (MAE), Variance Accounted For (VAF), and Root Mean Squared Error (RMSE). Results indicate that WAOA-ANN exhibits excellent and stable prediction performance, particularly on the test set, outperforming the single-output ANN model. Additionally, SHAP sensitivity analysis conducted on the WAOA-ANN model reveals that maximum horizontal principal stress (σH) is the most influential parameter in predicting both the angle and depth of borehole breakout. Combining the results of the studies and analyses conducted, WAOA-ANN is considered to be an effective hybrid multi-output model in the prediction of borehole breakout size.

Accurate prediction of the thermal conductivity of ethylene glycol (EG) and aluminum oxide (Al2O3) nanofluids is crucial for improving the utilization rate of energy in industries such as electronics cooling, automotive, and renewable energy systems. However, current theoretical models and simulations face challenges in accurately predicting the thermal conductivity of EG–Al2O3 nanofluids due to their complex and dynamic nature. To that end, this study develops several supervised ML models, including artificial neural network (ANN), decision tree (DT), gradient boosting decision tree (GBDT), k-nearest neighbor (KNN), multi-layer perceptron (MLP), and extreme gradient boosting (XGBoost) models, to predict the thermal conductivity of EG–Al2O3 nanofluids. Three key parameters, particle size (D), temperature (T), and volume fraction (VF) of EG–Al2O3 nanoparticles, are considered as input features for modeling. Furthermore, five indices combining with regression graphs and Taylor diagrams are used to evaluate model performance. The evaluation results indicate that the GBDT model achieved the highest performance among all models, with mean squared errors (MSE) of 6.7735 × 10−6 and 1.0859 × 10−5, root mean squared errors (RMSE) of 0.0026 and 0.0033, mean absolute errors (MAE) of 0.0009 and 0.0028, correlation coefficients (R2) of 0.9974 and 0.9958, and mean absolute percent errors (MAPE) of 0.2764% and 0.9695% in the training and testing phases, respectively. Furthermore, the results of sensitivity analysis conducted using Shapley additive explanations (SHAP) demonstrate that T is the most important feature for predicting the thermal conductivity of EG–Al2O3 nanofluids. This study provides a novel calculation model based on artificial intelligence to realize an innovation beyond the traditional measurement of the thermal conductivity of EG–Al2O3 nanofluids.

Predicting the post-blast re-entry time precisely can improve productivity and reduce accidents significantly. The empirical formulas for the time prediction are practical to implement, but lack accuracy. In this study, a novel method based on the back-propagation neural network (BPNN) was proposed to tackle the drawbacks. A numerical model was constructed and 300 points of sample data were recorded, with consideration to fresh air volume, occupational exposure limit, toxic gas volume per kg of explosives and roadway length. The BPNN model with six neurons in a hidden layer was then developed and prediction performance was discussed in terms of four indicators, namely, the root mean square error (RMSE), the coefficient of determination (R2), the mean absolute error (MAE) and the sum of squares error (SSE). Furthermore, one representative empirical formula was introduced and calibrated for the comparison. The obtained results showed that the BPNN model had a more remarkable performance, with RMSE of 21.45 (R2: 0.99, MAE: 10.78 and SSE: 40934), compared to the empirical formula, with RMSE of 76.89 (R2: 0.90, MAE: 42.06 and SSE: 526147). Hence, the BPNN model is a superior method for predicting the post-blast re-entry time. For better practical application, it was then embedded into the software.

Accurate rainfall-runoff modeling is crucial for disaster prevention, mitigation, and water resource management. This study aims to enhance precision and reliability in predicting runoff patterns by integrating physical-based models like HEC-HMS with data-driven models, such as LSTM. We present a novel hybrid model, Ia-LSTM, which combines the strengths of HEC-HMS and LSTM to improve hydrological modeling. By optimizing the “initial loss” (Ia) with HEC-HMS and utilizing LSTM to capture the effective rainfall-runoff relationship, the model achieves a substantial improvement in precision. Tested in the Yufuhe basin in Jinan City, Shandong province, the Ia-LSTM consistently outperforms individual HEC-HMS and LSTM models, achieving notable average Nash-Sutcliffe Efficiency (NSE) values of 0.873 and 0.829, and average R2 values of 0.916 and 0.870 for calibration and validation, respectively. The study shows the potential of integrating physical mechanisms to enhance the efficiency of data-driven rainfall-runoff modeling. The Ia-LSTM model holds promise for more accurate runoff estimation, with wide applications in flood forecasting, water resource management, and infrastructure planning.

Currently, the primary methods for action recognition involve RGB-based approaches, pose-based approaches (e.g., skeleton coordinates), and multi-stream fusion methods. In this paper, we propose a novel action recognition framework based on both RGB images and motion pose images to enhance the accuracy of action recognition in videos. As a single feature representation fail to effectively capture motion trends and image variation information, it cannot accurately reflect expected action judgments in real-world scenarios. Therefore, we utilize the appearance features of video frames and the motion variation features of the subject, aiming to cooperate the action itself with appearance information for precise action recognition. We construct video representations based on local spatiotemporal features and global features, and utilize the ResNet backbone network and Temporal Shift Module (TSM) to extract action representations from multi-stream information. Driven by the motion features, the fusion of multi-stream information achieves effective expression of motion features. Experimental results on public datasets demonstrate the effectiveness of our proposed method. It achieves competitive performance compared to state-of-the-art techniques while maintaining a less complex and more interpretable model. Overall, our approach demonstrates superior effectiveness.

Abstract The ongoing outbreak of Severe Acute Respiratory Syndrome Coronavirus 2 (SARS‐CoV‐2) pandemic has posed significant challenges in early viral diagnosis. Hence, it is urgently desirable to develop a rapid, inexpensive, and sensitive method to aid point‐of‐care SARS‐CoV‐2 detection. In this work, we report a highly sequence‐specific biosensor based on nanocomposites with aggregation‐induced emission luminogens (AIEgen)‐labeled oligonucleotide probes on graphene oxide nanosheets (AIEgen@GO) for one step‐detection of SARS‐CoV‐2‐specific nucleic acid sequences (Orf1ab or N genes). A dual “turn‐on” mechanism based on AIEgen@GO was established for viral nucleic acids detection. Here, the first‐stage fluorescence recovery was due to dissociation of the AIEgen from GO surface in the presence of target viral nucleic acid, and the second‐stage enhancement of AIE‐based fluorescent signal was due to the formation of a nucleic acid duplex to restrict the intramolecular rotation of the AIEgen. Furthermore, the feasibility of our platform for diagnostic application was demonstrated by detecting SARS‐CoV‐2 virus plasmids containing both Orf1ab and N genes with rapid detection around 1 h and good sensitivity at pM level without amplification. Our platform shows great promise in assisting the initial rapid detection of the SARS‐CoV‐2 nucleic acid sequence before utilizing quantitative reverse transcription‐polymerase chain reaction for second confirmation.

This study employs a supervised learning method to predict the tunnel boring machine (TBM) penetration rate (PR) with high accuracy. To this end, the extreme gradient boosting (XGBoost) model is optimized based on two swarm intelligence algorithms, i.e., the sparrow search algorithm (SSA) and the whale optimization algorithm (WOA). Three other machine learning models, including random forest (RF), support vector machine (SVM), and artificial neural network (ANN) models, are also developed as the drawback. A database created in Shenzhen (China), comprising 503 entries and featuring 10 input variables and 1 output variable, was utilized to train and test the prediction models. The model development results indicate that the use of SSA and WOA has the potential to improve the XGBoost model performance in predicting the TBM performance. The performance evaluation results show that the proposed WOA-XGBoost model has achieved the most satisfactory performance by resulting in the most reliable prediction accuracy of the four performance indices. This research serves as a compelling illustration of how combined approaches, such as supervised learning methods and swarm intelligence algorithms, can enhance TBM prediction performance and can provide a reference when solving other related engineering problems.

The uniaxial compressive strength (UCS) of rocks is one of the key parameters for evaluating the safety and stability of civil and mining structures. In this study, 386 rock samples containing four properties named the load strength (PLS), the porosity (Pn), the P-wave velocity (Vp), and the Schmidt hardness rebound number (SHR) are utilized to predict the UCS using several typical empirical equations (EA) and artificial intelligence (AI) methods, i.e., 16 single regression (SR) equations, 2 multiple regression (MR) equations, and the random forest (RF) models optimized by grey wolf optimization (GWO), moth flame optimization (MFO), lion swarm optimization (LSO), and sparrow search algorithm (SSA). The root mean square error (RMSE), determination coefficient (R2), Willmott’s index (WI), and variance accounted for (VAF) are used to evaluate the predictive performance of all developed models. The evaluation results show that the overall performance of AI models is superior to empirical approaches, especially the LSO-RF model. In addition, the most important input variable is the Pn for predicting the UCS. Therefore, AI techniques are considered as more efficient and accurate approaches to replace the empirical equations for predicting the UCS of these collected rock samples, which provides a reliable and effective idea to predict the rock UCS in the filed site.

Modulation format identification (MFI) and optical signal-to-noise ratio (OSNR) monitoring are essential for elastic optical networks. A method for joint modulation format identification and OSNR monitoring based on ternary neural networks was proposed. Further, a ternary neural network was established, and the constellation images after constant modulus algorithm (CMA) equalization were used as input features. Four commonly used modulation formats were distinguished, including dual-polarization (DP)-QPSK, 8QAM, 16QAM, and 64QAM. A 32G baud simulation system was constructed, and the results were analyzed. First, we investigated the influence of resolution and sample length on the identification accuracy. The values 32 and 7000 were selected for the two parameters, respectively, based on the balance between resource consumption and accuracy. Then, we compared the performance of the binary neural network (BNN), ternary neural network (TNN), and full-precision neural network (FNN). The results indicate that the memory consumption and extraction time of the TNN are similar to those of the BNN, and the accuracy is further improved. Moreover, the robustness of the system was analyzed. The results validate that the proposed method can tolerate fiber nonlinearity (from 500 km to 1500 km). Finally, an experiment was conducted to prove the practicality of the proposed method.

Pillar stability is always evaluated using the safety factor (SF), which is defined as the ratio of pillar strength to pillar stress. However, most researchers have estimated pillar stress using the pillar shape ratio (w/h), uniaxial compressive strength (UCS) of the intact rock mass, and pillar depth (H). In this study, the geological strength index (GSI) of hard rock pillars was considered as a new variable for predictive purposes. This index was developed by combining numerical simulation software (i.e., FLAC3D) and a backpropagation neural network (BPNN). A hard rock pillar stability analysis, based on three methods including deterministic method, sensitivity analysis, and Monte Carlo simulation (MCS), was performed. A new formula was proposed to estimate the SF values based on the predicted stress, considering the GSI variable in the deterministic method. The sensitivity analysis indicated that the variables impacting the SF from high to low are UCS, GSI, w/h, and H. In this study, pillar stability was analyzed mainly using the GSI and MCS techniques. The MCS results revealed that the GSI is also a major factor in pillar stability and has a greater effect on weak pillars than on strong ones. Furthermore, a pillar is more likely to be unstable when both the GSI and the UCS are decreased. This study provides several references and procedures for improving the design of stable pillars considering the GSI as an important factor.

Predicting the punching shear strength (PSS) of fiber-reinforced polymer reinforced concrete (FRP-RC) beams is a critical task in the design and assessment of reinforced concrete structures. This study utilized three meta-heuristic optimization algorithms, namely ant lion optimizer (ALO), moth flame optimizer (MFO), and salp swarm algorithm (SSA), to select the optimal hyperparameters of the random forest (RF) model for predicting the punching shear strength (PSS) of FRP-RC beams. Seven features of FRP-RC beams were considered as inputs parameters, including types of column section (TCS), cross-sectional area of the column (CAC), slab’s effective depth (SED), span–depth ratio (SDR), compressive strength of concrete (CSC), yield strength of reinforcement (YSR), and reinforcement ratio (RR). The results indicate that the ALO-RF model with a population size of 100 has the best prediction performance among all models, with MAE of 25.0525, MAPE of 6.5696, R2 of 0.9820, and RMSE of 59.9677 in the training phase, and MAE of 52.5601, MAPE of 15.5083, R2 of 0.941, and RMSE of 101.6494 in the testing phase. The slab’s effective depth (SED) has the largest contribution to predicting the PSS, which means that adjusting SED can effectively control the PSS. Furthermore, the hybrid machine learning model optimized by metaheuristic algorithms outperforms traditional models in terms of prediction accuracy and error control.

Abstract Carbonaceous materials are considered strong candidates as anode materials for sodium‐ion batteries (SIBs), which are expected to play an indispensable role in the carbon‐neutral era. Herein, novel braided porous carbon fibres (BPCFs) are prepared using the chemical vapour deposition (CVD) method. The BPCFs possess interwoven porous structures and abundant vacancies. The growth mechanism of the BPCFs can be attributed to the polycrystalline transformation of the nanoporous copper catalyst in the early stage of CVD process. Density functional theory calculations suggest that the Na+ adsorption energies of the mono‐vacancy edges of the BPCFs (−1.22 and −1.09 eV) are lower than that of an ideal graphene layer (−0.68 eV), clarifying in detail the adsorption‐dominated sodium storage mechanism. Hence, the BPCFs as an anode material present an outstanding discharge capacity of 401 mAh g−1 at 0.1 A g−1 after 500 cycles. Remarkably, this BPCFs anode, under high‐mass‐loading of 5 mg cm−2, shows excellent long‐term cycling ability with a reversible capacity of 201 mAh g−1 at 10 A g−1 over 1000 cycles. This study provided a novel strategy for the development of high‐performance carbonaceous materials for SIBs.

The combination of rice husk ash and common concrete both reduces carbon dioxide emission and solves the problem of agricultural waste disposal. However, the measurement of the compressive strength of rice husk ash concrete has become a new challenge. This paper proposes a novel hybrid artificial neural network model, optimized using a reptile search algorithm with circle mapping, to predict the compressive strength of RHA concrete. A total of 192 concrete data with 6 input parameters (age, cement, rice husk ash, super plasticizer, aggregate, and water) were utilized to train proposed model and compare its predictive performance with that of five other models. Four statistical indices were adopted to evaluate the predictive performance of all the developed models. The performance evaluation indicates that the proposed hybrid artificial neural network model achieved the most satisfactory prediction accuracy regarding R2 (0.9709), VAF (97.0911%), RMSE (3.4489), and MAE (2.6451). The proposed model also had better predictive accuracy than that of previously developed models on the same data. The sensitivity results show that age is the most important parameter for predicting the compressive strength of RHA concrete.

Most approaches to action recognition based on pseudo-images involve encoding skeletal data into RGB-like image representations. This approach cannot fully exploit the kinematic features and structural information of human poses, and convolutional neural network (CNN) models that process pseudo-images lack a global field of view and cannot completely extract action features from pseudo-images. In this paper, we propose a novel pose-based action representation method called Optical Flow Pose Image (OFPI) in order to fully capitalize on the spatial and temporal information of skeletal data. Specifically, in the proposed method, an advanced pose estimator collects skeletal data before locating the target person and then extracts skeletal data utilizing a human tracking algorithm. The OFPI representation is obtained by aggregating these skeletal data over time. To test the superiority of OFPI and investigate the significance of the model having a global field of view, we trained a simple CNN model and a transformer-based model, respectively. Both models achieved superior outcomes. Because of the global field of view, especially in the transformer-based model, the OFPI-based representation achieved 98.3% and 94.2% accuracy on the KTH and JHMDB datasets, respectively. Compared with other advanced pose representation methods and multi-stream methods, OFPI achieved state-of-the-art performance on the JHMDB dataset, indicating the utility and potential of this algorithm for skeleton-based action recognition research.

The determination of the rock elasticity modulus (EM) is an indispensable key step for the design of rock engineering problems. Traditional experimental analysis can accurately measure the rock EM, but it requires manpower and material resources, and it is time consuming. The EM estimation of new rocks using former published empirical formulas is also a possibility but can be attached of high uncertainties. In this paper, four types of metaheuristic optimization algorithms (MOA), named the backtracking search optimization algorithm (BSA), multi-verse optimizer (MVO), golden eagle optimizer (GEO) and poor and rich optimization algorithm (PRO), were utilized to optimize the random forest (RF) model for predicting the rock EM. A data-driven technology was used to generate an integrated database consisting of 120 rock samples from the literature. To verify the predictive performance of the proposed models, five common machine-learning models and one empirical formula were also developed to predict the rock EM. Four popular performance indices, including the root-mean-square error (RMSE), mean absolute error (MAE), the coefficient of determination (R2) and Willmott’s index (WI), were adopted to evaluate all models. The results showed that the PRO-RF model has obtained the most satisfactory prediction accuracy. The porosity (Pn) is the most important variable for predicting the rock EM based on the sensitive analysis. This paper compares the performance of the RF models optimized by using four MOA for the rock EM prediction. It provides a good example for the subsequent application of soft techniques on the EM and other important rock parameter estimations.

Construction-induced ground settlement is a serious hazard in underground tunnel construction. Accurate ground settlement prediction has great significance in ensuring the surface building’s stability and human safety. To that end, 148 sets of data were collected from the Singapore Circle Line rail traffic project containing seven defining parameters to create a database for predicting ground settlement. These parameters are the tunnel depth (H), the tunnel advance rate (AR), the EPB earth pressure (EP), the mean SPTN value from the soil crown to the surface (Sm), the mean water content of the soil layer (MC), the mean modulus of elasticity of the soil layer (E), and the grout pressure used for injecting grout into the tail void (GP). Three hybrid models consisting of random forest (RF) and three types of meta-heuristics, Ant Lion Optimizier (ALO), Multi-Verse Optimizer (MVO), and Grasshopper Optimization Algorithm (GOA), were developed to predict ground settlement. Furthermore, the mean absolute error (MAE), the mean absolute percentage error (MAPE), the coefficient of determination (R2) and the root mean square error (RMSE) were used to assess predictive performance of the constructed models for predicting ground settlement. The evaluation results demonstrated that the GOA-RF with a population size of 10 has achieved the most outstanding predictive capability with the indices of MAE (Training set: 2.8224; Test set: 2.3507), MAPE (Training set: 40.5629; Test set: 38.5637), R2 (Training set: 0.9487; Test set: 0.9282), and RMSE (Training set: 4.93; Test set: 3.1576). Finally, the sensitivity analysis results indicated that MC, AR, Sm, and GP have a significant impact on ground settlement prediction based on the GOA-RF model.

The application of aseismic materials in foundation engineering structures is an inevitable trend and research hotspot of earthquake resistance, especially in tunnel engineering. In this study, the pelican optimization algorithm (POA) is improved using the Latin hypercube sampling (LHS) method and the Chaotic mapping (CM) method to optimize the random forest (RF) model for predicting the aseismic performance of a novel aseismic rubber-concrete material. Seventy uniaxial compression tests and seventy impact tests were conducted to quantify this aseismic material performance, i.e., strength and energy absorption properties and four other artificial intelligence models were generated to compare the predictive performance with the proposed hybrid RF models. The performance evaluation results showed that the LHSPOA-RF model has the best prediction performance among all the models for predicting the strength and energy absorption property of this novel aseismic concrete material in both the training and testing phases (R2: 0.9800 and 0.9108, VAF: 98.0005% and 91.0880%, RMSE: 0.7057 and 1.9128, MAE: 0.4461 and 0.7364; R2: 0.9857 and 0.9065, VAF: 98.5909% and 91.3652%, RMSE: 0.5781 and 1.8814, MAE: 0.4233 and 0.9913). In addition, the sensitive analysis results indicated that the rubber and cement are the most important parameters for predicting the strength and energy absorption properties, respectively. Accordingly, the improved POA-RF model not only is proven as an effective method to predict the strength and energy absorption properties of aseismic materials, but also this hybrid model provides a new idea for assessing other aseismic performances in the field of tunnel engineering.

Uniaxial compressive strength (UCS) is one of the most important parameters to characterize the rock mass in geotechnical engineering design and construction. In this study, a novel kernel extreme learning machine-grey wolf optimizer (KELM-GWO) model was proposed to predict the UCS of 271 rock samples. Four parameters namely the porosity (Pn, %), Schmidt hardness rebound number (SHR), P-wave velocity (Vp, km/s), and point load strength (PLS, MPa) were considered as the input variables, and the UCS is the output variable. To verify the effectiveness and accuracy of the KELM-GWO model, extreme learning machine (ELM), KELM, deep extreme learning machine (DELM) back-propagation neural network (BPNN), and one empirical model were established and compared with the KELM-GWO model to predict the UCS. The root mean square error (RMSE), determination coefficient (R2), mean absolute error (MAE), prediction accuracy (U1), prediction quality (U2), and variance accounted for (VAF) were adopted to evaluate all models in this study. The results demonstrate that the proposed KELM-GWO model was the best model for predicting UCS with the best performance indices. Additionally, the identified most important parameter for predicting UCS is the porosity by using the mean impact value (MIV) technique.

Abstract Constructing unique and highly stable structures with plenty of electroactive sites in sodium storage materials is a key factor for achieving improved electrochemical properties through favorable sodium ion diffusion kinetics. An SnS2@carbon hollow nanospheres (SnS2@C) has been designed and fabricated via a facile solvothermal route, followed by an annealing treatment. The SnS2@C hybrid possesses an ideal hollow structure, rich active sites, a large electrode/electrolyte interface, a shortened ion transport pathway, and, importantly, a buffer space for volume change, generated from the repeated insertion/extraction of sodium ions. These merits lead to the significant reinforcement of structural integrity during electrochemical reactions and the improvement in sodium storage properties, with a high specific reversible capacity of 626.8 mAh g−1 after 200 cycles at a current density of 0.2 A g−1 and superior high-rate performance (304.4 mAh g−1 at 5 A g−1).

Abstract Sodium ion batteries have drawn extensive attentions for large-scale energy storage to replace lithium ion batteries primarily due to the natural abundance of sodium resource and low cost, but their energy density and electrochemical performance are hindered by the sluggish diffusion kinetics of sodium ion. Herein, free-standing nitrogen-doped graphene aerogel has been fabricated via hydrothermal reaction as the potential anode material for sodium ion batteries. The three dimensional porous network structure of the graphene aerogel provides sufficient interstitial space for sodium ion accommodation, allowing fast and reversible ion intercalation/de-intercalation. The nitrogen doping could introduce defects on the graphene sheets, making the feasible transport of large-sized sodium ion. Benefiting from the effective structure and nitrogen doping, the obtained material demonstrates high reversible capacities, good cycling performance (287.9 mA h g−1 after 200 cycles at a current density of 100 mA g−1), especially superior rate capability (151.9 mA h g−1 at a high current density of 5 A g−1).

The intention of this paper is to evaluate the sensitivity of the Storm Water Management Model (SWMM) output to its input parameters. A global parameter sensitivity analysis is conducted in order to determine which parameters mostly affect the model simulation results. Two different methods of sensitivity analysis are applied in this study. The first one is the partial rank correlation coefficient (PRCC) which measures nonlinear but monotonic relationships between model inputs and outputs. The second one is based on the mutual information which provides a general measure of the strength of the non-monotonic association between two variables. Both methods are based on the Latin Hypercube Sampling (LHS) of the parameter space, and thus the same datasets can be used to obtain both measures of sensitivity. The utility of the PRCC and the mutual information analysis methods are illustrated by analyzing a complex SWMM model. The sensitivity analysis revealed that only a few key input variables are contributing significantly to the model outputs; PRCCs and mutual information are calculated and used to determine and rank the importance of these key parameters. This study shows that the partial rank correlation coefficient and mutual information analysis can be considered effective methods for assessing the sensitivity of the SWMM model to the uncertainty in its input parameters.

The shear strength of rockfill materials (RFM) is an important engineering parameter in the design and audit of geotechnical structures. In this paper, the predictive reliability and feasibility of random forests and Cubist models were analyzed by estimating the shear strength from the relative density, particle size, distribution (gradation), material hardness, gradation and fineness modulus, and confining (normal) stress. For this purpose, case studies of 165 rockfill samples have been applied to generate training and testing datasets to construct and validate the models. Thirteen key material properties for rockfill characterization were selected to develop the proposed models. Validation and comparison of the models have been performed using the root mean square error (RMSE), coefficient of determination (R2), and mean estimation error (MAE) between the measured and estimated values. A sensitivity analysis was also conducted to ascertain the importance of various inputs in the prediction of the output. The results demonstrated that the Cubist model has the highest prediction performance with (RMSE = 0.0959, R2 = 0.9697 and MAE = 0.0671), followed by the random forests model with (RMSE = 0.1133, R2 = 0.9548 and MAE= 0.0665), the artificial neural network (ANN) model with (RMSE = 0.1320, R2 = 0.9386 and MAE = 0.0841), and the conventional multiple linear regression technique with (RMSE = 0.1361, R2 = 0.9345 and MAE = 0.0888). The results indicated that the Cubist and random forests models are able to generate better predictive results of the shear strength of RFM than ANN and conventional regression models. The Cubist model was considered to be more promising for interpreting the complex relationships between the influential properties of RFM and the shear strengths of RFM to some extent, which can be extremely helpful in estimating the shear strength of rockfill materials.

Current formulas for calculating scour depth below of a free over fall are mostly deterministic in nature and do not adequately consider the uncertainties of various scouring parameters. A reliability-based assessment of scour, taking into account uncertainties of parameters and coefficients involved, should be performed. This paper studies the reliability of a dam foundation under the threat of scour. A model for calculating the reliability of scour and estimating the probability of failure of the dam foundation subjected to scour is presented. The Maximum Entropy Method is applied to construct the probability density function (PDF) of the performance function subject to the moment constraints. Monte Carlo simulation (MCS) is applied for uncertainty analysis. An example is considered, and there liability of its scour is computed, the influence of various random variables on the probability failure is analyzed.

The slope stability is a very important problem in geotechnical engineering. This paper presents an approach for slope reliability analysis based on the maximum-entropy method. The key idea is to implement the maximum entropy principle in estimating the probability density function. The performance function is formulated by the Simplified Bishop’s method to estimate the slope failure probability. The maximum-entropy method is used to estimate the probability density function (PDF) of the performance function subject to the moment constraints. A numerical example is calculated and compared to the Monte Carlo simulation (MCS) and the Advanced First Order Second Moment Method (AFOSM). The results show the accuracy and efficiency of the proposed method. The proposed method should be valuable for performing probabilistic analyses.

BACKGROUND: Excess body weight measured as body mass index (BMI) has a positive association with risk of common cancers. However, previous meta-analyses related to BMI and liver cancer had inconsistent results. The purpose of the current study is to establish a nonlinear dose-response relationship between BMI and incidence risk of liver cancer. METHODS: A systematic literature search for relevant articles published from 1966 to November 2011 was conducted in PUBMED and EMBASE digital databases. Additional articles were manually searched by using the reference lists of identified papers. Restricted cubic splines and generalized least-squares regression methods were used to model a potential curvilinear relationship and to make a dose-response meta-analysis. Stratified analysis, sensitivity analysis and assessment of bias were performed in our meta-analysis. RESULTS: 8 articles including 1,779,471 cohort individuals were brought into meta-analysis. A non-linear dose-response association between BMI and risk of liver cancer was visually significant (P for nonlinearity0.1), and all value of BMI still presented significantly increased risk of cancer. CONCLUSIONS: The findings from meta-analysis provided that excess BMI had significant increased association with risk of liver cancer, although the biological mechanisms underlying the obesity-cancer link still need to be clarified.