Search

Manual calculation of the compressive strength of concrete (CSC) is an expensive and time-consuming process. Soft computing methods outperform the statistical methods used to resolve these problems. Nonetheless, complicated prediction models are still incomplete and require more exploration. Artificial neural networks (ANNs) provide a better and faster technique featuring solitary hidden layers and have improved the generalization capacity. The present paper presents three ANN-based (shuffled complex evolution, evaporation rate based water cycle algorithm (ERWCA), and Cuckoo optimization algorithm) prediction models to anticipate the compressive strength of concrete efficiently. An available database from the UCI repository is employed to develop and access the model performance. A comparison is made between the prediction accuracies of the above three techniques. Using all models, a comparative investigation has been conducted to predict the compressive strength of concrete at the curing ages of 91, 56, and 28 days. The experimental findings obtained from the ERWCA-MLP method indicate its capability of robust CSC prediction. On average, this method achieves the minimum RMSE of 0.55314 and 0.43329 and R2 of 0.99803 and 0.99824. The statistical significance test and the comparative analysis of simulation results indicate the superiority of ERWCA-MLP in predicting the compressive strength of concrete. [ABSTRACT FROM AUTHOR]

Eight optimizer methods are combined with a perceptron neural network to achieve an optimal network and minimize errors for predicting the heat transfer rate of a ribbed triple-tube heat exchanger operating with the graphene nanoplatelets-based nanofluid. The optimization techniques consist of Harris Hawks Optimizer (HHO), Grey Wolf Optimizer (GWO), Whale Optimization Algorithm (WOA), Artificial Bee Colony (ABC), Ant Colony Optimization (ACO), Ant Lion Optimizer (ALO), Biogeography-Based Optimization (BBO), and Dragonfly Algorithm (DA). The required data are provided with the aid of numerical simulations. The structural parameters are considered using different rib pitches and heights. The ALO algorithm is the best method for estimating the output. The best performance of this algorithm is gained by population size of 350. By this method, the heat transfer rate is estimated with the Root Mean Square Error (RMSE) values of about 0.0310 and 0.0385 for the training and testing data samples, respectively. Unlabelled Image • Predicting heat transfer of a triple-tube heat exchanger operating with nanofluid. • Eight advanced optimizer algorithms to enhance the performance of neural network. • Using nanofluid having graphene platelets decorated with platinum as working fluid. • ALO is the best method for estimating the output due to lowest deviations. [ABSTRACT FROM AUTHOR]

In this investigation, the individual and synergetic influences of the SiC whiskers and WC particles on the various features of TiC were studied. Fully dense specimens were secured when 40 vol% SiC additive was added to the TiC and TiC-WC systems. The nucleation and growth of the new SiC grains were found as the two main mechanisms positively affecting the sinterability of TiC. Although WC particles were completely dissolved into the TiC matrix in the TiC-WC system, they were entrapped in the newly grown SiC grains in the TiC-WC-SiC system, contributing to strengthening of the specimen. The highest values of flexural strength (590 MPa) and Vickers hardness (2525 HV 0.5 kg) were attained for the sample codoped with SiC whiskers and WC particles. [ABSTRACT FROM AUTHOR]

This investigation aimed to study the individual and synergic impacts of SiC and TiN additives on the sinterability and microstructure of TiB 2 -based ceramics. The hot-pressing method at 2000 °C was implemented to fabricate the samples. All three samples reached their near full densities thanks to the beneficial role of the incorporated phases. In terms of the TiB 2 –SiC composite, the in-situ SiO 2 was produced over the sintering process because of a chemical reaction between TiO 2 oxide and SiC reinforcement. On the other hand, the X-ray diffraction (XRD) pattern, along with the microstructural observations, revealed the in-situ formation of hexagonal BN (hBN) in the TiB 2 –TiN system. Moreover, the dissolution of boron into the TiN additive led to the formation of a solid solution, and consequently, a strong diffusion bonding was achieved. Although no hBN compound was identified in the ternary system of TiB 2 –SiC–TiN, the results confirmed the generation of TiC and TiC 0·3 N 0.7 ingredients during the hot pressing. [ABSTRACT FROM AUTHOR]

The purpose of this paper was to investigate the influence of WC as a sintering aid on the sinterability and mechanical characteristics of TiC. For this purpose, two specimens, namely TiC-5 vol% WC and monolithic TiC, were manufactured using the hot-pressing route at 2000 °C for 2 h under 50 MPa. The addition of WC uplifted the sintering behavior of TiC. The XRD and microscopical evaluations revealed the precipitation of graphitized carbon in the TiC matrix. The results also manifested the complete dissolution of WC in the matrix, forming the (Ti,W)C solid solution. The addition of WC improved the Vickers hardness and flexural strength of TiC by ~12% and ~20%, respectively. Grain size, remaining porosity, and composition of the matrix were identified as the essential factors in boosting the mechanical properties of the TiC-WC specimen compared to the monolithic TiC. [ABSTRACT FROM AUTHOR]

The impact of adding 40 vol% SiC whiskers on the sinterability, flexural strength, and hardness of TiC ceramics was studied. The hot-pressing route was employed to fabricate the TiC–SiC composite, as well as the monolithic TiC ceramic. The microstructural studies and X-ray diffractometry revealed the precipitation of carbon within the TiC matrix owing to the formation of non-stoichiometric TiC x during the hot-pressing. The addition of SiC whiskers noticeably improved the sinterability of TiC, attaining a fully dense composite sample. The nucleation and growth of new SiC grains were identified as the dominant factors in enhancing the relative density of the TiC-40 vol% SiC composite. Moreover, the SiC additive had an effective impact on both flexural strength and hardness of TiC, standing at 543 MPa and 2280 HV 0.5 kg , respectively. [ABSTRACT FROM AUTHOR]

The objective of this research was to evaluate the impact of the morphology of SiC additive on the microstructure development, sintering behavior, hardness, and fracture toughness of TiB 2 -based ceramics. For this purpose, three different samples were produced via the hot-pressing method at 1950 °C under 25 MPa for 120 min. Subsequently, the samples were characterized by XRD, SEM, and optical microscopy. The samples containing SiC particles (SiC p) reached their theoretical densities. XRD results manifested the formation of an in-situ TiC during the hot-pressing. Thermodynamical investigation and SEM fractographs revealed the role of a liquid phase in boosting the sintering behavior of as-sintered ceramics. The SEM images also confirmed the in-situ generation of B 4 C in the specimens doped with SiC whiskers (SiC w). Finally, the most significant Vickers hardness (28.9 GPa) and fracture toughness (6.4 MPa m1/2) was secured for the sample toughened by 30 vol% SiC w , whereas the lowest values, namely a Vickers hardness of 18.1 GPa and a fracture toughness of 5.1 MPa m1/2, were obtained for the composites doped with 30 vol% SiC p , and 15 vol% SiC w + 15 vol% SiC p , respectively. [ABSTRACT FROM AUTHOR]

• Using Sisko model, blood flow is simulated inside an artery with cone shape of stenosis. • An artery radius of 0.002 m was fixed to study the effects of stenosis on the flow behavior. • With increasing stenosis angle, maximum blood flow velocity is sharply increased. • Effect of increasing artery radius versus the influences of stenosis angle, is affected by the stress tension. In this work, using Sisko model, blood flow is simulated inside an artery which have cone shape of stenosis with different angles of φ = 0.25, φ = 0.5, φ = 0.75, φ = 1 and φ = 1.25 degree, respectively. In the first step, an artery radius of 0.002 m is fixed to study the effects of cone shape of arterial stenosis on the flow behavior. Then, stenosis angle of φ = 0.5 degree is fixed to study the effects of different Artery radii of 0.002 m, 0.0025 m, 0.003m, and 0.0035 m orderly on the flow behavior. For simulation the blood flow, Sisko model is used. Afterward, stenosis angle of φ = 0.5 degrees with a radius of 0.002m is fixed for investigating the influences of different behavior of blood fluid by manipulation of constant parameters of the Sisko model. It is reported that with increasing arterial stenosis angle, maximum blood flow velocity is sharply increased in central region of artery from 0.12 m/s to 0.16 m/s, 0.25 m/s, 0.36 m/s and 0.56 m/s in order of increasing stenosis angles from φ = 0.25 to φ = 0.5, φ = 0.75, φ = 1 and φ = 1.25 degree, respectively. Also, maximum shear stress of artery wall are as much as 64 Pa, 42 Pa, 24 Pa, 18 Pa and 16Pa respectively in order of stenosis angles of φ = 0.25, φ = 0.5, φ = 0.75, φ = 1 and φ = 1.25 degree. On the other side, the effect of increasing artery radius is against the influences of stenosis angle, and contradiction of these parameters is affected by the stress tension and viscosity of blood. Variations of blood behavior from non-Newtonian to Newtonian shows that shear stress in blood stream in the stenosis artery with non-Newtonian blood is higher than that of Newtonian blood due to differences in their viscous behaviors and reactions in exposure of stenosis and artery wall effects. [ABSTRACT FROM AUTHOR]

• Newtonian and non-Newtonian behaviors of blood flow are simulated. • Different parameters of Sisko model are employed. • Results of temperature and Nusselt number of blood flow are reported. • Effects of different artery radiuses are studied on the Nusselt number. In this paper, different behaviors of blood flow are simulated inside the artery under applying a constant heat flux on the artery boundary walls. To simulate the blood flow, the Sisko model is employed. Then, the temperature and Nusselt number of blood flow are reported for different Sisko parameters. Afterward, the effects of different artery radiuses are studied on the Nusselt number. Medical treatment by replenishes fluid and electrolytes in the body vessels can change blood flow properties from non-Newtonian behavior to Newtonian behavior, which increases heat transfer in blood flow and causes to reduce blood flow temperature. In this research, the maximum temperature of Newtonian blood fluid flow is reported as much as 310.0045 K, whereas; maximum flow temperature in non-Newtonian blood fluid is 310.007 K. These results emphasize the effects of the type of Newtonian and non-Newtonian fluid model on the thermal behavior of blood inside body vessels. Since medical science does not permit body temperature to be changed from the normal condition, this small variation can be noticeable and sensible on the health. Hence, medical scientific research centers and institutes of vaccine and serum have to be careful in the mechanical design of drugs for blood fluid. The results of this research show the application of mechanical engineering for some of the medical concerns in designing the drugs which are effective on the behavior of human body blood. [ABSTRACT FROM AUTHOR]

Here, an environmentally friendly bottom-up method introduced as an easy, inexpensive, and affordable method for synthesize of graphene-like nanostructures. Results indicated that the presence of FeCl 3 and oxalic acid could improve the quality of the final product impressively. FeCl 3 plays key role for the generation of the high-quality graphene because it acts as both template and catalyst for the formation of graphene. The products were characterized by XRD, FT-IR, TGA, SEM, Raman and TEM analyses. The photocatalytic degradation ability of (graphene/iron oxide/titanium dioxide) Gr/Fe 3 O 4 /TiO 2 nanocomposite for the removal of rhodamine B dyes from wastewater was reported. The obtained adsorbent with porous structure not only exhibited fast adsorption rate, superior adsorption capacity, but also presented convenient magnetic separation characteristic. Synthesized magnetic nanostructures can be separated from reaction mixtures by an external magnet. As a result of its attractive features such as; simple preparation, superior catalytic activity and magnetic recyclability the synthesized nanocomposite obtained in this work provides a new insight to enhance the photocatalytic efficiency. Image 1 • Graphene-like nanosheets produced by a series of green reducing agents via a nontoxic process. • The electrical conductivity was checked and band gap of nanostructures was about 2.65 eV. • Gr/Fe3O4/TiO2 nanocomposite indicated acceptable magnetic behavior for magnetic separation. • Gr/Fe 3 O 4 /TiO 2 nanocomposite indicated photocatalytic activity for the removal of rhodamine B dyes. [ABSTRACT FROM AUTHOR]

In this study, the pollution risks related to arsenic, fluorine, iron, physicochemical parameters, and various indices have been investigated in the Bazoft dam site. The proposed dam is a double-curvature arch dam with a height of 211 m in order to produce hydroelectric energy and the supply of agricultural and drinking water in the west of Iran. Chemical analysis of water samples obtained from springs, river, and boreholes in the dam site was conducted. Anions such as HCO3, Cl, SO4, CO3, and NO3, and cations including Ca, Na, Mg, K, F, Fe, and As had the highest amounts, respectively. The concentration of assessed variables was lower than the WHO permissible limit. The results of the principal factor analysis (PCA) showed that four factors control 82% of the water quality variations. The factors such as EC, TDS, Na, K, SO4−, CO3, HCO3, total hardness, and alkalinity with 43.10% were the most important factors in the dam site. The heavy metals of iron and arsenic have no meaningful relationship with any of the ions. The accuracy of the relations was investigated based on different statistical criteria. The main processes in controlling the water quality are weathering and the dissolution of the carbonates caused by the interaction of water and rock. Ionic ratios indicated that the water origin of the springs is the dolomitic aquifers and the main source of magnesium is carbonate dissolution. The water resources of the dam site are corrosive, and all indices indicate the appropriate quality of water for irrigation and drinking purposes. Filed studies and boreholes water level variations showed that karstification is limit in the dam site. [ABSTRACT FROM AUTHOR]

This investigation intended to assess the influence of SiC morphology on the sinterability and physical-mechanical features of TiB 2 -SiC composites. For this aim, different volume percentages of SiC particles and SiC whiskers were introduced to TiB 2 samples hot-pressed at 1950 °C for 2 h under an external pressure of 25 MPa. The characterization of as-sintered specimens was carried out using X-ray diffraction, optical microscopy, and scanning electron microscopy. The relative density studies revealed that SiC w had a more significant impact on the sinterability of TiB 2 -based composites. The XRD investigation confirmed the production of an in-situ TiC phase during the hot-pressing; however, some peaks related to the graphitized carbon also appeared in the patterns of SiC w -doped ceramics. The addition of 25 vol% SiC p halved the average grain size of TiB 2 while introducing the same content of SiC w decreased this value by just around 20%. Finally, the highest Vickers hardness and fracture toughness were obtained for the sample reinforced with 25 vol% SiC w , standing at 29.3 GPa and 6.1 MPa m1/2, respectively. [ABSTRACT FROM AUTHOR]

In this work, NiAl-WC composite was synthesized by a mechanical activated thermal explosion process from the powder mixture of nickel, tungsten, aluminum, and graphite. The phase, morphology, and microstructure development during milling and after the thermal explosion process were evaluated by XRD, FE-SEM, and TEM-EDS analysis techniques, respectively. The results indicated that after the thermal explosion of an as-mixed powder mixture, unreacted starting powder remained, and some new phases like Al 0.42 Ni 0.52 and W 2 C formed, which confirmed that the synthesis reactions were not completed. But, the final product of 5 h milled powder after the thermal explosion consisted of desired phases, NiAl and WC. XRD results of 5 h milled powder showed that the mechanical activation had two effects on NiAl-WC composite synthesis, reduction of crystallite and particle size, and better mixing of reactant powders and formation of W 2 C phase as an intermediate phase. These effects increased kinetics of reactions, and finally, NiAl-WC composite formed. [ABSTRACT FROM AUTHOR]

• Encasement of stone columns can improve bearing capacity by 3–6 times. • Lateral displacement (bulging) of stone columns decreases with encasement of stone column. • Elasticity modulus of encasement geogrid material can decrease vertical settlement of superstructure. • Short stone columns with low height/diameter ratio are more prone to bulging in shallow depths. • Encasement of short stone columns is more necessary. Improvement of weak base soils under low-rise buildings, storage tanks, bridge piers, and also the treatment of soft foundations of factories and embankments can be achieved by using stone columns. This technique represents an economical method for the improvement of soft and compressible soils. Moreover, because of their environmental compatibility, low cost, and ease of implementation, they have been used for the improvement of weak soils around the world. This paper has investigated the effects of the dimensions, length and main related parameters on the strain–stress behavior of encased and unreinforced (uncased) stone columns. Settlement assessment, the effects of bulging on efficiency, and also geogrid-capped stone columns have been studied. The experimental results have been compared using parametric finite element modeling software. These results showed that short stone columns, even under small stresses, punched into soft soil. In that case, stress concentration occurred along the columns and they punched into the soft soil instead of resisting against wedge rupture formation below the overlying structure. Stone columns at least doubled the bearing capacity of the soft soils and decreased the differential and total settlements if designed according to appropriate conditions, and even if short in length. [ABSTRACT FROM AUTHOR]

This article addresses the spatial analysis of landslide susceptibility in the Ardabil province of Iran. To this end, two well-known optimization algorithms, namely genetic algorithm (GA) and particle swarm optimization (PSO) are synthesized with an adaptive neuro-fuzzy inference system (ANFIS) to create the ensembles of GA-ANFIS and PSO-ANFIS. Besides, the statistical index (SI) model is also performed to be compared with the mentioned intelligent techniques. Fourteen landslide conditioning factors including elevation, slope aspect, land use, plan curvature, profile curvature, soil type, distance to river, distance to road, distance to fault, rainfall, slope degree, stream power index (SPI), topographic wetness index (TWI), and lithology were considered within the geographic information system (GIS). Out of 253 identified landslides, 177 points (70% of them) were randomly selected and used for the training phase, and the remaining 76 points (30% of them) were used to evaluate the accuracy of the SI, GA-ANFIS, and PSO-ANFIS models. Referring to the calculated area under the receiver operating characteristic curve (AUROC) index, the GA-ANFIS (AUROC = 0.914) and SI (AUROC = 0.821) showed the best performance, respectively in the training and testing phases. Notably, ANFIS-PSO emerged as the faster prediction method compared to the GA-ANFIS. Also, from spatial analysis, it was revealed that around 95%, 87%, and 97% of the training landslides, and 96%, 84%, and 76% of the testing landslides are located in hazardous areas. [ABSTRACT FROM AUTHOR]

Current study aimed to combine the multi-layer Perceptron (MLP) neural network technique with five metaheuristic computational algorithms, namely invasive weed optimization (IWO-MLP), dragonfly algorithm (DA-MLP), evolution strategy (ES-MLP), genetic algorithm (GA-MLP), and imperialist competitive algorithm (ICA-MLP) for estimating the monthly natural gas consumption (NGC). For the case of this study, the NGC data was collected from the United States (U.S.) was chosen. To achieve this, a dataset composed of eight independent factors, namely, dry gas production, NGPL production, gross withdrawals, supplemental gaseous fuels, net storage withdrawals, marketed production, net imports, and balancing items, along with a dependent variable of natural gas consumption is provided. Out of 39 samples, a 3-fold ratio is taken to select the datasets of training and testing randomly. During the calculation phase, and through a trial and error procedure, the optimal parameters of the MLP, IWO-MLP, DA-MLP, ES-MLP, GA-MLP, ICA-MLP networks are taken into consideration. To assess the reliability of the proposed technique with the real collected data, three well-known statistical criteria, including mean square error (MSE) and root mean square error (RMSE) as well as coefficient of determination (R ²), are introduced. These indices help to measure the level of accuracy of the used models. It is found that the IWO can be a better predictive network comparing to other hybridized techniques reducing the error performance of the MLP method. The predicted results reveal that hybridizing optimization algorithms could improve the prediction accuracy and helps the MLP to perform more efficiently. The recorded in testing MSE for the IWO-MLP, DA-MLP, ES-MLP, GA-MLP, ICA-MLP prediction techniques (i.e., used for U.S. natural gas consumption estimation) were found 0.000013, 0.002358, 0.024744, 0.013244, and 0.048572, respectively. In the sense of U.S. natural gas consumption prediction, the training R 2 value to 0.9999, 0.9996, 0.9971, 0.9996, and 1.0000 and testing R 2 value of 0.9999, 0.9995, 0.9956, 0.9984, and 0.8115 show that the outputs of the ensemble models are more correlated with the real data. [ABSTRACT FROM AUTHOR]

One of the essential specifications of nanofluids is the rheological behavior that has a significant effect on the system's performance. The primary objective of the present study is to investigate the rheological behavior and dynamic viscosity of the CuO-TiO 2 /water hybrid nanofluid. First of all, the chemical, atomic, and surface structures of the CuO and TiO 2 nanoparticles were examined using X-ray diffraction, Fourier-Transform Infrared Spectroscopy, and Field Emission Scanning Electron Microscopy tests. Then, the two-step method was employed to prepare the needed samples. At the next step, the Dynamic Light Scattering test was used to examine the stability of the nanofluid. Furthermore, dynamic viscosity was measured in the different temperatures, ranging from 25 to 55 °C, and solid concentrations, ranging from 0.1 to 1 vol%. Moreover, the effect of shear rate on the rheological properties of the hybrid nanofluid was investigated. The results revealed that the prepared nanofluid is a Newtonian fluid. The results of dynamic viscosity measurements indicated that the maximum dynamic viscosity is at the solid concentration of 1 vol%, and a temperature of 25 °C. Finally, based on the obtained results, it can be said that considering different cost-benefit analyses, including high stability and low production cost, the studied nanofluids have a high quality and can be considered as an appropriate alternative for replacing the water-based fluid. • Chemical, atomic, and surface structures examined using FESEM, XRD, and FTIR tests. • The nanofluid showed Newtonian behavior over the studied range of shear rates. • The stability of the nanofluid examined by conducting DLS test. • Viscosity showed increasing trend as the solid concentration increased. • Maximum viscosity increased takes place at concentration 1% and temperature 25. [ABSTRACT FROM AUTHOR]

This study pursues optima modification of heating, ventilating, and air conditioning (HVAC) systems embedded in residential buildings through predicting heating load (HL) and cooling load (CL). This purpose is carried out by employing four wise metaheuristic algorithms, namely wind-driven optimization (WDO), whale optimization algorithm (WOA), spotted hyena optimization (SHO), and salp swarm algorithm (SSA) synthesized with a multi-layer perceptron (MLP) neural work in order to overcome the computational shortcomings of this model. The used dataset consists of overall height, glazing area, orientation, relative compactness, wall area, glazing area distribution, roof area, and surface area as independent factors, and the HL and CL as target factors. The results indicated a high capability of all four metaheuristic ensembles for understanding the non-linear relationship between the mentioned factors. Meanwhile, a comparison between the used models revealed that SSA-MLP (Error HL = 1.9178 and Error CL = 2.1830) is the most accurate model, followed by WDO-MLP (Error HL = 1.9863 and Error CL = 2.2424), WOA-MLP (Error HL = 2.1921 and Error CL = 2.5390), and SHO-MLP (Error HL = 3.1092 and Error CL = 4.5930). Regarding the satisfying accuracy of the SSA-based ensemble, it can be a reliable tool for estimating the HL and CL for future smart city planning. [ABSTRACT FROM AUTHOR]

• Prediction of purity has been studied in biodiesel production. • Using machine learning to predict the methyl ester purity of an ultrasound-assisted reactor. • The models performed based on the eight influential inputs. The main effort of this study is to examine the feasibility of four novel machine learning models namely Alternating Model Tree, Random Tree, Least Median Square, and Multi-Layer Perceptron Regressor to estimate the biodiesel purity. Then, the mentioned methods are utilized to identify a relationship between the input and output parameters of the biodiesel system. The parameter response was taken as the essential output of fatty acid methyl ester, while the input parameters opted the oil type, catalyst type, catalyst concentration, reaction temperature, methanol-to-oil ratio, reaction time, frequency as well as amplitude. The predicted results obtained by the tools mentioned supra were evaluated according to several known statistical indices. The obtained results proved that the AMT is the best predictive network. [ABSTRACT FROM AUTHOR]

Sustainable consumption of energy is a crucial task in the building sector. In this paper, a novel hybrid technique, namely elephant herding optimization (EHO) is used to optimize the heating ventilation and air conditioning (HVAC) system through analyzing the relationship between the cooling load (CL) and key factors. In other words, the EHO algorithm is combined with a multi-layer perceptron neural network (MLP) to predict the CL. Two metaheuristic algorithms of ant colony optimization (ACO) and Harris hawks optimization (HHO) are also used as benchmark models. Based on the carried out sensitivity analysis, the EHO with population size = 200 suggests the best-fitted computational parameters of the MLP. The findings revealed that metaheuristic algorithms can develop efficient MLPs for the mentioned objective. However, the proposed EHO-MLP (Error = 2.1284 and Correlation = 0.8934) presents the most accurate perdiction of the CL, followed by the HHO-MLP (Error = 2.3265 and Correlation = 0.8829) and ACO-MLP (Error = 2.6011 and Correlation = 0.8721). Based on the obtained results, the EHO-MLP can be a reliable alternative to traditional models for estimating the CL. [ABSTRACT FROM AUTHOR]

This paper introduces a novel and green way for preparation of Nd 2 Sn 2 O 7 nanostructures applying date palm extract. Various quantities of new fuel, date palm extract, have been applied to achieve the most favorable condition for pure and uniform nanostructures of Nd 2 Sn 2 O 7 through a facile way. Our results revealed that usage of new fuel, date palm extract, and its quantity had substantial role in purity, homogeneity and shape of Nd 2 Sn 2 O 7. To characterize the resulting nanostructures in terms of shape, porosity, dimension, composition and level of purity, different techniques have been served. Moreover, the performance of the fabricated Nd 2 Sn 2 O 7 with date palm extract for electrochemical hydrogen storage has been explored through chronopotentiometry way in alkaline medium, for the first time. The discharge capacity of the fabricated Nd 2 Sn 2 O 7 with date palm extract has been recorded after twenty cycles around 4013 mA h/g (≈14.2 wt%) and the efficiency of the mesoporous Nd 2 Sn 2 O 7 for hydrogen storage has been very favorable at room temperature. [ABSTRACT FROM AUTHOR]

Alcohols have always been an important component of drugs, and their design, discovery, synthesis and preparation play an important role in the diagnosis, prevention and treatment of diseases. To synthesize most of organic compounds, we need to perform a variety of selective hydroxyl protections of reagents to synthesize target molecules. Among these protection reactions, formylation is the most commonly used method to protect the hydroxyl groups in organic synthesis. Methods to convert alcohols to formamides are of interest due to the many uses of formamides as synthetic intermediates. These methods include stoichiometric reactions of formylating reagents and catalytic reactions with ethyl formate as the carbonyl source. This review discusses the reported catalytic approaches for the formylation of alcohols to preparation of formate esters. [ABSTRACT FROM AUTHOR]

One of the most studied topics in analytical chemistry and physics is to develop bio-sensors. Aptamers are small single-stranded RNA or DNA oligonucleotides (5–25 kDa), which have advantages in comparison to their antibodies such as physicochemical stability and high binding specificity. They are able to integrate with proteins or small molecules, including intact viral particles, plant lectins, gene-regulation factor, growth factors, antibodies and enzymes. The aptamers have reportedly shown some unique characteristics, including long shelf-life, simple modification to provide covalent bonds to material surfaces, minor batch variation, cost-effectiveness and slight denaturation susceptibility. These features led important efforts toward the development of aptamer-based sensors, known as apta-sensors classified into optical, electrical and mass-sensitive based on the signal transduction mode. This review provided a number of current advancements in selecting, development criteria, and aptamers application with the focus on the effect of apta-sensors, specifically for disease-associated analyses. The review concentrated on the current reports of apta-sensors that are used for evaluating different food and environmental pollutants. [ABSTRACT FROM AUTHOR]

Using single layer microchannels accompanied by nanofluids is one of the most practical solutions in thermal management of high power density devices. The main challenge in cooling systems of electronic devices is to provide a uniform temperature distribution. In the present study, fluid flow and heat transfer in a fractal microchannel heatsink have been simulated employing the computational fluid dynamics (CFD) method. The fractal microchannel is used to achieve uniform temperature distribution. Thermal performance of single-walled carbon nanotubes (SWCNT) and multi-walled carbon nanotubes (MWCNT) dispersed in the two base fluids of water and kerosene in a fractal microchannel at Reynolds (Re) numbers of 1500 to 3000 are investigated. It should be noted that the nanofluids have been simulated by the two-phase mixture model. The results indicated that the use of fractals silicon microchannel leads to having a uniform temperature distribution. Based on the results, at maximum Re number when the working fluid is water, Nu number and pumping power are 20.9 and 0.033 W whereas, in kerosene flow at the same condition, Nu number and pumping power are 6 and 0.054 W, respectively. According to the obtained results, using the SWCNT nanoparticle compared with the MWCNT nanoparticle leads to a significant enhancement in the Nusselt (Nu) number. This difference is more pronounced by increasing the Re number and nanoparticle volume fraction. In addition, the results indicated that at the same Re number and nanoparticle volume fraction, the performance evaluation criterion of the water-based nanofluid is 4 times higher than that of the kerosene-based nanofluid. So the use of the water as the working fluid with the SWCNT nanoparticle for cooling in the fractal silicon microchannel is recommended. [ABSTRACT FROM AUTHOR]

Strong ground motions usually trigger lots of slope failures in the affected area. In this work, we analyse the occurrence likelihood of earthquake-triggered landslide by employing the ensembles of adaptive neuro-fuzzy inference systems (ANFIS) with four well-known metaheuristics techniques, namely particle swarm optimization (PSO), genetic algorithm (GA), ant colony optimization (ACO), and differential evolution (DE) algorithms. Twelve landslide conditioning factors namely, elevation, slope degree, lithology, peak ground acceleration (PGA), stream power index (SPI), topographic wetness index (TWI), distance to road, distance to river, distance to fault, normalized difference vegetation index (NDVI), slope aspect, and plan curvature are considered within the geographic information system (GIS) to produce the required spatial database. In this paper, frequency ratio (FR) model is used to evaluate the spatial interaction between the landslides and conditioning factors. Meantime, among a total of 458 marked earthquake-induced landslides, 366 (80%) are specified to the learning process, and the remaining 92 (20%) landslides are used to evaluate the accuracy of applied models. The landslide susceptibility maps are generated in the GIS environment. Three accuracy criteria of mean square error (MSE), root mean square error (RMSE), and area under the receiving operating characteristic curve (AUROC) are used to develop a ranking system for comparing the integrity of the designed models. The total ranking scores (TRSs) of 15, 8, 10, and 18, respectively, obtained for PSO-ANFIS, GA-ANFIS, ACO-ANFIS, and DE-ANFIS revealed the superiority of the DE algorithm compared to other metaheuristics techniques. Also, the DE-ANFIS emerged as the fastest ensemble, due to the highest convergence speed obtained for this model. [ABSTRACT FROM AUTHOR]

• An efficient method for image thresholding is proposed. • The Harris hawk optimizer is used for image segmentation. • The Harris hawk optimizer is tested over a multidimensional real problem. • The quality of the segmentation results is higher than other algorithms. • The performance of the algorithm is tested on digital mammograms. Segmentation is a crucial phase in image processing because it simplifies the representation of an image and facilitates its analysis. The multilevel thresholding method is more efficient for segmenting digital mammograms compared to the classic bi-level thresholding since it uses a higher number of intensities to represent different regions in the image. In the literature, there are different techniques for multilevel segmentation; however, most of these approaches do not obtain good segmented images. In addition, they are computationally expensive. Recently, statistical criteria such as Otsu, Kapur, and cross-entropy have been utilized in combination with evolutionary and swarm-based strategies to investigate the optimal threshold values for multilevel segmentation. In this paper, an efficient methodology for multilevel segmentation is proposed using the Harris Hawks Optimization (HHO) algorithm and the minimum cross-entropy as a fitness function. To substantiate the results and effectiveness of the HHO-based method, it has been tested over a benchmark set of reference images, with the Berkeley segmentation database, and with medical images of digital mammography. The proposed HHO-based solver is verified based on other comparable optimizers and two machine learning algorithms K -means and the Fuzzy IterAg. The comparisons were performed based on three groups. This first one is to provide evidence of the optimization capabilities of the HHO using the Wilcoxon test, and the second is to verify segmented image quality using the PSNR, SSIM, and FSIM metrics. Then, the third way is to verify the segmented image comparing it with the ground-truth through the metrics PRI, GCE, and VoI. The experimental results, which are validated by statistical analysis, show that the introduced method produces efficient and reliable results in terms of quality, consistency, and accuracy in comparison with the other methods. This HHO-based method presents an improvement over other segmentation approaches that are currently used in the literature. [ABSTRACT FROM AUTHOR]

• A numerical study is done on the blood flow inside an artery with a cone shape of stenosis. • An artery has different stenosis angles. • The finite volume method is employed to determine blood properties. • Different values of parameters of the Sisko model are employed. • Results of this research show the application of mechanical engineering to support medial concerns. In this work, a numerical study is done on the blood flow inside an artery with a cone shape of stenosis. An artery has different stenosis angles. Also, blood flow is energized by constant heat flux which is applied on the wall. The finite volume method is employed to determine blood properties on the basis of a Sisko fluid model with different constant parameters. Firstly, the effects of applying constant heat flux of q'' = 4 W/m2 are studied on the velocity profile of blood flow inside an artery with stenosis angles of φ = 0.5°. Afterward, effects of different stenosis angles of φ = 0.25, φ = 0.5, φ = 0.75, φ = 1 and φ = 1.25 is studied on blood flow temperature profile. Then, different values of the Sisko model are employed to investigate influences of Newtonian and non-Newtonian behaviors of blood fluid on the temperature profiles of blood flow inside an artery with stenosis angle of φ = 0.5°. It is reported that with increasing stenosis angles, blood flow temperature is decreased due to velocity enhancement. This phenomenon is convinced by non-slip condition and sticking non-Newtonian blood fluid to the internal surface of artery wall which reduce velocity from wall surface region to central region of vessel. Also, it is concluded that changing behavior of blood fluid from non-Newtonian to Newtonian behaviors can empower the capability of blood in thermal energy transfer inside human body vessels. Any treatment by balloon angioplasty, percutaneous transluminal angioplasty, and serum injection, which changes the behavior of blood flow inside body veins, can be effective on blood flow temperature. [ABSTRACT FROM AUTHOR]

One of the famous blue pigments is cobalt aluminate which has a normal spinel that in this work has been synthesized with thermal decomposition technique via the help of olive leaf extract as a precipitation agent. Furthermore, CoAl 2 O 4 /SiO 2 , CoAl 2 O 4 /TiO 2 and CoAl 2 O 4 /graphene nanocomposites were prepared besides the pure one. To investigate the structure and composition of products, X-ray diffraction (XRD) pattern and Fourier transform infrared (FT-IR) analysis were served. Also, the morphologies of products were studied by scanning electron microscopy (SEM) and transmission electron microscopy (TEM) and the effect of different nucleation and growth conditions of the products were investigated. The hydrogen storage ability of the pure CoAl 2 O 4 nanostructures was investigated and to increase the hydrogen storage capacity, different CoAl 2 O 4 nanocomposites were prepared and studied. The maximum discharge capacity and Coulombic efficiencies are 2800 mAh/g and 62% that related toCoAl 2 O 4 /TiO 2 composition and CoAl 2 O 4 , respectively. • The CoAl 2 O 4 spinel was synthesized via olive leaf extract. • Hydrogen storage capacities of CoAl 2 O 4 with its composites were compared. • The Coulombic efficiency of samples was calculated, for the first time. • The discharge capacity increased with the increase of cycle number. • Hydrogen adsorption sites increased by repeating cycles of charge and discharge. [ABSTRACT FROM AUTHOR]

• Non-Newtonian blood flow in the cerebral blood vessels studied. • We used Magnetic Resonance Image to take Digital Imaging. • Impact of Reynolds number, power-law indexes and heat fluxes are investigated. • Pressure drop increase with increasing the Reynolds number and power-law index. • The maximum Nusselt number vessels accrued in the running position of the body. Hemodynamic blood flow analysis in the cerebrovascular is has become one of the important research topics in the bio-mechanic in recent decades. The primary duty of the cerebral blood vessel is supplying Glucose and oxygen for the brain. In this investigation, the non-Newtonian blood flow in the cerebral blood vessels studied. For modeling the geometry of this problem, we used Magnetic Resonance Image (MRI) approach to take Digital Imaging and Communications in Medicine (DICOM) images and using an open-source software package to construct the geometry, which is a complicated one. The power-law indexes, heat flux, and Reynolds number range in the investigation are 0.6 ≤ n ≤ 0.8, 5 ≤ q ≤ 15 Wm −2 and 160 ≤ Re ≤ 310. Effects of Reynolds number, power-law indexes and heat fluxes are investigated. We found that the pressure drop increase with increasing the Reynolds number and power-law index. The maximum Nusselt number in the cerebral blood vessels accrued in the running position of the body in n = 0.8. Also, the highest average wall shear stress occurs in maximum power-law indexes and Reynolds number. By increasing the power-law index and Reynolds number, the wall shear stress increases. [ABSTRACT FROM AUTHOR]

The paper develops a control scheme for a hybrid energy system, including a photovoltaic (PV) panel and a battery energy storage (BES) system. The capital cost of PV systems is considerably high today and it has been continuously trying to mitigate the manufacturing cost and also, several research works have been devoted to developing effective methods to maximize the power output of these generation systems. In this respect, the most efficient technique is named maximum power point tracking (MPPT) for solar PV systems. To this end, this paper utilizes the fuzzy controller and BAT algorithm (BA) to find the optimal values of the parameters of the controller for the MPPT. The presented framework is known as BAT-Fuzzy. Using the mentioned method, the membership functions of the input and output, which are triangular, are autonomously set. The results obtained from simulating the proposed model on a test system shows the superiority of the BAT-Fuzzy technique in terms of the preciseness and convergence rate, while taking into consideration altering values of solar irradiance and temperature. It also performs better, considering the efficiency of the system in practical cases. Besides, the impact of temperature variations and also, different states of the partial shading conditions (PSC) have discussed. The PV system alone does not produce power over some hours of the day and it should be operated jointly with a storage system to generate the required power over all hours of the day. The presented method is simulated using a test system and the results are compared to some well-known methods, verifying that the developed framework is associated with a fast response during transients with enhanced stability. [ABSTRACT FROM AUTHOR]

• EHO, SFLA, SSA, and WDO are Hybridized with MLP. • SSA-MLP presents the most efficient prediction. • Computational weights and biases of the MLP and proposed hybrid algorithms are optimized. Due to the vital significance of precise determination of soil shear strength (SSS) in many civil engineering projects, this study is dedicated to proposing novel intelligent models for estimating this parameter. To this end, elephant herding optimization (EHO), shuffled frog leaping algorithm (SFLA), salp swarm algorithm (SSA), and wind-driven optimization (WDO) are synthesized with artificial neural network (ANN) to create neural ensembles. The results indicated the efficiency of metaheuristic science for dealing with the non-linear analysis of the SSS and influential soil parameters. Also, a comparison between the models revealed that the SSA-MLP (Error = 0.0386 and Correlation = 0.8219) presents the most efficient prediction, followed by WDO-MLP (Error = 0.0403 and Correlation = 0.8025), SFLA-MLP (Error = 0.0408 and Correlation = 0.7559), and EHO-MLP (Error = 0.0436 and Correlation = 0.7195). Therefore, the proposed SSA-MLP can function as a reliable substitute for traditional approaches in prediction of the SSS. [ABSTRACT FROM AUTHOR]

• Indirect measurement of driven piles capacity is presented in this study. • Developing an FA-ANFIS model for prediction of driven piles capacity. • Results signify effectiveness of FA-ANFIS to predict driven piles capacity. Parametric studies of driven piles response during dynamic and static load experiments, especially in the field, are generally too costly to measure. This study constructs and verifies a computational intelligence technique for predicting the bearing capacity of driven piles. The proposed technique is a hybridization of adaptive neuro-fuzzy inference system (ANFIS) and firefly algorithm (FA). It is worth mentioning that this is the first work that explores the ability of FA-ANFIS in the field of piles capacity prediction. In modeling, different FA-ANFIS and ANFIS models were constructed based on different combination of input parameters, and finally, the performances of all models were compared using statistical functions. The results demonstrated that the proposed FA-ANFIS model with coefficient of determination (R2) of 0.997 was more effective than the ANFIS in predicting the pile capacity, and thereby the effectiveness of FA to optimize ANFIS was proved. [ABSTRACT FROM AUTHOR]

Forests are important dynamic systems which are widely affected by fire worldwide. Due to the complexity and non-linearity of the forest fire problem, employing hybrid evolutionary algorithms is a logical task to achieve a reliable approximation of this environmental threat. Three fuzzy-metaheuristic ensembles, based on adaptive neuro-fuzzy inference systems (ANFIS) incorporated with genetic algorithm (GA), particle swarm optimization (PSO), and differential evolution (DE) evolutionary algorithms are used to produce the forest fire susceptibility map (FFSM) of a fire-prone region in Iran. A sensitivity analysis is also executed to evaluate the effectiveness of the proposed ensembles in terms of time and complexity. The results revealed that all models produce FFSMs with acceptable accuracy. However, the superiority of the GA-ANFIS was shown in both recognizing the pattern (AUROC train = 0.912 and Error = 0.1277) and predicting unseen fire events (AUROC test = 0.850 and Error = 0.1638). The optimized structures of the proposed GA-ANFIS and PSO-ANFIS ensembles could be good alternatives to traditional forest fire predictive models, and their FFSMs can be promisingly used for future planning and decision making in the proposed area. • Three Fuzzy-Metaheuristic Ensembles proposed for Spatial Forest Fire Susceptibility Assessment. • The superiority of the GA-ANFIS was proved. • Pattern recognition, as well as unseen fire event predictions, are assessed. [ABSTRACT FROM AUTHOR]

Tailored welded blanks (TWBs) technology can give the important possibilities to obtain components in the automobile industry. Friction stir welding (FSW) is a joining approach, which can adhere parts well with desired properties in weld zone. In this article, the main aim is investigation the effect of weld zone orientation on forming limit diagram (FLD) of the TWBs using experimental and finite element model. Three TWBs are produced FSW with three different orientations of weld zones including 0 0 , 45 0 and 90 0 against major stress direction. The microstructure of the weld zones is divided and then observed via metallography procedures. Tensile tests are carried out to determine the mechanical properties of TWB sections and duplicate the tests numerically to validate the formability results. The Nakazima stretch test is used to derive the limit strains for three different weld orientations (between rolling direction and welding path) and what can be seen is the changeable effect of these ordinations on varying strain paths. The best formability is for TWB with orientation weld 90 0 in tension mode while, results reveals that in Plane strain condition best formability is originated from TWB with weld orientation 0 0 . For biaxial tension condition ε 2 = ε 1 , changing the weld orientation has no effect on formability. The comparison between FEM and experimental tests reveals good agreement and high recommended FEM for this type of study. • Influence of the weld orientation on the Tailor Weld Blanks (TWBs) joined by friction stir welding (FSW). • Three different orientation of weld zones including 0 ∘ , 45 ∘ , a n d 90 ∘ against major stress direction. • Transverse weld orientation has the best formability in uniaxial tension side. • Longitudinal weld orientation is the most formable in plane strain area. • In biaxial tension condition, changing the weld orientation has negligible effect on formability. [ABSTRACT FROM AUTHOR]

• LaFeO 3 nanostructures by new sonochimical method. • Ultrasonic power and time have significant effect on photocatalytic activity. • LaFeO 3 nanostructures prepared by using corn, starch, and rice show higher photocatalytic and antibacterial activity. • Using corn increased degradation efficiency by 65% under visible light. • Fe 2 O 3 as an impurity significantly boosts the degradation efficiency under UV light. In the present work, LaFeO 3 perovskite was prepared via ultrasonic probe with power of 60 W and frequency of 18 KHz. LaFeO 3 nanorods were formed when sonication time was 20 min. In this research, green materials including corn, starch, and rice were used to control the size, morphology, and purity of final products. As-prepared LaFeO 3 nanostructures were used to purify water containing organic contaminants. LaFeO 3 nanostructures prepared by using corn, starch, and rice showed higher photocatalytic activity compare to LaFeO 3 nanostructures without natural capping agents. Using corn increased degradation efficiency by 65% under visible light. XRD results show that Fe 2 O 3 appeared as an impurity when starch was used to prepare LaFeO 3 nanostructures. This impurity significantly boosts the degradation efficiency under UV light. Fe 2 O 3 under UV light act as co-absorbent and boost efficiency by 43%. LaFeO 3 nanostructures were characterized by XRD, EDX, SEM, CV, BET, TEM, DRS and FT-IR. [ABSTRACT FROM AUTHOR]

• Nano-BaMnO 3 fabricated by simple, clean and low cost sonochemical route for the first time. • The effect of different reaction condition investigated on morphology, purity and size of product. • Particle sizes of the nanoparticles depend on the various precursor, reaction time and power of sonication. • BaMnO 3 can use as a catalyst factor in O 2 evolution reaction from water splitting. In the current paper, the main aim is to fabricate the BaMnO 3 nanostructures via the sonochemical route. The various factor, including precursors, reaction time and power of sonication can affect the shape, size, and purity of the samples. We utilized X-ray diffraction (XRD), scanning electron microscope (SEM), transmission electron microscopy (TEM), Fourier transform infrared spectroscopy (FT-IR), and X-ray energy dispersive spectroscopy (EDS) to characterize the BaMnO 3 nanostructures. The optical property of BaMnO 3 nanostructures was explored by Ultraviolet–visible spectroscopy (UV–vis) and the energy gap was suitable for catalytic activity (about 2.75 eV). Changing the precursor can affect the size, nanoparticle shape, architectures, and uniformity of the samples. We employed the BaMnO 3 nanostructures for O 2 evolution reaction as catalysts. It can observe that increasing the homogeneity of the catalysts can increase the efficiency of the Oxygen evolution reaction. The maximum amount of the O 2 evolution and the highest TOF and TON are related to nanoplate disc using barium salicylate as a precursor of barium. As a result, we can nominate the BaMnO 3 nanostructures as an effective and novel catalyst for water-splitting reaction. [ABSTRACT FROM AUTHOR]

In this paper, cadmium sulfide (CdS), sulfur and nitrogen co-doped carbon dots (S,N-CDs) and cadmium sulfide/sulfur and nitrogen co-doped carbon dots (CdS/S,N-CDs) were prepared via hydrothermal route. Cadmium acetate dihydrate, thiourea and citric acid were applied as a source of cadmium, sulfur and carbon respectively. Thiourea plays dual role as a dopant source for doping of carbon dots and sulfur source for the synthesis of cadmium sulfide. The influence of hydrothermal temperature on the morphology of CdS and CdS/S,N-CDs was determined in terms of structure, size and morphology through X-ray diffraction (XRD), transmission electron microscopy (TEM), scanning electron microscopy (SEM), energy-dispersive X-ray spectroscopy (EDS) and Fourier-transform infrared spectroscopy (FTIR) analysis. Results showed that temperature has a significant effect on the morphology of cadmium sulfide. Homogenous flower like morphology of CdS in 160 °C was converted to non-homogenous worm-like particles at 200 °C. Moreover, the flower-like morphology of CdS was converted to the particle morphology during the preparation of CdS/S,N-CDs since the acidity of solution is changed for the presence of citric acid. After morphological and structural engineering, nitrogen and sulfur co-doped carbon dots and CdS/S,N-CDs were applied in dye sensitized solar cells. The J SC of S,N-CDs and CdS/S,N-CDs were measured 14.07 and 18.38 mA/cm2 respectively. Results showed that the V OC equal to 0.61 V for CDs while decreased to 0.59 V in CdS/S,N-CDs case. Although V OC decreased, hole PCE show improvement in CdS/S,N-CDs case, PCE enhanced from 3.44% to 5.7%. Unlabelled Image • CdS/S,N-CDs have been prepared via new and non-complex strategy. • The effect of temperature on the morphological properties of CdS and CdS/S,N-CDs was investigated. • Flower like and particle morphology of CdS and CdS/S,N-CDs were prepared. • Prepared S,N-CDs and CdS/S,N-CDs were applied in dye sensitized solar cells. • The effect of S,N-CDs and CdS/S,N-CDs on performance of solar cell was investigated and compared. [ABSTRACT FROM AUTHOR]

Adding small amounts of drag-reducing agents (DRA) to the crude oil can effectively reduce energy losses and its associated pressure drop in transportation pipelines. They do their roles by reducing the turbulent friction factor of the flowing liquids in the pipeline. In this study, the artificial neural networks (ANN) are utilized for estimation of drag reduction (DR) in crude oil pipelines as a function of Reynolds number, concentration, and type of drag-reducing agents, temperature, and type of pipe. Two different training algorithms, i.e. Levenberg-Marquardt (LM) and imperialist competition algorithm (ICA) are used for adjustment of parameters of multi-layer perceptron (MLP) networks. Predictive accuracies of trained MLP by Levenberg-Marquardt (LM-MLP) and imperialist competition algorithm (ICA-MLP) for estimating drag reduction in crude oil pipelines were compared. The comparisons were done by three statistical criteria, i.e. root mean square error (RMSE), the coefficient of determination (R2), and mean absolute error (MAE). The obtained results show that replacing LM by ICA evolutionary algorithm for adjustment of parameters of MLP leads to increasing R2 from 0.9585 to 0.9791 in the training phase, and from 0.9310 to 0.9698 in the testing phase. Furthermore, ICA has reduced the RMSE and MAE of testing group from 3.0396 to 2.2616 to the 2.0080 and 1.5579, respectively. Finally, a simple ANN-based formulation is provided for using our developed ICA-MLP model to estimate DR in the crude oil pipelines. • Prediction of pressure drop has been investigated in crude oil pipelines. • Artificial neural network employed to predict the drag reduction. • The models performed based on the five influential variables. [ABSTRACT FROM AUTHOR]

Regular optimization techniques have been widely used in landslide-related problems. This paper outlines two novel optimizations of artificial neural network (ANN) using grey wolf optimization (GWO) and biogeography-based optimization (BBO) metaheuristic algorithms in the Ardabil province, Iran. To this end, these algorithms are synthesized with a multi-layer perceptron (MLP) neural network for optimizing its computational parameters. The used spatial database consists of fourteen landslide conditioning factors, namely elevation, slope aspect, land use, plan curvature, profile curvature, soil type, distance to river, distance to road, distance to fault, rainfall, slope degree, stream power index (SPI), topographic wetness index (TWI) and lithology. 70% of the identified landslides are randomly selected to train the proposed models and the remaining 30% is used to evaluate the accuracy of them. Also, the frequency ratio theory is used to analyze the spatial interaction between the landslide and conditioning factors. Obtained values of area under the receiver operating characteristic curve, as well as mean square error and mean absolute error showed that both GWO and BBO hybrid algorithms could efficiently improve the learning capability of the MLP. Besides, the BBO-based ensemble surpasses other implemented models. [ABSTRACT FROM AUTHOR]

In this study, we employed various machine learning-based techniques in predicting factor of safety against slope failures. Different regression methods namely, multi-layer perceptron (MLP), Gaussian process regression (GPR), multiple linear regression (MLR), simple linear regression (SLR), support vector regression (SVR) were used. Traditional methods of slope analysis (e.g., first established in the first half of the twentieth century) used widely as engineering design tools. Offering more progressive design tools, such as machine learning-based predictive algorithms, they draw the attention of many researchers. The main objective of the current study is to evaluate and optimize various machine learning-based and multilinear regression models predicting the safety factor. To prepare training and testing datasets for the predictive models, 630 finite limit equilibrium analysis modelling (i.e., a database including 504 training datasets and 126 testing datasets) were employed on a single-layered cohesive soil layer. The estimated results for the presented database from GPR, MLR, MLP, SLR, and SVR were assessed by various methods. Firstly, the efficiency of applied models was calculated employing various statistical indices. As a result, obtained total scores 20, 35, 50, 10, and 35, respectively for GPR, MLR, MLP, SLR, and SVR, revealed that the MLP outperformed other machine learning-based models. In addition, SVR and MLR presented an almost equal accuracy in estimation, for both training and testing phases. Note that, an acceptable degree of efficiency was obtained for GPR and SLR models. However, GPR showed more precision. Following this, the equation of applied MLP and MLR models (i.e., in their optimal condition) was derived, due to the reliability of their results, to be used in similar slope stability problems. [ABSTRACT FROM AUTHOR]