Search

ABSTRACTThis study explores the potential of the GPBoost approach for groundwater quality assessment in comparison to three other gradient boosting-based algorithms. Three methods, random search, grid search, and Bayesian optimization were used to find the optimal values of various hyperparameters with all four-gradient boosting-based algorithms. One hundred and two samples of Entropy weighted water quality index with 14 input parameters are used for assessing groundwater quality. The calculated EWQI values for drinking range between 80.4 and 394.96 in pre-monsoon and 39.6 to 338.79 during the post-monsoon period. Moreover, spatial distribution maps displayed that the central portions of the study area fall under medium water quality. The performances of models were compared based on multiple statistical criteria, including Correlation Coefficient (CC), root mean square error (RMSE), and mean absolute error (MAE). The results reveal that the CC value by all modeling approaches is more than 0.93, suggesting a comparable performance by all methods. Results in terms of RMSE values in predicting the EWQI values suggest GPBoost (random search) model performed better than the other three models, thus suggesting a competitive performance by GPBoost in comparison to other gradient boosting-based approaches. Relative importance analysis provided by random and grid search methods highlights the significance of NO3−, Mg2+, TDS, EC, and TH as important input parameters for predicting EWQI.

ABSTRACTAndrographis paniculatais a medicinal plant used to treat many different ailments. The biomass of A. paniculatacan be used safely either as fresh plant material, after decoction, or in pharmaceutical formulations. In the present study, different application rates of press mud were evaluated for organic cultivation of A. paniculatain the Indo-Gangetic Plains of Uttar Pradesh, India. The vegetative plant growth parameters were positively affected by increased application rates of press mud up to 7.5 and 10 t ha-1. Macro- and micro-nutrient (N, P, Ca, Fe, Zn, Cu, Mn, Mo and Ni) concentrations of the plant tissue increased with the application of press mud. Yields of active compounds in the A. paniculate, i.e. andrographolide, neo-andrographolide and wogonin, increased in line with the increased total plant biomass in response to increased press mud application rates. Soil microbial populations, total heterogeneous bacteria, fungi, actinomycetes and Azotobacteralso increased with increased rates of press mud, as did soil enzyme activities, i.e. dehydrogenase, β-glucosidase, urease, protease and acid phosphatase. Soil pH and bulk density decreased with increased rates of press mud, which was seen as indications of improved soil properties. Furthermore, available macro- and micro-nutrient concentrations in the soil increased with increased rates of press mud. The present study demonstrated that in organic cultivation of A. paniculata, optimised application rates of press mud can be used not only to supplement soil nutrients but also to enhance yields of plant biomass and active constituents of A. paniculata.

The fatal virus SARS-CoV-2 emerged in December 2019, which caused a global pandemic of coronavirus disease, also known as COVID-19. Identification of the naturally occurring bioactive compounds that can inhibit or modulate the proteins and enzymes of the virus SARS-CoV-2 by targeting the host cells and immune system of the human body is an instrumental approach for COVID-19 therapy. It is an attempt to assess the potential of naturally occurring bioactive compounds and their derivatives against coronavirus using molecular docking and molecular dynamics simulation studies, i.e. binding affinity of the active receptors of the host cells to the selected bioactive compound against SARS-CoV-2. Docking and MD simulation studies were carried out in this study to estimate the affinity of the selected bioactive compounds along with the reference drugs remdesivir and ivermectin in opposition to the vital target proteins and enzymes of coronavirus. Among all selected bioactives, as per the computational docking parameters, curcumin has shown excellent binding, especially against ACE-2 and RdRp. Apigenin also showed encouraging results against spike protein comparable to reference drugs remdesivir and ivermectin. These results are furthermore established by the molecular dynamic simulation study and analysis of protein–ligand complex, which shows minimum binding deviation and minor average fluctuations in energies of protein residues throughout the simulation period. Curcumin glucuronide and apigenin 7-glucoside showed the most suitable response as they have a marvellous binding affinity with COVID-19 targets that are responsible for viral entry as well as their further replication into the host cell; hence, they could be some possible potential drug candidates for COVID-19 therapy.

ABSTRACTThis study used data collected over 19 sites to assess groundwater quality status of Kurukshetra (Haryana state, India) for irrigation purposes. Irrigation Water Quality Index (IWQI), Wilcox diagram, and principal component analysis were considered to determine current water quality. ArcGIS was used for spatial distribution of irrigation parameters. Results suggest that out of total samples, 5.3% of groundwater samples fall under ‘High Restriction,’ 68.42% of groundwater samples under ‘Moderate Restriction,’ and 26.28% of groundwater samples under ‘Low Restriction.’ Results of Wilcox and USSL diagrams suggested the suitability of groundwater for irrigation. Wilcox diagram indicated that 78.9% of groundwater samples fall in the Excellent-to-Good region, whereas USSL diagram classified all groundwater samples in low-to-medium or from medium-to-high class range. The results of PCA approach demonstrated that first five principal components (PCs) consisting of nine input variable represent 79.23% of total variance in groundwater quality.

This study presents the development and validation of a high-performance thin layer chromatography (HPTLC) method for quantification of quercetin, stigmasterol, psoralen and niloticin in methanolic extract of leaf samples of Limonia acidissima. For achieving good separation, a mobile phase of Ethyl acetate: Toluene: Formic acid: Methanol in the ratio of 5.5:3:1:0.5 v/v/v/vwas used for stigmasterol and quercetin, and 5:2:1:0.2 v/v/v/vfor psoralen and niloticin. The scanning was performed at 386 and 299 nm. Linear regression analysis showed a good linear range of 100–500 ng per spot. The highest content of quercetin (0.02%) in Karnataka, and stigmasterol (0.081%), psoralen (0.035%), niloticin (0.033%) was found in sample of Uttar Pradesh. The proposed method is precise, reliable and reproducible. The method is selective and can be used for routine analysis of quercetin, stigmasterol, psoralen and niloticin in various crude drugs and extracts that contain these compounds as active ingredients.

ABSTRACTAdvancement in computing power over last decades, deep neural networks (DNNs), consisting of two or more hidden layers with large number of nodes, are being suggested as an alternate to commonly used back-propagation neural networks (BPNN). DNN are found to be flexible models with a very large number of parameters, thus making them capable of modeling complex and highly nonlinear relationships. This paper investigates the potential of a DNN to predict the local scour around bridge piers using field dataset. To update the weights and bias of DNN, an adaptive learning rate optimization algorithm was used. The dataset consists of 232 pier scour measurements, out of which a total of 154 data were used to train whereas remaining 78 data to test the created model. A correlation coefficient value of 0.962 (root mean square error = 0.296 m) was achieved by DNN in comparison to 0.937 (0.390 m) by BPNN, indicating an improved performance by DNN for scour depth perdition. Encouraging performance in present work suggests the need of further studies on the use of DNN for various applications related to water resource engineering as an alternate to much used BPNN.

Bituminous pavements are greatly vulnerable to moisture damage. Most of the studies all over the world conclude that presence of moisture on road surface contributes significantly to pavement failures. Sustainable bituminous pavement needs high quality bitumen material. In roadway design, the tensile strength of bituminous pavements is an important engineering property. Indirect tensile strength (ITS) tests are performed on bituminous mixes for evaluating tensile strength ratio (TSR). Knowledge of TSR is helpful in determining the moisture susceptibility of bituminous concrete (BC) mixes for highway pavements. In the past different modelling techniques were developed to predict the TSR of bituminous mixes. In this study, support vector machines (SVM), M5 model tree and regression-based technique were used to estimate the TSR value of BC mixes. Two kernel functions, i.e. polynomial and radial-based kernel function were used with SVM model. Cross validation technique with 10-fold analysis was used for testing the models. SVM model with radial basis function (RBF) outclasses M5P model all in terms of correlation coefficient and R2values. This paper proposes a simple linear equation for the prediction of the TSR, which is based on ITS tests performed on different types of bituminous mixes.

Net Primary Productivity (NPP) is a fundamental ecological metric that underpins the functioning of ecosystems. NPP estimation using the Carnegie–Ames–Stanford Approach (CASA) biosphere model is carried out for the Roorkee and Hyderabad study sites. The CASA model estimates the NPP at regional and global scales by using data of environmental factors like temperature, precipitation, total solar radiation, and the normalized difference vegetation index. For the study sites, the NPP is estimated using the CASA model, with high agreement between modeled and observed values. The findings show the usefulness of the CASA model for calculating the NPP. For the Roorkee site, the NPP estimates are significantly higher than those for the Hyderabad site. To determine the solar radiation for the Roorkee and Hyderabad stations, this study examines the monthly average values of cloud cover fraction, the duration of sunny hours and global solar radiation on a horizontal surface. It is found out that the relationship between cloud cover fraction and the maximum number of hours that can be spent in the sun is nonlinear. This results in a nonlinear relationship between cloud cover fraction and the solar radiation. The moderate resolution imaging spectroradiometer (MODIS) composite and the Landsat imagery are combined to generate the synthetic normalized difference vegetation index (NDVI) images which are further used as remote sensing data for the estimation of NPP. This study employs a hybrid methodology that combines smoothing, filtering, and regression analysis techniques. The combined mode filter combines the forward and backward Kalman filters.

ABSTRACTThis letter proposes to use two k-nearest neighbours (k-NN) based algorithms namely: randomized k-NN and weighted k-NN for feature selection with two hyperspectral datasets. Two embedded feature selection methods, extreme gradient boosting and random forest classifier and one wrapper-based approach using support vector machine classifier, were used for comparison in terms of classification accuracy with selected features. For all classifications, a support vector machine classifier was used. Comparison of results in terms of classification accuracy with the selected features suggests better performance by randomized k-NN algorithm in comparison to weighted k-NN and other feature selection approaches used in this study. Results with both dataset also indicate that selected features by randomized k-NN based feature selection approach achieve higher accuracy than that with full datasets.

AbstractArtemisia absinthiumis a herbaceous perennial plant with fibrous root and it belongs to the family Asteraceae. Due to having strong fragrance and pungent taste it has ability to defend itself from the herbivore animals. Essential oil extracted from leaves, stem and seeds of A. absinthiumwere analyzed for termite mortality as well as termite repellency. Chemical constituents of essential oil from all three parts were identified and compared by gas chromatography-mass spectroscopy. Total 16 compounds identified in the essential oil of leaves, stem and seeds in which boronyl acetate was present in major amount 26.59 %, 27.17 % and 26.63 % respectively. L-terpenen-4-ol was also identified in higher amount in leaves, stem and seeds; 18.24 %, 17.07 % and 17.3 % respectively. Leaf, stem and seed essential oil tested for termite mortality and repellency against Microcerotermes beesoni. Leaf essential oil showed significant and seed essential oil all were found to have moderate activity.

Groundwater is one of the most valuable sources of water for drinking use. This study uses 94 groundwater samples collected from the tube wells during pre- and post-monsoon period of 2022 from different locations in Rohtak district, Haryana (India). Fourteen hydrochemical parameters for each sample were determined and compared with the standard values prescribed by World Health Organization (WHO) and Bureau of Indian Standards (BIS) 10,500:2015 for drinking purpose. Drinking Water Quality Index (DWQI) calculated using different hydrochemical parameters was found to vary from 95.02 to 448.92 and 93.91–497.72 during pre- and post-monsoon season, respectively. Spatial distribution maps of different hydrochemical parameters and DWQI indicate that the not-permissible water quality values for drinking were found in the western region of the study area during both seasons. Two machine learning algorithms, including Gaussian Process Regression (GPR) and Support-Vector Regression (SVR) algorithms with four kernel functions, were used to predict DWQI value using pre-monsoon samples (training) and post-monsoon samples (testing). Results suggest an improved performance by the SVR algorithm using Radial basis kernel (SVR-RBF) compared to other kernel functions with both SVR and GPR approaches. Sensitivity analysis indicates that TDS, NO3−, and F−are three important parameters for predicting the DWQI. The outcomes of the proposed algorithms will benefit the government authorities and help recommend alternative drinking water in the affected areas.

The comparative analysis of the fatty acid composition of Cassia tora(leaves and stem) was determined using gas chromatography–mass spectrometry. Twenty-seven fatty acids were identified in C. tora(leaves and stem) which was collected from three different geographical areas of India: Lucknow (Uttar Pradesh), Nainital (Uttarakhand), and Bhavnagar (Gujarat), coded as CT-1, CT-2, and CT-3, respectively. The gas chromatography–mass spectrometry analysis showed the presence of various saturated and unsaturated fatty acids. The major fatty acids found were palmitic acid, linoleic acid, linolenic acid, margaric acid, melissic acid, and behenic acid. The highest amounts of saturated fatty acids were found in leaves of C. toracollected from Bhavnagar (Gujarat) (60.7% ± 0.5%). Thus, the study reveals that C. torahas a major amount of nutritionally important fatty acids, along with significant antimicrobial potential. Fatty acids play a significant role in the development of fat products with enhanced nutritional value and clinical application. Remarkable differences were found in the present study between fatty acid profiles of C. toracollected from different locations in India. To the best of our knowledge there is no previously reported comparative study of the fatty acids of C. tora.

M5 model tree, random forest regression (RF) and neural network (NN) based modelling approaches were used to predict oblique load carrying capacity of batter pile groups using 247 laboratory experiments with smooth and rough pile groups. Pile length (L), angle of oblique load (α), sand density (ρ), number of batter piles (B), and number of vertical piles (V) as input and oblique load (Q) as output was used. Results suggest improved performance by RF regression for both pile groups. M5 model tree provides simple linear relation which can be used for the prediction of oblique load for field data also. Model developed using RF regression approach with smooth pile group data was found to be in good agreement for rough piles data. NN based approach was found performing equally well with both smooth and rough piles. Sensitivity analysis using all three modelling approaches suggest angle of oblique load (α) and number of batter pile (B) affect the oblique load capacity for both smooth and rough pile groups.

The present investigation emphasizes the pharmacognostic and phytochemical screening of Eulaliopsis binataand further evaluates the extracts of this plant for toxicological profile and anti-bacterial potential based on in vivo/in vitroassays. Microscopy, powder characteristics of the leaf material, and physicochemical and phytochemical screening were assessed for pharmacognostic evaluation. Dry leaves of Eulaliopsis binatawere extracted using different solvents (methanol, ethyl acetate, and hexane), and the extracts obtained were further investigated for in vitro/in vivotoxicological study. Moreover, acute toxicity was assessed by evaluating the anti-oxidant defense system and anatomical damage in vital organs. In addition, anti-bacterial activity of all the extracts was assessed by the Kirby-Bauer method. Physicochemical and microscopic observations showed the unique identification mark for leaf powder and leaf transverse section. Phytochemical investigation evidenced the presence of flavonoids and phenolic contents in the methanolic extract. All extracts were found to be hemocompatible and exhibited no induction of behavioral alteration and no alteration in the anti-oxidant potential and anatomical structure of the vital organs. On the other hand, the methanolic extract showed a significant upsurge in the reduced glutathione level, whereas all extracts showed significant anti-bacterial potential in a dose-dependent manner. Eulaliopsis binatahas inimitable pharmacognostical characteristics, good safety profile and significant anti-oxidant and anti-bacterial potential that show immense possibility for its further investigation for pharmacological use.

AbstractDietary supplements derived from plants gaining importance in recent years for development of antimicrobial agents due to their lesser side effects and easy availability. The present study consists of comparative study of essential oil components and their antimicrobial activity against human pathogenic bacteria collected from three different geographical areas of India: Baddi (Himachal Pradesh), Lucknow (Uttar Pradesh), and Bangalore (Karnataka), coded as LC-1, LC-2, and LC-3, respectively. Evaluation of chemical constituents of essential oil by gas chromatography-mass spectrometry (GC-MS) were performed. We identified seventeen compounds, representing 85.19-88.52% of the oil under study. The identified sesquiterpene hydrocarbons are in essential oil, with 63.92-70.18%, oxygenated sesquiterpens with 15.68-22.93%, fatty acid with 0.01-0.51% and aldehyde with 0.01-0.02% of the total percentage identified. The major constituents were sesquiterpene hydrocarbon (70.18%) found in essential oil collected from Lucknow, (India). Remarkable difference in content of essential oil and their antimicrobial activity were noticed collected from three different locations of India. Antibacterial activity of the tested oil revealed the highest antibacterial porential was produced by Litchi chinensisoil collected from Lucknow (30 ± 0.01) on S. pyrogens.

A testing program comprising 250 oblique pullout tests was conducted to study the effect of variable parameter on pullout capacity of batter pile groups in sand. Test was conducted in laboratory on five pile groups. Model piles consist of aluminium having three length 0.40, 0.60, 0.90 m at two unit weights 16.28 and 15.79 kN/m3. Two pile surfaces were tested and angle of oblique load was kept at 0°, 10°, 20°, 30°,45º. Analysis of results indicates that increasing value of pile length, sand unit weight, and surface roughness increases the the pullout capacity of oblique piles. Increasing angle of oblique load from horizontal also increases the oblique pullout capacity for batter pile group but have no significant difference at lower angle of oblique load. Difference in oblique load caring capacity for each pile length, unit weight and surface roughness became significant at higher angle of oblique load. ANOVA single factor test indicate except pile surface other parameter viz length, unit weight and angle of oblique load significantly affect oblique load caring capacity.

AbstractEssential oil of Artemisia nilagiricaisolated from aerial parts was analyzed for antitermite activity. Chemical constituents were identified by gas chromatography-mass spectroscopy. Total forty constituents have been identified which is 93.55 % of the essential oil. Major constituents of the oil were α-thujone (33.78 %), germacrene-D (9.31 %), β-thujone (6.01 %), caryophyllene (5.86 %), caryophyllene oxide (6.17 %), borneol (2.16 %). The essential oil consist of 41.34 % monoterpene hydrocarbon, 30.9 % sesquiterpene hydrocarbon, 10.24 % monoterpene alcohol, 8.33 % sesquiterpene oxide along with 2.74 % sesquiterpene alcohol. The essential oil exhibited significant antitermite activity against Microtermes beesonithe termite. ED50for termite repellency was found 4.44 mg/g and 5.81 mg/g for termite mortality. Chlorpyriphos 20 % TC was taken as control, ED50of chlorpyriphos was found 1.53 mg/g. This study indicated that A. nilagiricaessential oil can be used as a wood preservative to control the termites infesting wooden material and commodities.

AbstractHigher and aromatics plants have traditionally been used in folk medicine as well as to extend the shelf life of foods, showing inhibition against bacteria, fungi and yeasts. Most of their properties are due to essential oils produced by their secondary metabolism. Essential oils and extracts from several plant species are able to control microorganisms related to skin, dental caries, and food spoilage, including Gramnegative and Gram-positive bacteria. The present study is based on the evaluation of antimicrobial activity of the essential oil of the fresh leaves of Justicia adhatodaand to identify the chemical constituents responsible for antimicrobial potential. The chemical constituents of essential oil were identified by gas chromatographymass spectrometry (GC-MS).The essential oil was evaluated for the antimicrobial potential against methicillin resistant and sensitive Staphylococcus aureusalong with its clinical isolates. GC-MS analysis revealed that the major constituents of the essential oil were phytol (57.8 %), n-hentriacontane (3.92 %), nonacosane (3.65 %), pentacosane (2.65 %), β-Eudesmol (1.14 %), heneicosane (1.13 %). Result indicates that J. adhatodaleaves essential oil has a strong antimicrobial activity against mentioned microorganisms (MIC: 62.5–250 μg/mL).

Performance of neural networks depends upon several input parameters. Several attempts have been made for optimization of neural network parameters using Taguchi methodology for achieving single objective such as computation effort, computation time, etc. Determination of optimum setting to these parameters still remains a difficult task. Trial-and-error method is one of the frequently used approaches to determine the optimal choice of these parameters. Keeping in view the problems with trial-and-error method, a systematic approach is required to find the optimum value of different parameters of neural network. In the present work, three most important distinct performance measures such as mean square error between actual and prediction, number of iteration, and total training time consumption have been probably considered first time concurrently. The multiobjective problem has been solved using Grey–Taguchi methodology. In this study, optimal combinations of different neural network parameters have been identified by using the Taguchi-based Grey relational analysis. The data set includes 81 sets of milling data corresponding to three-level full factorial experimental design for four cutting parameters, i.e. cutting speed, feed, axial depth of cut, and radial depth of cut, respectively. The output is average surface roughness for the experiment. The performance of different neural network models has been tabulated in L36 orthogonal array. Confidence interval has also been estimated for 95% consistency level to validate the optimum level of different parameters. It was found that the Taguchi-based Grey relational analysis approach can effectively be used as a structured method to optimize the neural network parameters settings, which can be easily implemented to enhance the performance of the neural network model with a relatively small size and time saving experiment. The result clearly indicates that the optimal combination of neural network parameters obtained by using the proposed approach performs better in terms of low mean square error, small number of iterations, and lesser training time required to perform the analysis which further results in lesser computation effort and processing time. Methodology proposed in this work can be utilized for any type of neural network application to find the optimum levels of different parameters.

AbstractCompounds having antimicrobial activity obtained from plant sources are useful because they are new sources against antibiotic resistance. The present study is based on the evaluation of antimicrobial activity of the essential oil of the fresh bark of Betula utilisand to identify the chemical constituents responsible for antimicrobial potential, grown in high altitude of Himalaya, India. The chemical constituents of essential oil were identified by gas chromatography-mass spectrometry (GC-MS). The essential oil was evaluated for the antimicrobial potential against human pathogenic bacteria and fungi by using a micro-dilution assay. GC-MS analysis revealed that the major constituents of the essential oil were geranic acid (11.38 %), β-seleneol (10.98 %), β-linalool (10.91 %), terragon (10.61 %), β-sesquiphellendrene (8.02 %), champacol (6.33 %) and 1,8-cineol (5.49 %). Result showed that B. utilisessential oil has a strong antimicrobial activity against the fungus Candida albicansand Gram (+) and Gram (-) human pathogenic bacteria (MIC: 60.5-240 µg/ml).

Five selective 11β-hydroxysteroid dehydrogenase type 1 (11β-HSD1) competitive inhibitors, hupehenols A–E (1–5), were isolated from Viburnum hupehense. The structure elucidation indicated that compounds 1–5are new 20,21,22,23,24,25,26,27-octanordammarane triterpenoids. Their structures were established on the basis of NMR spectroscopic and mass spectrometric analysis. Hupehenols A–E (1–5) showed inhibition against human 11β-HSD1, with hupehenols B (2) and E (5) having IC50values of 15.3 and 34.0 nM, respectively. Moreover, hupehenols C (3) and D (4) are highly selective inhibitors of human 11β-HSD1 when compared to murine 11β-HSD1.

Three kernel-based modeling approaches are proposed to predict the local scour around bridge piers using field data. Modeling approaches include Gaussian processes regression (GPR), relevance vector machines (RVM) and a kernlised extreme learning machine (KELM). A dataset consisting of 232 upstream pier scour measurements derived from the Bridge Scour Data Management System (BSDMS) was used. The radial basis kernel function was used with all three kernel-based approaches and results were compared with support vector regression and four empirical relations. Coefficient of determination value of 0.922,0.922 and 0.900 (root mean square error, RMSE = 0.297,0.310 and 0.343 m) was achieved by GPR, RVM and KELM algorithm respectively. Comparisons of results with support vector regression and Froehlich equation, Froehlich design, HEC-18 and HEC-18/Mueller predictive equations suggest an improved performance by the proposed approaches. Results with dimensionless data using all three algorithms suggest a better performance by dimensional data. [ABSTRACT FROM AUTHOR]

Holoptelea integrifolia(Sanskrit: chirivilva, Hindi: chilbil, family: Ulmaceae) is a large deciduous tree, growing up to 18 m tall, distributed throughout the greater part of India up to an altitude of 2000 ft. It has grey bark, covered with blisters, peeling in corky scales on old trees. The plant has several medicinal properties such as antiinflammatory, anthelmintic, and antidiabetic activity. The present work was taken up with a view to lay down standards which will contribute significantly to the quality control of the medicinally useful Holopteleaspecies. Till date, there is no comparative phytochemical and antioxidant literature available of this traditionally valuable drug. Biomarkers such as stigmasterol, olenolic acid, ursolic acid, betulin, and lupeol were estimated through high-performance thin-layer chromatography (HPTLC) method, and it was found maximum in Behraich plant sample. The bark of Behraich’s sample shows strong antioxidant activity (2,2-diphenyl-2-picrylhydrazyl [DPPH] assay). It suggests secondary metabolites present in H. integrifoliahaving antioxidant effects, which indicate their effectiveness in diseases caused by overproduction of free radicals. Over all, these comparative data provide a suitable criteria to differentiate the stem barks of the above four Holopteleabarks of different places from India and open a new vista for the exploitation of these species for the development of herbal formulations.

This letter evaluates the effectiveness of a new kernel-based extreme learning machine (ELM) algorithm for a land cover classification using both multi- and hyperspectral remote-sensing data. The results are compared with the most widely used algorithms – support vector machines (SVMs). The results are compared in terms of the ease of use (in terms of the number of user-defined parameters), classification accuracy and computation cost. A radial basis kernel function was used with both the SVM and the kernel-based extreme-learning machine algorithms to ensure compatibility in the comparison of the two algorithms. The results suggest that the new algorithm is similar to, or more accurate than, SVM in terms of classification accuracy, has notable lower computational cost and does not require the implementation of a multiclass strategy.

This letter evaluates the performance of a wrapper–filter genetic algorithm (GA) for feature selection using Digital Airborne Imaging Spectrometer hyperspectral data set. Classification accuracy by k-nearest neighbour (k-NN) and support vector machine (SVM) were used as fitness function with four filter algorithms. Results of wrapper–filter GA-based feature selection approach were compared with a steady-state GA-based approach in terms of number of selected features and the accuracy with selected feature. Result indicates the unsuitability of SVM as wrapper due to large computational cost in comparison to k-NN. Choice of filter algorithm seems to be having no significant effect on classification accuracy obtained using selected features. Comparison in terms of number of selected features and the accuracy with selected features suggests comparable performance by both wrapper–filter and steady-state GAs for the used data set.

This paper presents a Geographic Information System (GIS) based cost estimation methodology, which may be helpful in increasing the productivity of quantity estimator by reducing the manual work in quantity takeoffs. Proposed methodology also eliminates missing or duplication of various items of work by visualizing each components corresponding to the items in three dimension (3D). Several scripts developed within ArcView, a desktop GIS based mapping system, have been used to extract the necessary dimensions from the design drawings (prepared in GIS environment) and to perform various calculations of quantity takeoffs. Accurate Bill of Quantities (BOQ) may be generated on the basis of dimensions of various data themes. Methodology has been designed to store construction resource data (materials, workers, and equipments) in tabular form within the GIS environment. Separate tables have been used for each project to generate BOQ, Bill of Materials (BOM), and labor requirements.

This paper investigates the potential of random forest–based regression approach to predict the local scour around bridge piers using field data set. A data set consisting of 232 field measurements were used. Comparison of results with M5 model tree, bagged M5 model tree, back-propagation neural network and four predictive equations suggests an improved performance by random forest regression approach in modelling the pier scour depth with dimensioned data. The use of random forest regression was also explored to judge the importance of each input variable in predicting bridge pier scour. Results in terms of increase in mean square error with the removal of each input variable suggest the importance of pier width and depth and flow in predicting the pier scour depth with random forest regression.

ABSTRACTKernel-based machine learning algorithms are based on mapping data from the original input feature space to a kernel feature space of higher dimensionality to solve a linear problem in that space. Over the last decade, kernel based classification and regression approaches such as support vector machines have widely been used in remote sensing as well as in various civil engineering applications. In spite of their better performance with different datasets, support vector machines still suffer from shortcomings such as visualization/interpretation of model, choice of kernel and kernel specific parameter as well as the regularization parameter. Relevance vector machines are another kernel based approach being explored for classification and regression with in last few years. The advantages of the relevance vector machines over the support vector machines is the availability of probabilistic predictions, using arbitrary kernel functions and not requiring setting of the regularization parameter. This paper presents a state-of-the-art review of SVM and RVM in remote sensing and provides some details of their use in other civil engineering application also.

ABSTRACTThis paper present results of pan evaporation estimations using Support Vector Machines (SVMs) based approach for the meteorological data from Manasgaon climatic station near Anand Sagar Reservoir, Shegaon. At this station four meteorological variables are measured simultaneously, namely, air temperature, wind speed, sunshine hours and relative humidity. The SVMs architecture involves in using one output parameter (i.e. evaporation) and up to four input parameters representing air temperature, wind speed, sunshine hours and relative humidity. The performance of SVMs approach was compared with multiple linear regression using different combination of meteorological parameters so as to judge the significance of the input parameters in estimating the evaporation. The SVMs algorithm provide good estimation of evaporation with high correlation coefficient along with low Root Mean Square Error. Further, the Scatter Plot between the actual and estimated values of evaporation suggests that most of the values lie within a scatter of ±15%. The findings of this study suggest the usefulness of SVMs algorithm technique in estimating the pan evaporation from reservoirs.

For Abstract see ChemInform Abstract in Full Text.

ChemInform is a weekly Abstracting Service, delivering concise information at a glance that was extracted from about 100 leading journals. To access a ChemInform Abstract of an article which was published elsewhere, please select a “Full Text” option. The original article is trackable via the “References” option.

ChemInform is a weekly Abstracting Service, delivering concise information at a glance that was extracted from about 100 leading journals. To access a ChemInform Abstract of an article which was published elsewhere, please select a “Full Text” option. The original article is trackable via the “References” option.