Search

Stroke is a major cause of mortality and disability, highlighting the importance of prevention. Clinical trials play an important role in evaluating interventions that can maximize stroke prevention. Traditional composite endpoints (TCE) used in clinical trials have limitations, as they pool together events of varying clinical importance. Weighted composite endpoints (WCE) have emerged as a solution to address these limitations and provide more accurate assessments of outcomes. In this study, we investigate the use of WCE in a previously reported negative clinical trial for stroke prevention. We analyzed data from the Vitamin Intervention for Stroke Prevention (VISP) trial, which compared high dose and low dose multivitamin therapy. We utilized weighted methods to analyze time-to-event outcomes with censoring. The primary outcomes of interest were time to nonfatal stroke, nonfatal coronary events, and death. We calculated modified Kaplan-Meier (KM) curves for each intervention group. We also performed a modified log-rank test to assess significant differences based on the weighted KM curves. The analysis included 3668 VISP trial participants, and most remained event-free throughout the study period. The TCE KM curve showed no significant difference in outcomes between high dose and low dose groups. Similarly, the WCE KM curves, with different weights assigned to each outcome, did not reveal significant differences in outcomes between the studied groups. This post-hoc analysis confirms the negative trial results of VISP and demonstrates the feasibility of using WCE in assessing nutrition-based interventions for stroke prevention. • Most cardiovascular trials use composite endpoints to determine efficacy of an outcome. • This traditional form of composite endpoint analysis is limited by pooling events of varying clinical importance. • Weighted composite outcome endpoints have emerged as a solution to provide more accurate assessments of outcomes. [ABSTRACT FROM AUTHOR]

Human Suspicious Activity Recognition (HSAR) is a critical and active research area in computer vision that relies on artificial intelligence reasoning. Significant advances have been made in this field recently due to important applications such as video surveillance. In video surveillance, humans are monitored through video cameras when doing suspicious activities such as kidnapping, fighting, snatching, and a few more. Although numerous techniques have been introduced in the literature for routine human actions (HAR), very few studies are available for HSAR. This study proposes a deep convolutional neural network (CNN) and optimal featuresbased framework for HSAR in video frames. The framework consists of various stages, including preprocessing video frames, fine-tuning deep models (Darknet 19 and Nasnet mobile) using transfer learning, serial-based feature fusion, feature selection via equilibrium feature optimizer, and neural network classifiers for classification. Fine-tuning two models using some hit and trial methods is the first challenge of this work that was later employed for feature extraction. Next, features are fused in a serial approach, and then an improved optimization method is proposed to select the best features. The proposed technique was evaluated on two action datasets, Hybrid-KTH01 and Hybrid-KTH02, and achieved an accuracy of 99.8% and 99.7%, respectively. The proposed method exhibited higher precision compared to existing state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Copyright of Revista Cientifica de la Facultade de Veterinaria is the property of Universidad del Zulia, Facultad de Ciencias Veterinarias and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This research proposed an approach that is intended to determine the minimal set of important factors that influence the desire of learning Korean language in the Gulf Cooperation Council (GCC). Those factors will then influence marketing of the Korean language in GCC by guiding interested people to increase their commercial abilities, improve their information about Korean drama, and prepare them to study or travel to Korea. A total of 500 responses out of 526 questionnaires were used for the analysis process. Merging the weight by SVM and the weight guided feature selection (WGFS) techniques were proposed to build a strong hybrid model of reduction for the investigated dataset. Five different classifiers were used to test the results. Empirical results have showed that the generated factors (the reduct) are very significant to test the ability/inability of learning the Korean language. SVM was shown as the best with accuracy value of 94%. This research contributed to the literature by highlighting the importance of the Korean language in the GCC and by presenting the important factors that influence learners of the Korean language: encouragements and obstacles. Moreover, current research presented the best classifier which yields to the high performance of classification. [ABSTRACT FROM AUTHOR]

We introduce and investigate weighted context-free grammars over an arbitrary bimonoid K. Thus, we do not assume that the operations of K are commutative or idempotent or they distribute over each other. We prove a Chomsky-Schützenberger type theorem for the series generated by our grammars. Moreover, we show that the class of series generated by weighted right-linear grammars over a linearly ordered alphabet Σ and K coincides with that of recognizable series over Σ and K. [ABSTRACT FROM AUTHOR]

As one of the most potential types of low-density parity-check (LDPC) codes, CPM-QC-LDPC code has considerable advantages but there still exist some limitations in practical application, for example, the existing decoding algorithm has a low convergence rate and a high decoding complexity. According to the structural property of this code, we propose a new method based on a CPM-RID decoding algorithm that decodes block-by-block with weights, which are obtained by neural network training. From the simulation results, we can conclude that our proposed method not only improves the bit error rate and frame error rate performance but also increases the convergence rate, when compared with the original CPM-RID decoding algorithm and scaled MSA algorithm. [ABSTRACT FROM AUTHOR]

With the advent of E-Commerce, a huge amount of data is being generated these days. This data can be useful if knowledge can be extracted from the business perspective. People often use websites reviews for decision making about whether the products should be bought or not. Opinion Mining enables the process of selection and decision making easier. Though several techniques exist for opinion mining based on decision making in this paper the approach is novel. In this paper the approach used is in addition to the opinions generated from the reviews collected from E-Commerce websites and calculating the overall sentiment for decision making, this paper also incorporates a priority for particular features of a product entered by the buyer for making the final decision. This has been incorporated in the form of additional weights which can be entered by the user and adjusted according to the priority. The reason to do this is that priority for a particular feature of a product may vary from person to person. Moreover, the final decision lay in the buyer’s hand in addition to the opinions collected and analysed from reviews. [ABSTRACT FROM AUTHOR]

Copyright of Journal of International Social Research is the property of Journal of International Social Research and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Conventional time series forecast models can hardly develop the inherent rules of complex non-linear dynamic systems because the strict assumptions they need cannot always be met in reality, whereas fuzzy time series (FTS) techniques can be used even the records of times series have uncertainty and instability since they do not need strict assumptions. In previous study of FTS, the process of aggregating the past observations and assigning proper weights of fuzzy logical relationship groups are ignored, which may lead to poor forecasting accuracy since they are important aspects in time series prediction and analysis where determination of future trends depends only on past observations. In this paper, a novel high-order FTS model is constructed to make time series forecasting. Specifically, by applying the harmony search intelligence algorithm, the optimal lengths of intervals are tuned. Moreover, regularly increasing monotonic quantifiers are employed on fuzzy sets to obtain the weights of ordered weighted aggregation. Simultaneously, the weights of right-hand side of fuzzy logical relationship groups are explored to compensate the presence of bias in the prediction. In the part of empirical analysis, the developed model was applied to predict three well-known time series: numbers of enrollment of Alabama University, TAIEX and electricity load demand of New South Wales and the results obtained were compared with several counterparts, including some old and recently developed models. Experimental results demonstrate that the developed model cannot only achieve higher accuracy of prediction, but also capture the fuzzy features and characters. [ABSTRACT FROM AUTHOR]

We give a brief overview of common sampling designs used in a survey setting, and introduce the principal inferential paradigms under which data from complex surveys may be analyzed. In particular, we distinguish between design-based, model-based and model-assisted approaches. Simple examples highlight the key differences between the approaches. We discuss the interplay between inferential approaches and targets of inference and the important issue of variance estimation. [ABSTRACT FROM AUTHOR]

Copyright of Archaeologia Baltica is the property of Archaeologia Baltica and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The aim of the paper is to present a new methodology for evaluating quality of distance learning courses (DLC). DLC quality management is one of the main parts of the overall knowledge management activities in Higher Education institutions. The methodology proposed consists of creation of DLC quality model (i.e. criteria system), and consecutive application of several stages of new quality evaluation method based both on Fuzzy and Analytic Hierarchy Process (AHP) methods. Since DLC consists of two parts i.e. the content of the course and particular learning methods implemented by application of services and tools provided by virtual learning environments (VLE), DLC quality model should consist both of online content quality criteria, and VLE quality criteria. Since quality is a very complicated notion depending on multiple criteria, one should use multiple criteria decision analysis theory to create DLC alternatives’ evaluation methodology. Evaluation method proposed consists of application of MCEQLS (multiple criteria evaluation of the quality of learning software) approach using triangular Fuzzy numbers to elaborate the ratings (values) of the quality criteria, and criteria weights elaboration method based on Fuzzy and AHP methods. The last method is absolutely novel in scientific literature. [ABSTRACT FROM AUTHOR]

In this paper, we wish to define a 2-inner product, non-standard, possibly with weights, on ℓ p . For this purpose, we aim to obtain a different 2-norm ‖., .‖ 2, v,w , which is not equivalent to the usual 2-norm ‖., .‖ p on ℓ p (except with the condition p = 2 ), satisfying the parallelogram law. We discuss the properties of the induced 2-norm ‖., .‖ 2, v,w and its relationships with the usual 2-norm on ℓ p . We also find that the 2-inner product ⟨., .|.⟩ v,w is actually defined on a larger space. [ABSTRACT FROM AUTHOR]

Copyright of Arquivo Brasileiro de Medicina Veterinaria e Zootecnia is the property of Universidade Federal de Minas Gerais, Escola de Veterinaria and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Community detection is the one of the most relevant and important topics in the field of graph mining, principally for its applications in number of domains such as social or biological networks analysis to transport systems. Different community detection algorithms have been proposed earlier. This paper discusses and proposes a new technique on particular community detection and its retrieval in social community graph. Community detection constitutes a significant role for analysis of a large community graph by enabling and selecting the desired community's graph. It tries to extract a sub-community graph from a very large community graph for analysis. This paper presents both a theoretical and experimental result in this direction with certain example. We have retrieved the sub-community graph from a compressed community graph in the context of graph mining techniques. Observation concludes that the proposed technique is simpler, easier and efficient in terms of complexities. [ABSTRACT FROM AUTHOR]

Latin was studied and used by scholars in many Western countries before. If we, the people, give up all humanities studies and practices, individuals will become more or less machines. Humanities study and practice do not destroy our ecological system and the practices, if resumed or widely continued, are themselves the very sustainability of human tradition and identity. [ABSTRACT FROM AUTHOR]

The description of quality software metrics is presented. Based on a set of quality characteristics, specialized and application oriented characteristics systems are built. For each characteristic there are countless level estimation models, from which a significant one is debated. A model in which the codomain is between [0,1] is selected for each characteristic correlated with a high level of orthogonality in relation to other characteristics that are part of the system. An aggregate indicator with the codomain between [0,1] is built using weights that create a more comprehensive overview of software quality. The importance of defining techniques for weights calculation is presented. The properties obtained for the weights are analyzed using different techniques. [ABSTRACT FROM AUTHOR]

Due to the exponential growth of documents on internet, users want all the relevant data at one place without any hassle. This led to the growth of Automatic Text Summarization. For extractive text summarization in which representative sentences from the document itself are selected as summary, various statistical, knowledge based and discourse based methods are proposed by researchers. The goal of this paper is to give a survey on the important techniques and methodologies that are employed using Genetic Algorithms in Automatic Text Summarization. This paper gives a review of the growth and improvement in the techniques of Automatic Text Summarization on implementing Evolutionary Algorithms techniques. We propose a broad set of features that considers additional features in the fitness function. [ABSTRACT FROM AUTHOR]

Copyright of Archeologické Rozhledy is the property of Academy of Sciences of the Czech Republic, Institute of Archaeology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The article presents a study which analyses the rainfall and actual rainfall in Huanren basin using the global forecast system (GFS). Results indicate that the GFS rainfall forecast is higher than without the consideration of forecast horizon weights. Moreover, proposed is a method that has greater significance for reservoir operation.

In Romania, law 151/1998 were created 8 development regions, which constitute the design, implementation and evaluation of regional development policy, as well as for collecting specific statistical data in accordance with the regulations issued by EUROSTAT. They were created through the voluntary cooperation of the counties. These regions have similar dimensions as the number of inhabitants, and with the exception of the Bucharest-Ilfov region and area. Starting from the role that SMEs have in the development of the national economy we intend to analyse, in the following, to what extent the investment effort in the indicators of results and the value turnover using data available for 2011. [ABSTRACT FROM AUTHOR]

In this paper, we assumed to analyze the distribution of SMEs in regional structure for the year 2012. The importance of those enterprises in the national economy after 1999 is confirmed by their more and more addition to the economic growth, the creation of new work places, the intensification of the privatization process and improvement of the regional repartition of economic activities, and also the access to European funds. [ABSTRACT FROM AUTHOR]

Territorial statistical series were and are used to analyze phenomena depending on space or place where they are produced, having a special importance at macroeconomic level. In our opinion, to understand how the local series are very helpful, we have to know the system of indicators, the methodology for calculating the indices as a measure of phenomena variability and possibilities / issues related to graphical representation. [ABSTRACT FROM AUTHOR]

Heart failure (HF) is a significant health problem in the United States. It is estimated that 5.8 million Americans currently live with a diagnosis of HF (American Heart Association, 2010). Despite the fact that daily weight monitoring of patients with HF in the hospital has long been a standard part of monitoring effectiveness of treatment, the literature is lacking recommendations based on evidence specific to the optimal time of day for weighing inpatients. The clinical question under consideration is the following: In hospitalized patients with HF, does consistently measuring weights in the evening compared to early morning accurately reflect differences in net weight gain or loss? In this quasi-experimental, prospective cohort pilot study, 29 patients who met inclusion criteria were weighed in the morning and again in the evening. Results of this study revealed predictable differences for morning (M = 3.09, SD = 2.06) and evening weights (M = 2.47, SD = 1.80); t(28) = -2.602, p = .015. For study patients with three consecutive days of weights (N = 24), Pearson product-moment correlations revealed a statistically significant correlation between individual differences/changes in a.m. and p.m. weights, r.22) = .752,p < .001. The implication for clinical practice is that weights should be measured at a consistent time of day. This may be the morning or evening. [ABSTRACT FROM AUTHOR]

Abstract: This paper presents a blind robust digital image watermarking approach based on back propagation neural network in DWT domain. The cover image is decomposed up to 4-levels using DWT. The bitmap of size 64x64 is selected as a watermark. The Back Propagation Neural Network (BPNN) is implemented while embedding and extracting the watermark. In BPNN the errors will be back propagated to the input layer, so that the weights and learning rate parameters may be changed to get the output. The BPNN is trained in such a way that it converges fast and reaches high accuracy. The proposed watermarking algorithm is imperceptible and robust to some normal attacks such as JPEG compression, salt and pepper noise, rotation, median filtering and cropping. [Copyright &y& Elsevier]

Abstract: In order to design geo-hazard prevention and control planning better, according to a detailed investigation of geohazard information, the geological environment conditions and the characteristics of geo-hazard in Huangling County were detailed analyzed, the geo-hazard evaluation index were determined and quantified, the weights were gotten using a method combining the qualitative analysis with quantitative calculation, geo-hazard risk was evaluated in weighted sum method. The results show that the high-risk areas mainly distributed in Luohe River valley area, Juhe River valley area and Nanchuan River valley area. The area have great resident population, frequent movement of floating, fast urbanization and strong human engineering activities. The high-risk and middle-risk geo-hazards are widely developed. The risk evaluation result is consistent with the actual situation, and is credible. [Copyright &y& Elsevier]

To improve the face recognition rate of two dimension principal component analysis (2DPCA), a modified method of 2DPCA based on modular images is proposed. In this paper, the weights function is introduced to define the total scatter matrix according to the distances between the within-class images and the average of the within-class images. We apply it into the modular images. The improved 2DPCA is used to extract feature in the training sample sub-images for pattern classification. Results of the experiments based on ORL face database show that it can effectively improve the rate of face recognition. [ABSTRACT FROM AUTHOR]

The paper presents the process of selection the pile-columns instalment alternative, which have to be the most appropriate and effective. The selection is based on a set of criteria: Mass, Cost of instalment, Labour expenditures, Machinery expenditures, Earthwork amount and Instalment tolerance. The criteria for evaluation are selected by taking into consideration the interests and goals of the client as well as factors that influence the efficiency of construction process. Their weights were determined by applying entropy method. The entropy is described as the casual value of the uncertainty which makes it more valuable in comparison with other factors. The solution of problem was made by applying Additive Ratio ASsessment (ARAS) method. The proposed technique could further be applied to substantiate the selection of effective alternative of structures, technologies, investments, etc. [ABSTRACT FROM AUTHOR]

The article discusses the assessment of the influence of the epistasis parameter in the models of genetic assessment by examining composite bovine data. The inclusion of the epistasis effects on the model of the genetic assessment did not modify much the estimation of the genetic additive (co)variances components and the heritability, but it was considerably superior based on the likelihood ratio test for the examined properties.

To effectively protect drinking water resources, a scientific assessment on site selection of River drinking water resources was carried out. Twenty - eight key factors including law, environmental quality, water resources assurance and environmental risk were selected, and based on analytic hierarchy process (AHP), a mathematical model of assessment system was established. The weight of factors was defined by the method of document data and expert questionnaire, and these weights were synthesized under single criterion. These influence factors were classified and quantized with laws, technical standards and statistical data. According to the calculation of factor scores and weights, the recommendations of site selection can be given. [ABSTRACT FROM AUTHOR]

Copyright of Health SA Gesondheid is the property of African Online Scientific Information System PTY LTD and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

One of the most pronounced changes associated with aging is the impairment of movement, related in part to decreased strength. This study evaluated the effect of using hand-held and ankle weights on isometric strength and functional ability with a group of healthy older adults participating in an 8-week Body Recall exercise programme. Body Recall consists of 60 minutes of group instruction using rhythmic movements in a manner feasible for older adults of all fitness levels. Thirty-two healthy subjects were randomly assigned to two experimental groups; Body Recall (BR) or Body Recall with weights (BR+W). Isometric strength was measured with a hand-held dynamometer for shoulder flexion, knee extension, hip flexion, ankle plantar flexion and grip strength. Subjects in the BR+W group underwent a functional ability test designed to simulate grocery shopping. This test consisted of standing from a sitting position, walking 15.2 m and returning 15.2 m carrying a self-selected weight simulating a bag of groceries. A decreased time or increased weight carried while performing this task was an indication of greater functional ability. A significant increase in isometric strength for BR+W in comparison to BR was found for ankle plantar flexion (53.2 ± 16.9 to 69.6 ± 12.2 Kg, p< 0.01) as well as hip flexion (34.2 ±13.9 to 46.0 ± 7.3 Kg, p< 0.05). There was no significant change (p > 0.05) in the time to complete the functional ability test, however, subjects significantly increased (p <0.05) the weight carried during this assessment. Adding weights to low intensity body movements increased lower extremity isometric strength as well as the capacity to carry weight during a functional task. [ABSTRACT FROM AUTHOR]

A simplified neural model to optimize a project team and to attain maximum throughput as well as to obtain high quality software has been proposed here. A novel approach, which uses the concept of Artificial Neural Networks, to train the software professionals and make them perform at high level of standards, is adopted In this approach, a high level of communication among the professionals is achieved which will lead to good team work and finally produce quality software that meets the required level of standard. [ABSTRACT FROM AUTHOR]

In this paper, we present a study on the sensitivity of aggregation methods with respect to the weights associated with objective functions of a multiobjective optimization problem. To do this study, we have developped some measurements such as the speed metric or the distribution metric. We have performed this study on a set of biobjective optimization test problems: a convex, a non-convex, a continuous and a combinatorial test problems. We show that some aggregation methods are more sensitive than others. [ABSTRACT FROM AUTHOR]

This article introduces a discrete choice model which incorporates a nonlinear structural adjustment to the standard utility coefficients or decision weights. The proposed model is theoretically and empirically appealing when compared to several alternative approaches, and it can be estimated by conventional maximum likelihood. Application of the proposed model in a case study shows that it outperforms two competing approaches in model fit. Given its simplicity, this model is also capable of revealing consumers' heterogeneous choices. It is shown that based on consumers' different characteristics, their product choice and its welfare implications are also potentially different. [ABSTRACT FROM AUTHOR]

Fuzzy Multiple Attribute Decision Making (MADM) problems are commonly encountered in everyday aspect of life. They aim at selecting the optimal alternative among some courses of action in the presence of multiple, usually conflicting, attributes with fuzzy performance ratings. The selection procedures of ranking alternatives of almost all the studies in the area of fuzzy MADM are based on the decision matrix. However, in real situations, the selection procedure of an MADM problem is usually conducted by a group of experts (or consultants). Due to the intrinsic differences between these experts (or consultants), the performance ratings for each alternative of the alternatives obtained from them are different from one another. Hence, it seems to be inappropriate to use only one value as the representative of the performance ratings for each alternative of the alternatives. The main purpose of this paper is to determine the attribute weights of the MADM problem where the decision maker's preference information on alternatives is known and is described by a reciprocal binary fuzzy relation through probability techniques. Besides, after the attribute weights being determined, we further concern with the problem of determining the optimal number of the performance ratings for each attribute of the alternatives. [ABSTRACT FROM AUTHOR]

Weights of 118 female and 141 male Minnesota Wolves (Canis lupus) aged 2-24 months increased almost linearly from about 8kg for females and 10kg for males at 3 months to 30kg for females and 32kg for males at 10-12 months and then tended to increase much more slowly in an overall curvilinear trend. Considerable variation was apparent for both sexes during their first year. [ABSTRACT FROM AUTHOR]

While planned complex suicides utilize more than one method, on occasion a planned suicide merely involves augmentation of the lethality of the chosen single method. A study was undertaken of augmented suicidal drownings from Forensic Science SA, Adelaide, Australia over a 25-year period (1993-2017). 493 cases (M:F 2.6:1) were found in which death was attributed to drowning. The age range for males was 7mths-93yrs (mean 43.7yrs) and for females 11mths-87yrs (mean 48.2yrs). A subset of 116 suicidal drownings (M:F 1.2:1) had a male age range of 17-86yrs (mean 52.3yrs) and for females 19-68yrs (mean 57.4yrs). 16 individuals in this group (3% of drownings overall) had utilised weights to assist in their submersion (M:F 1.7:1), with an age range for males of 30-84yrs (mean 63.3yrs) and for females 38-81yrs (mean 54.6yrs). The most common weights were bricks, rocks or concrete blocks (N = 7) with weights that were tied to the body most often attached to the neck (N = 7). Augmented drowning by using weights to enhance submersion was not common in this population and was predominantly a technique utilised by older males. Augmentation of a suicide method may be extremely useful support at a death scene to exclude an accident. [ABSTRACT FROM AUTHOR]

The quasi-sparse response surface (QSRS) can be employed in simulation based design and optimization of complex products since it can accurately and efficiently approach the black-box function using a few design sampling points. In the training process, a few atoms from a dictionary are chosen to fit the sampling points to construct the response surface. Due to their higher oscillation frequency, higher-order atoms are able to better fit only a few sampling points; however, the overfitting problem decreases the prediction accuracy. In this paper, the weighting method is employed for QSRS to regularize the order of atoms in the process of atom selection to reduce the problem of overfitting. The coefficients of atoms are calculated based on the ł 1 minimization method. Lower-order atoms are given larger weights, while higher-order atoms are given smaller weights. Lower-order atoms with larger weights will receive smaller coefficients and be more easily chosen to construct the response surface, which can reduce overfitting. For the QSRS of low-dimensional simulation problem contains higher order atoms than high-dimensional simulation problem, the weighting method can have better results. The Gaussian kernel function is recommended as the weight function for QSRS. The Gaussian kernel weighed QSRS is compared with an inverse function weighted QSRS, un-weighted QSRS, and other 4 response surface models based on 16 benchmark functions and 1 engineering application. The results show that the weighting method can effectively improve the approximation accuracy and maintain good robustness for QSRS. • Weighting method is proposed to reduce overfitting for quasi-sparse response surface. • The proposed method is suitable for the low-dimensional simulation problems. • Gaussian kernel function is compared and selected as the weighting function. • The advantage is proved in 16 benchmark functions and 1 engineering application. [ABSTRACT FROM AUTHOR]

Water quality assessment and monitoring is one of the most important aspects for ensuring a good environmental health. A Water Quality Index (WQI) is one of the most frequently used tools for assessing overall quality of water resources. This study uses Factor Analysis (FA) for one of the most significant steps in WQI development – weight determination. Factor analysis has been applied to the water quality parameters shortlisted from Principal Component Analysis in the study area and it grouped the parameters into different sets of loadings. Each loading contained a group of parameters contributing to the overall variance addressed by that loading. Weights were allocated to each loading as well as to individual parameters within each loading. For final aggregation, a hybrid method was followed; where weighted harmonic means were estimated for the parameters within each loading and weighted arithmetic mean was estimated from the results of harmonic mean. The use of multivariate statistical technique reduces the subjectivity in the development of the final WQI and makes the current study a useful step in future for the development of a Ganga Water Quality Index (GWQI). In addition to this, the developed methodology can also be used for developing WQI for any water body depending on the availability of historical data. Image 1 • Ganga Water Quality Index is a novel approach to give a complete picture of the water quality of river Ganga. • Factor Analysis complements it by statistically distributing weights. • Weights are assigned to parameters and individual factors to which they contribute. • Hybrid weighted aggregation gives the final index value. [ABSTRACT FROM AUTHOR]