A comparative study of different machine learning methods for landslide susceptibility assessment: A case study of Uttarakhand area (India)

Landslide susceptibility assessment of Uttarakhand area of India has been done by applying five machine learning methods namely Support Vector Machines (SVM), Logistic Regression (LR), Fisher's Linear Discriminant Analysis (FLDA), Bayesian Network (BN), and Naïve Bayes (NB). Performance of these methods has been evaluated using the ROC curve and statistical index based methods. Analysis and comparison of the results show that all five landslide models performed well for landslide susceptibility assessment (AUC = 0.910–0.950). However, it has been observed that the SVM model (AUC = 0.950) has the best performance in comparison to other landslide models, followed by the LR model (AUC = 0.922), the FLDA model (AUC = 0.921), the BN model (AUC = 0.915), and the NB model (AUC = 0.910), respectively.     

Classifier ensemble generation and selection with multiple feature representations for classification applications in computer-aided detection and diagnosis on mammography

This paper presents a novel ensemble classifier framework for improved classification of mammographic lesions in Computer-aided Detection (CADe) and Diagnosis (CADx) systems. Compared to previously developed classification techniques in mammography, the main novelty of proposed method is twofold: (1) the “combined use” of different feature representations (of the same instance) and data resampling to generate more diverse and accurate base classifiers as ensemble members and (2) the incorporation of a novel “ensemble selection” mechanism to further maximize the overall classification performance. In addition, as opposed to conventional ensemble learning, our proposed ensemble framework has the advantage of working well with both weak and strong classifiers, extensively used in mammography CADe and/or CADx systems. Extensive experiments have been performed using benchmark mammogram dataset to test the proposed method on two classification applications: (1) false-positive (FP) reduction using classification between masses and normal tissues, and (2) diagnosis using classification between malignant and benign masses. Results showed promising results that the proposed method (area under the ROC curve (AUC) of 0.932 and 0.878, each obtained for the aforementioned two classification applications, respectively) impressively outperforms (by an order of magnitude) the most commonly used single neural network (AUC = 0.819 and AUC =0.754) and support vector machine (AUC = 0.849 and AUC = 0.773) based classification approaches. In addition, the feasibility of our method has been successfully demonstrated by comparing other state-of-the-art ensemble classification techniques such as Gentle AdaBoost and Random Forest learning algorithms.     

Cardiac ScoreCard: A diagnostic multivariate index assay system for predicting a spectrum of cardiovascular disease

Clinical decision support systems (CDSSs) have the potential to save lives and reduce unnecessary costs through early detection and frequent monitoring of both traditional risk factors and novel biomarkers for cardiovascular disease (CVD). However, the widespread adoption of CDSSs for the identification of heart diseases has been limited, likely due to the poor interpretability of clinically relevant results and the lack of seamless integration between measurements and disease predictions. In this paper we present the Cardiac ScoreCard—a multivariate index assay system with the potential to assist in the diagnosis and prognosis of a spectrum of CVD. The Cardiac ScoreCard system is based on lasso logistic regression techniques which utilize both patient demographics and novel biomarker data for the prediction of heart failure (HF) and cardiac wellness. Lasso logistic regression models were trained on a merged clinical dataset comprising 579 patients with 6 traditional risk factors and 14 biomarker measurements. The prediction performance of the Cardiac ScoreCard was assessed with 5-fold cross-validation and compared with reference methods. The experimental results reveal that the ScoreCard models improved performance in discriminating disease versus non-case (AUC = 0.8403 and 0.9412 for cardiac wellness and HF, respectively), and the models exhibit good calibration. Clinical insights to the prediction of HF and cardiac wellness are provided in the form of logistic regression coefficients which suggest that augmenting the traditional risk factors with a multimarker panel spanning a diverse cardiovascular pathophysiology provides improved performance over reference methods. Additionally, a framework is provided for seamless integration with biomarker measurements from point-of-care medical microdevices, and a lasso-based feature selection process is described for the down-selection of biomarkers in multimarker panels.     

Comparison of artificial neural network and combined models in estimating spatial distribution of snow depth and snow water equivalent in Samsami basin of Iran

Snow water equivalent (SWE) is a key parameter in hydrological cycle, and information on regional SWE is required for various hydrological and meteorological applications, as well as for hydropower production and flood forecasting. This study compares the snow depth and SWE estimated by multivariate linear regression (MLR), discriminant function analysis, ordinary kriging, ordinary kriging-multivariate linear regression, ordinary kriging-discriminant function analysis, artificial neural network (ANN) and neural network-genetic algorithm (NNGA) models. The analysis was performed in the 5.2 km² area of Samsami basin, located in the southwest of Iran. Statistical criteria were used to measure the models’ performances. The results indicated that NNGA, ANN and MLR methods were able to predict SWE at the desirable level of accuracy. However, the NNGA model with the highest coefficient of determination (R ² = 0.70, P value < 0.05) and minimum root mean square error (RMSE = 0.202 cm) provided the best results among the other models. The lower SWE values were registered in the east of study area and higher SWE values appeared in the west of study area where altitude was higher.     

A gender matching effect in learning with pedagogical agents in an immersive virtual reality science simulation

The main objective of this study is to determine whether boys and girls learn better when the characteristics of the pedagogical agent are matched to the gender of the learner while learning in immersive virtual reality (VR). Sixty‐six middle school students (33 females) were randomly assigned to learn about laboratory safety with one of two pedagogical agents: Marie or a drone, who we predicted serve as a role models for females and males, respectively. The results indicated that there were significant interactions for the dependent variables of performance during learning, retention, and transfer, with girls performing better with Marie (d = 0.98, d = 0.67, and d = 1.03; for performance, retention, and transfer, respectively) and boys performing better with the drone (d = ?0.41, d = ?0.45, d = ?0.23, respectively). The results suggest that gender‐specific design of pedagogical agents may play an important role in VR learning environments.     

Integration of supervised ART-based neural networks with a hybrid genetic algorithm

In this paper, two evolutionary artificial neural network (EANN) models that are based on integration of two supervised adaptive resonance theory (ART)-based artificial neural networks with a hybrid genetic algorithm (HGA) are proposed. The search process of the proposed EANN models is guided by a knowledge base established by ART with respect to the training data samples. The EANN models explore the search space for “coarse” solutions, and such solutions are then refined using the local search process of the HGA. The performances of the proposed EANN models are evaluated and compared with those from other classifiers using more than ten benchmark data sets. The applicability of the EANN models to a real medical classification task is also demonstrated. The results from the experimental studies demonstrate the effectiveness and usefulness of the proposed EANN models in undertaking pattern classification problems.     

Applications of soft computing techniques for prediction of energy dissipation on stepped spillways

In this study, numbers type of soft computing including artificial neural network (ANN), support vector machine (SVM), multivariate adaptive regression splines (MARS), and group method of data handling (GMDH) were applied to model and predict energy dissipation of flow over stepped spillways. Results of ANN indicated that this model including hyperbolic tangent sigmoid as transfer function obtained coefficient of determination (R ² = 0.917) and root-mean-square error (RMSE = 6.927) in testing stage. Results of development of SVM showed that developed model consists of radial basis function as kernel function achieved R ² = 0.98 and RMSE = 2.61 in validation stage. Developed MARS model with R ² = 0.99 and RMSE = 0.65 has suitable performance for predicating the energy dissipation. Results of developed GMDH model show with R ² = 0.95 and RMSE = 5.4 has suitable performance for modeling energy dispersion. Reviewing of results of prepared models showed that all of them have suitable performance to predict the energy dissipation. However, MARS and SVM are more accurate than the others. Attention to structures of GMDH and MARS models declared that Froude number, drop number, and ratio of critical depth to height of step are the most important parameters for modeling energy dissipation. The best radial basis function was found that as best kernel function in developing the SVM.

     

Identifying mortality risk factors amongst acute coronary syndrome patients admitted to Arabian Gulf hospitals using machine‐learning methods

Acute coronary syndrome (ACS) is a leading cause of mortality and morbidity in the Arabian Gulf. In this study, the in‐hospital mortality amongst patients admitted with ACS to Arabian Gulf hospitals is predicted using a comprehensive modelling framework that combines powerful machine‐learning methods such as support‐vector machine (SVM), Naïve Bayes (NB), artificial neural networks (NN), and decision trees (DT). The performance of the machine‐learning methods is compared with that of the performance of a commonly used statistical method, namely, logistic regression (LR). The study follows the current practise of computing mortality risk using risk scores such as the Global Registry of Acute Coronary Events (GRACE) score, which has not been validated for Arabian Gulf patients. Cardiac registry data of 7,000 patients from 65 hospitals located in Arabian Gulf countries are used for the study. This study is unique as it uses a contemporary data analytics framework. A k‐fold (k = 10) cross‐validation is utilized to generate training and validation samples from the GRACE dataset. The machine‐learning‐based predictive models often incur prejudgments for imbalanced training data patterns. To mitigate the data imbalance due to scarce observations for in‐hospital mortalities, we have utilized specialized methods such as random undersampling (RUS) and synthetic minority over sampling technique (SMOTE). A detailed simulation experimentation is carried out to build models with each of the five predictive methods (LR, NN, NB, SVM, and DT) for the each of the three datasets k‐fold subsamples generated. The predictive models are developed under three schemes of the k‐fold samples that include no data imbalance, RUS, and SMOTE. We have implemented an information fusion method rooted in computing weighted impact scores obtain for an individual medical history attributes from each of the predictive models simulated for a collective recommendation based on an impact score specific to a predictor. Finally, we grouped the predictors using fuzzy c‐mean clustering method into three categories, high‐, medium‐, and low‐risk factors for in‐hospital mortality due to ACS. Our study revealed that patients with medical history related to the presences of peripheral artery disease, congestive heart failure, cardiovascular transient ischemic attack valvular disease, and coronary artery bypass grafting amongst others have the most risk for in‐hospital mortality.     

Using multimedia for e‐learning

This paper reviews 12 research‐based principles for how to design computer‐based multimedia instructional materials to promote academic learning, starting with the multimedia principle (yielding a median effect size of d = 1.67 based on five experimental comparisons), which holds that people learn better from computer‐based instruction containing words and graphics rather than words alone. Principles aimed at reducing extraneous processing (i.e., cognitive processing that is unrelated to the instructional objective) include coherence (d = 0.70), signalling (d = 0.46), redundancy (d = 0.87), spatial contiguity (d = 0.79) and temporal contiguity (d = 1.30). Principles for managing essential processing (i.e., mentally representing the essential material) include segmenting (d = 0.70), pre‐training (d = 0.46) and modality (d = 0.72). Principles for fostering generative processing (i.e., cognitive processing aimed at making sense of the material) include personalization (d = 0.79), voice (d = 0.74) and embodiment (d = 0.36). Some principles have boundary conditions, such as being stronger for low‐ rather than high‐knowledge learners.     

Pack hike test finishing time for Australian firefighters: pass rates and correlates of performance

The pack hike test (PHT, 4.83 km hike wearing a 20.4-kg load) was devised to determine the job readiness of USA wildland firefighters. This study measured PHT performance in a sample of Australian firefighters who currently perform the PHT (career land management firefighters, LMFF) and those who do not (suburban/regional volunteer firefighters, VFF). The study also investigated the relationships between firefighters' PHT performance and their performance across a range of fitness tests for both groups. Twenty LMFF and eighteen age-, body mass-, and height-matched VFF attempted the PHT, and a series of muscular endurance, power, strength and cardiorespiratory fitness tests. Bivariate correlations between the participants’ PHT finishing time and their performance in a suite of different fitness tests were determined using Pearson’s product moment correlation coefficient. The mean PHT finishing time for LMFF (42.2 ± 2.8 min) was 9 ± 14% faster (p = 0.001) than for VFF (46.1 ± 3.6 min). The pass rate (the percentage of participants who completed the PHT in under 45 min) for LMFF (90%) was greater than that of VFF (39%, p = 0.001). For LMFF, VO_2peak in L min⁻¹(r = −0.66, p = 0.001) and the duration they could sustain a grip ‘force’ of 25 kg (r = −0.69, p = 0.001) were strongly correlated with PHT finishing time. For VFF, VO_2peak in mL kg⁻¹ min⁻¹(r = −0.75, p = 0.002) and the duration they could hold a 1.2-m bar attached to 45.5 kg in a ‘hose spray position’ (r = −0.69, p = 0.004) were strongly correlated with PHT finishing time. This study shows that PHT fitness-screening could severely limit the number of VFF eligible for duty, compromising workforce numbers and highlights the need for specific and valid firefighter fitness standards. The results also demonstrate the strong relationships between PHT performance and firefighters’ cardiorespiratory fitness and local muscular endurance. Those preparing for the PHT should focus their training on these fitness components in the weeks and months prior to undertaking the PHT.     

Feasibility of PSO–ANFIS model to estimate rock fragmentation produced by mine blasting

Desired rock fragmentation is the main goal of the blasting operation in surface mines, civil and tunneling works. Therefore, precise prediction of rock fragmentation is very important to achieve an economically successful outcome. The primary objective of this article is to propose a new model for forecasting the rock fragmentation using adaptive neuro-fuzzy inference system (ANFIS) in combination with particle swarm optimization (PSO). The proposed PSO–ANFIS model has been compared with support vector machines (SVM), ANFIS and nonlinear multiple regression (MR) models. To construct the predictive models, 72 blasting events were investigated, and the values of rock fragmentation as well as five effective parameters on rock fragmentation, i.e., specific charge, stemming, spacing, burden and maximum charge used per delay were measured. Based on several statistical functions [e.g., coefficient of correlation (R ²) and root-mean-square error (RMSE)], it was found that the PSO–ANFIS (with R ² = 0.89 and RMSE = 1.31) performs better than the SVM (with R ² = 0.83 and RMSE = 1.66), ANFIS (with R ² = 0.81 and RMSE = 1.78) and nonlinear MR (with R ² = 0.57 and RMSE = 3.93) models. Finally, the sensitivity analysis shows that the burden and maximum charge used per delay have the least and the most effects on the rock fragmentation, respectively.

     

Performance evaluation of hybrid Wavelet-ANN and Wavelet-ANFIS models for estimating evapotranspiration in arid regions of India

This paper evaluates the ability of wavelet transform in improving the accuracy of artificial neural network (ANN) and adaptive neuro-fuzzy interface systems (ANFIS) models. In this study, the performance of hybrid Wavelet-ANN and Wavelet-ANFIS models for estimating daily evapotranspiration in arid regions was evaluated. Prior to the development of models, gamma test was used to identify the best input combinations that could be used under limited data scenario. Performance of the proposed hybrid models was compared to ANN, ANFIS, and conventionally used Hargreaves equation. The results revealed that use of wavelet transform as data preprocessing technique enhanced the efficiency of ANN and ANFIS models. Wavelet-ANN and Wavelet-ANFIS performed reasonably better than other models. Better handling of wavelet-decomposed input variables enabled Wavelet-ANN models to perform slightly better than the Wavelet-ANFIS models. W-ANN2 (RMSE = 0.632 mm/day and R = 0.96) was found to be the best model for estimating daily evapotranspiration in arid regions. The proposed W-ANN2 model used second-level db3 wavelet-decomposed subseries of temperature and previous day evapotranspiration values as inputs. The study concludes that hybrid Wavelet-ANN and Wavelet-ANFIS models can be effectively used for modeling evapotranspiration.

     

Adaptive water demand forecasting for near real-time management of smart water distribution systems

This paper presents a novel methodology to perform adaptive Water Demand Forecasting (WDF) for up to 24 h ahead with the aim to support near real-time operational management of smart Water Distribution Systems (WDSs). The novel WDF methodology is exclusively based on the analysis of water demand time series (i.e., demand signals) and makes use of Evolutionary Artificial Neural Networks (EANNs). It is implemented in a fully automated, data-driven and self-learning Demand Forecasting System (DFS) that is readily transferable to practice. The main characteristics of the DFS are: (a) continuous adaptability to ever changing water demand patterns and (b) generic and seamless applicability to different demand signals. The DFS enables applying two alternative WDF approaches. In the first approach, multiple EANN models are used in parallel to separately forecast demands for different hours of the day. In the second approach, a single EANN model with a fixed forecast horizon (i.e., 1 h) is used in a recursive fashion to forecast demands. Both approaches have been tested and verified on a real-life WDS in the United Kingdom (UK). The results obtained illustrate that, regardless of the WDF approach used, the novel methodology allows accurate forecasts to be generated thereby demonstrating the potential to yield substantial improvements to the state-of-the-art in near real-time WDS management. The results obtained also demonstrate that the multiple-EANN-models approach slightly outperforms the single-EANN-model approach in terms of WDF accuracy. The single-EANN-model approach, however, still enables achieving good WDF performance and may be a preferred option in engineering practice as it is easier to setup/implement.     

Estimating oxygen consumption from heart rate using adaptive neuro-fuzzy inference system and analytical approaches

In new approaches based on adaptive neuro-fuzzy systems (ANFIS) and analytical method, heart rate (HR) measurements were used to estimate oxygen consumption (VO₂). Thirty-five participants performed Meyer and Flenghi's step-test (eight of which performed regeneration release work), during which heart rate and oxygen consumption were measured. Two individualized models and a General ANFIS model that does not require individual calibration were developed. Results indicated the superior precision achieved with individualized ANFIS modelling (RMSE = 1.0 and 2.8 ml/kg min in laboratory and field, respectively). The analytical model outperformed the traditional linear calibration and Flex-HR methods with field data. The General ANFIS model's estimates of VO₂ were not significantly different from actual field VO₂ measurements (RMSE = 3.5 ml/kg min). With its ease of use and low implementation cost, the General ANFIS model shows potential to replace any of the traditional individualized methods for VO₂ estimation from HR data collected in the field.     

Mining Evolving Data Streams with Particle Filters

We propose a particle filter‐based learning method, PF‐LR, for learning logistic regression models from evolving data streams. The method inherently handles concept drifts in a data stream and is able to learn an  ensemble of logistic regression models with particle filtering. A key feature of PF‐LR is that in its resampling, step particles are sampled from the ones that maximize the classification accuracy on the current data batch. Our experiments show that PF‐LR gives good performance, even with relatively small batch sizes. It reacts to concept drifts quicker than conventional particle filters while being robust to noise. In addition, PF‐LR learns more accurate models and is more computationally efficient than the gradient descent method for learning logistic regression models. Furthermore, we evaluate PF‐LR on both synthetic and real data sets and find that PF‐LR outperforms some other state‐of‐the‐art streaming mining algorithms on most of the data sets tested.     

Time-series modeling of fishery landings using ARIMA models and Fuzzy Expected Intervals software

Forecasting, using historic time-series data, has become an important tool for fisheries management. ARIMA modeling, Modeling for Optimal Forecasting techniques and Decision Support Systems based on fuzzy mathematics may be used to predict the general trend of a given fish landings time-series with increased reliability and accuracy. The present paper applies these three modeling methods to forecast anchovy fish catches landed in a given port (Thessaloniki, Greece) during 1979–2000 and hake and bonito total fish catches during 1982–2000. The paper attempts to assess the model's accuracy by comparing model results to the actual monthly fish catches of the year 2000. According to the measures of forecasting accuracy established, the best forecasting performance for anchovy was shown by the DSS model (MAPE = 28.06%, RMSE = 76.56, U-statistic = 0.67 and R² = 0.69). The optimal forecasting technique of genetic modeling improved significantly the forecasting values obtained by the selected ARIMA model. Similarly, the DSS model showed a noteworthy forecasting efficiency for the prediction of hake landings, during the year 2000 (MAPE = 2.88%, RMSE = 13.75, U-statistic = 0.19 and R² = 0.98), as compared to the other two modeling techniques. Optimal forecasting produced by combined modeling scored better than application of the simple ARIMA model. Overall, DSS results showed that the Fuzzy Expected Intervals methodology could be used as a very reliable tool for short-term predictions of fishery landings.     

Modelling heat,water and carbon fluxes in mown grassland under multi-objective and multi-criteria constraints

A Monte Carlo-based calibration and uncertainty assessment was performed for heat, water and carbon (C) fluxes, simulated by a soil-plant-atmosphere system model (CoupModel), in mown grassland. Impact of different multi-objective and multi-criteria constraints was investigated on model performance and parameter behaviour. Good agreements between hourly modelled and measurement data were obtained for latent and sensible heat fluxes (R² = 0.61, ME = 0.48 MJ m⁻² day⁻¹), soil water contents (R² = 0.68, ME = 0.34%) and carbon-dioxide flux (R² = 0.60, ME = −0.18 g C m⁻² day⁻¹). Multi-objective and multi-criteria constraints were efficient in parameter conditioning, reducing simulation uncertainty and identifying critical parameters. Enforcing multi-constraints separately on heat, water and C processes resulted in the highest model improvement for that specific process, including some improvement too for other processes. Imposing multi-constraints on all groups of variables, associated with heat, water and C fluxes together, resulted in general effective parameters conditioning and model improvement.     

Evolutionary optimization of sparsely connected and time-lagged neural networks for time series forecasting

Time series forecasting (TSF) is an important tool to support decision making (e.g., planning production resources). Artificial neural networks (ANNs) are innate candidates for TSF due to advantages such as nonlinear learning and noise tolerance. However, the search for the best model is a complex task that highly affects the forecasting performance. In this work, we propose two novel evolutionary artificial neural networks (EANNs) approaches for TSF based on an estimation distribution algorithm (EDA) search engine. The first new approach consist of sparsely connected evolutionary ANN (SEANN), which evolves more flexible ANN structures to perform multi-step ahead forecasts. The second one, consists of an automatic Time lag feature selection EANN (TEANN) approach that evolves not only ANN parameters (e.g., input and hidden nodes, training parameters) but also which set of time lags are fed into the forecasting model. Several experiments were held, using a set of six time series, from different real-world domains. Also, two error metrics (i.e., mean squared error and symmetric mean absolute percentage error) were analyzed. The two EANN approaches were compared against a base EANN (with no ANN structure or time lag optimization) and four other methods (autoregressive integrated moving average method, random forest, echo state network and support vector machine). Overall, the proposed SEANN and TEANN methods obtained the best forecasting results. Moreover, they favor simpler neural network models, thus requiring less computational effort when compared with the base EANN.     

Pharmacophore and docking-based combined in-silico study of KDR inhibitors

The growth and metastasis of solid tumors is dependent on angiogenesis. The vascular endothelial growth factor (VEGF) and its cell surface receptor in human KDR (kinase domain containing receptor or VEGFR-2) have particular interest because of their importance in angiogenesis. The development of novel inhibitors of VEGFR-2 would be helpful to check the growth of tumors. Quantitative structure activity relationship (QSAR) analyses used to understand the structural factors affecting inhibitory potency of thiazole-substituted pyrazolone derivatives. Several pharmacophore-based models indicated the importance of steric, hydrophobic and hydrogen bond acceptor groups to inhibitory activity. The comparative molecular field analyses (CoMFA) and comparative molecular similarity indices analyses (CoMSIA) based 3D-QSAR models were derived using pharmacophore-based alignment. Both CoMFA (q² = 0.70, r² = 0.97 and ) and CoMSIA (q² = 0.54, r² = 0.82 and ) gave reasonable results. The molecular docking (receptor-guided technique) with a recently reported receptor structure (PDB = 1YWN) were performed. The docked alignment was subsequently used for 3D-QSAR (CoMFA; q² = 0.56, r² = 0.97, , CoMSIA; q² = 0.58 r² = 0.91, ). The overall both studies were indicated, steric, electrostatic and hydrogen bond acceptor effects contribute to the inhibitory activity. CoMFA and CoMSIA models suggested that a positive bulk with hydrophobic effect is desirable around position 4 and 5 and hydrogen bond acceptor groups around pyrazolones ring will be helpful.     

Enriching feedback in audience response systems: Analysis and implications of objective and subjective metrics on students' performance and attitudes

The aim of the present study (n = 113) was to examine how (objective and subjective) information on peers' preparation, confidence, and past performance can support students in answering correctly in audience response systems (aka clickers). The result analysis shows that in the “challenging” questions, in which answers diverged, students who received additional information about peers' self‐reported preparation and/or confidence outperformed students who were only given the objective percentage with or without past performance feedback. In addition, students expressed a positive attitude towards the activity, commenting its usefulness in better understanding course material and identifying misconceptions.