Soft computing techniques are becoming even more popular and particularly amenable to model the complex behaviors of most geotechnical engineering systems since they have demonstrated superior ...predictive capacity, compared to the traditional methods. This paper presents an overview of some soft computing techniques as well as their applications in underground excavations. A case study is adopted to compare the predictive performances of soft computing techniques including eXtreme Gradient Boosting (XGBoost), Multivariate Adaptive Regression Splines (MARS), Artificial Neural Networks (ANN), and Support Vector Machine (SVM) in estimating the maximum lateral wall deflection induced by braced excavation. This study also discusses the merits and the limitations of some soft computing techniques, compared with the conventional approaches available.
Display omitted
•Systematic state-of-the-art review of soft computing applications in underground excavations.•Performance comparisons of chosen SCMs including MARS, ANN, XGBoost, and SVM.•Some discussions and further research recommendations provided.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UILJ, UL, UM, UPCLJ, UPUK, ZAGLJ, ZRSKP
Abstract
The use of high-throughput sequencing technologies to produce genome-scale data sets was expected to settle some long-standing controversies across the Tree of Life, particularly in areas ...where short branches occur at deep timescales. Instead, these data sets have often yielded many well-supported but conflicting topologies, and highly variable gene-tree distributions. A variety of branch-support metrics beyond the nonparametric bootstrap are now available to assess how robust a phylogenetic hypothesis may be, as well as new methods to quantify gene-tree discordance. We applied multiple branch-support metrics to a study of an ancient group of marine fishes (Teleostei: Pelagiaria) whose interfamilial relationships have proven difficult to resolve due to a rapid accumulation of lineages very early in its history. We analyzed hundreds of loci including published ultraconserved elements and newly generated exonic data along with their flanking regions to represent all 16 extant families for more than 150 out of 284 valid species in the group. Branch support was typically lower at inter- than intra-familial relationships regardless of the type of marker used. Several nodes that were highly supported with bootstrap had a very low site and gene-tree concordance, revealing underlying conflict. Despite this conflict, we were able to identify four consistent interfamilial clades, each comprised of two or three families. Combining exons with their flanking regions also produced increased branch lengths at the deep branches of the pelagiarian tree. Our results demonstrate the limitations of employing current metrics of branch support and species-tree estimation when assessing the confidence of ancient evolutionary radiations and emphasize the necessity to embrace alternative measurements to explore phylogenetic uncertainty and discordance in phylogenomic data sets.Concatenation; exons; introns; phylogenomics; species-tree methods; target capture.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
The aim of the study is to compare four recent gradient boosting algorithms named as Gradient Boosting Machine (GBM), Categorical Boosting (CatBoost), Extreme Gradient Boosting (XGBoost), and Light ...Gradient Boosting Machine (LightGBM) for modelling landslide susceptibility (LS). In the first step of the study, the geodatabase including landslide inventory map and landslide conditioning factors was constructed. In the second step, chi-square (CHI) statistic-based feature selection (FS) technique was utilized to compute the importance of the landslide causative factors. In the third step, tree-based ensemble learning algorithms were applied to predict the potential distribution of landslide susceptibility. Also, the prediction performance of ensemble methods was compared to that of Random Forest (RF) ensemble method. Finally, the prediction capabilities of the methods were assessed using overall accuracy (Acc), area under the receiver operating characteristic curve (AUC), kappa index, root mean square error (RMSE), and F score measures. In order to further evaluation, the McNemar's test was utilized to assess statistical significance in the differences between the four gradient boosting models. The accuracy results indicated that the CatBoost model had the highest prediction capability (Acc= 0.8503 and AUC= 0.8975), followed by the XGBoost (Acc= 0.8336 and AUC= 0.8860), the LightGBM (Acc= 0.8244 and AUC= 0.8796) and the GBM (Acc= 0.8080 and AUC= 0.8685). On the other hand, the estimated accuracy measures considered in this study showed that the RF method had the lowest prediction capability of compared the others. Although the individual performances of the methods were found to be acceptable level, the CatBoost method showed the superior performance compared to others with respect to the AUC and Acc values estimated in this study. The results of the study confirmed that the relatively new ensemble learning techniques were efficient and robust for producing LS maps and furthermore, it is probably that these algorithms will be preferred more often in the future studies due to their robustness.
Full text
Available for:
BFBNIB, GIS, IJS, KISLJ, NUK, PNG, UL, UM, UPUK
The rapid diversification of Myotis bats into more than 100 species is one of the most extensive mammalian radiations available for study. Efforts to understand relationships within Myotis have ...primarily utilized mitochondrial markers and trees inferred from nuclear markers lacked resolution. Our current understanding of relationships within Myotis is therefore biased towards a set of phylogenetic markers that may not reflect the history of the nuclear genome. To resolve this, we sequenced the full mitochondrial genomes of 37 representative Myotis, primarily from the New World, in conjunction with targeted sequencing of 3648 ultraconserved elements (UCEs). We inferred the phylogeny and explored the effects of concatenation and summary phylogenetic methods, as well as combinations of markers based on informativeness or levels of missing data, on our results. Of the 294 phylogenies generated from the nuclear UCE data, all are significantly different from phylogenies inferred using mitochondrial genomes. Even within the nuclear data, quartet frequencies indicate that around half of all UCE loci conflict with the estimated species tree. Several factors can drive such conflict, including incomplete lineage sorting, introgressive hybridization, or even phylogenetic error. Despite the degree of discordance between nuclear UCE loci and the mitochondrial genome and among UCE loci themselves, the most common nuclear topology is recovered in one quarter of all analyses with strong nodal support. Based on these results, we re-examine the evolutionary history of Myotis to better understand the phenomena driving their unique nuclear, mitochondrial, and biogeographic histories.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Ensemble-tree machine learning (ML) regression models can be prone to systematic bias: small values are overestimated and large values are underestimated. Additional bias can be introduced if the ...dependent variable is a transform of the original data. Six methods were evaluated for their ability to correct systematic and introduced bias. Method performance was evaluated using four case studies of groundwater quality: the units of the dependent variable were pH in two and log-concentration in the others. When performance metrics (bias and RMSE for both points and the CDF) were computed using the same units as those in the ML model, empirical distribution matching (EDM) provided the best results. When the metrics were computed using retransformed concentration, EDM and a method incorporating Duan's smearing estimate were both effective. A method based on the Z-score transform approximates EDM if the correlation coefficient between rank-ordered ML estimates and rank-ordered observations approaches one.
•Ensemble-tree machine learning regression models can be prone to systematic bias.•Systematic bias is defined as overestimation of small values and underestimation of large values.•Empirical Distribution Matching (EDM) can correct the systematic bias.•EDM can also correct for introduced bias (dependent variable is a transform of the original data).•A method based on the Z-score transform approximates EDM under certain circumstances.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
Using RAxML to Infer Phylogenies Stamatakis, Alexandros
Current protocols in bioinformatics,
September 2015, Volume:
51
Journal Article
Inference of phylogenetic trees under the maximum likelihood (ML) criterion represents a routine task in biological data analysis. In this unit we describe how to plan analyses and use Randomized ...Accelerated Maximum Likelihood (RAxML) for phylogenetic inferences under ML, how to infer support values using the standard bootstrap procedure as well as other statistical measures, and how to conduct post-analyses on collections/sets of phylogenetic trees including statistical significance tests and consensus tree methods. We also discuss what measures can be taken and what further analyses can be conducted when relationships in the inferred tree exhibit "low" support.
Objective: Decision-tree methods are machine-learning methods which provide results that are relatively easy to interpret and apply by human decision makers. The resulting decision trees show how ...baseline patient characteristics can be combined to predict treatment outcomes for individual patients, for example. This paper introduces GLMM trees, a decision-tree method for multilevel and longitudinal data.
Method: To illustrate, we apply GLMM trees to a dataset of 3,256 young people (mean age 11.33, 48% girls) receiving treatment at one of several mental-health service providers in the UK. Two treatment outcomes (mental-health difficulties scores corrected for baseline) were regressed on 18 demographic, case and severity characteristics at baseline. We compared the performance of GLMM trees with that of traditional GLMMs and random forests.
Results: GLMM trees yielded modest predictive accuracy, with cross-validated multiple R values of .18 and .25. Predictive accuracy did not differ significantly from that of traditional GLMMs and random forests, while GLMM trees required evaluation of a lower number of variables.
Conclusion: GLMM trees provide a useful data-analytic tool for clinical prediction problems. The supplemental material provides a tutorial for replicating the GLMM tree analyses in R.
Full text
Available for:
BFBNIB, IZUM, KILJ, NUK, PILJ, PNG, SAZU, UL, UM, UPUK
Restriction-site associated DNA sequencing (RAD-seq) and target capture of specific genomic regions, such ultraconserved elements (UCEs), are emerging as two of the most popular methods for ...phylogenomics using reducedrepresentation genomic data sets. These two methods were designed to target different evolutionary timescales: RAD-seq was designed for population-genomic level questions and UCEs for deeper phylogenetics. The utility of both data sets to infer phylogenies across a variety of taxonomic levels has not been adequately compared within the same taxonomic system. Additionally, the effects of uninformative gene trees on species tree analyses (for target capture data) have not been explored. Here, we utilize RAD-seq and UCE data to infer a phylogeny of the bird genus Piranga. The group has a range of divergence dates (0.5-6 myr), contains 11 recognized species, and lacks a resolved phylogeny. We compared two species tree methods for the RAD-seq data and six species tree methods for the UCE data. Additionally, in the UCE data, we analyzed a complete matrix as well as data sets with only highly informative loci. A complete matrix of 189 UCE loci with 10 or more parsimony informative (PI) sites, and an approximately 80% complete matrix of 1128 PI single-nucleotide polymorphisms (SNPs) (from RAD-seq) yield the same fully resolved phylogeny of Piranga. We inferred non-monophyletic relationships of Piranga lutea individuals, with all other a priori species identified as monophyletic. Finally, we found that species tree analyses that included predominantly uninformative gene trees provided strong support for different topologies, with consistent phylogenetic results when limiting species tree analyses to highly informative loci or only using less informative loci with concatenation or methods meant for SNPs alone.
Full text
Available for:
DOBA, IZUM, KILJ, NUK, PILJ, PNG, SAZU, SIK, UILJ, UKNU, UL, UM, UPUK
Complex environmental models typically require global sensitivity analysis (GSA) to account for non-linearities and parametric interactions. However, variance-based GSA is highly computationally ...expensive. While different screening methods can estimate GSA results, these techniques typically impose restrictions on sampling methods and input types. As an alternative, this work evaluates two decision tree-based methods to approximate GSA results: random forests, and Extra-Trees. These techniques are applicable with common sampling methods, and continuous or categorical inputs. The tree-based methods are compared to reference Sobol GSA and Morris screening techniques, for three cases: an Ishigami-Homma function, a H1N1 pandemic model, and the CDICE integrated assessment model. The Extra-Trees algorithm performs favorably compared to Morris elementary effects, accurately approximating the relative importance of Sobol total effect indices. Furthermore, Extra-Trees can estimate variable interaction importances using a pairwise permutation measure. As such, this approach could offer a user-friendly option for screening in models with inputs of mixed types.
•The Extra-Trees tree-based ensemble method can estimate relative Sobol total indices for sensitivity analysis.•A permutation metric is used to estimate pairwise variable interactions.•The method is applicable with generic input sampling and heterogeneous input types.
Full text
Available for:
GEOZS, IJS, IMTLJ, KILJ, KISLJ, NLZOH, NUK, OILJ, PNG, SAZU, SBCE, SBJE, UL, UM, UPCLJ, UPUK, ZRSKP
Landslide susceptibility mapping is an indispensable prerequisite for landslide prevention and reduction. At present, research into landslide susceptibility mapping has begun to combine machine ...learning with remote sensing and geographic information system (GIS) techniques. The random forest model is a new integrated classification method, but its application to landslide susceptibility mapping remains limited. Landslides represent a serious threat to the lives and property of people living in the Zigui–Badong area in the Three Gorges region of China, as well as to the operation of the Three Gorges Reservoir. However, the geological structure of this region is complex, involving steep mountains and deep valleys. The purpose of the current study is to produce a landslide susceptibility map of the Zigui–Badong area using a random forest model, multisource data, GIS, and remote sensing data. In total, 300 pre-existing landslide locations were obtained from a landslide inventory map. These landslides were identified using visual interpretation of high-resolution remote sensing images, topographic and geologic data, and extensive field surveys. The occurrence of landslides is closely related to a series of environmental parameters. Topographic, geologic, Landsat-8 image, raining data, and seismic data were used as the primary data sources to extract the geo-environmental factors influencing landslides. Thirty-four layers of causative factors were prepared as predictor variables, which can mainly be categorized as topographic, geological, hydrological, land cover, and environmental trigger parameters. The random forest method is an ensemble classification technique that extends diversity among the classification trees by resampling the data with replacement and randomly changing the predictive variable sets during the different tree induction processes. A random forest model was adopted to calculate the quantitative relationships between the landslide-conditioning factors and the landslide inventory map and then generate a landslide susceptibility map. The analytical results were compared with known landslide locations in terms of area under the receiver operating characteristic curve. The random forest model has an area ratio of 86.10%. In contrast to the random forest (whole factors, WF), random forest (12 major factors, 12F), decision tree (WF), decision tree (12F), the final result shows that random forest (12F) has a higher prediction accuracy. Meanwhile, the random forest models have higher prediction accuracy than the decision tree model. Subsequently, the landslide susceptibility map was classified into five classes (very low, low, moderate, high, and very high). The results demonstrate that the random forest model achieved a reasonable accuracy in landslide susceptibility mapping. The landslide hazard zone information will be useful for general development planning and landslide risk management.
Full text
Available for:
EMUNI, FIS, FZAB, GEOZS, GIS, IJS, IMTLJ, KILJ, KISLJ, MFDPS, NLZOH, NUK, OBVAL, OILJ, PNG, SAZU, SBCE, SBJE, SBMB, SBNM, UKNU, UL, UM, UPUK, VKSCE, ZAGLJ