We used a novel hybrid functional machine learning algorithm to predict the spatial distribution of landslides in the Sarkhoon watershed, Iran. We developed a new ensemble model which is a combination of a functional algorithm, stochastic gradient descent (SGD) and an AdaBoost (AB) Meta classifier namely ABSGD model to predict the landslides. The model incorporates 20 landslide conditioning factors, which we ranked using the least-square support vector machine (LSSVM) technique. For the modeling, we considered 98 landslide locations, of which 70% (79) were used for training and 30% (19) for validation processes. Model validation was performed using sensitivity, specificity, accuracy, the root mean square error (RMSE) and the area under the receiver operatic characteristic (AUC) curve. We also used soft computing benchmark models, including SGD, logistic regression (LR), logistic model tree (LMT) and functional tree (FT) algorithms for model validation and comparison. The selected conditioning factors were significant in landslide occurrence but distance to road was found to be the most important factor. The ABSGD model (AUC= 0.860) outperformed the LR (0.797), SGD (0.776), LMT (0.740) and FT (0.734) models. Our results confirm that the combined use of a functional algorithm and a Meta classifier prevents over-fitting, reduces noise and enhances the power prediction of the individual SGD algorithm for the spatial prediction of landslides.

In this study, we introduced a novel hybrid artificial intelligence approach of rotation forest (RF) as a Meta/ensemble classifier based on alternating decision tree (ADTree) as a base classifier called RF-ADTree in order to spatially predict gully erosion at Klocheh watershed of Kurdistan province, Iran. A total of 915 gully erosion locations along with 22 gully conditioning factors were used to construct a database. Some soft computing benchmark models (SCBM) including the ADTree, the Support Vector Machine by two kernel functions such as Polynomial and Radial Base Function (SVM-Polynomial and SVM-RBF), the Logistic Regression (LR), and the Naïve Bayes Multinomial Updatable (NBMU) models were used for comparison of the designed model. Results indicated that 19 conditioning factors were effective among which distance to river, geomorphology, land use, hydrological group, lithology and slope angle were the most remarkable factors for gully modeling process. Additionally, results of modeling concluded the RF-ADTree ensemble model could significantly improve (area under the curve (AUC) = 0.906) the prediction accuracy of the ADTree model (AUC = 0.882). The new proposed model had also the highest performance (AUC = 0.913) in comparison to the SVM-Polynomial model (AUC = 0.879), the SVM-RBF model (AUC = 0.867), the LR model (AUC = 0.75), the ADTree model (AUC = 0.861) and the NBMU model (AUC = 0.811).

No abstract

The Tajan River was investigated for one year in seven stations, analyzing the relationships between physical properties, water chemistry and aquatic macroinvertebrates. Biotic and diversity indices were compared with canonical unconstrained (CA) and constrained (CCA) ordination to test different methods able to estimate river ecology status. An upstream-downstream gradient was emphasized, in presence of anthropogenic stressors, coming from trout farms, paper factory, agriculture, urbanization, river regulation; the first CCA axis emphasized a natural gradient, bound to altitude, source distance, water temperature, the second CCA axis a pollution gradient. Biotic and diversity indices detected three polluted stations: S3, downstream the Korcha tributary, S6 downstream a paper factory and S7 situated after the Sari town. S4 showed high macroinvertebrates densities, which were attributed to the presence of a dam. Both multimetric and multivariate methods emphasized the need to separate the influence of natural variables from anthropogenic stressors in the Tajan River. To separate the influence of longitudinal gradient from the influence of pollution, it was suggested to evaluate the anthropogenic impact as deviation from a regression line, considering a multimetric index as dependent variable and source distance as predictor variable. The definition of reference sites was problematic in this poorly investigated area and a progress in taxonomic resolution is in any case recommended to better define the ecological status of these waters.

Background and objectives: Pre-hospital emergency medical services (EMS) personnel are responsible for transferring patients. In case of improper patient handling, these individuals become vulnerable to various musculoskeletal problems including back pain. In this study, we aimed to evaluate the impact of an eight-hour training intervention about patient handling and transfer ergonomics on low back pain in pre-hospital EMS personnel working in the Golestan Province, Iran. Methods: This was a quasi-experimental study with a pre-test/post-test design. The study population consisted of 200 pre-hospital EMS personnel working in the Golestan Province, Iran. Overall, 40 EMS personnel were eligible to participate in the study. Data were collected using a demographic questionnaire, the Oswestry low back pain disability questionnaire and the Quebec back pain disability scale. The eight-hour training session was held by a research nurse, a physiotherapist and a physician. The subjects recompleted the Oswestry low back pain disability questionnaire and the Quebec back pain disability scale at baseline, four weeks and 12 weeks postintervention. The collected data were analyzed using SPSS 16 and descriptive statistics. Results: The mean age, body mass index and work experience was 38.6 ± 7.6 years, 25.9 ± 3.5 kg/m 2 and 8.27± 5.2 years, respectively. The mean score of functional disability reduced significantly from 35.9 ± 9 at baseline to 27.5 ± 2.5 and 19.6 ± 7 four weeks and 12 weeks after the intervention, respectively (P=0.0001). Furthermore, the mean pain score decreased from 38.7 ± 13.86 to 31.05 ± 10.75 one month post-intervention and to 22.4 ± 9.47 three months postintervention (P=0.0001). Conclusion: Our findings suggest that training intervention on ergonomic patient transfer and patient handling can reduce the rate of lower back pain in pre-hospital EMS personnel.