| 1. |
- Anaraki, Mahdi Valikhan, et al.
(författare)
-
Modeling of Monthly Rainfall–Runoff Using Various Machine Learning Techniques in Wadi Ouahrane Basin, Algeria
- 2023
-
Ingår i: Water. - : MDPI. - 2073-4441. ; 15:20
-
Tidskriftsartikel (refereegranskat)abstract
- Rainfall–runoff modeling has been the core of hydrological research studies for decades. To comprehend this phenomenon, many machine learning algorithms have been widely used. Nevertheless, a thorough comparison of machine learning algorithms and the effect of pre-processing on their performance is still lacking in the literature. Therefore, the major objective of this research is to simulate rainfall runoff using nine standalone and hybrid machine learning models. The conventional models include artificial neural networks, least squares support vector machines (LSSVMs), K-nearest neighbor (KNN), M5 model trees, random forests, multiple adaptive regression splines, and multivariate nonlinear regression. In contrast, the hybrid models comprise LSSVM and KNN coupled with a gorilla troop optimizer (GTO). Moreover, the present study introduces a new combination of the feature selection method, principal component analysis (PCA), and empirical mode decomposition (EMD). Mean absolute error (MAE), root mean squared error (RMSE), relative RMSE (RRMSE), person correlation coefficient (R), Nash–Sutcliffe efficiency (NSE), and Kling Gupta efficiency (KGE) metrics are used for assessing the performance of the developed models. The proposed models are applied to rainfall and runoff data collected in the Wadi Ouahrane basin, Algeria. According to the results, the KNN–GTO model exhibits the best performance (MAE = 0.1640, RMSE = 0.4741, RRMSE = 0.2979, R = 0.9607, NSE = 0.9088, and KGE = 0.7141). These statistical criteria outperform other developed models by 80%, 70%, 72%, 77%, 112%, and 136%, respectively. The LSSVM model provides the worst results without pre-processing the data. Moreover, the findings indicate that using feature selection, PCA, and EMD significantly improves the accuracy of rainfall–runoff modeling.
|
|
| 2. |
|
|
| 3. |
|
|
| 4. |
- Hakeem, Abbas Saeed, et al.
(författare)
-
Microstructural and thermal evaluation of the formation of tin-tellurium (Sn-Te) alloy by ball milling process
- 2023
-
Ingår i: Powder Technology. - : Elsevier. - 0032-5910 .- 1873-328X. ; 428
-
Tidskriftsartikel (refereegranskat)abstract
- A mechanically induced phase transition in tin-tellurium (Sn-Te) system and its dependence on the milling time of the masses of metastable Sn-Te phase(s) produced during ball milling have been investigated. The synthesis approach involves top-down ball milling of elemental Sn and Te powders in an argon environment with a milling time of 1 to 5 h at a low ball milling speed of 300 RPM. The Sn-Te solid solution forms as particles, resulting in large masses due to the ball milling operation. Ball milling of initial micron-sized powders of Sn and Te resulted in a homogenized nano-sized powder mixture. This mechanical mixture of Sn and Te powders exhibiting in-termediate phases with a crystal structure similar to that of elemental Sn and Te were detected in the ball-milled mixtures at various milling times, which resulted in a stable phase that ultimately transformed into a Sn-Te solid solution. Morphological and structural modifications at different stages of ball milling were investigated through X-ray diffraction, field emission scanning electron microscopy, transmission electron microscopy, differential scanning calorimetry, dynamic light scattering, density measurement, and surface analysis. Subsequently, dense pellets were fabricated by spark plasma sintering from synthesized Sn-Te solid-solution powders produced by ball milling for 5 h. The sintered samples showed excellent structural integrity with densities of up to 6.35 g/cm3. It is to be noted that the formation of large quantities of uniform Sn-Te powder alloy produced by ball milling is reported for the first time in this study. These findings could be extended in the future to prepare bulk quantities of many solid solutions of the elements of the same periodic group.
|
|
| 5. |
|
|
| 6. |
|
|
| 7. |
|
|
| 8. |
|
|
| 9. |
- Younis, Brima Musa, et al.
(författare)
-
Safety and efficacy of paromomycin/miltefosine/liposomal amphotericin B combinations for the treatment of post-kala-azar dermal leishmaniasis in Sudan : A phase II, open label, randomized, parallel arm study
- 2023
-
Ingår i: PLoS Neglected Tropical Diseases. - : Public Library of Science (PLoS). - 1935-2727 .- 1935-2735. ; 17:11
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Treatment for post-kala-azar dermal leishmaniasis (PKDL) in Sudan is currently recommended only for patients with persistent or severe disease, mainly because of the limitations of current therapies, namely toxicity and long hospitalization. We assessed the safety and efficacy of miltefosine combined with paromomycin and liposomal amphotericin B (LAmB) for the treatment of PKDL in Sudan.Methodology/principal findings: An open-label, phase II, randomized, parallel-arm, non-comparative trial was conducted in patients with persistent (stable or progressive disease for >= 6 months) or grade 3 PKDL, aged 6 to <= 60 years in Sudan. The median age was 9.0 years (IQR 7.0-10.0y) and 64% of patients were <= 12 years old. Patients were randomly assigned to either daily intra-muscular paromomycin (20mg/kg, 14 days) plus oral miltefosine (allometric dose, 42 days)-PM/MF-or LAmB (total dose of 20mg/kg, administered in four injections in week one) and oral miltefosine (allometric dose, 28 days)-AmB/MF. The primary endpoint was a definitive cure at 12 months after treatment onset, defined as clinical cure (100% lesion resolution) and no additional PKDL treatment between end of therapy and 12-month follow-up assessment. 104/110 patients completed the trial. Definitive cure at 12 months was achieved in 54/55 (98.2%, 95% CI 90.3-100) and 44/55 (80.0%, 95% CI 70.2-91.9) of patients in the PM/MF and AmB/MF arms, respectively, in the mITT set (all randomized patients receiving at least one dose of treatment; in case of error of treatment allocation, the actual treatment received was used in the analysis). No SAEs or deaths were reported, and most AEs were mild or moderate. At least one adverse drug reaction (ADR) was reported in 13/55 (23.6%) patients in arm 1 and 28/55 (50.9%) in arm 2, the most frequent being miltefosine-related vomiting and nausea, and LAmB-related hypokalaemia; no ocular or auditory ADRs were reported.Conclusions/significance: The PM/MF regimen requires shorter hospitalization than the currently recommended 60-90-day treatment, and is safe and highly efficacious, even for patients with moderate and severe PKDL. It can be administered at primary health care facilities, with LAmB/MF as a good alternative. For future VL elimination, we need new, safe oral therapies for all patients with PKDL.
|
|
