| 1. |
- Abbafati, Cristiana, et al.
(författare)
-
- 2020
-
Tidskriftsartikel (refereegranskat)
|
|
| 2. |
- Singh, Vijay Kumar, et al.
(författare)
-
Novel Genetic Algorithm (GA) based hybrid machine learning-pedotransfer Function (ML-PTF) for prediction of spatial pattern of saturated hydraulic conductivity
- 2022
-
Ingår i: Engineering Applications of Computational Fluid Mechanics. - : Taylor & Francis. - 1994-2060 .- 1997-003X. ; 16:1, s. 1082-1099
-
Tidskriftsartikel (refereegranskat)abstract
- Saturated hydraulic conductivity (Ks) is an important soil characteristic that controls water moves through the soil. On the other hand, its measurement is difficult, time-consuming, and expensive; hence Pedotransfer Functions (PTFs) are commonly used for its estimation. Despite significant development over the years, the PTFs showed poor performance in predicting Ks. Using Genetic Algorithm (GA), two hybrid Machine Learning based PTFs (ML-PTF), i.e. a combination of GA with Multilayer Perceptron (MLP-GA) and Support Vector Machine (SVM-GA), were proposed in this study. We compared the performances of four machine learning algorithms for different sets of predictors. The predictor combination containing sand, clay, Field Capacity, and Wilting Point showed the highest accuracy for all the ML-PTFs. Among the ML-PTFs, the SVM-GA algorithm outperformed the rest of the PTFs. It was noticed that the SVM-GA PTF demonstrated higher efficiency than the MLP-GA algorithm. The reference model for hydraulic conductivity prediction was selected as the SVM-GA PTF paired with the K-5 predictor variables. The proposed PTFs were compared with 160 models from past literature. It was found that the algorithms advocated were an improvement over these PTFs. The current model would help in efficient spatio-temporal measurement of hydraulic conductivity using pre-available databases.
|
|
| 3. |
- Feigin, Valery L., et al.
(författare)
-
Global, regional, and national burden of stroke and its risk factors, 1990-2019 : a systematic analysis for the Global Burden of Disease Study 2019
- 2021
-
Ingår i: Lancet Neurology. - : Elsevier. - 1474-4422 .- 1474-4465. ; 20:10, s. 795-820
-
Tidskriftsartikel (refereegranskat)abstract
- Background Regularly updated data on stroke and its pathological types, including data on their incidence, prevalence, mortality, disability, risk factors, and epidemiological trends, are important for evidence-based stroke care planning and resource allocation. The Global Burden of Diseases, Injuries, and Risk Factors Study (GBD) aims to provide a standardised and comprehensive measurement of these metrics at global, regional, and national levels. Methods We applied GBD 2019 analytical tools to calculate stroke incidence, prevalence, mortality, disability-adjusted life-years (DALYs), and the population attributable fraction (PAF) of DALYs (with corresponding 95% uncertainty intervals [UIs]) associated with 19 risk factors, for 204 countries and territories from 1990 to 2019. These estimates were provided for ischaemic stroke, intracerebral haemorrhage, subarachnoid haemorrhage, and all strokes combined, and stratified by sex, age group, and World Bank country income level. Findings In 2019, there were 12.2 million (95% UI 11.0-13.6) incident cases of stroke, 101 million (93.2-111) prevalent cases of stroke, 143 million (133-153) DALYs due to stroke, and 6.55 million (6.00-7.02) deaths from stroke. Globally, stroke remained the second-leading cause of death (11.6% [10.8-12.2] of total deaths) and the third-leading cause of death and disability combined (5.7% [5.1-6.2] of total DALYs) in 2019. From 1990 to 2019, the absolute number of incident strokes increased by 70.0% (67.0-73.0), prevalent strokes increased by 85.0% (83.0-88.0), deaths from stroke increased by 43.0% (31.0-55.0), and DALYs due to stroke increased by 32.0% (22.0-42.0). During the same period, age-standardised rates of stroke incidence decreased by 17.0% (15.0-18.0), mortality decreased by 36.0% (31.0-42.0), prevalence decreased by 6.0% (5.0-7.0), and DALYs decreased by 36.0% (31.0-42.0). However, among people younger than 70 years, prevalence rates increased by 22.0% (21.0-24.0) and incidence rates increased by 15.0% (12.0-18.0). In 2019, the age-standardised stroke-related mortality rate was 3.6 (3.5-3.8) times higher in the World Bank low-income group than in the World Bank high-income group, and the age-standardised stroke-related DALY rate was 3.7 (3.5-3.9) times higher in the low-income group than the high-income group. Ischaemic stroke constituted 62.4% of all incident strokes in 2019 (7.63 million [6.57-8.96]), while intracerebral haemorrhage constituted 27.9% (3.41 million [2.97-3.91]) and subarachnoid haemorrhage constituted 9.7% (1.18 million [1.01-1.39]). In 2019, the five leading risk factors for stroke were high systolic blood pressure (contributing to 79.6 million [67.7-90.8] DALYs or 55.5% [48.2-62.0] of total stroke DALYs), high body-mass index (34.9 million [22.3-48.6] DALYs or 24.3% [15.7-33.2]), high fasting plasma glucose (28.9 million [19.8-41.5] DALYs or 20.2% [13.8-29.1]), ambient particulate matter pollution (28.7 million [23.4-33.4] DALYs or 20.1% [16.6-23.0]), and smoking (25.3 million [22.6-28.2] DALYs or 17.6% [16.4-19.0]). Interpretation The annual number of strokes and deaths due to stroke increased substantially from 1990 to 2019, despite substantial reductions in age-standardised rates, particularly among people older than 70 years. The highest age-standardised stroke-related mortality and DALY rates were in the World Bank low-income group. The fastest-growing risk factor for stroke between 1990 and 2019 was high body-mass index. Without urgent implementation of effective primary prevention strategies, the stroke burden will probably continue to grow across the world, particularly in low-income countries.
|
|
| 4. |
- Kim, Min Seo, et al.
(författare)
-
Global burden of peripheral artery disease and its risk factors, 1990-2019 : a systematic analysis for the Global Burden of Disease Study 2019
- 2023
-
Ingår i: The Lancet Global Health. - : Elsevier. - 2214-109X. ; 11:10, s. E1553-E1565
-
Tidskriftsartikel (refereegranskat)abstract
- Background: Peripheral artery disease is a growing public health problem. We aimed to estimate the global disease burden of peripheral artery disease, its risk factors, and temporospatial trends to inform policy and public measures.Methods: Data on peripheral artery disease were modelled using the Global Burden of Disease, Injuries, and Risk Factors Study (GBD) 2019 database. Prevalence, disability-adjusted life years (DALYs), and mortality estimates of peripheral artery disease were extracted from GBD 2019. Total DALYs and age-standardised DALY rate of peripheral artery disease attributed to modifiable risk factors were also assessed.Findings: In 2019, the number of people aged 40 years and older with peripheral artery disease was 113 million (95% uncertainty interval [UI] 99 center dot 2-128 center dot 4), with a global prevalence of 1 center dot 52% (95% UI 1 center dot 33-1 center dot 72), of which 42 center dot 6% was in countries with low to middle Socio-demographic Index (SDI). The global prevalence of peripheral artery disease was higher in older people, (14 center dot 91% [12 center dot 41-17 center dot 87] in those aged 80-84 years), and was generally higher in females than in males. Globally, the total number of DALYs attributable to modifiable risk factors in 2019 accounted for 69 center dot 4% (64 center dot 2-74 center dot 3) of total peripheral artery disease DALYs. The prevalence of peripheral artery disease was highest in countries with high SDI and lowest in countries with low SDI, whereas DALY and mortality rates showed U-shaped curves, with the highest burden in the high and low SDI quintiles.Interpretation: The total number of people with peripheral artery disease has increased globally from 1990 to 2019. Despite the lower prevalence of peripheral artery disease in males and low-income countries, these groups showed similar DALY rates to females and higher-income countries, highlighting disproportionate burden in these groups. Modifiable risk factors were responsible for around 70% of the global peripheral artery disease burden. Public measures could mitigate the burden of peripheral artery disease by modifying risk factors.
|
|
| 5. |
- Kumar, Amarjeet, et al.
(författare)
-
Development of Novel Hybrid Models for Prediction of Drought-and Stress-Tolerance Indices in Teosinte Introgressed Maize Lines Using Artificial Intelligence Techniques
- 2022
-
Ingår i: Sustainability. - : MDPI. - 2071-1050. ; 14:4
-
Tidskriftsartikel (refereegranskat)abstract
- Maize (Zea mays subsp. mays) is a staple food crop in the world. Drought is one of the most common abiotic challenges that maize faces when it comes to growth, development, and production. Further knowledge of drought tolerance could aid with maize production. However, there has been less study focused on investigating in depth the drought tolerance of inbred maize lines using artificial intelligence techniques. In this study, multi-layer perceptron (MLP), support vector machine (SVM), genetic algorithm-based multi-layer perceptron (MLP-GA), and genetic algorithm-based support vector machine (SVM-GA) hybrid artificial intelligence algorithms were used for the prediction of drought tolerance and stress tolerance indices in teosinte maize lines. Correspondingly, the gamma test technique was applied to determine efficient input and output vectors. The potential of the developed models was evaluated based on statistical indices and graphical representations. The results of the gamma test based on the least value of gamma and standard error indices show that days of anthesis (DOA), days of silking (DOS), yield index (YI), and gross yield per plant (GYP) information vector arrangements were determined to be an efficient information vector combination for the drought-tolerance index (DTI) as well as the stress-tolerance index (STI). The MLP, SVM, MLP-GA, and SVM-GA algorithms’ results were compared based on statistical indices and visual interpretations that have satisfactorily predict the drought-tolerance index and stress-tolerance index in maize crops. The genetic algorithm-based hybrid models (MLP-GA and SVM-GA) were found to better predict the drought-tolerance index and stress-tolerance index in maize crops. Similarly, the SVM-GA model was found to have the highest potential to forecast the DTI and STI in maize crops, compared to the MLP, SVM, and MLP-GA models.
|
|
| 6. |
- Kumar, Deepak, et al.
(författare)
-
Multi-ahead electrical conductivity forecasting of surface water based on machine learning algorithms
- 2023
-
Ingår i: Applied water science. - : Springer Nature. - 2190-5487 .- 2190-5495. ; 13:10
-
Tidskriftsartikel (refereegranskat)abstract
- The present research work focused on predicting the electrical conductivity (EC) of surface water in the Upper Ganga basin using four machine learning algorithms: multilayer perceptron (MLP), co-adaptive neuro-fuzzy inference system (CANFIS), random forest (RF), and decision tree (DT). The study also utilized the gamma test for selecting appropriate input and output combinations. The results of the gamma test revealed that total hardness (TH), magnesium (Mg), and chloride (Cl) parameters were suitable input variables for EC prediction. The performance of the models was evaluated using statistical indices such as Percent Bias (PBIAS), correlation coefficient (R), Willmott’s index of agreement (WI), Index of Agreement (PI), root mean square error (RMSE) and Legate-McCabe Index (LMI). Comparing the results of the EC models using these statistical indices, it was observed that the RF model outperformed the other algorithms. During the training period, the RF algorithm has a small positive bias (PBIAS = 0.11) and achieves a high correlation with the observed values (R = 0.956). Additionally, it shows a low RMSE value (360.42), a relatively good coefficient of efficiency (CE = 0.932), PI (0.083), WI (0.908) and LMI (0.083). However, during the testing period, the algorithm’s performance shows a small negative bias (PBIAS = − 0.46) and a good correlation (R = 0.929). The RMSE value decreases significantly (26.57), indicating better accuracy, the coefficient of efficiency remains high (CE = 0.915), PI (0.033), WI (0.965) and LMI (− 0.028). Similarly, the performance of the RF algorithm during the training and testing periods in Prayagraj. During the training period, the RF algorithm shows a PBIAS of 0.50, indicating a small positive bias. It achieves an RMSE of 368.3, R of 0.909, CE of 0.872, PI of 0.015, WI of 0.921, and LMI of 0.083. During the testing period, the RF algorithm demonstrates a slight negative bias with a PBIAS of − 0.06. The RMSE reduces significantly to 24.1, indicating improved accuracy. The algorithm maintains a high correlation (R = 0.903) and a good coefficient of efficiency (CE = 0.878). The index of agreement (PI) increases to 0.035, suggesting a better fit. The WI is 0.960, indicating high accuracy compared to the mean value, while the LMI decreases slightly to − 0.038. Based on the comparative results of the machine learning algorithms, it was concluded that RF performed better than DT, CANFIS, and MLP. The study recommended using the current month’s total hardness (TH), magnesium (Mg), and chloride (Cl) parameters as input variables for multi-ahead forecasting of electrical conductivity (ECt+1, ECt+2, and ECt+3) in future studies in the Upper Ganga basin. The findings also indicated that RF and DT models had superior performance compared to MLP and CANFIS models. These models can be applied for multi-ahead forecasting of monthly electrical conductivity at both Varanasi and Prayagraj stations in the Upper Ganga basin.
|
|
| 7. |
- Micah, Angela E., et al.
(författare)
-
Tracking development assistance for health and for COVID-19 : a review of development assistance, government, out-of-pocket, and other private spending on health for 204 countries and territories, 1990-2050
- 2021
-
Ingår i: The Lancet. - : Elsevier. - 0140-6736 .- 1474-547X. ; 398:10308, s. 1317-1343
-
Forskningsöversikt (refereegranskat)abstract
- Background The rapid spread of COVID-19 renewed the focus on how health systems across the globe are financed, especially during public health emergencies. Development assistance is an important source of health financing in many low-income countries, yet little is known about how much of this funding was disbursed for COVID-19. We aimed to put development assistance for health for COVID-19 in the context of broader trends in global health financing, and to estimate total health spending from 1995 to 2050 and development assistance for COVID-19 in 2020. Methods We estimated domestic health spending and development assistance for health to generate total health-sector spending estimates for 204 countries and territories. We leveraged data from the WHO Global Health Expenditure Database to produce estimates of domestic health spending. To generate estimates for development assistance for health, we relied on project-level disbursement data from the major international development agencies' online databases and annual financial statements and reports for information on income sources. To adjust our estimates for 2020 to include disbursements related to COVID-19, we extracted project data on commitments and disbursements from a broader set of databases (because not all of the data sources used to estimate the historical series extend to 2020), including the UN Office of Humanitarian Assistance Financial Tracking Service and the International Aid Transparency Initiative. We reported all the historic and future spending estimates in inflation-adjusted 2020 US$, 2020 US$ per capita, purchasing-power parity-adjusted US$ per capita, and as a proportion of gross domestic product. We used various models to generate future health spending to 2050. Findings In 2019, health spending globally reached $8. 8 trillion (95% uncertainty interval [UI] 8.7-8.8) or $1132 (1119-1143) per person. Spending on health varied within and across income groups and geographical regions. Of this total, $40.4 billion (0.5%, 95% UI 0.5-0.5) was development assistance for health provided to low-income and middle-income countries, which made up 24.6% (UI 24.0-25.1) of total spending in low-income countries. We estimate that $54.8 billion in development assistance for health was disbursed in 2020. Of this, $13.7 billion was targeted toward the COVID-19 health response. $12.3 billion was newly committed and $1.4 billion was repurposed from existing health projects. $3.1 billion (22.4%) of the funds focused on country-level coordination and $2.4 billion (17.9%) was for supply chain and logistics. Only $714.4 million (7.7%) of COVID-19 development assistance for health went to Latin America, despite this region reporting 34.3% of total recorded COVID-19 deaths in low-income or middle-income countries in 2020. Spending on health is expected to rise to $1519 (1448-1591) per person in 2050, although spending across countries is expected to remain varied. Interpretation Global health spending is expected to continue to grow, but remain unequally distributed between countries. We estimate that development organisations substantially increased the amount of development assistance for health provided in 2020. Continued efforts are needed to raise sufficient resources to mitigate the pandemic for the most vulnerable, and to help curtail the pandemic for all. Copyright (C) 2021 The Author(s). Published by Elsevier Ltd.
|
|
| 8. |
- Garlapati, Vijay Kumar, et al.
(författare)
-
Invasive weed optimization coupled biomass and product dynamics of tuning soybean husk towards lipolytic enzyme.
- 2022
-
Ingår i: Bioresource Technology. - : Elsevier BV. - 0960-8524 .- 1873-2976. ; 344:Pt B
-
Tidskriftsartikel (refereegranskat)abstract
- Waste to the product approach was proposed for tuning environ-threat soybean husk towards lipolytic enzyme by integrating the invasive weed optimization with biomass and product dynamics study. The invasive weed optimization constitutes based on the non-linear regression model results in a 47 % enhancement in lipolytic enzyme using the optimization parameters of 7% Sigma Final, 9% exponent; Smax of 5 with a population size of 35 and Max. generations of 99. The biomass dynamic study showcases the dynamic parameters of 0.0239 µmax, 8.17 XLimst and 0.852 RFin values. The product dynamic studies reveal the kinetic parameters of kst, kdiv, PFin, which seem to be equal to -0.0338, 0.0896 and 68.1, respectively. Overall, the present study put forth the zero-waste (soybean husk) to the product (lipolytic enzyme) approach by introducing the novel "Invasive Weed Optimization" coupled with "Biomass and product dynamics" to the bioprocessing field.
|
|
| 9. |
- Joshi, Bhupendra, et al.
(författare)
-
A comparative survey between cascade correlation neural network (CCNN) and feedforward neural network (FFNN) machine learning models for forecasting suspended sediment concentration
- 2024
-
Ingår i: Scientific Reports. - : Springer Nature. - 2045-2322. ; 14
-
Tidskriftsartikel (refereegranskat)abstract
- Suspended sediment concentration prediction is critical for the design of reservoirs, dams, rivers ecosystems, various operations of aquatic resource structure, environmental safety, and water management. In this study, two different machine models, namely the cascade correlation neural network (CCNN) and feedforward neural network (FFNN) were applied to predict daily-suspended sediment concentration (SSC) at Simga and Jondhara stations in Sheonath basin, India. Daily-suspended sediment concentration and discharge data from 2010 to 2015 were collected and used to develop the model to predict suspended sediment concentration. The developed models were evaluated using statistical indices like Nash and Sutcliffe efficiency coefficient (NES), root mean square error (RMSE), Willmott’s index of agreement (WI), and Legates–McCabe’s index (LM), supplemented by a scatter plot, density plots, histograms and Taylor diagram for graphical representation. The developed model was evaluated and compared with CCNN and FFNN. Nine input combinations were explored using different lag-times for discharge (Qt-n) and suspended sediment concentration (St-n) as input variables, with the current suspended sediment concentration as the desired output, to develop CCNN and FFNN models. The CCNN4 model with 4 lagged inputs (St-1, St-2, St-3, St-4) outperformed the other developed models with the lowest RMSE = 95.02 mg/l and the highest NES = 0.0.662, WI = 0.890 and LM = 0.668 for the Jondhara Station while the same CCNN4 model secure as the best with the lowest RMSE = 53.71 mg/l and the highest NES = 0.785, WI = 0.936 and LM = 0.788 for the Simga Station. The result shows the CCNN model was better than the FFNN model for predicting daily-suspended sediment at both stations in the Sheonath basin, India. Overall, CCNN showed better forecasting potential for suspended sediment concentration compared to FFNN at both stations, demonstrating their applicability for hydrological forecasting with complex relationships.
|
|
| 10. |
|
|
