Forecasting cardiovascular disease mortality using artificial neural networks in Sindh, Pakistan

BMC Public Health, Journal Year: 2025, Volume and Issue: 25(1)

Published: Jan. 4, 2025

Abstract Cardiovascular disease (CVD) is a leading cause of death and disability worldwide, its incidence prevalence are increasing in many countries. Modeling CVD plays crucial role understanding the trend cases, evaluating effectiveness interventions, predicting future trends. This study aims to investigate modeling forecasting mortality, specifically Sindh province Pakistan. The civil hospital Nawabshah area province, Pakistan, provided data set used this study. It time series dataset with actual cardiovascular mortality cases from 1999 2021 included. analyzes forecasts deaths Pakistan using classical models, including Naïve, Holt-Winters, Simple Exponential Smoothing (SES), which have been adopted compared machine learning approach called Artificial Neural Network Auto-Regressive (ANNAR) model. performance both models ANNAR model has evaluated key indicators such as Root Mean Square Deviation Error, Absolute Error (MAE), Percentage (MAPE). After comparing results, it was found that outperformed all selected demonstrating quantifying burden concludes best-selected among competing for province. provides valuable insights into impact interventions aimed at reducing can assist formulating health policies allocating economic resources. By accurately policymakers make informed decisions address public issue effectively.

Language: Английский

---

Analysis of energy-related CO2 emissions in Pakistan: carbon source and carbon damage decomposition analysis

Environmental Science and Pollution Research, Journal Year: 2023, Volume and Issue: 30(49), P. 107598 - 107610

Published: Sept. 22, 2023

Language: Английский

---

Modeling and forecasting carbon dioxide emission in Pakistan using a hybrid combination of regression and time series models

Heliyon, Journal Year: 2024, Volume and Issue: 10(13), P. e33148 - e33148

Published: June 20, 2024

Carbon dioxide (CO

Language: Английский

---

Modeling and Monitoring CO2 Emissions in G20 Countries: A Comparative Analysis of Multiple Statistical Models

Sustainability, Journal Year: 2024, Volume and Issue: 16(14), P. 6114 - 6114

Published: July 17, 2024

The emission of carbon dioxide (CO2) is considered one the main factors responsible for greatest challenges faced by world today: climate change. On other hand, with increase in energy demand due to population and industrialization, CO2 has increased rapidly past few decades. However, world’s leaders, including United Nations, are now taking serious action on how minimize into atmosphere. Towards this end, accurate modeling monitoring historical can help development rational policies. This study aims analyze emitted Group Twenty (G20) countries period 1971–2021. datasets include emissions, nonrenewable (NREN), renewable (REN), Gross Domestic Product (GDP), Urbanization (URB). Various regression-based models, multiple linear regression quantile panel data models different variants, were used quantify influence independent variables response variable. In study, a variable, covariates. ultimate objective was choose best model among competing models. It noted that USA, Canada, Australia produced highest amount consistently entire duration; however, last decade (2011–2021) it decreased 12.63–17.95 metric tons per capita as compared duration 1971–1980 (14.33–22.16 capita). contrast, emissions have Saudi Arabia China recently. For purposes, been divided two independent, equal parts: 1971–1995 1996–2021. fixed effect (PFEM) mixed (PMEM) outperformed using selection prediction criteria. Different provide insights relationship between variables. later duration, all show REN negative impacts except tau = 0.25. NREN strong positive emissions. URB significantly globally. findings hold potential valuable information policymakers addition, results addressing some sustainable goals Nation Development Programme.

Language: Английский

---

Forecasting Thailand’s Transportation CO2 Emissions: A Comparison among Artificial Intelligent Models

Forecasting, Journal Year: 2024, Volume and Issue: 6(2), P. 462 - 484

Published: June 20, 2024

Transportation significantly influences greenhouse gas emissions—particularly carbon dioxide (CO2)—thereby affecting climate, health, and various socioeconomic aspects. Therefore, in developing implementing targeted effective policies to mitigate the environmental impacts of transportation-related emissions, governments decision-makers have focused on identifying methods for accurate reliable forecasting emissions transportation sector. This study evaluates these policies’ CO2 using three models: ANN, SVR, ARIMAX. Data spanning years 1993–2022, including those population, GDP, vehicle kilometers, were analyzed. The results indicate superior performance ANN model, which yielded lowest mean absolute percentage error (MAPE = 6.395). Moreover, highlight limitations ARIMAX model; particularly its susceptibility disruptions, such as COVID-19 pandemic, due reliance historical data. Leveraging a scenario analysis trends under “30@30” policy revealed reduction from fuel combustion sector 14,996.888 kTons 2030. These findings provide valuable insights policymakers fields strategic planning sustainable development.

Language: Английский

---

Statistical Analysis and Modeling of the CO2 Series Emitted by Thirty European Countries

Climate, Journal Year: 2024, Volume and Issue: 12(3), P. 34 - 34

Published: Feb. 29, 2024

In recent decades, an increase in the earth’s atmospheric temperature has been noticed due to augmentation of volume gases with greenhouse effect (GHG) released into atmosphere. To reduce this effect, European Union’s directives indicate action directions for reducing these emissions, among which carbon dioxide (CO2) recorded highest amount. context, article analyzes CO2 series reported 1990–2021 by 30 countries. The Kruskal-Wallis test rejected hypothesis that comes from same underlying distribution. Anderson-Darling normality seven out thirty, and Sen’s procedure found a decreasing trend slope only 17 series. ARIMA models have built all individual Grouping (by k-means hierarchical clustering) provided base building Regional (RegS), describes pollution evolution over Europe. advantage approach is provide synthetic image regional emission (mt), incorporating information (one each country) one—RegS. It also shown selecting number clusters involved RegS assessing their stability essential model’s goodness fit.

Language: Английский

---

Addressing the resource curse: Empirical analysis of greenhouse gas mitigation strategies for sustainable development

Resources Policy, Journal Year: 2023, Volume and Issue: 88, P. 104454 - 104454

Published: Dec. 3, 2023

Language: Английский

---

Analysis and Forecasting of Carbon Emission in SAARC Countries using Attention-based LSTM

2021 IEEE International Conference on Big Data (Big Data), Journal Year: 2023, Volume and Issue: unknown, P. 3396 - 3404

Published: Dec. 15, 2023

Climate change and global warming are urgent environmental issues demanding immediate action to safeguard future generations. The major contributor the greenhouse effect, carbon dioxide $\left(\mathrm{CO}_{2}\right)$, primarily originates from industrial transportation fossil fuel combustion. International agreements, like Paris Agreement, call for a 30-35% reduction in CO 2 emissions compared 2005 levels. This research aims predict raise awareness among SAARC nations governments about increasing trend. We introduce novel predictive framework using Attention-based Long Short-Term Memory (A-LSTM) analysis. Attention mechanism assigns variable weights input data, facilitating indirect connections between LSTM outputs pertinent inputs. enhances resource allocation A-LSTM model, overcoming computational constraints. integrate parameters encompassing land-use changes, oil, natural gas, coal combustion forecast correlate them with population per capita GDP. Our comparative analysis conclusively demonstrates superior performance of models over baseline when applied emission dataset sourced World Data (OWID) Bank Indicator database. Specifically, model registers MAPE 24.968 an RMSE 0.34, whereas showcases marked improvement 57% considerably lower 10.5902 0.107.

Language: Английский

---

TESTING THE UNEMPLOYMENT HYSTERESIS HYPOTHESIS FOR TÜRKİYE BY AGE, GENDER AND FREQUENCY DIFFERENCES: EVIDENCE FROM WAVELET-BASED UNIT ROOT TESTS

Akademik Yaklaşımlar Dergisi, Journal Year: 2024, Volume and Issue: unknown

Published: Nov. 27, 2024

The main objective of this study is to test the unemployment hysteresis hypothesis by age, gender and frequency differences (period) for Türkiye. For purpose, monthly data cover a long period between 2005 2023.Wavelet transforms rates, along with their original values, are used investigate effect short, medium, long-run components. First, linearity series significance structural breaks tested. Fourier Augmented Dickey-Fuller (FADF) linear significant breaks. Kapetanios-Shin-Snell (FKSS) non-linear without breaks, ADF KSS tests used. findings reveal that in Türkiye differs gender, differences.

Language: Английский

---