Article
Computer Science, Artificial Intelligence
Yatong Zhou, Minghui Zhang, Kuo-Ping Lin
Summary: This study proposes a novel model called Gaussian Process Wavelet Self-join Adjacent-feedback Loop Reservoir (GP-WSALR), which combines the advantages of SALR and Gaussian process regression. By adjusting the neurons in the reservoir, it solves the issues of poor nonlinear approximation ability and easily falling into singular solutions caused by a single S-type neuron. The experimental results demonstrate that GP-WSALR achieves superior forecasting accuracy in electrical load and network traffic forecasting problems.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Green & Sustainable Science & Technology
Elham Shabani, Babollah Hayati, Esmaeil Pishbahar, Mohammad Ali Ghorbani, Mohammad Ghahremanzadeh
Summary: This study aims to evaluate the IMM model as a new method for predicting CO2 emissions in the agriculture sector of Iran, which showed to be more accurate compared to other models. Therefore, future research activities could focus on further improving the IMM model.
JOURNAL OF CLEANER PRODUCTION
(2021)
Article
Environmental Sciences
Sen Wang, Jintai Gong, Haoyu Gao, Wenjie Liu, Zhongkai Feng
Summary: This paper investigates a hybrid model combining Gaussian process regression (GPR) and cooperation search algorithm (CSA) for forecasting nonstationary hydrological data series. The developed GPR-CSA model accurately predicts nonlinear runoff and outperforms traditional models in terms of various statistical indicators.
Article
Computer Science, Artificial Intelligence
Rakshitha Godahewa, Kasun Bandara, Geoffrey Webb, Slawek Smyl, Christoph Bergmeir
Summary: Ensembling techniques are used to improve the performance of Global Forecasting Models (GFM) and univariate models in heterogeneous datasets. A new clustered ensembles methodology is proposed to train multiple GFMs on different clusters of series, achieving higher accuracy than baseline models.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Yuntong Hu, Fuyuan Xiao
Summary: This study proposes a novel forecasting model for time series based on network self attention, which aims to mine more information from time series and improve prediction accuracy. Experimental results demonstrate that the proposed method outperforms other methods in predicting construction cost index, M1, and M3 datasets, and exhibits good robustness.
APPLIED SOFT COMPUTING
(2022)
Article
Computer Science, Interdisciplinary Applications
Tong Zhang, Jianlong Wang, Tong Wang, Yiwei Pang, Peixiao Wang, Wangshu Wang
Summary: This study proposes a deep marked graph process model for predicting traffic congestion on complex signalized road networks. By integrating a specially designed spatiotemporal graph convolutional network, this model can effectively emulate the evolution of congestion. Experimental results demonstrate that the proposed method outperforms existing methods in terms of prediction accuracy and computational efficiency.
COMPUTER-AIDED CIVIL AND INFRASTRUCTURE ENGINEERING
(2023)
Article
Construction & Building Technology
Wen-jing Niu, Zhong-kai Feng
Summary: Accurate runoff forecasting is crucial for ensuring sustainable utilization and management of water resources. Research indicates that support vector machine, Gaussian process regression, and extreme learning machine outperform artificial neural network and adaptive neural based fuzzy inference system in streamflow prediction, emphasizing the importance of selecting appropriate forecasting models based on reservoir characteristics.
SUSTAINABLE CITIES AND SOCIETY
(2021)
Article
Thermodynamics
P. C. Mukesh Kumar, R. Kavitha
Summary: The study predicted the dynamic viscosity ratio of nanofluids using machine learning techniques, achieving low error values with multilayer perceptron and Gaussian process regression models. This helps to reduce experimental costs and improves prediction accuracy.
JOURNAL OF THERMAL ANALYSIS AND CALORIMETRY
(2021)
Article
Energy & Fuels
Pradyot Ranjan Jena, Shunsuke Managi, Babita Majhi
Summary: The study develops a multilayer artificial neural network model to forecast CO2 emissions of 17 key emitting countries with 96% prediction accuracy, higher than previous models. High emitting countries like China and India are expected to increase emissions, while low emitting countries like Brazil and South Africa will also see high emission growth.
Article
Geosciences, Multidisciplinary
Weiqi Yang, Yuran Feng, Jian Wan, Lingling Wang
Summary: Landslide hazards are complex nonlinear systems and accurate forecasting of landslide displacement and evolution is crucial. In this study, a probabilistic landslide displacement forecasting model based on the quantification of epistemic uncertainty is proposed, depicting the uncertainty of landslide displacement series using sparse Gaussian process regression.
FRONTIERS IN EARTH SCIENCE
(2022)
Article
Computer Science, Artificial Intelligence
Francisco Martinez, Francisco Charte, Maria Pilar Frias, Ana Maria Martinez-Rodriguez
Summary: This paper discusses the use of generalized regression neural networks for time series forecasting, aiming at fast and accurate forecasts. The key modeling decisions and proposed strategies are analyzed in terms of forecast accuracy and computational time. Additionally, clever techniques for capturing seasonal and trend patterns in time series are suggested. The paper also introduces a publicly available R package that incorporates the best modeling approaches and transformations for making forecasts with generalized regression neural networks.
Article
Computer Science, Artificial Intelligence
Paolo Mancuso, Veronica Piccialli, Antonio M. Sudoso
Summary: This paper introduces a machine learning approach for forecasting hierarchical time series, using a deep neural network to directly generate accurate and reconciled forecasts, while incorporating explanatory variables to improve forecasting accuracy.
EXPERT SYSTEMS WITH APPLICATIONS
(2021)
Article
Energy & Fuels
Jui-Sheng Chou, Ngoc-Quang Nguyen
Summary: The energy sector needs to find a delicate balance between energy supply and demand. Accurate energy consumption forecasts can assist plant operators in achieving this goal. This study explores the application of various techniques from three categories of artificial intelligence, namely convolutional neural networks (CNNs), machine learning (ML), and time-series deep learning (DL), to predict short-term regional energy consumption.
INTERNATIONAL JOURNAL OF ENERGY RESEARCH
(2023)
Article
Computer Science, Artificial Intelligence
Minglan Zhang, Linfu Sun, Yisheng Zou, Songlin He
Summary: In this paper, a novel Deep Implicit Memory Gaussian (DIMG) Network is proposed for time series forecasting, which combines bidirectional deep memory kernel process and implicit features enhancement method. The model is able to capture complex patterns in time series data and improve prediction accuracy by integrating the structural properties of deep learning with the adaptability of kernel methods.
APPLIED SOFT COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Dawei Cheng, Fangzhou Yang, Sheng Xiang, Jin Liu
Summary: Financial time series analysis is essential for hedging market risks and optimizing investment decisions. The proposed multi-modality graph neural network (MAGNN) leverages multimodal inputs for financial time series prediction by constructing a heterogeneous graph network and utilizing a two-phase attention mechanism for joint optimization. Extensive experiments demonstrate the superior performance of MAGNN in financial market prediction, providing investors with profitable and interpretable options to make informed investment decisions.
PATTERN RECOGNITION
(2022)
Review
Green & Sustainable Science & Technology
Yuetao Yang, Gowhar Ahmad Wani, V. Nagaraj, Mohammad Haseeb, Sameer Sultan, Md. Emran Hossain, Mustafa Kamal, Syed Mehmood Raza Shah
Summary: Sustainable tourism research has been investigated through a comprehensive literature review in this study, which evaluates the current research level and provides guidelines for future research. The study clarifies the existing studies, presents a tabulated overview, and analyzes research gaps. It makes a significant contribution to the field by offering a research pathway for aspiring researchers to advance the literature. The study suggests exploring the broad domains of sustainability, sustainable infrastructure and services, livelihood, and destination management for further scientific research.
Article
Economics
Haishi Li, Youxue Jiang, Anam Ashiq, Asma Salman, Mohammad Haseeb, Malik Shahzad Shabbir
Summary: This study explores how various contingencies affect the organizational structure of privately held businesses in China. The cross-section primary data set from 83 Chinese private firms is collected through face-to-face interviews with entrepreneurs, and six hypotheses tests are conducted regarding the contingencies of organizational form. The empirical findings demonstrate that environment, strategy, size, and technology are significant factors in explaining organizational form. Additionally, financial factors are crucial in addressing cash flow issues and forming profit expectations.
MANAGERIAL AND DECISION ECONOMICS
(2023)
Article
Geosciences, Multidisciplinary
Najia Saqib, Ilhan Ozturk, Muhammad Usman, Arshian Sharif, Asif Razzaq
Summary: This study investigates the relationship between economic growth and ecological footprint for 16 European countries from 1990 to 2020. The empirical analysis reveals some correlations, including a negative correlation between foreign direct investment and ecological footprint, and an inverted U-shaped curve between GDP and ecological footprint, supporting the environmental Kuznets Curve hypothesis. Furthermore, renewable energy is found to have a negative correlation with ecological footprint, while energy structure has a positive correlation.
Article
Green & Sustainable Science & Technology
Partha Gangopadhyay, Narasingha Das, G. M. Monirul Alam, Uzma Khan, Mohammad Haseeb, Md. Emran Hossain
Summary: This study investigates the influence of renewable energy intake, globalization, trade, and GDP on carbon pollution in the United States. The findings show that renewable energy consumption has an inverse relationship with CO2 emission, while globalization has a positive relationship. Trade does not affect CO2 emission, and GDP has a favorable influence only in the lower quantiles.
Article
Environmental Studies
Narasingha Das, Md. Emran Hossain, Pinki Bera, Partha Gangopadhyay, Javier Cifuentes-Faura, Ranjan Aneja, Mustafa Kamal
Summary: This study explores the impact of innovations in sustainable energy technologies on decarbonization in the 20 most innovative nations globally. Using the Panel Non-linear Autoregressive Distributed Lag (P-NARDL) technique, the assessment of cause-and-effect relationship revealed a long-term relationship between variables. Positive asymmetric shock in innovations in sustainable energy technologies positively affects decarbonization, while the negative asymmetric effect is insignificant. The findings indicate that clean energy has a negative consequence on carbonization, whereas economic growth is significantly and favorably associated with it. Furthermore, the study suggests bidirectional causation among all variables except for the unidirectional causality from the usage of sustainable energy technology to CO2 emissions. In a global context, the research recommends governments to reform patenting regulations to identify the roles of new sustainable energy technologies and rectify environmental damages.
ENERGY & ENVIRONMENT
(2023)
Article
Computer Science, Hardware & Architecture
Mustafa Kamal, Ali Bostani, Julian L. Webber, Abolfazl Mehbodniya, Ruby Mishra, Mahendran Arumugam
Summary: In this research, a unified controller consisting of PID, fuzzy, and artificial neural network controllers is proposed to reduce the total harmonic distortion (THD) in a 31-level multilevel inverter in a solar photovoltaic (PV) system. Simulation results show that the proposed controller achieves a THD reduction to 0.94%.
COMPUTERS & ELECTRICAL ENGINEERING
(2023)
Article
Mathematics, Interdisciplinary Applications
Amar Johri, Misbah Ul Islam, Mustafa Kamal
Summary: The significance of financial literacy is increasing in today's world as it provides individuals with necessary financial knowledge and plays a vital role in economic development. A study conducted in Saudi Arabia analyzed the impact of financial literacy on investors' financial decisions, planning, product selection, and investment choices. The results showed that financial literacy has a significant effect on these aspects and is influenced by financial literacy awareness programs, which positively influence investment decisions. The findings will help prospective investors understand the importance of improving their financial knowledge for future financial goals.
DISCRETE DYNAMICS IN NATURE AND SOCIETY
(2023)
Article
Geosciences, Multidisciplinary
Rong Wang, Muhammad Usman, Magdalena Radulescu, Javier Cifuentes-Faura, Daniel Balsalobre-Lorente
Summary: This research examines the impact of technological innovations, financial development, renewable and non-renewable energy, and FDI inflows on ecological footprint in 14 developing European Union economies. The study finds that renewable energy and technological innovation can reduce environmental degradation, while financial development, non-renewable energy use, and FDI contribute to increased environmental degradation. The study suggests implementing measures in clean technology, renewable energy use, financial development, and FDI to address these issues.
Article
Construction & Building Technology
Sajjad Wali Khan, Mustafa Kamal, Fasih Ahmed Khan, Akhtar Gul, Muhammad Alam, Feroz Shah, Khan Shahzada
Summary: This paper experimentally investigates the effect of different polyvinyl alcohol (PVA) fibres on the mechanical and physical properties of Engineered Cementitious Composites (ECC). Three different types of ECC mixes were tested, with varying dosages of fibre contents. The workability of the mixes decreased with increasing fibre percentages, but remained within ASTM's allowable range. The ductile behavior of ECC was compromised with the use of coarse aggregate, but strain hardening and multiple-cracking properties remained intact. Mechanical properties increased with increasing fibre contents up to a maximum dosage of 1.5%, beyond which there was a slight decrease.
CASE STUDIES IN CONSTRUCTION MATERIALS
(2023)
Article
Environmental Sciences
Ijaz Uddin, Muhammad Usman, Najia Saqib, Muhammad Sohail Amjad Makhdum
Summary: This study investigates the impact of geopolitical risk, corruption, and governance on environmental degradation proxies by carbon emissions in BRICS countries using data from 1990 to 2018. The empirical findings show that government effectiveness, regulatory quality, the rule of law, FDI, and innovation have a negative effect on CO2 emissions, while geopolitical risk, corruption, political stability, and energy consumption have a positive effect on CO2 emissions. Based on these results, the study calls for the central authorities and policymakers of these economies to redesign more sophisticated strategies to protect the environment.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Environmental Sciences
Ijaz Uddin, Atta Ullah, Najia Saqib, Rakhshanda Kousar, Muhammad Usman
Summary: This research investigates the impact of energy consumption, financial development, and economic development on the ecological footprint in a panel of developed and developing countries. The findings reveal that various factors have different effects on the ecological footprint in developed and developing countries. These findings imply the necessity of different policy implications to reduce the ecological footprint in both developed and developing countries.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Review
Environmental Sciences
Mariuam Shafi, Carlos Samuel Ramos-Meza, Vipin Jain, Asma Salman, Mustafa Kamal, Malik Shahzad Shabbir, Masood Ur Rehman
Summary: The purpose of this study is to examine the impact of green tax incentives on environmental sustainability and climate change in developing countries. Introducing green tax incentives related to the environment and climate change helps achieve the sustainability objectives of growth and development. The study analyzes the top 100 listed companies on the Swedish stock market to understand the real facts and figures of green tax environment. Using a longitudinal research design, probit and logistic regression are conducted to identify the beneficiaries of the tax incentives. The findings suggest that firm-level characteristics significantly impact the probability of being an ITC beneficiary.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Environmental Sciences
Daniel Balsalobre-Lorente, Lucia Ibanez Luzon, Muhammad Usman, Atif Jahanger
Summary: This study examines the relationship between natural resource rent, mobile use, foreign direct investment, international tourism, and economic growth in Mexico, Indonesia, Nigeria, and Turkey (MINT) from 1971 to 2019 using balanced panel data. The findings reveal that foreign direct investment, natural resource rent, mobile use, and international tourism have a positive and significant impact on MINT economies' economic growth. Additionally, the study empirically supports the tourism-led growth hypothesis in the case of MINT nations. Furthermore, the Granger causality analysis demonstrates a unidirectional causality from economic growth to tourism. The study recommends implementing practical tourism strategies to enhance economic development and foster positive contributions to the tourism sector.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2023)
Article
Economics
Najia Saqib, Muhammad Usman, Ilhan Ozturk, Arshian Sharif
Summary: This study examines the impact of environmental technologies, financial growth, and energy use on ecological footprint and green growth. Environmental innovation and renewable energy deployment contribute to green growth, while financial expansion and non-renewable energy use have negative effects on the environment. The study also identifies causal relationships between different factors.
Article
Geosciences, Multidisciplinary
Muhammad Ramzan, Ummara Razi, Muhammad Usman, Suleman Sarwar, Amogh Talan, Hardeep Singh Mundi
Summary: This paper investigates the impact of nuclear energy, geothermal energy, agriculture development, and urbanization on carbon emissions and ecological footprint in China. The findings show statistically significant correlations between these factors and environmental degradation, while agricultural development has a pollution-mitigation impact.