Article
Computer Science, Artificial Intelligence
Zichen Zhang, Wei -Chiang Hong
Summary: Accurate electric load forecasting is crucial for the efficiency of power system operation. Hybrid intelligent computing methods and swarm-based algorithms, along with the SVR model, show promising results in solving convergence issues. The proposed VMD-SVR-CGWO model outperforms other models in forecasting accuracy based on numerical examples from two electric load data sets.
KNOWLEDGE-BASED SYSTEMS
(2021)
Article
Economics
Jian Luo, Tao Hong, Zheming Gao, Shu-Cherng Fang
Summary: Electric load forecasting is crucial in the energy industry, and this study proposes a robust support vector regression (SVR) model to forecast electricity demand under data integrity attacks. By introducing a weight function to calculate the relative importance of each observation in the load history, a weighted quadratic surface SVR model is constructed, and some theoretical properties are derived. Computational experiments based on publicly available data demonstrate the superior accuracy of the proposed robust model compared to other recent robust models in load forecasting literature.
INTERNATIONAL JOURNAL OF FORECASTING
(2023)
Article
Construction & Building Technology
Zeyu Wang, Xiaojun Zhou, Jituo Tian, Tingwen Huang
Summary: This paper presents a hybrid support vector regression model for medium and long term power load forecasting, and proposes a hierarchical optimization method based on nested strategy and state transition algorithm to enhance prediction accuracy.
SUSTAINABLE CITIES AND SOCIETY
(2021)
Article
Energy & Fuels
Ghulam Hafeez, Imran Khan, Sadaqat Jan, Ibrar Ali Shah, Farrukh Aslam Khan, Abdelouahid Derhab
Summary: In the context of the smart grid, accurate and stable real-time forecasting is crucial for strategic decision-making. By integrating feature engineering and modified firefly optimization algorithm with support vector regression, the FE-SVR-mFFO forecasting framework achieves the relatively independent goals of accuracy, stability, and convergence rate simultaneously.
Article
Energy & Fuels
Guo-Feng Fan, Meng Yu, Song-Qiao Dong, Yi-Hsuan Yeh, Wei-Chiang Hong
Summary: This paper presents a novel short-term load forecasting model that combines support vector regression, grey catastrophe, and random forest modeling. The proposed model demonstrates higher forecasting accuracy and provides analytical support for accurately forecasting electricity consumption.
Article
Engineering, Civil
Saeed Mozaffari, Saman Javadi, Hamid Kardan Moghaddam, Timothy O. Randhir
Summary: A simulation-optimization hybrid model using the PSO algorithm was developed to forecast groundwater levels in aquifers. The model outperformed other models in terms of RMSE and R 2 , providing a reliable tool for decision support and management of similar aquifers.
WATER RESOURCES MANAGEMENT
(2022)
Article
Green & Sustainable Science & Technology
Siwei Li, Xiangyu Kong, Liang Yue, Chang Liu, Muhammad Ahmad Khan, Zhiduan Yang, Honghui Zhang
Summary: Demand prediction has a crucial role in electricity management and decision-making. Due to the variability in electrical load and the emergence of new renewable energy technologies, power systems face technical challenges. Therefore, short-term forecasting is vital for dispatching commands, managing the spot market, and detecting anomalies. In this study, a hybrid method that optimizes support vector machine parameters using Manta ray foraging optimization is proposed for short-term load forecasting. The proposed method's accuracy is evaluated and compared with five other optimizers. Results from a case study using actual data show that the hybridized technique can address the limitations of single methods, achieving high accuracy for electrical load forecasting.
JOURNAL OF CLEANER PRODUCTION
(2023)
Article
Energy & Fuels
Rui Wang, Xiaoyi Xia, Yanping Li, Wenming Cao
Summary: In this study, a Clifford fuzzy support vector machine for regression (CFSVR) based on geometric algebra is proposed for electric load forecasting. Through fuzzy membership, different input points have different contributions to deciding the optimal regression hyperplane. The experiment results show that CFSVR outperforms CSVR and other SVR algorithms in improving the accuracy of electric load forecasting and achieving multistep forecasting.
FRONTIERS IN ENERGY RESEARCH
(2021)
Article
Construction & Building Technology
Enhui Yang, Qinlong Yang, Jie Li, Haopeng Zhang, Haibo Di, Yanjun Qiu
Summary: A prediction method for asphalt pavement icing based on the SVR algorithm is proposed, incorporating the BOA algorithm to automatically adjust parameters and considering the impact of external environmental factors. The prediction accuracy is high compared to existing methods.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Engineering, Electrical & Electronic
Zhibin Qiu, Louxing Zhang, Yan Liu, Jianben Liu, Huasheng Hou, Xiongjian Zhu
Summary: This article introduces a methodology for predicting air gap breakdown voltage using SVR and GA, showing it to be effective. The study provides a reference for AI algorithms in predicting dielectric strength, guiding the optimal design of air insulation structures.
IEEE TRANSACTIONS ON MAGNETICS
(2021)
Article
Engineering, Mechanical
Guo-Feng Fan, Ruo-Tong Zhang, Cen-Cen Cao, Yi-Hsuan Yeh, Wei-Chiang Hong
Summary: This paper proposes a feature extraction and antlion hybrid intelligent power forecasting algorithm that can accurately predict the volatility and nonlinearity of residential power load using empirical wavelet decomposition and support vector regression.
NONLINEAR DYNAMICS
(2023)
Article
Chemistry, Multidisciplinary
Juntao Wei, Shuangjin Zheng, Jiafan Han, Kai Bai
Summary: A cementing quality prediction model based on support vector regression (SVR) was established in this study, and the model was optimized using different optimization algorithms to improve prediction accuracy. The results showed that the GA-SVR model optimized using a genetic algorithm achieved the highest accuracy in predicting cementing quality.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Electrical & Electronic
Guo-Feng Fan, Yan-Rong Liu, Hui-Zhen Wei, Meng Yu, Yin-He Li
Summary: This paper proposes a hybrid model based on EEMD-RF-SVR-RR algorithm for electric load forecasting. Numerical experiments have shown that the model outperforms other models in terms of forecasting accuracy, confirming its feasibility and effectiveness in short-term load forecasting.
ELECTRIC POWER SYSTEMS RESEARCH
(2022)
Article
Energy & Fuels
Suqi Zhang, Ningjing Zhang, Ziqi Zhang, Ying Chen
Summary: This study proposes a high precision load forecasting method based on the Improved Seagull Optimization Algorithm and Support Vector Machine (SVM). By optimizing the internal parameters of SVM and improving the convergence accuracy of the Seagull Optimization Algorithm, the performance and accuracy of the load forecasting model are improved.
Article
Computer Science, Artificial Intelligence
Quan Quan, Zou Hao, Huang Xifeng, Lei Jingchun
Summary: This study presents a water temperature prediction model incorporating with solar radiation to analyze and evaluate the water temperature of large high-altitude reservoirs in western China. The results show that the improved support vector machine model is the best, and it can accurately predict the water temperature at different depths of the reservoir.
NEURAL COMPUTING & APPLICATIONS
(2022)
Article
Management
Guo-Feng Fan, Xiang-Ru Jin, Wei-Chiang Hong
Summary: This paper forecasts the tourism demand of Sanya City using a combination of empirical mode decomposition, support vector regression, and error factor adjustment, demonstrating that the proposed model is more accurate than other models. The paper also provides insight analyses of economic behaviors through the tourism demand's rectangular-ambulatory matrix, revealing the regulation of tourism industry and the future benefits of Sanya's tourism.
JOURNAL OF THE OPERATIONAL RESEARCH SOCIETY
(2022)
Article
Computer Science, Artificial Intelligence
Ming-Wei Li, Dong-Yang Xu, Jing Geng, Wei-Chiang Hong
Summary: This study proposes a hybrid SHM forecasting model and a new algorithm for optimizing hyperparameters. Experimental results show that the model is more robust, exhibits better nonlinear characteristics, and the new algorithm performs well in the forecasting process.
APPLIED SOFT COMPUTING
(2022)
Article
Green & Sustainable Science & Technology
Amit Sagu, Nasib Singh Gill, Preeti Gulia, Pradeep Kumar Singh, Wei-Chiang Hong
Summary: Due to the increase in cyberattacks, IoT devices are facing higher security risks. Existing centralized systems cannot achieve significant outcomes due to the diverse requirements of IoT devices. This paper introduces two novel metaheuristic optimization algorithms for optimizing deep learning models to detect and prevent cyberattacks. The proposed approach, including hybrid DL classifiers, outperforms conventional and cutting-edge methods in terms of model accuracy.
Review
Chemistry, Multidisciplinary
Dilbag Singh, Suhasini Monga, Sudeep Tanwar, Wei-Chiang Hong, Ravi Sharma, Yi-Lin He
Summary: Blockchain technology, originated from bitcoin, has diversified applications beyond finance, including the healthcare industry. This study provides an exhaustive analysis of blockchain technology in healthcare, identifying challenges and proposing solutions through comparative analysis.
APPLIED SCIENCES-BASEL
(2023)
Article
Energy & Fuels
Guo-Feng Fan, Yun Li, Xin-Yan Zhang, Yi-Hsuan Yeh, Wei-Chiang Hong
Summary: With the development of the electric market, electric load forecasting has become an increasing focus for many scholars. Due to the volatility and uncertainty of electric load, it cannot be accurately forecasted by a single model. This study proposes a short-term load forecasting integrated model to address the issue of inaccurate forecasting by a single model.
ENERGY SCIENCE & ENGINEERING
(2023)
Article
Computer Science, Artificial Intelligence
Da Li, Mei-Rong Jiang, Ming-Wei Li, Wei-Chiang Hong, Rui-Zhe Xu
Summary: Accurate prediction of floating offshore platform motion is crucial for controlling the platform's movement and ensuring equipment operates normally. Due to various factors like the mooring system, operation system, wind, wave, and current, accurately predicting the platform motion is challenging. To improve prediction accuracy, this study introduces the Convolutional LSTM network to simulate the platform's nonlinear dynamical system, utilizes the EEMD for modal decomposition, and proposes the FOPM-EEMD-ConvLSTM forecasting model with optimized hyperparameters using the CQALO algorithm. Experimental results using real data demonstrate the improved accuracy and robustness of the proposed approach. (Abstract from: © 2023 Elsevier B.V. All rights reserved.)
APPLIED SOFT COMPUTING
(2023)
Article
Engineering, Electrical & Electronic
Guo-Feng Fan, Li-Ling Peng, Hsin-Pou Huang, Wei-Chiang Hong
Summary: A local constant first-order weighted forecasting model is developed to accurately forecast the electric load of a city at the weekend. The model improves upon the nonlinearity and model interpretability issues in power behavior. Numerical experimental results show that the proposed model outperforms other models in forecasting errors and the significance test confirms the effectiveness and consistency of the method. The study's findings provide valuable insights for weekend power management and commercial design.
ELECTRIC POWER SYSTEMS RESEARCH
(2023)
Article
Construction & Building Technology
Guo-Feng Fan, Ya Zheng, Wen-Jing Gao, Li-Ling Peng, Yi-Hsuan Yeh, Wei-Chiang Hong
Summary: This paper proposes a novel hybrid method, the EWT-MOLSTM-SVR model, for power load forecasting, which combines Long Short-term Memory (LSTM) with the dual optimization of particle swarm algorithm and butterfly algorithm. Experimental results show that the model significantly outperforms other models such as Recurrent Neural Network (RNN), General Regression Neural Network (GRNN), and PSO-SVM in improving forecast accuracy.
ENERGY AND BUILDINGS
(2023)
Article
Computer Science, Artificial Intelligence
Guo-Feng Fan, Ying-Ying Han, Jing-Jing Wang, Hao-Li Jia, Li-Ling Peng, Hsin-Pou Huang, Wei-Chiang Hong
Summary: This article proposes a bidirectional memory feature hybrid model based on a new intelligent optimization method, combining statistical analysis of load and meteorological factors with convolutional neural networks and bidirectional short-term memory neural networks for load forecasting, achieving higher prediction accuracy.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Engineering, Mechanical
Guo-Feng Fan, Ruo-Tong Zhang, Cen-Cen Cao, Yi-Hsuan Yeh, Wei-Chiang Hong
Summary: This paper proposes a feature extraction and antlion hybrid intelligent power forecasting algorithm that can accurately predict the volatility and nonlinearity of residential power load using empirical wavelet decomposition and support vector regression.
NONLINEAR DYNAMICS
(2023)
Article
Computer Science, Artificial Intelligence
Zichen Zhang, Yongquan Dong, Wei-Chiang Hong
Summary: Accurate and reliable probabilistic load forecasting is essential for efficient operation of power systems and efficient use of energy resources. This study proposes a probabilistic load forecasting model that estimates uncertainties in forecasting models and nonstationary electric load data using data filtering, feature extraction, and parameter optimization. Experimental results demonstrate significant improvement in probabilistic and point forecasting compared to suboptimal models.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Zhong-Yi Yang, Xia Cao, Rui-Zhe Xu, Wei-Chiang Hong, Su-Long Sun
Summary: This paper proposes a new berth-tugboat-quay crane joint scheduling method to reduce the economic cost of container ports. By constructing a chaotic quantum adaptive satin bower bird optimizer algorithm, this method provides a better solution when solving the EBUQC model.
EXPERT SYSTEMS WITH APPLICATIONS
(2024)
Article
Computer Science, Information Systems
G. M. Harshvardhan, Aanchal Sahu, Mahendra Kumar Gourisaria, Pradeep Kumar Singh, Wei-Chiang Hong, Vijander Singh, Bunil Kumar Balabantaray
Summary: It is generally observed that increasing the number of convolutional layers in generic image classification procedures can negatively impact model performance. However, state-of-the-art CNN architectures, such as ResNet50, show that deeper architectures with skip-connections can achieve higher performance metrics. This paper examines the feasibility of implementing state-of-the-art CNNs for breast cancer diagnosis by comparing their performance with vanilla CNNs and evaluating different models' performance metrics. The results suggest that VGG16, VGG19, LeNet-5, and a selected vanilla CNN performed the best among all the models.
Article
Computer Science, Information Systems
Dhiren Rohera, Harshal Shethna, Keyur Patel, Urvish Thakker, Sudeep Tanwar, Rajesh Gupta, Wei-Chiang Hong, Ravi Sharma
Summary: This paper investigates fake news identification techniques and proposes a hybrid fake news detection technique using machine learning models.
Article
Medicine, General & Internal
Ishwa Shah, Chelsy Doshi, Mohil Patel, Sudeep Tanwar, Wei-Chiang Hong, Ravi Sharma
Summary: This paper reviews the impact of COVID-19 on human life and discusses the application of technologies such as AI, IoT, AR/VR, and blockchain in combating the pandemic. These technologies provide new solutions and applications that are vital for enhancing healthcare systems, increasing life expectancy, and promoting economic growth.
MEDICINA-LITHUANIA
(2022)
Article
Engineering, Multidisciplinary
A. A. Aganin, A. I. Davletshin
Summary: A mathematical model of interaction of weakly non-spherical gas bubbles in liquid is proposed in this paper. The model equations are more accurate and compact compared to existing analogs. Five problems are considered for validation, and the results show good agreement with experimental data and numerical solutions. The model is also used to analyze the behavior of bubbles in different clusters, providing meaningful insights.
APPLIED MATHEMATICAL MODELLING
(2024)
Article
Engineering, Multidisciplinary
Hao Wu, Jie Sun, Wen Peng, Lei Jin, Dianhua Zhang
Summary: This study establishes an analytical model for the coupling of temperature, deformation, and residual stress to explore the mechanism of residual stress formation in hot-rolled strip and how to control it. The accuracy of the model is verified by comparing it with a finite element model, and a method to calculate the critical exit crown ratio to maintain strip flatness is proposed.
APPLIED MATHEMATICAL MODELLING
(2024)
Article
Engineering, Multidisciplinary
Shengwen Tu, Naoki Morita, Tsutomu Fukui, Kazuki Shibanuma
Summary: This study aimed to extend the finite element method to cope with elastic-plastic problems by introducing the s-version FEM. The s-version FEM, which overlays a set of local mesh with fine element size on the conventional FE mesh, simplifies domain discretisation and provides accurate numerical predictions. Previous applications of the s-version FEM were limited to elastic problems, lacking instructions for stress update in plasticity. This study presents detailed instructions and formulations for addressing plasticity problems with the s-version FEM and analyzes a stress concentration problem with linear/nonlinear material properties.
APPLIED MATHEMATICAL MODELLING
(2024)
Article
Engineering, Multidisciplinary
Bo Fan, Zhongmin Wang
Summary: A 3D rotating hyperelastic composite REF model was proposed to analyze the influence of tread structure and rotating angular speed on the vibration characteristics of radial tire. Nonlinear dynamic differential equations and modal equations were established to study the effects of internal pressure, tread pressure sharing ratio, belt structure, and rotating angular speed on the vibration characteristics.
APPLIED MATHEMATICAL MODELLING
(2024)
Article
Engineering, Multidisciplinary
X. W. Chen, Z. Q. Yue, Wendal Victor Yue
Summary: This paper examines the axisymmetric problem of a flat mixed-mode annular crack near and parallel to an arbitrarily graded interface in functionally graded materials (FGMs). The crack is modeled as plane circular dislocation loop and an efficient solution for dislocation in FGMs is used to calculate the stress field at the crack plane. The analytical solutions of the stress intensity factors are obtained and numerical study is conducted to investigate the fracture mechanics of annular crack in FGMs.
APPLIED MATHEMATICAL MODELLING
(2024)
Article
Engineering, Multidisciplinary
Xumin Guo, Jianfei Gu, Hui Li, Kaihua Sun, Xin Wang, Bingjie Zhang, Rangwei Zhang, Dongwu Gao, Junzhe Lin, Bo Wang, Zhong Luo, Wei Sun, Hui Ma
Summary: In this study, a novel approach combining the transfer matrix method and lumped parameter method is proposed to analyze the vibration response of aero-engine pipelines under base harmonic and random excitations. The characteristics of the pipelines are investigated through simulation and experiments, validating the effectiveness of the proposed method.
APPLIED MATHEMATICAL MODELLING
(2024)
Article
Engineering, Multidisciplinary
Xiangyu Sha, Aizhong Lu, Ning Zhang
Summary: This paper investigates the stress and displacement of a layered soil with a fractional-order viscoelastic model under time-varying loads. The correctness of the solutions is validated using numerical methods and comparison with existing literature. The research findings are of significant importance for exploring soil behavior and its engineering applications under time-varying loads.
APPLIED MATHEMATICAL MODELLING
(2024)
Article
Engineering, Multidisciplinary
Thuy Dong Dang, Thi Kieu My Do, Minh Duc Vu, Ngoc Ly Le, Tho Hung Vu, Hoai Nam Vu
Summary: This paper investigates the nonlinear torsional buckling of corrugated core sandwich toroidal shell segments with functionally graded graphene-reinforced composite (FG-GRC) laminated coatings in temperature change using the Ritz energy method. The results show the significant beneficial effects of FG-GRC laminated coatings and corrugated core on the nonlinear buckling responses of structures.
APPLIED MATHEMATICAL MODELLING
(2024)
Article
Engineering, Multidisciplinary
Zhihao Zhai, Chengbiao Cai, Qinglai Zhang, Shengyang Zhu
Summary: This paper investigates the effect of localized cracks induced by environmental factors on the dynamic performance and service life of ballastless track in high-speed railways. A mathematical approach for forced vibrations of Mindlin plates with a side crack is derived and implemented into a train-track coupled dynamic system. The accuracy of this approach is verified by comparing with simulation and experimental results, and the dynamic behavior of the side crack under different conditions is analyzed.
APPLIED MATHEMATICAL MODELLING
(2024)
Article
Engineering, Multidisciplinary
James Vidler, Andrei Kotousov, Ching-Tai Ng
Summary: The far-field methodology, developed by J.C. Maxwell, is utilized to estimate the effective third order elastic constants of composite media containing random distribution of spherical particles. The results agree with previous studies and can be applied to homogenization problems in other fields.
APPLIED MATHEMATICAL MODELLING
(2024)
Article
Engineering, Multidisciplinary
Kim Q. Tran, Tien-Dat Hoang, Jaehong Lee, H. Nguyen-Xuan
Summary: This study presents novel frameworks for graphene platelets reinforced functionally graded triply periodic minimal surface (GPLR-FG-TPMS) plates and investigates their performance through static and free vibration analyses. The results show that the mass density framework has potential for comparing different porous cores and provides a low weight and high stiffness-to-weight ratio. Primitive plates exhibit superior performance among thick plates.
APPLIED MATHEMATICAL MODELLING
(2024)
Article
Engineering, Multidisciplinary
Bence Hauck, Andras Szekrenyes
Summary: This study explores several methods for computing the J-integral in laminated composite plate structures with delamination. It introduces two special types of plate finite elements and a numerical algorithm. The study presents compact formulations for calculating the J-integral and applies matrix multiplication to take advantage of plate transition elements. The models and algorithms are applied to case studies and compared with analytical and previously used finite element solutions.
APPLIED MATHEMATICAL MODELLING
(2024)
Article
Engineering, Multidisciplinary
Wu Ce Xing, Jiaxing Wang, Yan Qing Wang
Summary: This paper proposes an effective mathematical model for bolted flange joints to study their vibration characteristics. By modeling the flange and bolted joints, governing equations are derived. Experimental studies confirm that the model can accurately predict the vibration characteristics of multiple-plate structures.
APPLIED MATHEMATICAL MODELLING
(2024)
Article
Engineering, Multidisciplinary
Pingchao Yu, Li Hou, Ke Jiang, Zihan Jiang, Xuanjun Tao
Summary: This paper investigates the imbalance problem in rotating machinery and finds that mass imbalance can induce lateral-torsional coupling vibration. By developing a model and conducting detailed analysis, it is discovered that mass imbalance leads to nonlinear time-varying characteristics and there is no steady-state torsional vibration in small unbalanced rotors. Under largely unbalanced conditions, both resonant and unstable behavior can be observed, and increasing lateral damping can suppress instability and reduce lateral amplitude in the resonance region.
APPLIED MATHEMATICAL MODELLING
(2024)
Article
Engineering, Multidisciplinary
Yong Cao, Ziwen Guo, Yilin Qu
Summary: This paper investigates the mechanically induced electric potential and charge redistribution in a piezoelectric semiconductor cylindrical shell. The results show that doping levels can affect the electric potentials and mechanical displacements, and alter the peak position of the zeroth-order electric potential. The doping level also has an inhibiting effect on the first natural frequency. These findings are crucial for optimizing the design and performance of cylindrical shell-shaped sensors and energy harvesters.
APPLIED MATHEMATICAL MODELLING
(2024)
