Article
Forestry
Aivars Vilguts, Sveinung Orjan Nesheim, Haris Stamatopoulos, Kjell Arne Malo
Summary: This paper investigates a new timber frame structural system that consists of continuous columns, prefabricated hollow box timber decks, and beam-to-column moment-resisting connections. The system allows for long spans while maintaining stability and performance through semi-rigid connections. Experimental investigations confirm the stability and damping performance of the system.
EUROPEAN JOURNAL OF WOOD AND WOOD PRODUCTS
(2022)
Article
Energy & Fuels
Yanli Liu, Junyi Wang
Summary: This paper proposes a transfer learning-based method for probabilistic wind power forecasting. It utilizes model-based transfer learning to construct a multilayer extreme learning machine, optimizes the output mapping factors using particle swarm optimization, and updates the weights through joint distribution adaptation. The method achieves more accurate quantile forecasting results and better nonlinear fitting ability compared to other methods.
Article
Computer Science, Information Systems
Amin Mansour Saatloo, Arash Moradzadeh, Hamed Moayyed, Mostafa Mohammadpourfard, Behnam Mohammadi-Ivatloo
Summary: Dynamic Line Rating (DLR) technology adjusts overhead line's current carrying capacity based on climatic conditions, with benefits including reducing congestion costs, increasing renewable energy penetration, and improving network stability. This article develops various DLR forecasting models for two 400 kV overhead transmission lines in Iran, showing that the H-ELM method outperforms other techniques with the lowest forecasting error values and highest correlation coefficient value.
IEEE SYSTEMS JOURNAL
(2022)
Article
Automation & Control Systems
Keer Wu, Changhong Xu, Jingwen Yan, Fei Wang, Zhizhe Lin, Teng Zhou
Summary: Traffic flow modeling is crucial for intelligent transportation systems, aiming to mitigate congestion and reduce carbon emissions. Kernel-based extreme learning machine (KELM) has shown excellent performance in traffic flow prediction. However, its performance may decrease significantly under non-Gaussian noise. To address this issue, we propose an error-distribution-free kernel extreme learning machine (eDFKELM) model and develop an online version for continual forecasting.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Computer Science, Information Systems
Chunhao Liu, Guangyuan Pan, Dongming Song, Hao Wei
Summary: Using machine learning algorithms for AQI prediction helps analyze future air quality trends. An enhanced GA-KELM prediction method is proposed to address the limitations of conventional machine learning models. Experimental results show that the proposed model trains faster and makes more accurate predictions.
Article
Computer Science, Artificial Intelligence
Miguel Rodriguez Marquez, Esther D. Gutierrez, Juan S. Medina Alvarez, John G. Milton, Juan Luis Cabrera
Summary: This study focuses on predicting falls using real data from human stick balancing experiments. Various machine learning algorithms, including k-nearest neighbors, random forest, support vector machine, and a neural network, were implemented. The results demonstrate that, in certain cases, the neural network and random forest can classify prefall segments with an F1 score larger than 0.97 and detect changes in the pattern preceding a fall around 0.83 seconds before. Another approach identifies the temporal position of fall precursors with an F1 score > 0.9, at times approximately 0.83 seconds before. The classifiers performed well in this complex classification task.
KNOWLEDGE-BASED SYSTEMS
(2023)
Article
Engineering, Civil
Merve Sagiroglu Maali, Mahyar Maali, Casim Yazici
Summary: Using screws instead of bolts can save costs in cold-formed steel structures. The thickness of gusset plates, beam thickness, and use of stiffeners are found to affect the behavior of screwed beam-column connections. Additionally, the failure mode shape and moment resistance value are determined by the gusset plate thickness, beam thickness, and C/P ratio.
Article
Chemistry, Multidisciplinary
Cristhian Ramirez Ortiz, Gilberto Areiza Palma, Albio D. Gutierrez Amador, Jose L. Ramirez Duque, Ruth E. Cano Buitron, Luis F. Gonzales Escobar
Summary: This paper investigates the seismic behavior of a steel beam-to-concrete-filled steel tubular column connection with external diaphragms. The results indicate that this connection exhibits good ductility and dissipation capacity, meeting the design requirements for earthquake resistance.
APPLIED SCIENCES-BASEL
(2022)
Article
Computer Science, Information Systems
Zeynep Bala Duranay
Summary: This study uses the Extreme Learning Machine (ELM) method to estimate the daily average energy production of a solar power plant in Elazig, Turkey. The performance of the model is improved by optimizing ELM's hyperparameters using the Modified Golden Sine Algorithm. Charts of real power and ELM predicted power for different months, as well as numerical values of radiation, temperature, wind speed, real power, and ELM predicted power for a ten-month period, are presented. The calculated R and RMSE values demonstrate the performance of the ELM model used in the study.
Article
Engineering, Civil
Guangda Zhang, Qiang Han, Kun Xu, Yanchen Song, Zhipeng Li, Xiuli Du
Summary: A detailed numerical analysis model was established to investigate the bearing capacity and failure modes of socket CFST column-cap beam joints. The study found that the size and strength of the steel tube, the socket depth of the CFST, and the type of forming hole have significant effects on the strength and failure modes of the joints. Furthermore, a moment calculation method was proposed to accurately predict the bearing capacity under different failure modes. A design process was also developed for the widespread application of the socket CFST column-cap beam joint with UHPC grouted connection.
ENGINEERING STRUCTURES
(2023)
Article
Computer Science, Artificial Intelligence
Jungang Lou, Yunliang Jiang, Qing Shen, Ruiqin Wang, Zechao Li
Summary: This study proposes a novel probabilistic learning system, probabilistic regularized extreme learning machine combined with ANFIS (probabilistic R-ELANFIS), to improve the accuracy of traffic flow forecasting. The experimental results show that the proposed method achieves competitive performance in terms of forecasting ability and generalizability compared to other methods.
IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS
(2023)
Article
Computer Science, Artificial Intelligence
Qiye Yang, Ke Liang, Tiecheng Su, Kuihua Geng, Mingzhang Pan
Summary: This study introduces two tremor-filtering models based on artificial neural networks and a novel IEO-BLELM model to eliminate hand tremor signals in teleoperation control systems effectively. The proposed models show improved performance compared to existing models.
APPLIED SOFT COMPUTING
(2021)
Article
Meteorology & Atmospheric Sciences
Hongyu An, Qinglan Li, Xinyan Lv, Guangxin Li, Qifeng Qian, Guanbo Zhou, Gaozhen Nie, Lijie Zhang, Linwei Zhu
Summary: In this study, AI models were used to forecast extreme temperatures in nine Chinese cities, outperforming traditional numerical weather prediction methods. Among the AI models, the multilayer perceptron showed the best performance.
WEATHER AND CLIMATE EXTREMES
(2023)
Article
Engineering, Multidisciplinary
Guo Chun Wang, Qian Zhang, Shahab S. Band, Majid Dehghani, Kwok Wing Chau, Quan Thanh Tho, Senlin Zhu, Saeed Samadianfard, Amir Mosavi
Summary: This study utilizes multiple extreme learning machines to forecast hydrological drought, and the results show that ELMs can predict with high precision. The hybridization of wavelet with the models in data preprocessing significantly improves the model performance, especially in error reduction.
ENGINEERING APPLICATIONS OF COMPUTATIONAL FLUID MECHANICS
(2022)
Article
Engineering, Civil
Bingqing Dong, Jinlong Pan, Jingming Cai, Li Xu
Summary: The study proposed a novel ECC ring beam connection for ECC-encased CFST columns, demonstrating higher load bearing capacity, ductility, and energy dissipation compared to concrete specimens. The relative reinforcement ratio significantly influenced the failure modes of the ECC connection, while increased circumferential reinforcement ratio and joint size positively impacted the seismic behavior of the ECC connection.
ENGINEERING STRUCTURES
(2021)
Article
Mechanics
Yan Cao, Mohammad Hasan Asadi, Rayed Alyousef, Shahrizan Baharom, Abdulaziz Alaskar, Hisham Alabduljabbar, Abdeliazim Mustafa Mohamed, Hamid Assilzadeh
Summary: This study evaluates the loading capacity, energy absorption, and behavior ratios of semi-supported steel plate shear walls (SSPSWs) with different types and thicknesses of infill plate materials. The results show that SSPSWs with ASTM A572 infill plate have higher loading capacity and energy absorption, while SSPSWs with LPY100 infill plate have higher ductility ratio.
MECHANICS BASED DESIGN OF STRUCTURES AND MACHINES
(2023)
Article
Materials Science, Multidisciplinary
Yan Cao, Rayed Alyousef, Shahrizan Baharom, S. N. R. Shah, Abdulaziz Alaskar, Hisham Alabduljabbar, Abdeliazim Mustafa Mohamed, Hamid Assilzadeh
Summary: The study focused on the empirical test and finite element analysis of the dynamic response of SFRC slabs and beams with varying aspect ratios of steel fibers, finding that adding steel fibers increased slab capacity and reduced crack spacings.
MECHANICS OF ADVANCED MATERIALS AND STRUCTURES
(2022)
Article
Energy & Fuels
Nadja Lakovic, Afrasyab Khan, Biljana Petkovic, Dalibor Petkovic, Boris Kuzman, Sead Resic, Kittisak Jermsittiparsert, Sikander Azam
Summary: In this study, a soft computing model ANFIS was used to predict the higher heating value of biomass. The analysis showed that the ash percentage weight had the highest relevance to the biomass's higher heating value.
BIOMASS CONVERSION AND BIOREFINERY
(2023)
Article
Energy & Fuels
Momir Milic, Biljana Petkovic, Abdellatif Selmi, Dalibor Petkovic, Kittisak Jermsittiparsert, Aleksandar Radivojevic, Milos Milovancevic, Afrasyab Khan, Sladana T. Vidosavljevic, Nebojsa Denic, Boris Kuzman
Summary: This study optimized the predictors for fatty acid methyl ester yield and exergy efficiency in situ transesterification process. The results showed that the optimal combination for fatty acid methyl ester yield was ultrasonic power and reaction time, while the optimal combination for exergy efficiency was concentrations of methanol and chloroform in oil. These optimized predictors effectively improved the fatty acid methyl ester yield and exergy efficiency.
BIOMASS CONVERSION AND BIOREFINERY
(2023)
Article
Construction & Building Technology
Abdeliazim Mustafa Mohamed, Maaz Osman Bashir, Samir Dirar, Nisreen Beshir Osman
Summary: The study focused on assessing the compressive strength of self-compacting concrete with different supplementary materials, improving the strength by raising the content of rice husk and fly ash. Various soft computing models were utilized to analyze the influence of cementitious materials on the strength of concrete, with ANFIS showing remarkable reliability in comparison to ANN and PSO.
STRUCTURAL CONCRETE
(2022)
Article
Infectious Diseases
Roy Rillera Marzo, Absar Ahmad, Md Saiful Islam, Mohammad Yasir Essar, Petra Heidler, Isabel King, Arulmani Thiyagarajan, Kittisak Jermsittiparsert, Karnjana Songwathana, Delan Ameen Younus, Radwa Abdullah El-Abasiri, Burcu Kucuk Bicer, Nhat Tan Pham, Titik Respati, Susan Fitriyana, Erwin Martinez Faller, Aries Moralidad Baldonado, Md Arif Billah, Yadanar Aung, Shehu Muhammad Hassan, Muhammad Mujtaba Asad, Kareem Ahmed El-Fass, Sudip Bhattacharya, Sunil Shrestha, Nouran Ameen Elsayed Hamza, Pascal Friedmann, Michael Head, Yulan Lin, Siyan Yi
Summary: This study aims to investigate the characteristics that influence perceptions of COVID-19 vaccine efficacy and decision making among adult populations in different socioeconomic and cultural contexts. The findings reveal the prevalence of perceptions towards vaccine effectiveness, acceptance, hesitancy, and drivers of vaccination decision-making. Factors such as age, gender, residence, education, marital status, and income are identified as associated factors of outcome variables.
PLOS NEGLECTED TROPICAL DISEASES
(2022)
Article
Construction & Building Technology
Rayed Alyousef, Hossein Mohammadhosseini, Ahmed Farouk Deifalla, Shek Poi Ngian, Hisham Alabduljabbar, Abdeliazim Mustafa Mohamed
Summary: Sheep wool is a natural renewable fiber composite material with environmental, ecological, and economic advantages. However, natural fibers have certain drawbacks. Surface modification of natural fibers can improve their performance, and the addition of sheep wool in concrete composites can enhance tensile strength and impact resistance, increasing concrete ductility and energy absorption capacity.
CONSTRUCTION AND BUILDING MATERIALS
(2022)
Article
Energy & Fuels
Pannee Suanpang, Pitchaya Jamjuntr, Kittisak Jermsittiparsert, Phuripoj Kaewyong
Summary: This research paper proposes a novel microgrid model for an autonomous energy management system, utilizing deep reinforcement learning algorithms to control the power storage, solar panels, generator, and main grid effectively. The system achieves near-optimal performance and can save 13.19% in costs compared to manual control. Future work can focus on using deep learning to predict future energy prices and improving the system for better benefits in the tourism industry.
Article
Green & Sustainable Science & Technology
Panyu Tang, Mahdi Aghaabbasi, Mujahid Ali, Amin Jan, Abdeliazim Mustafa Mohamed, Abdullah Mohamed
Summary: This study used the 2017 U.S. National Household Travel Survey data and the Bayesian Network algorithm to analyze the non-linear and interaction effects of health condition attributes, work trip attributes, work attributes, and individual and household attributes on walking and privately owned vehicles to reach public transit stations for work in California. The study found that the trip time to public transit stations plays the most significant role in individuals' decision to walk, while population density is the most important factor in the privately owned vehicle model.
Article
Green & Sustainable Science & Technology
Musa Mohammed, Nasir Shafiq, Al-Baraa Abdulrahman Al-Mekhlafi, Amin Al-Fakih, Noor Amila Zawawi, Abdeliazim Mustafa Mohamed, Rana Khallaf, Hussein Mohammed Abualrejal, Abdulkadir Adamu Shehu, Ahmed Al-Nini
Summary: This paper discusses the advantages of using BIM for waste management in the planning and design stage of construction. Through a survey and regression analysis in Malaysia, the impact of BIM on waste management during this stage is highlighted.
Article
Green & Sustainable Science & Technology
A. A. I. N. Marhaeni, Kittisak Jermsittiparsert, Lucia Rita Sudarmo, Lucia Rita Indrawati, Andjar Prasetyo, Noviati Fuada, Arnis Rachmadhani, Tri Weda Raharjo, Heri Wahyudianto, Bekti Putri Harwijayanti, Jonni Sitorus, Mochammad Fahlevi, Mohammed Aljuaid
Summary: This study examines people's behavior in financial transactions and the practice of rural credit banks in promoting a green economy. The results indicate that using paper for savings transactions supports green economic initiatives. Additionally, the use of branchless banking demonstrates the penetration of financial literacy in the community.
Article
Green & Sustainable Science & Technology
Pannee Suanpang, Pitchaya Jamjuntr, Phuripoj Kaewyong, Chawalin Niamsorn, Kittisak Jermsittiparsert
Summary: This paper proposes an intelligent public-accessible charging station framework based on Spatio-Temporal Multi-Agent Reinforcement Learning (STMARL), considering long-term spatio-temporal parameters. The framework aims to reduce the overall charging wait time, average charging price, and charging failure rate for electric vehicles (EVs).
Retraction
Energy & Fuels
Nadja Lakovic, Afrasyab Khan, Biljana Petkovic, Dalibor Petkovic, Boris Kuzman, Sead Resic, Kittisak Jermsittiparsert, Sikander Azam
BIOMASS CONVERSION AND BIOREFINERY
(2023)
Article
Construction & Building Technology
Usman Akmal, Sana Fatima, Nauman Khurram, Qasim Shaukat Khan, Tauqir Ahmed, Hisham Alabduljabbar, Youssef Ahmed Awad
Summary: With the increasing construction activity, there is a growing demand for fine and coarse aggregates. However, relying on limited sources would quickly deplete the natural resources of aggregates. To alleviate the pressure on one source, this study conducted experiments to improve the gradation of natural river sand by adding quarry dust. The enhanced sand gradation showed improved concrete properties and cost-effectiveness compared to control concrete made with coarse pit sand.
ADVANCES IN CIVIL ENGINEERING
(2023)
