Article
Engineering, Electrical & Electronic
Gholamreza Memarzadeh, Farshid Keynia
Summary: This paper presents a new hybrid forecast model for short-term electricity load and price prediction. By using wavelet transform, feature selection, and deep learning algorithm, the accuracy of predictions has been improved and successfully validated on actual data from multiple electricity markets.
ELECTRIC POWER SYSTEMS RESEARCH
(2021)
Article
Computer Science, Artificial Intelligence
Christian Napoli, Giorgio De Magistris, Carlo Ciancarelli, Francesco Corallo, Francesco Russo, Daniele Nardi
Summary: In this study, a Wavelet Recurrent Network is proposed to predict multidimensional time series by exploiting multiple correlated features. The model combines wavelet transform and recurrent neural network to decompose input signal and predict future samples. The results demonstrate higher accuracy and wider forecast horizon compared to recurrent networks without wavelet transform.
EXPERT SYSTEMS WITH APPLICATIONS
(2022)
Article
Multidisciplinary Sciences
Zhanjie Jing, Xiaohong Gao
Summary: This paper proposes a tailings pond monitoring and early warning system, which utilizes a deep learning network to construct an infiltration line prediction model, aiming to improve the stability and safety management level of tailings ponds.
Article
Energy & Fuels
Astrid X. Rodriguez, Diego A. Salazar
Summary: This study introduces a methodology based on multivariate Long-Short Term Memory (LSTM) Neural Networks to predict oil and water production in an oil field exploited through waterflooding. Operational variables such as bottom-hole pressure and water injection rate provide significant approximations to predict oil or water production.
JOURNAL OF PETROLEUM SCIENCE AND ENGINEERING
(2022)
Article
Engineering, Electrical & Electronic
Mustafa Mert Keskin, Fatih Irim, Oguzhan Karaahmetoglu, Ersin Kaya
Summary: This paper investigates the modeling capability of LSTM for distant temporal interaction and proposes a novel hierarchical architecture (HLSTM) to enhance this capability. Experimental results demonstrate that the new architecture outperforms the traditional LSTM architecture and other studies in modeling deep temporal connections.
SIGNAL IMAGE AND VIDEO PROCESSING
(2023)
Article
Multidisciplinary Sciences
Yuguang Chen, Jintao Huang, Hongbin Xu, Jincheng Guo, Linyong Su
Summary: A dynamic spatiotemporal graph attention network traffic flow prediction model based on the attention mechanism was proposed to improve the accuracy of traffic flow prediction under the influence of nearby time traffic flow disturbance. Experimental results on public data sets demonstrate the superiority of the proposed model compared to six baseline models.
SCIENTIFIC REPORTS
(2023)
Article
Engineering, Environmental
Sunil Kumar, Dheeraj Kumar, Praveen Kumar Donta, Tarachand Amgoth
Summary: Land surface subsidence is mainly caused by underground mining and subsurface coal fires, with factors such as over-exploitation of resources contributing to the phenomenon. Monitoring and predicting subsidence can be challenging due to limitations in conventional techniques. The prediction model using Modified PSInSAR in Jharia Coalfield, India, shows alarming subsidence rates in certain areas.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2022)
Article
Engineering, Geological
Asmae Berhich, Fatima-Zahra Belouadha, Mohammed Issam Kabbaj
Summary: In this paper, the authors propose a location-dependent earthquake prediction method based on recurrent neural network algorithms. The method involves clustering and dividing the seismic dataset to focus on each region independently, resulting in accurate predictions of specific trends and especially good performance in predicting large earthquakes.
SOIL DYNAMICS AND EARTHQUAKE ENGINEERING
(2022)
Article
Physics, Multidisciplinary
Oscar Garibo-I-Orts, Alba Baeza-Bosca, Miguel A. Garcia-March, J. Alberto Conejero
Summary: Anomalous diffusion occurs at different scales in nature, and accurately measuring the associated exponent is important in understanding the diffusion process. Identifying the model behind the trajectory can be difficult, especially with short and noisy data.
JOURNAL OF PHYSICS A-MATHEMATICAL AND THEORETICAL
(2021)
Article
Construction & Building Technology
Yifan Zhao, Wei Li, Jili Zhang, Changwei Jiang, Siyu Chen
Summary: With increasing energy consumption, achieving energy-saving operation of air-conditioning systems is crucial for improving building energy efficiency. This paper proposes a real-time energy consumption prediction model for air-conditioning systems based on a long short-term memory neural network, which can select the optimal operating strategy by predicting energy consumption and achieve greater energy conservation.
ENERGY AND BUILDINGS
(2023)
Article
Energy & Fuels
Davi Guimaraes da Silva, Anderson Alvarenga de Moura Meneses
Summary: This study compares the performance of two deep learning models (LSTM and BLSTM) in short-term prediction of electricity consumption time series. Through evaluation on multiple datasets, it is concluded that the BLSTM model outperforms the LSTM model in different scales of electricity consumption. This study provides a baseline for future research on electricity consumption time series prediction.
Article
Computer Science, Information Systems
Licheng Zhang, Jingtian Ya, Zhigang Xu, Said Easa, Kun Peng, Yuchen Xing, Ran Yang
Summary: Conventional fuel consumption prediction models using neural networks often have low accuracy and poor correlation due to the use of driving parameters like speed and acceleration as training inputs. To address this, this study introduced jerk as an important variable in the training input of four selected neural network models: long short-term memory (LSTM), recurrent neural network (RNN), nonlinear auto-regressive model with exogenous inputs (NARX), and generalized regression neural network (GRNN). Evaluation of the prediction performance using root-mean-square error (RMSE), relative error (RE), and coefficient of determination (R2) revealed that the LSTM model outperformed the others. Overall, the addition of jerk improved the accuracy of fuel consumption prediction, with LSTM showing the greatest improvement under high-speed expressway scenarios, reducing RMSE by 14.3%, RE by 28.3%, and increasing R2 by 9.7%.
Article
Construction & Building Technology
Zhihong Li, Xiaoyu Wang, Kairan Yang
Summary: Vehicle exhaust is a major source of carbon emissions. Short-term traffic flow prediction has significant implications for alleviating traffic congestion, optimizing travel structure, and reducing carbon emissions. This study evaluates current advanced models for short-term traffic flow prediction, highlighting their limitations. To improve accuracy and ensure effective traffic management, a self-attention-based hybrid model is proposed.
ADVANCES IN CIVIL ENGINEERING
(2023)
Article
Computer Science, Information Systems
Yi Shi, Liumei Zhang, Shengnan Lu, Qiao Liu
Summary: In this study, London bike-sharing data were used to analyze the impact of meteorological elements and time factors on bike-sharing demand. LSTM neural network models and popular machine learning models were utilized to predict the demand for shared bikes on an hourly basis. The major factors affecting bike-sharing demand were found to include humidity, peak hours, and temperature. The LSTM model exhibited the smallest error compared to other machine learning models.
Article
Geochemistry & Geophysics
Mohtasin Golam, Rubina Akter, Jae-Min Lee, Dong-Seong Kim
Summary: The study proposes a high-precision LSTM-based neural network model named SIPNet for short-term prediction of solar irradiance. Analyzing meteorological and radiation data, SIPNet shows superior predictive accuracy compared to other models.
IEEE GEOSCIENCE AND REMOTE SENSING LETTERS
(2022)
Article
Construction & Building Technology
Arturo Martinez, Carmen Alonso, Fernando Martin-Consuegra, Gloria Perez, Borja Frutos, Alvaro Gutierrez
Summary: The study demonstrates a new Trombe wall technique by applying a thermochromic mortar on the wall to reduce solar absorption in summer without affecting winter heating. Through indoor and outdoor measurements, it was found that this technology can effectively improve the thermal transfer performance of buildings and energy saving effects.
BUILDING RESEARCH AND INFORMATION
(2021)
Article
Chemistry, Multidisciplinary
Rafael Sendra-Arranz, Alvaro Gutierrez
Summary: This paper examines the design of communication mechanisms in swarm robotics systems, showing how the evolution of controllers can lead to diverse forms of communication. The study focuses on leader selection and borderline identification tasks, demonstrating the emergence of abstract and situated communications. Scalability and robustness properties are successfully validated in the research.
APPLIED SCIENCES-BASEL
(2021)
Editorial Material
Energy & Fuels
Alvaro Gutierrez
Article
Environmental Sciences
Blanca Larraga-Garcia, Manuel Quintana-Diaz, Alvaro Gutierrez
Summary: Trauma is a major cause of death worldwide, especially for those under 45 years old. There is a significant increase in deaths within the first hour after a traumatic event. Therefore, it is crucial to learn how to manage traumatic injuries in a prehospital setting. Medical students from Universidad Autonoma conducted 66 simulations using a web-based trauma simulator to stabilize trauma patients. However, the evaluations from trauma experts revealed that a significant number of simulations received low scores. Thus, there is a need for further training in undergraduate education for prehospital trauma management and the development of an objective evaluation system.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2022)
Review
Environmental Sciences
Blanca Larraga-Garcia, Manuel Quintana-Diaz, Alvaro Gutierrez
Summary: This review analyzed current practices in teaching trauma management using simulations and summarized the findings. The study found that few articles targeted students for training, high-fidelity mannequins were the most commonly used simulation method, evaluation methods mainly consisted of checklists and questionnaires, and trauma training focused more on hospital environment than pre-hospital environment.
INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH
(2022)
Editorial Material
Chemistry, Multidisciplinary
Alvaro Gutierrez
APPLIED SCIENCES-BASEL
(2022)
Article
Construction & Building Technology
Elvira Nicolini, Maria Luisa Germana, Giulia Marcon, Marcello Chiodi, Alvaro Gutierrez, Francesca Olivieri
Summary: The aim of this study is to verify the improvement of a building envelope's performance with a green wall under high irradiance and variable meteorological conditions. The research is based on the analysis of a database covering a 3-year period and shows that a green wall can significantly reduce the temperature of the wall under high irradiance.
BUILDING AND ENVIRONMENT
(2022)
Article
Physics, Multidisciplinary
Alejandro Pascual-Valdunciel, Victor Lopo-Martinez, Alberto J. Beltran-Carrero, Rafael Sendra-Arranz, Miguel Gonzalez-Sanchez, Javier Ricardo Perez-Sanchez, Francisco Grandas, Dario Farina, Jose L. Pons, Filipe Oliveira Barroso, Alvaro Gutierrez
Summary: This study explores different machine learning and deep learning models for binary classification (Tremor; No Tremor) of kinematic and electromyography signals recorded from patients diagnosed with essential tremors and healthy subjects. All models showed high classification scores (Tremor vs. No Tremor) for different input data modalities, ranging from 0.8 to 0.99 for the f(1) score. The LSTM models achieved a 0.98 f(1) score for the classification of raw EMG signals, showing high potential for detecting tremors without any processed features or preliminary information. These models can be explored in real-time closed-loop PES strategies to detect tremors and enable stimulation with minimal signal processing steps.
Article
Computer Science, Information Systems
Alejandro Pascual-Valdunciel, Victor Lopo-Martinez, Rafael Sendra-Arranz, Miguel Gonzalez-Sanchez, Javier Ricardo Perez-Sanchez, Francisco Grandas, Diego Torricelli, Juan C. Moreno, Filipe Oliveira Barroso, Jose L. Pons, Alvaro Gutierrez
Summary: This study tested the use of LSTM neural networks to predict tremor signals and found that the predicted signals had high correlation with the expected values and a small phase delay. The prediction horizon was found to be the most important parameter affecting prediction performance, and the LSTM-based models outperformed previous studies in predicting both phase and amplitude of tremor signals.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2022)
Article
Chemistry, Multidisciplinary
Jaime Arcos-Legarda, David Torres, Fredy Velez, Hernan Rodriguez, Alexander Parra, Alvaro Gutierrez
Summary: This paper presents a mechatronics design of a gait-assistance exoskeleton for therapy in children with Duchenne muscular dystrophy (DMD). The design includes adaptable mechanisms and a series-elastic actuator to ensure proper adjustment and alignment with the patient. A mathematical dynamic hybrid model is developed to design a nonlinear control strategy that guarantees stable reference tracking. The proposed control law is numerically validated in a simulation to evaluate its performance and robustness under parameter variation during therapy.
APPLIED SCIENCES-BASEL
(2023)
Article
Chemistry, Multidisciplinary
Alvaro Gutierrez, Patricia Blanco, Veronica Ruiz, Christos Chatzigeorgiou, Xabier Oregui, Marta Alvarez, Sara Navarro, Michalis Feidakis, Izar Azpiroz, Gemma Izquierdo, Blanca Larraga-Garcia, Panagiotis Kasnesis, Igor Garcia Olaizola, Federico Alvarez
Summary: This paper presents a framework that allows real-time monitoring of first responders' vital signs and inference of their cognitive load. The framework ensures the adaptation of information provided to their assimilation capabilities under stressful situations. Experimental tests have demonstrated the functionality of the framework in both lab and field settings.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Marine
Jaime Arcos-Legarda, Alvaro Gutierrez
Summary: This work aims to develop a robust model predictive control (MPC) based on the active disturbance rejection control (ADRC) approach by using a discrete extended disturbance observer (ESO). The proposed technique combines disturbances and uncertainties into a total disturbance using the ADRC approach, which is estimated and rejected through feedback control using a discrete ESO. The performance of the proposed control technique is evaluated through simulation in a robotic autonomous underwater vehicle (AUV), showing superiority over classical MPC in reference tracking, external disturbances rejection, and model uncertainties attenuation tests.
JOURNAL OF MARINE SCIENCE AND ENGINEERING
(2023)
Review
Energy & Fuels
Isaac Gallardo, Daniel Amor, Alvaro Gutierrez
Summary: Photovoltaic power forecasting is a crucial issue for integrating renewable energy into the grid. This study reviews current methods for predicting photovoltaic power or solar irradiance, summarizing them, identifying gaps and trends, and providing an overview of recent advancements. A search on Web of Science yielded 60 articles published since 2020, which were analyzed to gather information on forecasting methods, time horizons, time steps, and parameters. Machine learning and deep learning techniques, particularly artificial neural networks, are the most commonly used forecasting methods. Most articles focus on predicting power within one hour or less, using weather variables as inputs, primarily irradiance, temperature, wind speed, and humidity. However, there is a lack of real-time hardware implementations, which is an important area for future development in the use of embedded prediction systems at photovoltaic installations.
Meeting Abstract
Regional & Urban Planning
Arturo Martinez, Carmen Alonso, Fernando Martin-Consuegra, Gloria Perez, Borja Frutos, Alvaro Gutierrez
JOURNAL OF PLANNING LITERATURE
(2022)
Article
Construction & Building Technology
Samiran Khorat, Debashish Das, Rupali Khatun, Sk Mohammad Aziz, Prashant Anand, Ansar Khan, Mattheos Santamouris, Dev Niyogi
Summary: Cool roofs can effectively mitigate heatwave-induced excess heat and enhance thermal comfort in urban areas. Implementing cool roofs can significantly improve urban meteorology and thermal comfort, reducing energy flux and heat stress.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Qi Li, Jiayu Chen, Xiaowei Luo
Summary: This study focuses on the vertical wind conditions as a main external factor that limits the energy assessment of high-rise buildings in urban areas. Traditional tools for energy assessment of buildings use a universal vertical wind profile estimation, without taking into account the unique wind speed in each direction induced by the various shapes and configurations of buildings in cities. To address this limitation, the study developed an omnidirectional urban vertical wind speed estimation method using direction-dependent building morphologies and machine learning algorithms.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Xiaojun Luo, Lamine Mahdjoubi
Summary: This paper presents an integrated blockchain and machine learning-based energy management framework for multiple forms of energy allocation and transmission among multiple domestic buildings. Machine learning is used to predict energy generation and consumption patterns, and the proposed framework establishes optimal and automated energy allocation through peer-to-peer energy transactions. The approach contributes to the reduction of greenhouse gas emissions and enhances environmental sustainability.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Ying Yu, Yuanwei Xiao, Jinshuai Chou, Xingyu Wang, Liu Yang
Summary: This study proposes a dual-layer optimization design method to maximize the energy sharing potential, enhance collaborative benefits, and reduce the storage capacity of building clusters. Case studies show that the proposed design significantly improves the performance of building clusters, reduces energy storage capacity, and shortens the payback period.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Felix Langner, Weimin Wang, Moritz Frahm, Veit Hagenmeyer
Summary: This paper compares two main approaches to consider uncertainties in model predictive control (MPC) for buildings: robust and stochastic MPC. The results show that compared to a deterministic MPC, the robust MPC increases the electricity cost while providing complete temperature constraint satisfaction, while the stochastic MPC slightly increases the electricity cost but fulfills the thermal comfort requirements.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Somil Yadav, Caroline Hachem-Vermette
Summary: This study proposes a mathematical model to evaluate the performance of a Double Skin Facade (DSF) system and its impact on indoor conditions. The model considers various design parameters and analyzes their effects on the system's electrical output and room temperature.
ENERGY AND BUILDINGS
(2024)
Article
Construction & Building Technology
Ruijun Chen, Holly Samuelson, Yukai Zou, Xianghan Zheng, Yifan Cao
Summary: This research introduces an innovative resilient design framework that optimizes building performance by considering a holistic life cycle perspective and accounting for climate projection uncertainties. The study finds that future climate scenarios significantly impact building life cycle performance, with wall U-value, windows U-value, and wall density being major factors. By using ensemble learning and optimization algorithms, predictions for carbon emissions, cost, and indoor discomfort hours can be made, and the best resilient design scheme can be selected. Applying this framework leads to significant improvements in building life cycle performance.
ENERGY AND BUILDINGS
(2024)
