Article
Computer Science, Artificial Intelligence
Arun Kumar, Tanya Chauhan, Srinivasan Natesan, Nhat Truong Pham, Ngoc Duy Nguyen, Chee Peng Lim
Summary: In this study, we propose an efficient machine learning model for financial time series forecasting through carefully designed feature extraction, elimination, and selection strategies. We leverage a binary particle swarm optimization algorithm to select the appropriate features and propose new evaluation metrics for better performance assessment in handling financial time series data. Our proposed model outperforms several existing methods in benchmark studies, confirming its effectiveness.
Article
Business
Soumya Das, Sarojananda Mishra, ManasRanjan Senapati
Summary: The time series data is predicted with Elephant Herd Optimization (EHO), which has been proven superior in comparison to other methods through experiments. The method shows good performance in feature selection and neural network training.
JOURNAL OF MANAGEMENT ANALYTICS
(2021)
Article
Computer Science, Artificial Intelligence
Salihu A. Abdulkarim, Andries P. Engelbrecht
Summary: Several studies have applied particle swarm optimization algorithms to train neural networks for time series forecasting, with good performance results. This study introduces a dynamic PSO algorithm for training NNs in forecasting non-stationary time series, outperforming standard PSO and Rprop algorithms. These findings suggest the potential of dynamic PSO in real-world forecasting applications.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Automation & Control Systems
N. Ashwini, V Nagaveni, Manoj Kumar Singh
Summary: Forecasting for time series signals with mixed characteristics is challenging. This paper proposes an approach based on function mapping and neural network models to overcome this challenge. By decomposing the signals into trend and cyclic patterns, dedicated models are developed for predicting individual data patterns. The performance is improved by utilizing an adaptive radial basis function neural network and a linear regression model. The approach shows satisfactory results in predicting power demand in individual houses and monthly power generation. The integrated neural model and linear regression approach is more efficient than individual neural models.
INTELLIGENT AUTOMATION AND SOFT COMPUTING
(2022)
Article
Computer Science, Artificial Intelligence
Erol Egrioglu, Eren Bas
Summary: A new hybrid recurrent artificial neural network is proposed for nonlinear time series forecasting in this study. The network combines simple exponential smoothing and a single multiplicative neuron model to solve the insufficiency of classical forecasting methods in forecasting nonlinear and complex time series structures. The proposed method outperforms other artificial neural networks in terms of performance.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Computer Science, Artificial Intelligence
Xinghan Xu, Weijie Ren
Summary: This paper proposes a hybrid model using stacked autoencoder and modified particle swarm optimization for multivariate chaotic time series forecasting. Experimental results show that the hybrid model performs well on multiple datasets.
APPLIED SOFT COMPUTING
(2022)
Article
Engineering, Multidisciplinary
Kiran Bala, Geeta Arora, Homan Emadifar, Masoumeh Khademi
Summary: This research focuses on optimizing the parameter related to radial basis function using Particle Swarm Optimization algorithm. The partial differential equations are transformed into ordinary differential equations and solved using MATLAB. The results are in conformity with those available in the literature.
ALEXANDRIA ENGINEERING JOURNAL
(2023)
Article
Computer Science, Artificial Intelligence
Yaoguo Dang, Yifan Zhang, Junjie Wang
Summary: To address the problem of the grey multivariate prediction model's inability to accurately simulate systems with periodic oscillations, a novel multivariate grey model named the GM(1,N|sin) power model is proposed. This model incorporates a power exponential term and dynamic sinusoidal function to represent the nonlinear relationship and periodic oscillations of the independent and dependent variables, respectively. Through case studies on electricity consumption and PM2.5 concentrations, the GM(1,N|sin) power model outperforms alternative models in accurately predicting time series with periodic oscillations.
EXPERT SYSTEMS WITH APPLICATIONS
(2023)
Article
Computer Science, Information Systems
Ruijin Wang, Xikai Pei, Juyi Zhu, Zhiyang Zhang, Xin Huang, Jiayi Zhai, Fengli Zhang
Summary: This paper proposes a model fusion-based time series forecasting method to improve the accuracy and efficiency of predictions using multivariate grey model and artificial fish swarm algorithm. Two fusion models based on data decomposition and weighted summation achieve good prediction results in different scenarios.
INFORMATION SCIENCES
(2022)
Article
Computer Science, Artificial Intelligence
Naresh Kumar, Seba Susan
Summary: The study optimizes the hyperparameters of fuzzy time series forecasting for the COVID-19 pandemic using Particle Swarm Optimization, proposing nested FTS-PSO and exhaustive search FTS-PSO techniques. The exhaustive search FTS-PSO outperformed all methods in forecasting coronavirus confirmed cases, demonstrating its effectiveness in achieving optimal hyperparameter values.
APPLIED SOFT COMPUTING
(2021)
Article
Computer Science, Interdisciplinary Applications
Benjamin K. Tapley, Helge I. Andersson, Elena Celledoni, Brynjulf Owren
Summary: A geometric numerical method is proposed for simulating suspensions of spherical and non-spherical particles with Stokes drag, which generates more accurate and cost-effective particle distributions compared to conventional methods.
JOURNAL OF COMPUTATIONAL PHYSICS
(2022)
Article
Computer Science, Artificial Intelligence
Kuihua Huang, Huixiang Zhen, Wenyin Gong, Rui Wang, Weiwei Bian
Summary: To solve high-dimensional expensive optimization problems, a surrogate-assisted evolutionary algorithm called ESPSO is proposed. ESPSO utilizes evolutionary sampling-assisted strategies to improve population initialization, approximate the objective function landscape with a local radial basis function model, and accelerate the search process with surrogate-assisted local search and surrogate-assisted trust region search. Experimental comparisons with five state-of-the-art surrogate-assisted evolutionary algorithms demonstrate that ESPSO outperforms the others in terms of search efficiency.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Environmental Sciences
Xiaodong Liu, Xuneng Tong, Lei Wu, Sanjeeb Mohapatra, Hongqin Xue, Ruochen Liu
Summary: Pollution source identification is crucial for water safety management. A simulation-optimization modelling framework using a hydrodynamic water quality model, artificial neural network surrogate model and particle swarm optimization (PSO) was proposed. The framework was tested for steady and unsteady flow conditions in a lab-based flume and the Yangtze River estuary. The results showed that the hybrid PBM-ANNs-PSO models were effective in identifying pollution sources and quantifying release intensity.
JOURNAL OF ENVIRONMENTAL MANAGEMENT
(2023)
Article
Computer Science, Artificial Intelligence
Xuemei Li, Shaojun Li
Summary: The paper introduces an adaptive surrogate-assisted particle swarm optimization algorithm that selects the appropriate surrogate model by comparing the best solution and the latest obtained solution, and proposes a model output criterion to enhance the performance of the ensemble model.
Article
Computer Science, Artificial Intelligence
Gourav Kumar, Uday Pratap Singh, Sanjeev Jain
Summary: This paper proposes a hybrid evolutionary intelligent system for predicting the future close price of stock market, comparing its forecasting efficiency with other methods, and showing superior accuracy.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2021)
Article
Automation & Control Systems
Hamideh Hamidian, Mohammad T. H. Beheshti
INTERNATIONAL JOURNAL OF SYSTEMS SCIENCE
(2018)
Article
Biology
Sh. Asadi, V. Nekoukar
MATHEMATICAL BIOSCIENCES
(2018)
Article
Automation & Control Systems
Behnaz Babaghorbani, Mohammad Taghi Hamidi Beheshti, Heidar Ali Talebi
ASIAN JOURNAL OF CONTROL
(2019)
Article
Engineering, Electrical & Electronic
Elnaz Azizi, Amin Mohammadpour Shotorbani, Mohhamd-Taghi Hamidi-Beheshti, Behnam Mohammadi-Ivatloo, Sadegh Bolouki
IEEE TRANSACTIONS ON CONSUMER ELECTRONICS
(2020)
Article
Green & Sustainable Science & Technology
Elnaz Azizi, Mohammad T. H. Beheshti, Sadegh Bolouki
Summary: This paper proposes a novel event-based NILM classification algorithm that accurately detects appliance operation modes from power signals and addresses issues existing in current NILM methods.
Article
Engineering, Electrical & Electronic
Keywan Mohammadi, Elnaz Azizi, Jeewon Choi, Mohammad-Taghi Hamidi-Beheshti, Ali Bidram, Sadegh Bolouki
Summary: This paper introduces a distributed secondary voltage and frequency control scheme for an islanded AC microgrid under event-triggered communication, which is able to handle the consensus problem in case of asynchronous communication. Under this scheme, each distributed generator can independently check its triggering condition without the need to synchronize to a common clock, leading to an efficient reduction in communication rate.
IEEE TRANSACTIONS ON POWER SYSTEMS
(2021)
Article
Engineering, Electrical & Electronic
Elnaz Azizi, Mohammad T. H. Beheshti, Sadegh Bolouki
Summary: This paper introduces a non-intrusive load monitoring approach to detect anomalies in electrical appliances, based on power distribution and the participation index of appliances. The method is cost-efficient, respects consumer privacy and comfort, and proves to be effective in increasing NILM accuracy and reducing energy waste.
IEEE TRANSACTIONS ON CONSUMER ELECTRONICS
(2021)
Article
Engineering, Multidisciplinary
Mohammadreza Ghorvei, Mohammadreza Kavianpour, Mohammad T. H. Beheshti, Amin Ramezani
Summary: Deep learning-based approaches for diagnosing bearing faults face challenges in real-world applications, such as the need for labeled data, distribution differences in training and test data, and noise impact. This study introduces the DSACNN method to overcome these challenges and validates its superiority in anti-noise performance and reduction of domain distribution discrepancies compared to other methods.
MEASUREMENT SCIENCE AND TECHNOLOGY
(2022)
Article
Engineering, Electrical & Electronic
Elnaz Azizi, Mohammad T. H. Beheshti, Sadegh Bolouki
Summary: Non-intrusive load monitoring (NILM) is an efficient approach to energy management that extracts appliance consumption by analyzing aggregated signals. The presence of numerous appliances and appliances with similar consumption values poses challenges for event-based NILM methods. Semi-intrusive load monitoring offers an alternative where appliances are divided into blocks and monitored using separate power smart meters. However, this approach increases the cost of load monitoring.
IEEE TRANSACTIONS ON SMART GRID
(2022)
Article
Automation & Control Systems
Bahar Rahmatizadeh, Mohamad Taghi Hamidi Beheshti, Masoumeh Azadegan, Mahmoud Najafi
Summary: The paper transforms the KM model and designs an SMC controller to regulate bubble radius and prevent collapse. The controller demonstrates robustness and eliminates chattering produced by SMC.
INTERNATIONAL JOURNAL OF DYNAMICS AND CONTROL
(2021)
Article
Engineering, Electrical & Electronic
Mehdi Doostinia, Mohammad T. H. Beheshti, Seyed A. Alavi, Josep M. Guerrero
Summary: A novel distributed secondary layer control strategy based on average consensus and fractional-order proportional-integral (FOPI) local controllers is proposed for the regulation of the bus voltages and energy level balancing in DC microgrids. The use of fractional-order local controllers increases the tuning flexibility of closed-loop controllers and improves the regulation of bus voltages in microgrids with high order dynamics. The performance of the proposed control strategy is validated in a 38-V DC microgrid case study with 10 buses and a photovoltaic renewable energy source, operating in both islanded and grid-connected modes.
Article
Automation & Control Systems
Mojtaba Ranjbar, Mohammad T. H. Beheshti, Sadegh Bolouki
Summary: In this research, a novel distributed event-triggered approach is proposed to address the formation control problem of multi-agent systems with directed communication graphs, eliminating the possibility of Zeno behavior through periodic samplings of agent states. The study shows that, under simple verifiable conditions, the proposed control strategy achieves the desired formation of agents. The results are verified through numerical examples.
IEEE CONTROL SYSTEMS LETTERS
(2021)
Proceedings Paper
Energy & Fuels
Mahdi S. Mousavi, S. Alireza Davari, Vahab Nekoukar, Jose Rodriguez
2019 10TH INTERNATIONAL POWER ELECTRONICS, DRIVE SYSTEMS AND TECHNOLOGIES CONFERENCE (PEDSTC)
(2019)
Proceedings Paper
Biophysics
Ali Yousefi, Reza Kakooee, Mohammad Th. Beheshti, Darin D. Dougherty, Emad N. Eskandar, Alik S. Widge, Uri T. Eden
2017 39TH ANNUAL INTERNATIONAL CONFERENCE OF THE IEEE ENGINEERING IN MEDICINE AND BIOLOGY SOCIETY (EMBC)
(2017)
Proceedings Paper
Engineering, Electrical & Electronic
Rahim Delavar, Babak Tavassoli, Mohammad Taghi Hamidi Beheshti
2017 25TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE)
(2017)
