Article
Meteorology & Atmospheric Sciences
Yousef Ramezani, Mohammad Nazeri Tahroudi, Carlo De Michele, Rasoul Mirabbasi
Summary: In this study, VAR-GARCH, copula, and copula-GARCH models were used for joint frequency analysis of storms in the Aras river basin in northwestern Iran. The VAR model was used to consider heteroskedasticity in the series, and two-dimensional copulas were used for bivariate analysis. The VAR-GARCH model showed higher accuracy in storm simulations compared to copula and copula-GARCH models. The generated curves from the analysis can be used as a flood warning system in the basin.
THEORETICAL AND APPLIED CLIMATOLOGY
(2023)
Article
Computer Science, Artificial Intelligence
Jian Lian, Fangzhou Xu
Summary: Feature extraction is crucial in epilepsy detection and recognition. In this study, a graph convolutional neural network-based framework is proposed to capture the spatial enhanced pattern of multichannel EEG signals, characterizing the behavior of EEG activity and visualizing salient regions. This approach can also be used as a novel classifier for distinguishing different types of EEGs, achieving high sensitivity, specificity, and accuracy.
INTERNATIONAL JOURNAL OF NEURAL SYSTEMS
(2022)
Article
Engineering, Environmental
Babak Mohammadi, Saeid Mehdizadeh, Farshad Ahmadi, Nguyen Thi Thuy Lien, Nguyen Thi Thuy Linh, Quoc Bao Pham
Summary: This study focused on developing hybrid time series models to estimate air temperature parameters more accurately, with statistical metrics used to evaluate model performance. The results showed that the hybrid models outperformed the single models, and the combination of MLP and AR-ARCH models can provide more accurate temperature estimations. Additionally, temperature data from nearby stations can be utilized to predict the temperatures at desired locations.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2021)
Article
Engineering, Biomedical
Begum Kara Gulay, Neslihan Demirel, Alper Vahaplar, Cagdas Guducu
Summary: Parkinson's disease (PD) is an incurable nervous system disease. This study proposes a hybrid feature extraction method called EEMD_VAR to diagnose PD more accurately in the early stage using difficult-to-study chemosensory electroencephalography (EEG) signals. The results show that the proposed method outperforms the conventional methods in PD classification.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Biomedical
Siuly Siuly, Yanhui Guo, Omer Faruk Alcin, Yan Li, Peng Wen, Hua Wang
Summary: This study introduces a feature extraction method based on deep residual networks to automatically extract features from EEG signal data for diagnosing schizophrenia. The experimental results demonstrate that this method outperforms existing approaches and can discover important biomarkers, aiding in the development of a computer-assisted diagnostic system.
PHYSICAL AND ENGINEERING SCIENCES IN MEDICINE
(2023)
Article
Economics
Astrid Loretta Ayala, Szabolcs Blazsek, Adrian Licht
Summary: In the literature on score-driven models, the optimal choice of scaling parameters for conditional score terms remains uncertain. This paper examines the quasi-autoregressive (QAR) plus Beta-t-EGARCH model using data on the S&P 500 and alternative scaling parameters. The best-performing scaling parameter for score-driven location is found to be the conditional inverse information matrix.
Article
Computer Science, Interdisciplinary Applications
Mostefa Mesbah, Mohamed S. Khlif, Siamak Layeghy, Christine E. East, Shiying Dong, Amy Brodtmann, Paul B. Colditz, Boualem Boashash
Summary: This study proposed a novel automatic fetal movement recognition algorithm utilizing wearable tri-axial accelerometers placed on the maternal abdomen. By extracting multiple features and using various classifiers for identification and artefact removal, the Bagging classifier algorithm was found to perform the best in distinguishing fetal movements.
COMPUTER METHODS AND PROGRAMS IN BIOMEDICINE
(2021)
Article
Physics, Multidisciplinary
Irena Barjasic, Nino Antulov-Fantulin
Summary: The article analyzes the time series of minute price returns on the Bitcoin market using statistical models of the GARCH family. By incorporating external information signals such as Bitcoin-related tweets, trade volume, and bid-ask spread, improvements in volatility prediction are tested. The results indicate that GARCH(1,1) and cGARCH(1,1) models react the best to the addition of external signals.
FRONTIERS IN PHYSICS
(2021)
Article
Computer Science, Artificial Intelligence
Guanglong Du, Wenpei Zhou, Chunquan Li, Di Li, Peter X. Liu
Summary: This article proposes a hybrid neural network learning framework called CSFFN to detect a player's emotional states in real-time during a gaming process based on electroencephalogram (EEG) signals. CSFFN combines a convolutional neural network (CNN), a fuzzy neural network (FNN), and a recurrent neural network (RNN) to improve the accuracy and noise resistance in game emotion recognition. Experimental results show that CSFFN outperforms other methods in recognizing four emotional states (happiness, sadness, superiority, and anger).
IEEE TRANSACTIONS ON AFFECTIVE COMPUTING
(2023)
Article
Computer Science, Artificial Intelligence
Abdurrahman Ozbeyaz
Summary: Neurocomputing research has recently made a significant contribution to branding psychology by investigating consumer decisions for a branded stimulus using advanced machine learning algorithms. This study utilized a four-stage methodology to classify EEG signals, achieving high classification accuracy. Results showed that using PCA in feature extraction, ABC in channel selection, and ANN in classification yielded the best classification performance.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Artificial Intelligence
Amir Naser, Onder Aydemir
Summary: Electroencephalography (EEG) was used to measure brain reactions to different odors. Various features such as Hilbert transform and spectrogram image were tested to classify EEG signals during the imagination of pleasant and unpleasant odors. The results showed that Hilbert Transform-based features have great potential for classification, achieving an average accuracy of 87.75% with a k-nearest neighbor classifier.
NEURAL COMPUTING & APPLICATIONS
(2023)
Article
Engineering, Biomedical
Yuchan Zhang, Guanghui Yan, Wenwen Chang, Wenqie Huang, Yueting Yuan
Summary: This study explores the connectivity patterns in different frequency bands of EEG signals and proposes a novel feature extraction method for emotion classification. The results show that delta, alpha, and beta frequency bands are highly correlated with emotions and the anterior and right temporal lobes of the brain are closely linked to emotions. Additionally, the proposed feature extraction method effectively improves the accuracy of emotion classification.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2023)
Article
Engineering, Civil
Mohammad Nazeri Tahroudi, Rasoul Mirabbasi, Yousef Ramezani, Farshad Ahmadi
Summary: This study investigates two efficient approaches for bivariate simulation and compares their applicability in simulating the river discharge in Talezang Basin, Iran. The Copula-GARCH model is found to be more accurate than the optimized SVR model, with increased accuracy at the minimum and maximum values of the data.
WATER RESOURCES MANAGEMENT
(2022)
Review
Health Care Sciences & Services
J. Prasanna, M. S. P. Subathra, Mazin Abed Mohammed, Robertas Damasevicius, Nanjappan Jothiraj Sairamya, S. Thomas George
Summary: This review paper focuses on automatic seizure detection in pediatric patients using EEG signals and classifiers. It summarizes the application of personalized medicine approaches in the diagnosis of epilepsy, analyzes challenges and performance metrics using data from the CHB-MIT database.
JOURNAL OF PERSONALIZED MEDICINE
(2021)
Article
Engineering, Electrical & Electronic
Lin Li, Yaxin Zhu, Zhigang Zhu
Summary: This article proposes a modulation classification scheme based on deep feature fusion, which utilizes the ResNeXt network to extract semantic features and the GRU to extract time-series features. A feature fusion model using discriminant correlation analysis (DCA) is employed to fuse the output responses of the ResNeXt and GRU. The simulation results show superior performance, promoting the application of feature fusion in AMC.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2023)
Article
Computer Science, Theory & Methods
Sara Mihandoost, Mehdi Chehel Amirani
MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING
(2018)
Article
Telecommunications
Ehsan Mostafapour, Changiz Ghobadi, Mehdi Chehel Amirani
WIRELESS PERSONAL COMMUNICATIONS
(2018)
Article
Engineering, Biomedical
Mehdi Shahrdad, Mehdi Chehel Amirani
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2018)
Article
Telecommunications
Amir Aminfar, Mehdi Chehel Amirani, Changiz Ghobadi
WIRELESS PERSONAL COMMUNICATIONS
(2019)
Article
Telecommunications
Amin Aliabadi, Mahdi Chehel Amirani, Changiz Ghobadi
WIRELESS PERSONAL COMMUNICATIONS
(2019)
Article
Computer Science, Theory & Methods
Mohammad Amin Choukali, Morteza Valizadeh, Mehdi Chehel Amirani
MULTIDIMENSIONAL SYSTEMS AND SIGNAL PROCESSING
(2020)
Article
Engineering, Biomedical
Akbar Asgharzadeh-Bonab, Mehdi Chehel Amirani, Alaeddin Mehri
BIOCYBERNETICS AND BIOMEDICAL ENGINEERING
(2020)
Article
Computer Science, Information Systems
Sedighe Mirbolouk, Morteza Valizadeh, Mehdi Chehel Amirani, Mohammad Amin Choukali
Summary: The paper introduces an efficient contrast enhancement approach based on a histogram weighting method using a fuzzy system. It is capable of enhancing image contrast while preserving details by dividing the original image histogram into sub-histograms through fuzzy clustering and weighting them with a Mamdani fuzzy inference system.
MULTIMEDIA TOOLS AND APPLICATIONS
(2021)
Article
Computer Science, Information Systems
Sara Mihandoost, Mehdi Chehel Amirani
Summary: This paper introduces two new algorithms for two-dimensional CSF estimation and evaluates their performance on texture analysis databases. The experiment results show significant improvements in processing time, classification accuracy, and noise resistance compared to other methods.
JOURNAL OF SIGNAL PROCESSING SYSTEMS FOR SIGNAL IMAGE AND VIDEO TECHNOLOGY
(2021)
Article
Engineering, Biomedical
Javad Ostadieh, Mehdi Chehel Amirani, Morteza Valizadeh
JOURNAL OF MEDICAL SIGNALS & SENSORS
(2020)
Article
Medical Informatics
Ali Rostami, Mehdi Chehel Amirani, Hossein Yousef-Banaem
HEALTH AND TECHNOLOGY
(2020)
Proceedings Paper
Engineering, Electrical & Electronic
Shabnam Hoseinzadeh, Mehdi Chehel Amirani
26TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE 2018)
(2018)
Proceedings Paper
Engineering, Electrical & Electronic
Sara Mihandoost, Mehdi Chehel Amirani
2017 25TH IRANIAN CONFERENCE ON ELECTRICAL ENGINEERING (ICEE)
(2017)
Proceedings Paper
Computer Science, Information Systems
Ali Younesi, Mehdi Chehel Amirani
INTERNATIONAL CONFERENCE ON COMPUTATIONAL SCIENCE (ICCS 2017)
(2017)
Article
Engineering, Biomedical
Sara Mihandoost, Mehdi Chehel Amirani
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2017)