Article
Engineering, Mechanical
Yanli Ma, Junsheng Cheng, Ping Wang, Jian Wang, Yu Yang
Summary: An improved multivariate multiscale fuzzy distribution entropy (IMMFDE) is proposed to extract fault features from multivariate vibration signals of the rotating machinery under different speeds. This method, based on multivariate empirical mode decomposition, can adaptively determine the maximum scale, eliminate frequency aliasing, and avoid the loss of potentially useful information. The trait of IMMFDE is verified by calculating the sequences and amplitude spectrums of simulated multivariate signals at each scale. A fault diagnosis method is further proposed for the rotating machinery under different speeds, which utilizes statistical parameters and IMMFDE as the fault feature set and support vector machine for fault diagnosis. The results show that the proposed method can achieve better fault diagnosis results.
NONLINEAR DYNAMICS
(2023)
Article
Anesthesiology
Darren Hight, Matthias Kreuzer, Gesar Ugen, Peter Schuller, Frank Stuber, Jamie Sleigh, Heiko A. Kaiser
Summary: This study compared five different monitors and found that there were significant differences in the determination of anesthetic depth based on the same EEG. Among the 52 cases, 52% had at least one monitor warning of potentially inadequate hypnosis, and 31% had at least one monitor signifying excessive hypnotic depth. The results emphasize the importance of personalized EEG interpretation for clinical decision-making.
BRITISH JOURNAL OF ANAESTHESIA
(2023)
Article
Physics, Multidisciplinary
Meryem Jabloun, Philippe Ravier, Olivier Buttelli
Summary: Ordinal pattern-based approaches have great potential in capturing the intrinsic structures of dynamical systems. Permutation entropy (PE) is an attractive measure for time series complexity. The impact of preprocessing on PE values has been theoretically decoupled. This study extends to nonlinear preprocessing, identifying possible pitfalls in the interpretation of PE values.
Article
Mathematical & Computational Biology
Ravichandra Madanu, Farhan Rahman, Maysam F. Abbod, Shou-Zen Fan, Jiann-Shing Shieh
Summary: A survey found that 47% of surgical complication mortalities are due to anesthetic overdose, highlighting the necessity for regulating anesthesia levels. Deep learning methods have been utilized for predicting patient anesthesia depth using EEG signals, with CNN being a popular algorithm. Various decomposition methods were used in this study to extract features from EEG signals, demonstrating potential for further research in visual mapping of DOA using EEG signals and DL methods.
MATHEMATICAL BIOSCIENCES AND ENGINEERING
(2021)
Article
Mathematics, Interdisciplinary Applications
Zhuo Wang, Pengjian Shang
Summary: Researchers have proposed three generalized entropy plane methods for evaluating the complexity of two-dimensional data, analyzed their performance, and applied them to the study of multivariate stock time series. The complexity-entropy causality plane method showed good performance, and multiscale multivariate dispersion entropy method was also proposed.
CHAOS SOLITONS & FRACTALS
(2021)
Article
Mathematics, Applied
Yujia Mi, Aijing Lin
Summary: Transfer entropy is used to quantify information flow and causal orientation in nonlinear systems. This study combines noise-assisted multivariate variational mode decomposition (NA-MVMD) and transfer entropy to propose a kernel-based multiscale partial Renyi transfer entropy for multivariate systems. The method is validated using henon mapping, VAR model, and multi-channel EEG signals, demonstrating its robustness to noise and its ability to measure information transfer at different scales.
COMMUNICATIONS IN NONLINEAR SCIENCE AND NUMERICAL SIMULATION
(2023)
Article
Engineering, Biomedical
Jian Shen, Yanan Zhang, Huajian Liang, Zeguang Zhao, Qunxi Dong, Kun Qian, Xiaowei Zhang, Bin Hu
Summary: Depression, a severe psychiatric illness, has a significant impact on patients' thoughts, behaviors, feelings, and well-being. However, current clinical practice lacks effective methods for recognizing and treating depression. Electroencephalogram (EEG) signals, which reflect the internal workings of the brain, show promise as an objective tool for depression recognition and diagnosis. In this study, we propose a regularization parameter-based improved intrinsic feature extraction method using empirical mode decomposition (EMD) to enhance depression recognition performance.
IEEE TRANSACTIONS ON NEURAL SYSTEMS AND REHABILITATION ENGINEERING
(2023)
Article
Mathematics, Interdisciplinary Applications
Boyi Zhang, Pengjian Shang, Qin Zhou
Summary: The paper introduces multivariate fractional dispersion entropy (MMFDE) and MMFDE plane to study the structural complexity of multivariate nonlinear systems, successfully identifying chaotic and fractional order chaotic systems, as well as demonstrating practical value in financial time series and epileptic EEG recordings.
CHAOS SOLITONS & FRACTALS
(2021)
Article
Computer Science, Information Systems
Jinbiao Liu, Gansheng Tan, Yixuan Sheng, Honghai Liu
Summary: The proposed multiscale transfer spectral entropy (MSTSE) method depicts multi-layer neural information transfer between the motor cortex and effector muscle, showing more robustness and optimal performance in detecting coupling properties compared to the single scale TSE method.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2021)
Article
Computer Science, Information Systems
Qinpei Zhao, Guangda Yang, Kai Zhao, Jiaming Yin, Weixiong Rao, Lei Chen
Summary: This article proposes a methodology to measure the upper limit of predictability for multivariate time series with multivariate constraint relations. The key of the methodology is a novel entropy named Multivariate Constraint Sample Entropy (McSE) that incorporates the multivariate constraint relations for better predictability. The authors conducted a systematic evaluation over eight datasets and compared existing methods with their proposed predictability, finding that their method achieved higher predictability. They also discovered that forecasting algorithms that capture the multivariate constraint relation information can achieve higher accuracy, confirming the importance of multivariate constraint relations for predictability.
IEEE TRANSACTIONS ON BIG DATA
(2023)
Article
Engineering, Electrical & Electronic
Abhijit Bhattacharyya, Rajesh Kumar Tripathy, Lalit Garg, Ram Bilas Pachori
Summary: This study introduces a novel multivariate-multiscale approach for computing spectral and temporal entropies from multichannel EEG signals to recognize human emotions. The proposed method shows promising results in emotion classification accuracy.
IEEE SENSORS JOURNAL
(2021)
Article
Engineering, Electrical & Electronic
Zhenzhen Jin, Yulong Xiao, Deqiang He, Zexian Wei, Yingqian Sun, Weifeng Yang
Summary: As one of the key components of the train, the condition of the bearing is crucial to ensure its safe operation. However, the vibration signal of the bearing is often nonlinear and nonstationary, making it difficult to extract fault features and resulting in low diagnostic accuracy. This study proposes a bearing fault diagnosis method based on refined piecewise composite multivariate multiscale fuzzy entropy (RPCMMFE) and convolutional neural network (CNN) to overcome these challenges. Experimental results demonstrate that the proposed method improves the stability and discrimination ability of the extracted features, leading to more accurate bearing fault identification with average accuracy rates of 99% and 99.17%, respectively. (c) 2022 Elsevier Inc. All rights reserved.
DIGITAL SIGNAL PROCESSING
(2023)
Article
Engineering, Biomedical
Yi Zhang, Qin Yang, Lifu Zhang, Yu Ran, Guan Wang, Branko Celler, Steven Su, Peng Xu, Dezhong Yao
Summary: This study introduces a noise-assisted multivariate empirical mode decomposition (NA-MEMD) based causal decomposition approach that emphasizes the phase relation where candidate causes not only follow effects, but also produce effects. The applicability of this method, particularly in studying brain physiological processes, is validated in neuroscience.
JOURNAL OF NEURAL ENGINEERING
(2021)
Article
Engineering, Biomedical
Haidong Gu, Chun-An Chou
Summary: A non-uniform multivariate multiscale entropy method has been developed to better assess the complexity of multivariate complex systems. Experimental results demonstrate that this method outperforms traditional approaches and may be applied for critical transition detection and pattern recognition.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Physics, Multidisciplinary
Qiang Yuan, Mingchen Lv, Ruiping Zhou, Hong Liu, Chongkun Liang, Lijiao Cheng
Summary: The study focuses on the fault signals of rolling bearings, characterized by nonlinearity, periodic impact, and low signal-to-noise ratio. A new method called Composite Multivariate Multiscale Permutation Fuzzy Entropy (CMvMPFE) was proposed to comprehensively and accurately extract fault characteristics from rolling bearings. The CMvMPFE method combines the advantages of entropy calculation, Multiscale Fuzzy Entropy (MFE), and Multiscale Permutation Entropy (MPE), addressing the problems of low accuracy, entropy perturbation, and information loss in fault feature parameter calculation.
Article
Engineering, Electrical & Electronic
Yu-Hsuan Liao, Chung-Hung Shih, Maysam F. Abbod, Jiann-Shing Shieh, Yu-Jen Hsiao
Summary: An offline gas detection system has been designed to monitor and detect metabolites of pneumonia at an early stage. The developed electronic nose showed high accuracy rates in clinical data validation, providing a simple and cost-effective solution for rapid screening of VAP at an early stage.
MICROSYSTEM TECHNOLOGIES-MICRO-AND NANOSYSTEMS-INFORMATION STORAGE AND PROCESSING SYSTEMS
(2022)
Editorial Material
Chemistry, Analytical
Maysam Abbod, Jiann-Shing Shieh
Article
Chemistry, Analytical
Mohamed Gaballa, Maysam Abbod, Ammar Aldallal
Summary: This paper investigates the impact of using Deep Neural Network (DNN) to explicitly estimate the channel coefficients for each user in NOMA system, and explores the multiuser recognition using DL-based channel estimation and power optimization scheme in PD-NOMA system. Through simulation experiments, the superiority of the proposed DL-based channel estimation method is demonstrated.
Review
Construction & Building Technology
Maher Ala'raj, Mohammed Radi, Maysam F. Abbod, Munir Majdalawieh, Marianela Parodi
Summary: This paper emphasizes the importance of improving the energy efficiency of HVAC systems and highlights the application of data-driven models in optimization, which should consider user needs to avoid underutilization of the systems. Future research directions may include incorporating user feedback into control loops and using easily accessible technologies to gather user information.
JOURNAL OF BUILDING ENGINEERING
(2022)
Article
Chemistry, Analytical
Wei-Horng Jean, Peter Sutikno, Shou-Zen Fan, Maysam F. Abbod, Jiann-Shing Shieh
Summary: This study compared the performance of multilayer perceptron (MLP) and long short-term memory (LSTM) algorithms in predicting pain scores during surgery. HRV analysis using MLP algorithm showed good correlation with expert assessment of pain scores, suggesting its potential as a continuous monitor for predicting intraoperative pain levels.
Article
Computer Science, Artificial Intelligence
Imene Mecheter, Maysam Abbod, Abbes Amira, Habib Zaidi
Summary: This study proposes an approach that combines multiresolution features and CNN-based features to efficiently segment the brain into three tissue classes. The results demonstrate significant improvement in bone class segmentation compared to other methods, and suggest that NSST coefficients provide more useful information than NSCT coefficients.
ARTIFICIAL INTELLIGENCE IN MEDICINE
(2022)
Article
Energy & Fuels
Sadeq D. Al-Majidi, Mohammed Kh AL-Nussairi, Ali Jasim Mohammed, Adel Manaa Dakhil, Maysam F. Abbod, Hamed S. Al-Raweshidy
Summary: This paper proposes an optimal load frequency controller (LFC) design using artificial neural network (ANN) and particle swarm optimization. The ANN model is trained to minimize mean square error and optimize the initial neurons. Simulations on single-area PSN and multi-area PSN show that the LFC based on the optimal ANN is more effective in adjusting frequency and improving power delivery.
Article
Chemistry, Analytical
Mohamed Gaballa, Maysam Abbod, Ammar Aldallal
Summary: This study examines the influence of adopting Reinforcement Learning (RL) to predict channel parameters for user devices in a Power Domain Multi-Input Single-Output Non-Orthogonal Multiple Access (MISO-NOMA) system. A Q-learning algorithm is developed and incorporated into the NOMA system for channel prediction. The algorithm is initialized using different channel statistics and updated based on interaction with the environment to approximate channel coefficients for each device. The predicted parameters are utilized to recover desired data at the receiver side, and power factors can be deduced analytically to allocate optimal power for each user.
Article
Computer Science, Artificial Intelligence
Ahmed Alrashedi, Maysam Abbod
Summary: This paper examines the ease of assigning different roles to users in an organization and emphasizes the importance of utilizing predictive analytical tools for effective task completion. The study adopts an ensemble of classification and regression tree link neural network to evaluate role-based tasks within an organization unit. A Human Resource Management System is designed and developed to gather comprehensive information on employee performance levels, capabilities, skills, and task execution. The findings demonstrate that linear regression models, decision trees, and genetic algorithms are effective in predicting outcomes. The research highlights the significance of ensuring timely task completion and enhancing an organization's ability to assign individual duties.
ADCAIJ-ADVANCES IN DISTRIBUTED COMPUTING AND ARTIFICIAL INTELLIGENCE JOURNAL
(2022)
Article
Computer Science, Information Systems
Stephen Sommerville, Gareth Taylor, Maysam Abbod
Summary: This paper investigates voltage fluctuations caused by the operation of battery energy storage units providing frequency response and fast frequency response services. The study uses a test network based on a typical part of the UK mainland system and introduces a frequency disturbance generator to simulate typical disturbances in the network. The paper contributes to knowledge by providing a systematic approach for assessing voltage disturbances and flicker concerns for battery energy storage units on island networks.
Article
Energy & Fuels
Ayed Banibaqash, Ziad Hunaiti, Maysam Abbod
Summary: The main objective of this study is to analyze the feasibility of deploying solar panels in Qatar houses and other organizations. The study aims to calculate different scenarios of solar panel deployment and estimate the generated energy, compare it with actual consumption, and provide a comparative indicator for renewable energy rating. The study also aims to support roadmaps for solar panel deployment in Qatar and explore the use of the generated-to-consumed energy ratio as a new renewable energy rating index.
Proceedings Paper
Energy & Fuels
Stephen Sommerville, Professor Gareth A. Taylor, Maysam Abbod
Summary: This paper examines the adverse effects on the distribution system voltage that may occur when multiple Battery Energy Storage Systems (BESS) units operate simultaneously in adjacent substations in the UK. A simple test network is constructed and DIgSILENT Powerfactory software is used to analyze the system voltage profile for various import-export and export-import cases.
2022 57TH INTERNATIONAL UNIVERSITIES POWER ENGINEERING CONFERENCE (UPEC 2022): BIG DATA AND SMART GRIDS
(2022)
Proceedings Paper
Energy & Fuels
Ali Jasim Mohammed, Sadeq D. Al-Majidi, Mohammed Kh. Al-Nussairi, Maysam F. Abbod, Hamed S. Al-Raweshidy
Summary: In this paper, a Load Frequency Controller based on an Artificial Neural Network (ANN) technique is designed for a single-area Power System Network (PSN). The proposed controller demonstrates better operation performance compared to a Proportional-Integral-Derivative (PID) controller in terms of transit state and deviation issues under different states of step-change loads.
2022 57TH INTERNATIONAL UNIVERSITIES POWER ENGINEERING CONFERENCE (UPEC 2022): BIG DATA AND SMART GRIDS
(2022)
Proceedings Paper
Energy & Fuels
Mohamed Darwish, Mohamed Rady, Maysam Abbod, Eydhah Almatrafi, Chun Sing Lai
Summary: This paper discusses the implementation of a successful model of electric vehicle (EV) forecourts in the UK into the Kingdom of Saudi Arabia (KSA) to support research, knowledge, and innovation in emerging EV technologies. It also addresses the challenges of implementing EV technologies through research, training, and curriculum development.
2022 57TH INTERNATIONAL UNIVERSITIES POWER ENGINEERING CONFERENCE (UPEC 2022): BIG DATA AND SMART GRIDS
(2022)
Article
Engineering, Electrical & Electronic
Yi-Feng Chen, Shou-Zen Fan, Maysam F. Abbod, Jiann-Shing Shieh, Mingming Zhang
Summary: This article proposes a new method (EEGV) to measure the effect of anesthesia on the central nervous system. By analyzing EEGV, including sample entropy, permutation entropy, detrended fluctuation analysis, and Poincare plots, the depth of anesthesia can be more accurately measured. The results show that EEGV can better differentiate awake and unconscious states and track changes in anesthesia states.
IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT
(2022)
