Article
Chemistry, Multidisciplinary
Ibrahim Hashlamon, Ehsan Nikbakht
Summary: This paper proposes a baseline-free method to detect bridge damage using a stationary vehicle. The method involves computing the contact-point response, decomposing it into intrinsic mode functions, and calculating the instantaneous amplitude to identify the damage location. Experimental results show that the method can accurately identify the location of bridge damage under different circumstances.
APPLIED SCIENCES-BASEL
(2022)
Article
Engineering, Mechanical
Xingxing Jiang, Qiuyu Song, Haien Wang, Guifu Du, Jianfeng Guo, Changqing Shen, Zhongkui Zhu
Summary: This study explores the challenges in variational mode decomposition (VMD) and its variants for the fault diagnosis of rotating machines. Based on the decomposing characteristics of two sub-models in VMD, a central frequency mode decomposition (CFMD) method is proposed. The CFMD method consists of three parts and achieves effective and adaptive signal decomposition. Numerical simulation and experimental cases validate the effectiveness and superiority of the CFMD method in the fault diagnosis of rotating machines.
MECHANISM AND MACHINE THEORY
(2022)
Article
Chemistry, Analytical
Qiuyan Miao, Qingxin Shu, Bin Wu, Xinglin Sun, Kaichen Song
Summary: Complex Variational Mode Decomposition (CVMD) is an extension of the original VMD algorithm for analyzing complex-valued data. However, it faces difficulties in decomposing low-frequency signals and requires prior knowledge about the decomposition number. This paper proposes a modified method, MCVMD, which improves the accuracy of low-frequency signal decomposition and requires less prior knowledge. The effectiveness of the proposed algorithm is verified using both synthetic and real-world complex-valued signals.
Article
Engineering, Mechanical
Hongbing Wang, Shiqian Chen, Wanming Zhai
Summary: In this paper, a fully data-driven adaptive chirp mode decomposition (DD-ACMD) is proposed to address the issue of fault diagnosis for non-linear and non-stationary signals. The proposed method enhances the high-frequency modes of the signal through derivative operation and estimates the initial instantaneous frequency (IF) of the highest-frequency mode using a normalization operator. An iterative time-varying filtering method based on demodulation technique is introduced to reduce the influence of noise and a time-varying low-pass filter is added to improve the noise robustness of the algorithm. The effectiveness of the DD-ACMD is validated through simulations and real-life applications for machine fault diagnosis.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2023)
Article
Engineering, Electrical & Electronic
Honglin Wu, Zhongbin Wang, Lei Si, Chao Tan, Xiaoyu Zou, Xinhua Liu, Futao Li
Summary: Signal denoising is a crucial step in signal analysis, and traditional methods often fail on non-linear and non-stationary signals. This study proposes a new denoising method that utilizes an improved VMD method for decomposition and an energy variation ratio function for distinguishing effective and non-effective components, resulting in improved denoising performance.
IET SIGNAL PROCESSING
(2023)
Article
Engineering, Electrical & Electronic
Qiming Chen, Xun Lang, Lei Xie, Hongye Su
Summary: The multivariate intrinsic chirp mode decomposition (MICMD) algorithm efficiently extracts time-varying signals by assuming a joint instantaneous frequency among all channels and modeling instantaneous frequencies and amplitudes as Fourier series. This method outperforms other multivariate decomposition techniques in terms of computational complexity and mode extraction.
Article
Computer Science, Information Systems
Chuting Zhang, Chien-Hung Yeh, Wenbin Shi
Summary: This study introduces a new method called variational phase-amplitude coupling to quantify the rhythmic nesting structure in EEGs during emotional processing. The proposed algorithm reduces the risk of spurious coupling compared to other decomposition methods. It is found that activity in the anterior frontal region is a critical indicator for neutral emotional state, and alpha amplitude is linked to both positive and negative emotional states. The alpha-amplitude-related coupling in EEGs is a promising biomarker for recognizing mental states, and the method is recommended for characterizing multifrequency rhythms in brain signals for emotion neuromodulation.
IEEE JOURNAL OF BIOMEDICAL AND HEALTH INFORMATICS
(2023)
Article
Chemistry, Analytical
Saiqiang Xia, Jun Yang, Wanyong Cai, Chaowei Zhang, Liangfa Hua, Zibo Zhou
Summary: In this paper, a method based on CVMD is proposed to suppress the strong clutter component and separate the effective fretting component from radar echo. The method extends VMD from the real domain to the complex domain and determines the optimal effective order of singular value through SVD, leading to higher accuracy. By calculating the Mahalanobis distance to judge correlated modes, the separation of micro-motion signals can be achieved more effectively.
Article
Engineering, Electrical & Electronic
Yu Guo, Xingxing Tong, Yanxia Shen, Haodong Wu
Summary: An optical fiber beat frequency sensing system for monitoring multiple human physiological parameters is proposed, which utilizes FBG and fiber laser sensor to achieve detection of respiration, heartbeat, pulse signals and human body temperature without interference. The system generates two types of beat frequency signals, PMBF for respiration, heartbeat and pulse signals monitoring, and LMBF for human body temperature sensing. The system demonstrates high SNR, stability, accuracy, and capability for multi-parameters sensing.
JOURNAL OF LIGHTWAVE TECHNOLOGY
(2023)
Article
Physics, Multidisciplinary
Fan Yang, Mengqi Fu, Bojan Bosnjak, Robert H. Blick, Yuxuan Jiang, Elke Scheer
Summary: Researchers investigated the sideband spectra of a driven nonlinear mode with its eigenfrequency modulated at a low frequency. They found that this additional parametric modulation leads to prominent antiresonance line shapes in the sideband spectra, which can be controlled through the vibration state of the driven mode.
PHYSICAL REVIEW LETTERS
(2021)
Review
Chemistry, Analytical
Marco Civera, Cecilia Surace
Summary: Signal processing is crucial in vibration-based Structural Health Monitoring (SHM), but analyzing real-life vibration measurements can be complex. Efficiently decomposing systems into independent components is necessary for understanding dynamic behavior. Three adaptive mode decomposition methods have been chosen for in-depth analysis and comparison in terms of their characteristics and performance.
Article
Engineering, Multidisciplinary
Yong Li, Gang Cheng, Sencai Ma, Xin Li
Summary: Considering the difficulty in selecting sensitive fault features in bearing health diagnosis, a fault diagnosis method based on complete center frequency distribution feature (CCFDF) is proposed. By utilizing the sensitivity of the center frequency to the signal spectrum distribution in variational mode decomposition (VMD) and extracting the complete distribution feature of the center frequency under different parameter combinations, CCFDF can effectively characterize the difference in bearing vibration signals under different health conditions and overcome the parameter setting issue in VMD. Experimental results show that the method achieves high recognition accuracy of 99% and 97% for two groups of data, respectively, demonstrating the effectiveness of the proposed method in bearing fault diagnosis.
STRUCTURAL HEALTH MONITORING-AN INTERNATIONAL JOURNAL
(2023)
Article
Environmental Sciences
Yanbing Li, Bo Feng, Weichuan Zhang
Summary: As an important remote sensing technology, millimeter-wave radar is used for environmental sensing in many fields due to its advantages of all-day, all-weather operation. However, with the increasing use of radars, inter-radar interference becomes increasingly critical, degrading radar signal quality and affecting post-processing performance. To mitigate this interference, a method based on variational mode decomposition (VMD) is proposed, effectively separating the target from the interference and obtaining an interference-free signal through reconstruction. Simulation and experimental results demonstrate the superiority of the proposed method over existing decomposition-based methods.
Article
Chemistry, Multidisciplinary
Gang Jing, Yixin Zhao, Yirui Gao, Pedro Marin Montanari, Giuseppe Lacidogna
Summary: Although exhaled aerosols may appear chaotic, they contain information about respiratory physiology and anatomy. This study created a database of simulated exhaled aerosol images and tested different convolutional neural network models. The performance of the models decreased for outbox test images, but ResNet-50 showed the best performance in both multi-level testing and continuous learning.
APPLIED SCIENCES-BASEL
(2023)
Article
Engineering, Mechanical
Bin Pang, Mojtaba Nazari, Guiji Tang
Summary: Variational mode extraction (VME) is developed based on variational mode decomposition (VMD) to effectively separate a specific mode from a multi-component signal by knowing an approximate center frequency. This method shows potential for extracting fault characteristics of rolling bearing, but determining the center frequency and penalty factor adaptively are difficult problems. Recursive variational mode extraction (RVME) is proposed as an iterative VME-based signal decomposition algorithm that adaptively determines the initial center frequency and penalty factor at each iteration, making it an adaptive signal decomposition algorithm.
MECHANICAL SYSTEMS AND SIGNAL PROCESSING
(2022)
Article
Engineering, Biomedical
Abhijit Bhattacharyya, Divyanshu Bhaik, Sunil Kumar, Prayas Thakur, Rahul Sharma, Ram Bilas Pachori
Summary: In this study, a new method based on X-ray images is proposed, utilizing segmentation and feature extraction of lung images along with artificial intelligence and machine learning models for classifying COVID-19, pneumonia, and normal lung images, achieving a high testing classification accuracy of 96.6%.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Engineering, Biomedical
Arti Anuragi, Dilip Singh Sisodia, Ram Bilas Pachori
Summary: This paper proposes a method based on the Fourier Bessel series expansion empirical wavelet transform PBSE-EWT for analyzing the non-linear characteristics of EEG signals. Features are extracted using 3D PSR for dimensionality reduction, and experiments are conducted on different ensemble learning classifiers to find the top five classifiers for classifying epileptic-seizure EEG signals.
BIOMEDICAL SIGNAL PROCESSING AND CONTROL
(2022)
Article
Computer Science, Artificial Intelligence
Manish Sharma, Ankit A. Bhurane, U. Rajendra Acharya
Summary: Humans' sleep health is an important indicator of overall health, and non-invasive methods like EEG are used to evaluate it. A study developed a model based on machine learning algorithms to accurately identify CAP phases using entropy features extracted by a biorthogonal wavelet filter bank. The model achieved high classification accuracy and can assist medical practitioners in assessing cerebral activity and sleep quality accurately.
Article
Computer Science, Artificial Intelligence
Manish Sharma, Sohamkumar Patel, U. Rajendra Acharya
Summary: Congestive heart failure (CHF) is a cardiac disorder caused by inefficient pumping of the heart, resulting in insufficient blood flow. This study proposes a method using an optimized wavelet filter bank and heart rate variability (HRV) signals to automatically identify CHF. The method achieves high classification accuracy when using classifiers such as support vector machine (SVM).
Article
Biology
Manish Sharma, Divyash Kumbhani, Jainendra Tiwari, T. Sudheer Kumar, U. Rajendra Acharya
Summary: Obstructive sleep apnea (OSA) is a common respiratory disorder. This study proposes an automated OSA detection system based on respiratory and oximetry signals, achieving high classification accuracy. The system is accurate, reliable, and less complex, making it suitable for elderly subjects.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Biology
Shruti Murarka, Aditya Wadichar, Ankit Bhurane, Manish Sharma, U. Rajendra Acharya
Summary: Sleep monitoring is crucial for overall well-being, but traditional manual methods for classifying sleep phases may result in inaccurate diagnoses. This study proposes an automated approach using deep learning to classify cyclic alternating patterns (CAP) phases. The proposed model achieved high classification accuracy for both healthy individuals and patients with various sleep disorders.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Article
Biology
Manish Sharma, Jay Darji, Madhav Thakrar, U. Rajendra Acharya
Summary: Sleep is crucial for a healthy life, but sleep disorders can cause various issues. Traditional sleep monitoring methods are complex and not suitable for real-time monitoring, so there is a need for a simple and convenient system to monitor sleep quality. This research proposes an automatic sleep disorder detection method using electrooculogram (EOG) and electromyogram (EMG) signals, and develops a model using machine learning classifiers. The results show that the proposed method can accurately classify different types of sleep disorders.
COMPUTERS IN BIOLOGY AND MEDICINE
(2022)
Review
Biophysics
Manish Sharma, Ruchit Kumar Patel, Akshat Garg, Ru SanTan, U. Rajendra Acharya
Summary: Schizophrenia is a devastating mental disorder that affects higher brain functions and has a profound impact on individuals. Deep learning models can automatically detect schizophrenia by learning signal data characteristics, without the need for traditional feature engineering. This systematic review explores various deep learning models and methodologies for schizophrenia detection based on EEG signals, structural and functional MRI data from diverse datasets. The study discusses the challenges and future works in using deep learning models for schizophrenia diagnosis.
PHYSIOLOGICAL MEASUREMENT
(2023)
Article
Medicine, General & Internal
Soumya Ranjan Nayak, Deepak Ranjan Nayak, Utkarsh Sinha, Vaibhav Arora, Ram Bilas Pachori
Summary: The research community is interested in developing automated systems for COVID-19 detection using deep learning approaches and chest radiography images. However, current deep learning techniques require more parameters and memory, making them unsuitable for real-time diagnosis. This paper proposes a lightweight CNN model called LW-CORONet, which extracts meaningful features from chest X-ray images with only five learnable layers. The proposed model achieves high classification accuracy on large datasets and can assist radiologists in COVID-19 diagnosis.
Article
Computer Science, Artificial Intelligence
Manish Sharma, Paresh Makwana, Rajesh Singh Chad, U. Rajendra Acharya
Summary: Nowadays, sleep deprivation due to busy work life has led to sleep-related disorders and adverse physiological conditions. Therefore, sleep study and scoring are crucial for detecting and assessing these disorders. In this study, an automated sleep stage classification model based on the biorthogonal wavelet filter bank's novel least squares (LS) design is proposed. The model achieves high accuracy and can be used in home-based clinical systems and wearable devices.
APPLIED INTELLIGENCE
(2023)
Article
Engineering, Biomedical
Bharti Jogi Dakhale, Manish Sharma, Mohammad Arif, Kushagra Asthana, Ankit A. Bhurane, Ashwin G. Kothari, U. Rajendra Acharya
Summary: Healthy sleep is important for physical and mental well-being, but factors like work schedules and medical complications can lead to sleep disorders. This study proposes a new method for automated sleep stage classification using machine learning and EEG signals. By analyzing data from 453 subjects, the developed model achieved a classification accuracy of 81.3%.
MEDICAL ENGINEERING & PHYSICS
(2023)
Article
Biology
Manish Sharma, Sarv Verma, Divyansh Anand, Vikram M. Gadre, U. Rajendra Acharya
Summary: The Cyclic Alternating Pattern (CAP) is a physiological marker of sleep instability and can examine various sleep-related disorders. The study proposes a novel WSN-based CAPSCNet for automatically detecting specific events (A-phases) during sleep. The model achieves high classification accuracy in healthy subjects and patients with different sleep disorders.
COMPUTERS IN BIOLOGY AND MEDICINE
(2023)
Article
Automation & Control Systems
Manish Sharma, Divyansh Anand, Sarv Verma, U. Rajendra Acharya
Summary: Sleep is crucial for human well-being, and insomnia is a common sleep disorder that affects both physical and mental health. This study proposes a method that uses single-channel EEG signals to automatically identify insomnia, extracting features using a deep convolutional network and developing a model for sleep stages classification.
ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE
(2023)
Article
Engineering, Biomedical
Kamlesh Kumar, Kapil Gupta, Manish Sharma, Varun Bajaj, U. Rajendra Acharya
Summary: This study successfully developed a model that integrates electrocardiogram with a convolutional neural network to accurately measure sleep quality for identifying insomnia. By employing continuous wavelet transform, 1-D time domain ECG signals were converted into 2-D scalograms, which were then fed to different neural networks for automated detection of insomnia. The proposed system showed high accuracy and performance in insomnia detection based on the validation experiments.
MEDICAL ENGINEERING & PHYSICS
(2023)
Article
Computer Science, Information Systems
Akanksha Tiwari, Ram Bilas Pachori, Premjit Khanganba Sanjram
Summary: The study investigates how the visuospatial characteristics of objects in a MR-based computer game influence cortical activities in dorsal-ventral visual pathways. The research found that angular disparity has a greater impact on cortical activation, showing higher activation for 2D objects and CA compared to 3D objects and RA, respectively. The dorsal pathway was more active than the ventral pathway, suggesting that angular disparity plays a significant role in engaging different visual pathways in the brain.
CMC-COMPUTERS MATERIALS & CONTINUA
(2022)