Improving seismic signal classification of different ground activities with advanced AI and signal processing techniques

Signal analysis is a fundamental field in engineering and data science, focused on the study of signal representation, transformation, and manipulation. The accurate estimation of harmonic vibration components and their associated parameters in vibrating mechanical systems presents significant challenges in the presence of very similar frequencies and mode mixing. In this context, a hybrid strategy to estimate harmonic vibration modes in weakly damped, multi-degree-of-freedom vibrating mechanical systems by combining Empirical Mode Decomposition and Variational Mode Decomposition is described. In this way, this hybrid approach leverages the detection of mode mixing based on the analysis of intrinsic mode functions through Empirical Mode Decomposition to determine the number of components to be estimated and thus provide greater information for Variational Mode Decomposition. The computational time and dependency on a predefined number of modes are significantly reduced by providing crucial information about the approximate number of vibratory components, enabling a more precise estimation with Variational Mode Decomposition. This hybrid strategy is employed to compute unknown natural frequencies of vibrating systems using output measurement signals. The algorithm for this hybrid strategy is presented, along with a comparison to conventional techniques such as Empirical Mode Decomposition, Variational Mode Decomposition, and the Fast Fourier Transform. Through several case studies involving multi-degree-of-freedom vibrating systems, the superior and satisfactory performance of the hybrid method is demonstrated. Additionally, the advantages of the hybrid approach in terms of computational efficiency and accuracy in signal decomposition are highlighted.

Machine-learning-enabled adaptive signal decomposition for a brain-computer interface using EEG

The bearing fault diagnosis is of vital significance in maintaining the safety of rotation machine. Among various fault detection techniques, the diagnosis based on vibration signal is widely applied in monitoring the condition of rotation machine. Variational mode decomposition (VMD) is a novel signal analysis method, which can decompose a multi-component signal into a certain number of band-limited intrinsic mode functions (BLIMFs) nonrecursively. VMD could overcome some problems such as mode mixing, the inference of noise, the determination of wavelet base, which exist in empirical mode decomposition, ensemble empirical mode decomposition, wavelet transform, respectively. However, the empirical selection of the parameters for VMD would affect the result of the decomposition. This paper presents an adaptive VMD method with parameter optimization for detecting the localized faults of rolling bearing. Kurtosis, sensitive to transient impulsive components, is employed as optimization index to evaluate the performance of the VMD. Two parameters in the VMD, namely the number of decomposition modes and data-fidelity constraint, are optimized synchronously based on the kurtosis index through artificial fish swarm algorithm. Executing VMD with the acquired parameters, the optimal BLIMF is obtained. The spectrum analysis of the optimal BLIMF could identify the characteristic frequency caused by the localized crack effectually. The validity of the proposed method is proved by means of a cyclic transient impulse response signal and two experiments with practical vibration signals of rolling bearings. Compared to several existing methods, the proposed method demonstrates reinforced results.

Internet traffic prediction is essential for effective network management, resource allocation, and ensuring efficient quality of service. Network resources can be dynamically managed by forecasting future traffic using past traffic patterns. Network traffic prediction enables the dynamic resource allocation to avoid the congestion and conflicts in the network. An Empirical mode decomposition (EMD) based machine learning models were proposed in this paper for the prediction of Software Defined Networks (SDN) traffic. SDN is a modern network architecture which separates the data plane from the control plane to provide centralized control over the network. EMD is an adaptive signal decomposition technique which extracts various frequencies from the collected network traffic at specified sampling intervals which are intrinsic mode frequencies (IMFs). Ensemble machine learning models such as Random Forest (RF), eXtreme Gradient Boosting (XGBoost), and Light Gradient Boosting Machine (LightGBM), were applied on intrinsic mode frequencies to generate the accurate predictions. SDN traffic traces were generated using CAIDA traffic traces and the experimental results suggests that EMD-XGBOOST outperforms than the other models with low root mean squared error (RMSE) and mean squared error (MSE).

Soldiers rely heavily on their vision, which is crucial not only for daily activities but also for the effective operation of defense systems, weaponry, and other military applications. However, various eye disorders, such as those related to increased intra-ocular pressure, can lead to irreversible vision loss, severely impacting a soldier’s operational capabilities. While extensive research has been conducted on detecting such ocular conditions, there remains a critical need for more accurate diagnostic methods to ensure early detection and treatment. In this study, we propose a novel approach combining Empirical Mode Decomposition (EMD) and Variational Mode Decomposition (VMD) for enhanced detection of eye disorders from retinal fundus images. The proposed method includes a comprehensive preprocessing phase, followed by decomposition using EMD and VMD techniques. The decomposed images undergo feature extraction through feature combination, with subsequent normalization and selection using z-score and the Relief method, respectively. Classification is performed using Support Vector Machines (SVM) with various kernels, including cubic, Gaussian, linear, and quadratic. The results demonstrate that the proposed method achieves high accuracy, with SVM kernel functions yielding accuracies of 98.30 %, 96.59 %, 96.59 %, and 97.87 % for 10-fold cross-validation, respectively. Additionally, the evaluation metrics, including sensitivity and specificity, indicate superior performance compared to state-of-the-art methods for similar datasets. This advanced diagnostic approach offers significant improvements in detecting eye disorders, which could be crucial in defense applications. Early and accurate diagnosis by military ophthalmologists can lead to better decision-making and timely interventions, ultimately preserving the vision and effectiveness of soldiers in the war.

Although the goal of rectal cancer treatment is to restore gastrointestinal continuity, some patients with rectal cancer develop a permanent stoma (PS) after sphincter-saving operations. Although many studies have identified the risk factors and causes of PS, few have precisely predicted the probability of PS formation before surgery. To validate whether an artificial intelligence model can accurately predict PS formation in patients with rectal cancer after sphincter-saving operations. Patients with rectal cancer who underwent a sphincter-saving operation at Taipei Medical University Hospital between January 1, 2012, and December 31, 2021, were retrospectively included in this study. A machine learning technique was used to predict whether a PS would form after a sphincter-saving operation. We included 19 routinely available preoperative variables in the artificial intelligence analysis. To evaluate the efficiency of the model, 6 performance metrics were utilized: accuracy, sensitivity, specificity, positive predictive value, negative predictive value, and area under the receiving operating characteristic curve. In our classification pipeline, the data were randomly divided into a training set (80% of the data) and a validation set (20% of the data). The artificial intelligence models were trained using the training dataset, and their performance was evaluated using the validation dataset. Synthetic minority oversampling was used to solve the data imbalance. A total of 428 patients were included, and the PS rate was 13.6% (58/428) in the training set. The logistic regression (LR), Gaussian Naïve Bayes (GNB), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), random forest, decision tree and light gradient boosting machine (LightGBM) algorithms were employed. The accuracies of the logistic regression (LR), Gaussian Naïve Bayes (GNB), Extreme Gradient Boosting (XGB), Gradient Boosting (GB), random forest (RF), decision tree (DT) and light gradient boosting machine (LightGBM) models were 70%, 76%, 89%, 93%, 95%, 79% and 93%, respectively. The area under the receiving operating characteristic curve values were 0.79 for the LR model, 0.84 for the GNB, 0.95 for the XGB, 0.95 for the GB, 0.99 for the RF model, 0.79 for the DT model and 0.98 for the LightGBM model. The key predictors that were identified were the distance of the lesion from the anal verge, clinical N stage, age, sex, American Society of Anesthesiologists score, and preoperative albumin and carcinoembryonic antigen levels. Integration of artificial intelligence with available preoperative data can potentially predict stoma outcomes after sphincter-saving operations. Our model exhibited excellent predictive ability and can improve the process of obtaining informed consent.

An accurate prediction of carbon pricing is essential in carbon emission management, and also provides an important role for governments to formulate corresponding policies. However, due to the inherent complexity and dynamics of carbon price sequence, the effectiveness of different decomposition algorithms for carbon price remains to be tested. In addition, existing studies lack a systematic framework to explore the organic integration of external factors and secondary decomposition technology, and the feature processing of complex external factors still needs to be improved. In order to overcome the shortcomings of existing research, This paper presents a Variational Modal Decomposition(VMD) algorithm and a Complete Ensemble Empirical Mode Decomposition with Adaptive Second decomposition technology of Noise(CEEMDAN) decomposition algorithm, and extract the features of external factors by Extreme Gradient Boosting (XGBoost) algorithm. The HI-VMD-PE-CEEMDAN-XGBoost-Transformer model for predicting carbon price is constructed by the combined Transformer algorithm. Specifically, first, we use Hampel identifer(HI) to detect and rectify the anomalies in the original sequence. After applying Variational Mode Decomposition(VMD) decomposition algorithm, Permutation Entropy(PE) is utilized to reassemble the decomposed component. Quadratic Decomposition is performed by Complete Ensemble Empirical Mode Decomposition with Adaptive Noise(CEEMDAN) algorithm. Then, the XGBoost algorithm is employed to extract features of external factors and screen key factors as predictive input variables. Finally, Transformer, which has stronger capability of large-scale data parallel processing, is selected as the prediction model to achieve a more scientific and effective carbon price prediction. The empirical analysis results based on EU carbon market data verify the validity and superiority of the proposed model in different forecasting scenarios.

Long-span bridges are susceptible to damage, aging, and deformation in harsh environments for a long time. Therefore, structural health monitoring (SHM) systems need to be used for reasonable monitoring and maintenance. Among various indicators, bridge displacement is a crucial parameter reflecting the bridge's health condition. Due to the simultaneous bearing of multiple environmental loads on suspension bridges, determining the impact of different loads on displacement is beneficial for the better understanding of the health conditions of the bridges. Considering the fact that extreme gradient boosting (XGBoost) has higher prediction performance and robustness, the authors of this paper have developed a data-driven approach based on the XGBoost model to quantify the impact between different environmental loads and the displacement of a suspension bridge. Simultaneously, this study combined wavelet threshold (WT) denoising and the variational mode decomposition (VMD) method to conduct a modal decomposition of three-dimensional (3D) displacement, further investigating the interrelationships between different loads and bridge displacements. This model links wind speed, temperature, air pressure, and humidity with the 3D displacement response of the span using the bridge monitoring data provided by the GNSS and Earth Observation for Structural Health Monitoring (GeoSHM) system of the Forth Road Bridge (FRB) in the United Kingdom (UK), thus eliminating the temperature time-lag effect on displacement data. The effects of the different loads on the displacement are quantified individually with partial dependence plots (PDPs). Employing testing, it was found that the XGBoost model has a high predictive effect on the target variable of displacement. The analysis of quantification and correlation reveals that lateral displacement is primarily affected by same-direction wind, showing a clear positive correlation, and vertical displacement is mainly influenced by temperature and exhibits a negative correlation. Longitudinal displacement is jointly influenced by various environmental loads, showing a positive correlation with atmospheric pressure, temperature, and vertical wind and a negative correlation with longitudinal wind, lateral wind, and humidity. The results can guide bridge structural health monitoring in extreme weather to avoid accidents.

Ensuring safety of civil infrastructure is a crucial goal in structural health monitoring (SHM). Amongst the variety of monitoring sensors, the Ground-Based Interferometric Radar (GBIR) systems have recently gained attention for their advantages such as the very high resolution and fast data collection, as opposed to other conventional methods [1]. However, this technology suffers from precise target location when the acquisition is carried out in dynamic conditions. For this purpose, external reflectors need to be installed in the portion of the structure under investigation, to which then the signal response is assumed to be related.Considering this, the present research focuses on the investigation of the dynamic response of structures using GBIR aided with augmented reality (AR) [2]. AR assisted in controlling the position of the targets inside the radar’s beam of radiation and creating different acquisition scenarios in the same range based on a combination of their number and position. Dynamic excitations were applied in the field using light weight deflectometer (LWD) [3], and their effects on the collected signal were investigated using empirical mode decomposition (EMD) signal processing technique across the different scenarios. This allowed to have a better understanding of the signal response for multiple targets or at the boundaries of the signal footprint.Results show that for data capturing using GBIR systems, AR can enhance the data quality by better controlling the collection phase. In addition, the use of multi-dimensional signal processing techniques, such as the EMD, facilitated a more comprehensive understanding of the signal response in complex scenarios. Keywords: Structural health monitoring (SHM), Ground-based interferometric radar (GBIR), Augmented reality (AR), dynamic excitation, Empirical mode decomposition (EMD). AcknowledgementsThis research was funded by the Vice-Chancellor’s PhD Scholarship at the University of West London. References[1] M. Pieraccini, M. Fratini, F. Parrini, C. Atzeni, and G. Bartoli, “Interferometric radar vs. accelerometer for dynamic monitoring of large structures: An experimental comparison,” NDT and E International, vol. 41, no. 4, pp. 258–264, Jun. 2008, doi: 10.1016/j.ndteint.2007.11.002.[2] S. Sotoudeh, F. Benedetto, S. Uzor, L. Lantini, K. Munisami, and F. Tosti, “A study into the integration of AR-based data collection and multi-dimensional signal processing methods for GB-SAR target detection,” in Second International Conference on Geographic Information and Remote Sensing Technology (GIRST 2023), M. Bilal and F. Tosti, Eds., SPIE, Aug. 2023, p. 49. doi: 10.1117/12.3007430.[3] F. Tosti, S. Adabi, L. Pajewski, G. Schettini, and A. Benedetto, “Large-scale analysis of dielectric and mechanical properties of pavement using GPR and LFWD,” in Proceedings of the 15th International Conference on Ground Penetrating Radar, IEEE, Jun. 2014, pp. 868–873. doi: 10.1109/ICGPR.2014.6970551.

We have proposed a new denoising method for the simultaneous noise reduction and preservation of seismic signals based on variational mode decomposition (VMD). VMD is a recently developed adaptive signal decomposition method and an advance in non-stationary signal analysis. It solves the mode-mixing and non-optimal reconstruction performance problems of empirical mode decomposition that have existed for a long time. By using VMD, a multi-component signal can be non-recursively decomposed into a series of quasi-orthogonal intrinsic mode functions (IMFs), each of which has a relatively local frequency range. Meanwhile, the signal will focus on a smaller number of obtained IMFs after decomposition, and thus the denoised result is able to be obtained by reconstructing these signal-dominant IMFs. Synthetic examples are given to demonstrate the effectiveness of the proposed approach and comparison is made with the complete ensemble empirical mode decomposition, which demonstrates that the VMD algorithm has lower computational cost and better random noise elimination performance. The application of on field seismic data further illustrates the superior performance of our method in both random noise attenuation and the recovery of seismic events.

An inefficient detection of a fault in a reciprocating compressor (RC) by a signal processing technique could lead to high energy losses. To achieve a high-pressure ratio, RCs are used in such pressure-based applications. This paper evaluates the performance of nonstationary signal processing techniques employed for monitoring the health of an RC, based on its vibration signal. Acquired vibration signals have been decomposed using empirical mode decomposition (EMD) and variational mode decomposition (VMD) and compared respectively. Afterward, few condition indicators (CIs) have been evaluated from decomposed modes of vibration signals. Perspectives of this work are therefore detailed at the end of this paper.

One of the paramount goals in petroleum exploration is the identification of the reservoir. The foremost objective of reservoir characterization is for prediction of reservoir precisely. Nowadays, geophysical characterization is used to characterize a reservoir; mainly, seismic data is being used for understanding the reservoir’s properties and internal structure. The reservoir can cause anomalies in the frequency of seismic signals. Over the past few decades, various transforms such as Fourier transform (FT) and wavelet transform (WT) have been used to extract the concealed attributes in the data. In the case of the Fourier transform (FT), it is the global transform that cannot reflect local specialty. This transform is the best applicable for stationary and linear data, but most of the geophysical data are non-stationary, nonlinear, and aperiodic in nature. Therefore, FT is good for spectral analysis but not fit for elucidating the temporal characteristics of the data. Wavelet transform (WT) overcomes the problem faced by Fourier transform as it is one of the efficient techniques for both spectral and temporal analysis of the data. The main problem with WT is that it does not work well with nonlinear data and suitable mother wavelet is needed to be assumed. This study focuses on highlighting the anomalies using the Hilbert–Huang Transform, which comprises two techniques, i.e., empirical mode decomposition (EMD) technique and Hilbert spectral analysis (HSA). EMD will decompose a signal into mono-components of frequency termed as intrinsic mode functions (IMFs). In this study, the EMD technique followed by HSA is applied to the data set which highlights the anomalies in the data set and makes facile to characterize a reservoir. It is difficult to characterize a reservoir because of varying properties such as porosity and permeability within small sections of the reservoir. This method shows its effectiveness in characterizing a reservoir.

Near-infrared spectroscopy (NIRS) can be used as the basis of non-invasive neuroimaging that may allow the measurement of haemodynamic changes in the human brain evoked by applied stimuli. Since this technique is very sensitive, physiological interference arising from the cardiac cycle and breathing can significantly affect the signal quality. Such interference is difficult to remove by conventional techniques because it occurs not only in the extracerebral layer but also in the brain tissue itself. Previous work on this problem employing temporal filtering, spatial filtering, and adaptive filtering have exhibited good performance for recovering brain activity data in evoked response studies. However, in this study, we present a time-frequency adaptive method for physiological interference reduction based on the combination of empirical mode decomposition (EMD) and Hilbert spectral analysis (HSA). Monte Carlo simulations based on a five-layered slab model of a human adult head were implemented to evaluate our methodology. We applied an EMD algorithm to decompose the NIRS time series derived from Monte Carlo simulations into a series of intrinsic mode functions (IMFs). In order to identify the IMFs associated with symmetric interference, the extracted components were then Hilbert transformed from which the instantaneous frequencies could be acquired. By reconstructing the NIRS signal by properly selecting IMFs, we determined that the evoked brain response is effectively filtered out with even higher signal-to-noise ratio (SNR). The results obtained demonstrated that EMD, combined with HSA, can effectively separate, identify and remove the contamination from the evoked brain response obtained with NIRS using a simple single source–detector pair.

The acquisition of ballistocardiogram (BCG) signals during sleeping always presents all kinds of high-frequency noise, which causes the problem to extract effective signals. This article proposes a new method to extract heartbeat and respiration signals by combining the whale optimization algorithm (WOA) and variational mode decomposition (VMD). Firstly, the sample entropy and energy difference ratio are used as the fitness function of WOA to optimize the penalty factor in the variational mode decomposition a and the number of decomposition layers K;Then the original signal was decomposed into multiple modal components (IMF) by optimized VMD; Finally, respiration and heartbeat signals were reconstructed, and their frequencies got calculated. Compared with the experimental results of empirical mode decomposition (EMD) and ensemble empirical mode decomposition (EEMD), the average respiratory rate error obtained by this algorithm is 0.097 and 0.013 lower than EMD and EEMD respectively, and the average heart rate error is 0.03 and 0.006 lower than EMD and EEMD respectively, it is proved that the algorithm can extract breath and heartbeat signals more effectively and accurately.

Removing noise from ECG signals is still a very frequently discussed topic. There are many challenges that make this problem more complex. These challenges are driven by the widespread use of ECG devices such as monitoring a heart disease of patients and a heart rate of athletes namely when reading and sending ECG signal data is done, there is a lot of noise that contaminates ECG signals, one of which is white Gaussian noise. In this research, noise elimination is done by using Variation mode decomposition (VMD) and Nonlocal Means (NLM) method. Denoising using the NLM technique approach is very effective in removing white Gaussian noise but it suffers from the issue of under-averaging in the high-frequency QRS-complex region and the VMD method which is the development of the Empirical Mode Decomposition (EMD) method has better capability to decompose the signal into several modes. By using the advantages of each method, we are capable of achieving good performance in removing noise from the ECG signals. Testing of the proposed method was performed using MIT-BIH arrhythmias database, which was given Gaussian white noise with different SNR levels. Measurements were made using three levels of measurement matrices i.e. Signal for Ratio Noise Enhancement (SNRimp), Mean Square Error (MSE) and Percentage root mean square difference (PRD). In addition, we may use methods that are compatible with state-of-the-art noise removal methods on ECG signals i.e. the DWT thresholding, EMD soft thresholding, EMD + Wavelet, NLM, M-EMD+NLM, and DWT+NLM. The end result is a method that is capable of producing a slightly higher SNRimp, a lower MSE and PRD value.