Power Spectrum Entropy Research Articles

Precise measurement of human heart rate based on multi-channel radar data fusion

To achieve non-contact measurement of human heart rate and improve its accuracy, this paper proposes a method for measuring human heart rate based on multi-channel radar data fusion. The radar data were firstly extracted by human body position identification, phase extraction and unwinding, phase difference, band-pass filtering optimized by power spectrum entropy, and fast independent component analysis for each channel data. After overlaying and fusing the four-channel data, the heartbeat signal was separated using frost-optimized variational modal decomposition. Finally, a chirp Z-transform was introduced for heart rate estimation. After validation with 40 sets of data, the average root mean square error of the proposed method was 2.35 beats per minute, with an average error rate of 2.39%, a Pearson correlation coefficient of 0.97, a confidence interval of [-4.78, 4.78] beats per minute, and a consistency error of -0.04. The experimental results show that the proposed measurement method performs well in terms of accuracy, correlation, and consistency, enabling precise measurement of human heart rate.

Partial Discharge Signal Pattern Recognition of Composite Insulation Defects in Cross-Linked Polyethylene Cables.

To investigate the pattern recognition of complex defect types in XLPE (cross-linked polyethylene) cable partial discharges and analyze the effectiveness of identifying partial discharge signal patterns, this study employs the variational mode decomposition (VMD) algorithm alongside entropy theories such as power spectrum entropy, fuzzy entropy, and permutation entropy for feature extraction from partial discharge signals of composite insulation defects. The mean power spectrum entropy (PS), mean fuzzy entropy (FU), mean permutation entropy (PE), as well as the permutation entropy values of IMF2 and IMF13 (Pe) are selected as the characteristic quantities for four categories of partial discharge signals associated with composite defects. Six hundred samples are selected from the partial discharge signals of each type of compound defect, amounting to a total of 2400 samples for the four types of compound defects combined. Each sample comprises five feature values, which are compiled into a dataset. A Snake Optimization Algorithm-optimized Support Vector Machine (SO-SVM) model is designed and trained, using the extracted features from cable partial discharge datasets as case examples for recognizing cable partial discharge signals. The identification outcomes from the SO-SVM model are then compared with those from conventional learning models. The results demonstrate that for partial discharge signals of XLPE cable composite insulation defects, the SO-SVM model yields better identification results than traditional learning models. In terms of recognition accuracy, for scratch and water ingress defects, SO-SVM improves by 14.00% over BP (Back Propagation) neural networks, by 5.66% over GA-BP (Genetic Algorithm-Back Propagation), and by 12.50% over SVM (support vector machine). For defects involving metal impurities and scratches, SO-SVM improves by 13.39% over BP, 9.34% over GA-BP, and 12.56% over SVM. For defects with metal impurities and water ingress, SO-SVM shows enhancements of 13.80% over BP, 9.47% over GA-BP, and 13.97% over SVM. Lastly, for defects combining metal impurities, water ingress, and scratches, SO-SVM registers increases of 11.90% over BP, 9.59% over GA-BP, and 12.05% over SVM.

The EEG-Based Fusion Entropy-Featured Identification of Isometric Contraction Forces under the Same Action.

This study explores the important role of assessing force levels in accurately controlling upper limb movements in human-computer interfaces. It uses a new method that combines entropy to improve the recognition of force levels. This research aims to differentiate between different levels of isometric contraction forces using electroencephalogram (EEG) signal analysis. It integrates eight different entropy measures: power spectrum entropy (PSE), singular spectrum entropy (SSE), logarithmic energy entropy (LEE), approximation entropy (AE), sample entropy (SE), fuzzy entropy (FE), alignment entropy (PE), and envelope entropy (EE). The findings emphasize two important advances: first, including a wide range of entropy features significantly improves classification efficiency; second, the fusion entropy method shows exceptional accuracy in classifying isometric contraction forces. It achieves an accuracy rate of 91.73% in distinguishing between 15% and 60% maximum voluntary contraction (MVC) forces, along with 69.59% accuracy in identifying variations across 15%, 30%, 45%, and 60% MVC. These results illuminate the efficacy of employing fusion entropy in EEG signal analysis for isometric contraction detection, heralding new opportunities for advancing motor control and facilitating fine motor movements through sophisticated human-computer interface technologies.

A novel method of rolling bearings fault diagnosis based on singular spectrum decomposition and optimized stochastic configuration network

Fault diagnosis of rolling bearings is essential for the safe operation of rotating machinery. However, in the production process, the rolling bearings have a complex working environment embedded with weak fault signals and a large number of interfering signals, which is a considerable challenge to automatically and accurately detect bearing fault type from the actual vibration signal. Therefore, a novel fault diagnosis scheme is proposed based on singular spectrum decomposition (SSD) and an optimized stochastic configuration network (SCN). Firstly, SSD is used to pre-process the original rolling bearings vibration signal to obtain several singular spectral components (SSCs) and the practical component is selected according to the maximum correlation coefficient for signal reconstruction. Furthermore, time domain and power spectrum entropy (PSE) features of the reconstructed signal are extracted to obtain a fault information-rich feature sets. In addition, the parameters of the SCN are optimized by marine predators algorithm (MPA) to enhance the learning ability and generalization performance of the SCN. Finally, the feature sets are input into MPA-SCN to achieve fault classification. Experimental results exhibit that the proposed method has higher accuracy in rolling bearings fault diagnosis compared with other methods, which provides a high-efficiency solution for rolling bearings fault diagnosis.

In-process feature extraction of milling chatter based on second-order synchroextracting transform and fast kutrogram

In the milling process,chatter is a self-excited vibration, which has adverse effects on the quality of the workpiece. So online milling chatter detection is very important for stable and accurate machining operation. This paper proposes an in-process feature extraction method for milling chatter based on second-order synchroextracting transform and fast kutrogram. Firstly, power spectrum entropy, mean value, standard deviation and Rényi entropy are used to preliminary determine whether the collected signal is a chattering signal. Secondly, the chattering part of the collected signal is reconstructed by second-order synchroextrating transform. Thirdly, the reconstructed signal is processed by fast kutrogram to obtain kurtosis distribution. Last, the milling chatter frequency can be obtained by envelope spectral processing of the signal part with maximum kurtosis. The experiment results show that the proposed chatter diagnosis algorithms not only can detect the milling chatter online, but also can find the chatter frequency effectively.

Electrical and photosynthetic response of Rosa chinensis under drought stress

Plants develop a series of mechanisms under drought stress, involving changes in chemical, physiological, and electrical signals. Measurement of these signal changes could reflect the growth status of plants under adversity stress. Aim of this study was to investigate the changes in water potential, photosynthetic parameters (i.e., net photosynthesis rate, transpiration rate, stomatal conductance, and the concentration of inter-cellular CO2), and electrical signals (peak-to-peak value, mean value, gravity frequency, power spectral entropy) of Rosa chinensis under drought stress. Analysing these parameters fills in the research need to have a comprehensive understanding of plants' responses to drought stress. The results show all parameters present an overall decreasing trend, except the concentration of inter-cellular CO2 and peak-to-peak value. There is a slight recovery at the end of the drought treatment, indicating that plants are adapted to the new level of drought status. Besides, most of the electrical signals (mean value, gravity frequency, power spectrum entropy) and water potential first showed significant differences (P < 0.05) from the control, followed by photosynthetic parameters, and transpiration. This result, combined with the results on the correlation between these parameters, indicates that changes in electrical signals can reflect physiological processes in plants. Therefore, this study reveals that electrical signals could serve as an early and accurate indicator to reflect the growth status of plants under drought stress, which provides a theoretical basis for the water management of Rosa chinensis.

Smoothness Evaluation Indices during Sit-to-Stand-to-Sit Motions in Healthy Older Females and after Hip Fracture Using an Accelerometer: A Pilot Study.

Studies that quantify the quality of sit-to-stand-to-sit (STS) motions, particularly in terms of smoothness, are limited. Thus, this study aimed to investigate the possibility and usefulness of quality evaluation during STS motions. This cross-sectional study enrolled 36 females aged >60 years, including 18 females each in the healthy and hip fracture groups. Measurements were performed at two different speeds: five STS as fast as possible (STSF) and two seconds for each motion (STS2s). Indices of smoothness, including harmonic ratio (HR) and power spectrum entropy (PSE), were calculated and compared from the measured data in each of the three axial directions. HR in the vertical direction was significantly higher in the healthy group (STSF: 3.65 ± 1.74, STS2s: 3.42 ± 1.54) than in the hip fracture group (STSF: 2.67 ± 1.01, STS2s: 2.58 ± 0.83) for STSF and STS2s. Furthermore, PSE for all directions and triaxial composites were significantly lower for STS2s (the healthy group (mediolateral (ML): 7.63 ± 0.31, vertical (VT): 7.46 ± 0.22, anterior-posterior (AP): 7.47 ± 0.15, triaxial: 7.45 ± 0.25), the hip fracture group (ML: 7.82 ± 0.16, VT: 7.63 ± 0.16, AP: 7.61 ± 0.17, triaxial: 7.66 ± 0.17)). This study suggests the usefulness of HR and PSE as quality evaluations for STS motions.

Impact of Temperament Types and Anger Intensity on Drivers' EEG Power Spectrum and Sample Entropy: An On-road Evaluation Toward Road Rage Warning

Impact of Temperament Types and Anger Intensity on Drivers' EEG Power Spectrum and Sample Entropy: An On-road Evaluation Toward Road Rage Warning

Multidimensional Analysis of Precursor Information of Rockburst during Loading and Unloading of Deep Diorite

At present, rockburst disasters cannot be predicted accurately, and the prevention and control of deep underground engineering disasters are significantly challenging. To explore the evolution law of precursory information of rockburst instability, the rockburst test of diorite was conducted with high confining pressure and different unloading rates (0.1 MPa/s, 0.3 MPa/s, 0.5 MPa/s, 0.7 MPa/s, and 0.9 MPa/s). Multidimensional analysis is carried out by evaluating deformation features, fast Fourier transform (FFT), energy entropy, singular spectrum entropy, and power spectrum entropy. The results show that Poisson’s ratio is hook-shaped before rockburst, the elastic modulus is in the shape of a step, ringing count and energy surge after a quiet period, three-dimensional law of 0.98 σ c ~ σ c stress location space shows a large red ball distribution along the shear plane, b value fluctuates in the low-value range, and low-frequency high amplitude and high-frequency low amplitude fluctuate in a large range after 300 s, with frequent abnormal fluctuations of the energy spectrum entropy, the singular spectrum entropy, and the power spectrum entropy curve. The above research results can be considered the evolution law of rockburst precursor information, which enriches the theoretical method of explosion disaster prediction.

Study of Motion Sickness Model Based on fNIRS Multiband Features during Car Rides

Motion sickness is a common physiological discomfort phenomenon during car rides. In this paper, the functional near-infrared spectroscopy (fNIRS) technique was used in real-world vehicle testing. The fNIRS technique was utilized to model the relationship between changes in blood oxygenation levels in the prefrontal cortex of passengers and motion sickness symptoms under different motion conditions. To enhance the accuracy of motion sickness classification, the study utilized principal component analysis (PCA) to extract the most significant features from the test data. Wavelet decomposition was used to extract the power spectrum entropy (PSE) features of five frequency bands highly related to motion sickness. The correlation between motion sickness and cerebral blood oxygen levels was modeled by a 6-point scale calibration for the subjective evaluation of the degree of passenger motion sickness. A support vector machine (SVM) was used to build a motion sickness classification model, achieving an accuracy of 87.3% with the 78 sets of data. However, individual analysis of the 13 subjects showed a varying range of accuracy from 50% to 100%, suggesting the presence of individual differences in the relationship between cerebral blood oxygen levels and motion sickness symptoms. Thus, the results demonstrated that the magnitude of motion sickness during the ride was closely related to the change in the PSE of the five frequency bands of cerebral prefrontal blood oxygen, but further studies are needed to investigate individual variability.

Research on interference and noise reduction technology of solar radio observation system

The dynamic spectrum of solar radio burst is a very important tool to study the characteristics of solar radio burst. However, due to the influence of the instruments noise of the solar radio telescope, external interference, the change of ambient temperature, absorption of clouds and so on, the sensitivity of the observation system will be reduced. In particular, the weak solar radio burst signal is easily submerged by various interference signals. In order to improve the sensitivity of solar radio telescope to observe solar radio burst signals and remove narrow-band interference signals, a spectrum data processing algorithm of spectral subtraction method based on entropy and energy threshold values (SSM-EE) is proposed in this article. There are multiple processing steps of SSM-EE. The first step is to improve the signal-to-noise ratio (SNR) through accumulating and averaging the spectrum data. The second step is to eliminate narrowband interference. The spectral kurtosis algorithm is used to calculate the spectral kurtosis of the narrowband interference signal, and then whether to smooth it is determined according to whether it is greater than the threshold. The third step is to establish a noise model. Calculating the power spectrum entropy and energy entropy of each frame of the processed spectrum data, judge whether it is a noise signal by judging the relationship between the power spectrum entropy and energy entropy and the corresponding threshold. The update model for noise floor is used to obtain the real-time noise floor data. The last step is to eliminate the background noise through spectral subtraction. The new spectrum data are obtained by subtraction method between the original spectrum data and the noise floor data. After a large number of data simulation and verification of the actual observation data, it shows that the method proposed in this article has good practical value.

Neural Markers of shootig performance: An explore of EEG frequency features during aiming

The frequency-domain characteristics of electroencephalogram (EEG) during shooting used to evaluate and improve shooting performance has become a research hotspot in recent years. However, neural markers that can be effectively and stably used to characterize various shooting performances remain unclear. In this study, a real shooting experiment was designed to study the effective EEG neural markers for different shooting performances. EEG data were obtained during the aiming period,the frequency domain characteristics such as spectrum, power spectrum, and differential entropy corresponding to Delta wave, Theta wave, Alpha wave, Beta wave, and Gamma wave were extracted respectively. Classical statistical analysis and machine learning methods were used to investigate the effectiveness of the characteristics. The results revealed that the overall energy of the EEG signals was low and stable for the participants with excellent shooting performance. The differential entropy feature of the gamma band as a effective neural marker had achieved the best classification accuracy of 74.91% throughout the aiming period. The results verified that the brain state of shooters is stable and their brains exhibit higher cognitive information processing efficiency during accurate shootings. The feasibility of using EEG neural markers to evaluate shooting performance is a novel avenue for the selection and performance evaluation of high-performance shooters.

Fault diagnosis of rolling bearing combining improved AWSGMD-CP and ACO-ELM model

The signal of rotating machinery is usually non-stationary, non-linear, and with noise interference. The early fault signal is too weak to extract fault features and the accuracy cannot be effectively guaranteed. A novel fault diagnosis method based on adaptive weighted symplectic geometry mode decomposition (AWSGMD-CP) with Cosine difference factor (CDF) and Pearson correlation coefficient (PCC) and extreme learning machine (ELM) optimized by ant colony optimization (ACO) is proposed. Firstly, the vibration signal is decomposed by SGMD, and several symplectic geometry components (SGCs) are obtained, which can effectively capture the signal characteristics. Secondly, the constrains based on CDF, PCC and variable entropy weighted matrix (VEWM) are adopted to reconstruct SGCs into weighted symplectic combined components (WSCCs). Then calculate the power spectrum entropy (PSE) weighted singular values as the fault feature vectors. Finally, the ELM optimized by ACO is introduced to perform fault classification. Simulation and experimental results show that the proposed method can effectively extract rich fault features from vibration signals, and has a higher diagnosis accuracy, up to 99.18%.

A Transferable Thruster Fault Diagnosis Approach for Autonomous Underwater Vehicle under Different Working Conditions with Insufficient Labeled Training Data

Existing thruster fault diagnosis methods for AUV (autonomous underwater vehicle) usually need sufficient labeled training data. However, it is unrealistic to get sufficient labeled training data for each working condition in practice. Based on this challenge, a transferable thruster fault diagnosis approach is proposed. In the approach, an IPSE (instantaneous power spectrum entropy) and a STNED (signal-to-noise energy difference) are added to SPWVD (smoothed pseudo Wigner-Ville distribution) to identify time and frequency boundaries of the local region in the time-frequency power spectrum caused by thruster fault, forming a TFE (time-frequency energy) method for feature extraction. In addition, the RCQFFV (relative change quantity of the fault feature value), an MSN (multiple scale normalization) and a LSP (least square prediction) are added to SVDD (support vector data description) to align distributions of fault samples, contributing a TSVDD (transferable SVDD) for classification of fault samples. The experimental results of a prototype AUV indicate that the fault feature is monotonic to the percentage of thrust loss for the proposed TFE but not for the SPWVD. The TSVDD has a higher overall classification accuracy in comparison to conventional SVDD under working conditions with no labeled training data.

Entropy of frequency domain of heart rate variability

Introduction. The heart rate variability (HRV) is based on measuring (time) intervals between R-peaks (of RR-intervals) of an electrocardiogram (ECG) and plotting a rhythmogram on their basis with its subsequent analysis by various mathematical methods which are classified as Time-Domain (TD), Frequency-Domain (FD) and Nonlinear [1, 2]. There are a number of popular Nonlinear methods used in HRV analysis, such as entropy-based measures that mostly applied for TD. Spectral Entropy (SE) is using for Frequency-Domain: it is defined to be the Shannon entropy of the power spectral density (PSD) of the data. An important characteristic of Frequency-Domain studies is sympatho-vagal balance, which has been overlooked by entropy-based analysis. This is due to the fact that good entropy analysis restricted the number of existing HRV data, which is shrinking in FD and also in total spectrum parts. Aim of the research. The goal of this paper is to provide a reliable formula for calculating entropy accurately for Frequency-domain of standard 5-min. HRV records and to show the advantages of such approach for analyzing of sympatho-vagal balance for healthy subjects (NSR), Congestive Heart Failure (CHF) and Atrial Fibrillation (AF) patients. Materials and Methods. We used MIT-BIH long-term HRV records for Normal Sinus Rhythm (NSR), Congestive Heart Failure (CHF) and Atrial Fibrillation (AF). The generalized form of the Robust Entropy Estimator (EnRE) for Frequency-domain of standard 5-min. HRV records was proposed and the key EnRE futures was shown. The difference between means of the two independent selections (NSR and CHF, before and after AF) has been determined by a t-test for independent samples; discriminant analysis and statistical calculations have been done by using the statistical package IBM SPSS 27. The results of the study. We calculate entropy for all valuable for HRV spectral interval, namely 0–0.4 Hz and to compare with existing results for Spectral Entropy: qualitatively we receive the same distribution number as [14] and significant difference (p &lt; 0.001) between entropy averages for NSR and CHF or AF patients. We define low-frequencies (LF) power spectrum components in the range of 0.04–0.15 Hz and high-frequencies (HF) power spectrum components in the range of 0.15–0.4 Hz [1]. The sympatho-vagal balance is a simple ratio LF/HF [1]. Then, we define an entropy eLF of the LF power spectrum components, an entropy eHF of the HF power spectrum components and entropy based sympatho-vagal balance as a ratio eLF/eHF. The difference between NSR and CHF groups are significant in both cases LF/HF and eLF/eHF with p &lt; 0.001, but in case of eLF/eHF the results are quite better (t = -4.8, compared to LF/HF where t = -4.4). The discriminant analysis shows total classification accuracy for eLF/eHF in 79.3 % (χ2 = 19.4, p &lt; 0.001) and for LF/HF in 72.4 % (χ2 = 16.6, p &lt; 0.001). We applied entropy-based Frequencies-domain analyzing for AF patients and showed that ratio eLF/eHF is significantly higher during AF than before AF (p &lt; 0.001). This is opposite to ordinary LF/HF where difference is insignificant due to high variation of this ratio. Conclusion. Proposed in the article is generalized form for Robust Entropy Estimator EnRE for Frequencies-domain, which allows, for time series of a limited length (standard 5-min. records), to find entropy value of HRV power spectrum (total spectrum, low- and high- frequencies bands). Using the proposed EnRE for MIT-BIH database of HRV records, we show for standard 5 min. HRV records the usage of EnRE of HRV power spectrum and entropy-based sympatho-vagal balance of Normal Sinus Rhythm (NSR) and Congestive Heart Failure (CHF) cases. It is demonstrated, that, entropy-based Frequencies-domain analyzing is applicable for case of Atrial Fibrillation (AF) even during AF episodes. We showed the significant difference (p &lt; 0.001) before and during AF for entropy of total spectrum, as well as for sympatho-vagal balance in form of eLF/eHF.

Research on the Recognition of Various Muscle Fatigue States in Resistance Strength Training.

Instantly and accurately identifying the state of dynamic muscle fatigue in resistance training can help fitness trainers to build a more scientific and reasonable training program. By investigating the isokinetic flexion and extension strength training of the knee joint, this paper tried to extract surface electromyogram (sEMG) features and establish recognition models to classify muscle states of the target muscles in the isokinetic strength training of the knee joint. First, an experiment was carried out to collect the sEMG signals of the target muscles. Second, two nonlinear dynamic indexes, wavelet packet entropy (WPE) and power spectrum entropy (PSE), were extracted from the obtained sEMG signals to verify the feasibility of characterizing muscle fatigue. Third, a convolutional neural network (CNN) recognition model was constructed and trained with the obtained sEMG experimental data to enable the extraction and recognition of EMG deep features. Finally, the CNN recognition model was compared with multiple support vector machines (Multi-SVM) and multiple linear discriminant analysis (Multi-LDA). The results showed that the CNN model had a better classification accuracy. The overall recognition accuracy of the CNN model applied to the test data (91.38%) was higher than that of the other two models, which verified that the CNN dynamic fatigue recognition model based on subjective and objective information feedback had better recognition performance. Furthermore, training on a larger dataset could further improve the recognition accuracy of the CNN recognition model.

Fault Feature Enhanced Extraction and Fault Diagnosis Method of Vibrating Screen Bearings

For mechanical equipment, bearings have a high incidence area of faults. A problem for bearings is that their fault characteristics include a vibrating screen exciter which is weak and thus easily covered in strong background noise, hence making the noise difficult to remove. In this paper, a noise reduction method based on singular value decomposition, improved by singular value’s unilateral ascent method (SSVD), and a fault feature enhancement method, i.e., variational mode decomposition, improved by revised whale algorithm optimization (RWOA-VMD), are proposed. These two methods are used in vibration signal processing with early faults of bearings having a vibrating screen and they have achieved significant application results. This paper also aims to construct a multi-modal feature matrix composed of energy entropy, singular value entropy, and power spectrum entropy, and then the early fault diagnosis of bearings of a vibrating screen exciter bearing is realized by using the proposed support vector machine, improved by the aquila optimizer algorithm (AO-SVM).

Dynamical analysis of a new chaotic system and its application in ADC

The improvement of Analog-to-Digital Converter (ADC) performance is crucial to improve the data quality of the signal acquisition system. Therefore, based on the dithering technology, combined with the chaotic system, the study designs and analyses a novel method to improve the Spurious-Free dynamic range (SFDR) of the ADC. First, a new five-dimensional chaotic system is proposed in this paper. The chaotic characteristics and dynamic behavior of the new system have been deeply analysed. The analysis methods mainly consist of the Lyapunov exponent, bifurcation diagram, power spectrum and sample entropy. The corresponding simulation model has been developed in Simulink, and the simulation results prove the reality and feasibility of the new chaotic system. Second, the random number homogenization universal algorithm is used to modify the amplitude of the chaotic sequences generated by the new chaotic system. The uniformity and correlation analysis prove that the Dither signal has strong uniformity and randomness. Third, a behaviour-level simulation model of the pipeline ADC is built; then, the narrowband, broadband and different amplitude Dither signals are added to verify the improvement effect for the dynamic performance of the ADC. The experimental results demonstrate that the designed method can improve the SFDR of the ADC by 10.37 dBc, which effectively eliminates the harmonic energy and improves the dynamic performance of the ADC.

Relationship among Electrical Signals, Chlorophyll Fluorescence, and Root Vitality of Strawberry Seedlings under Drought Stress

Drought area expansion has a great impact on the growth and development of plants. To contribute to the water management of strawberry, this work aims to study the chronological relationship between the electrical signals and representative physiological parameters of strawberry seedlings under drought stress. This study analyzed the characteristic variables of the electrical signals; physiological parameters under drought; and control treatments. Moreover, we compared the chronological sequence of the appearance of significant differences between drought and control treatment in terms of their physiological parameters and electrical signals. The results showed that with the increase of drought treatment, the time domain parameters (peak-to-peak value, standard deviation) and frequency domain parameters (spectral of central gravity, power spectrum entropy) of the drought-treated electrical signals showed significant differences from the control on Day 2 and Day 6, respectively (p &lt; 0.05). The root vitality of the drought treatment was significantly different from the control on Day 4 (p &lt; 0.05); the Fv/Fm and the SPAD were significantly different (p &lt; 0.05) on Day 7. Electrical signals first start to show a significant difference between drought and control treatment, followed by physiological parameters. Therefore, the electrical signal can be used as an early indicator of drought stress conditions. This will provide a scientific basis for the actual water management of strawberry seedlings. It also provides a methodological and theoretical basis for other studies analyzing the relationship between plant physiological parameters and electrical signals under other stress conditions.

Leakage identification in water pipes using explainable ensemble tree model of vibration signals

This paper proposes a method of an explainable ensemble tree model in an optimized feature space, which is based on the wave propagation model and the leakage noise mechanism. Specifically, the vibration signal is analyzed and the piecewise power spectrum entropy is proposed and used to construct the feature space.The Boruta algorithm is used for feature reduction; then, four ensemble tree models are applied to build leakage identification models. Furthermore, Shapley Additive explanation method is used to select the optimal feature space. In addition, four groups of experiments were designed with different aperture, and 13 features were obtained after dimensionality reduction with the measured distance as the variable, the XGBoost model with the highest accuracy was selected, and 7 features were obtained using SHAP. Finally, the performance of the methodology is evaluated with different pipeline leakage scenarios and different algorithms, and the results demonstrate its application capability in the field.