White Noise Research Articles

A novel speaker verification approach featuring multidomain acoustics based on the weighted city block Minkowski distance

AbstractAccess control is vital in interconnected environments like the Internet of Things, Industry 4.0, and smart connectivity, ensuring authorized access for security. Biometric‐based access, particularly speaker verification (SV), enhances security with unique vocal features, offering nonintrusive authentication with continuous monitoring. Single‐domain features prove insufficient in distinguishing similar traits, prompting latest SV advancements to adopt multidomain‐based speech features. This paradigm addresses the limitations of single‐domain features by amalgamating the merits of individual domains, establishing a cutting‐edge approach. It utilizes cepstral–frequency–time domain feature fusion, achieved via cepstral mean‐variance normalization for generalizability. The weighted city block Minkowski distance is proposed to compare reference and test speech templates. Parameters are computed based on the confusion matrix, template matching distance functions, dynamic acoustic conditions, and additive white Gaussian noise. A deep convolutional neural network classifier is assessed on open‐source LibriSpeech and Speaker in the Wild corpora, surpassing the current methodologies.

Response of MDOF nonlinear system with fractional derivative damping and driven by fractional Gaussian noise

The integration of fractional calculus into stochastic dynamics has introduced two innovative concepts, i.e., fractional derivative damping (FDD) and fractional Gaussian noise (fGn). To date, most studies on fractional stochastic dynamics have exclusively focused on either FDD or fGn, rather than concurrently exploring both. It is the first attempt for this paper to investigate a multi-degree-of-freedom (MDOF) nonlinear system with FDD and driven by fGn at the same time. Employing the generalized harmonic balance technique, FDD is equivalently decomposed into a quasi-linear restoring force and a quasi-linear damping force. Consequently, the original random Lagrangian system with FDD is transformed into the stochastically excited and dissipated Hamiltonian system. Utilizing the characteristic of the relatively flat power spectral density of fGn, it is approximated as wideband noise. This enables the application of the stochastic averaging method for quasi-integrable Hamiltonian system under wideband noise. Two detailed examples are carried out to provide the technical procedures and numerical verifications.

The acoustic change complex evoked by location-change sounds in the elderly

Objective We have shown that the acoustic change complex (ACC) can be elicited by changing the horizontal sound location in young individuals. In this study, we aimed to evaluate the application of ACC within the elderly and its relationship with behavioural results. Design The minimum audible angle (MAA), as well as onset cortical auditory evoked potentials (onset-CAEPs) and ACC elicited by the stimuli of location-change white noise (±45 to ±2 degrees) were recorded. Latencies and amplitudes were analysed using repeated-measures ANOVA. Pearson correlation analysis was conducted to examine the relationship between ACC and MAA. Study sample Ten older adults with normal hearing (NH) and twenty with presbycusis. Results The ACC was effectively elicited with angular variations in elderly participants. The onset-CAEP N1 latency, ACC N1’-P2’ amplitude, and N1’ latency were all associated with the angle shifts, with the N1’ latency being the most predictive factor for angle discrimination. The consistency between MAA and ACC made them complementary for the clinical evaluation of sound localisation. Conclusions The utilisation of ACC, evoked by location-change sounds, presented a promising clinical objective measure for evaluating sound localisation abilities in the elderly.

Remaining Useful Life Prediction for Power Storage Electronic Components Based on Fractional Weibull Process and Shock Poisson Model

For lithium-ion batteries and supercapacitors in hybrid power storage facilities, both steady degradation and random shock contribute to their failure. To this end, in this paper, we propose to introduce the degradation-threshold-shock (DTS) model for their remaining useful life (RUL) prediction. Non-homogeneous compound Poisson process (NHCP) is proposed to simulate the shock effect in the DTS model. Considering the long-range dependence and heavy-tailed characteristics of the degradation process, fractional Weibull process (fWp) is employed in the diffusion term of the stochastic degradation model. Furthermore, the drift and diffusion coefficients are constantly updated to describe the environmental interference. Prior to the model training, steady degradation and shock data must be separated, based on the three-sigma principle. Degradation data for the lithium-ion batteries (LIBs) and ultracapacitors are employed for model verification under different operation protocols in the power system. Recent deep learning models and stochastic process-based methods are utilized for model comparison, and the proposed model shows higher prediction accuracy.

Dynamic Research on the Collaborative Governance in Urban and Rural Black-Odorous Water: A Tripartite Stochastic Evolutionary Game Perspective

The issue of black-odorous water (BOW) represents a formidable challenge to the current aquatic ecosystems, and its governance exhibits characteristics of low efficiency, susceptibility to relapse, and fragmented management under the Central Environmental Protection Inspection, thereby emerging as a dynamically complex issue in the ecological governance of urban and rural settings. This study introduces Gaussian white noise to simulate environmental uncertainty and design a stochastic evolutionary game model encompassing the central government, local governments, and societal forces based on evolutionary game theory and classical governance theories and concepts. Numerical simulations are conducted to explore trajectories of the strategic evolution of various subjects influenced by numerous factors. Results indicate that under the environment of random disturbances, the strategies of the game subjects show significant fluctuations, but actively cultivating the subject’s initial willingness facilitates collaboration governance in inspection. Moreover, joint construction of a “belief system” by multi-subjects, the intensity of inspection interventions, the integration of heterogeneous resources, and effective punitive measures all influence the governance of BOW, but the efficiency of resource allocation should be considered throughout the governance process. Recommendations are made finally for collaborative governance of urban and rural BOW, promoting the sustainable development of the ecological environment.

Analyzing the influence of multiplicative white noise on optical solitons in birefringent fibers through the perturbed Gerdjikov–Ivanov model

Analyzing the influence of multiplicative white noise on optical solitons in birefringent fibers through the perturbed Gerdjikov–Ivanov model

Heartbeat-related spectral perturbation of electroencephalogram reflects dynamic interoceptive attention states in the trial-by-trial classification analysis

Attending to heartbeats for interoceptive awareness initiates distinct electrophysiological responses synchronized with the R-peaks of an electrocardiogram (ECG), such as the heartbeat-evoked potential (HEP). Beyond HEP, this study proposes heartbeat-related spectral perturbation (HRSP), a time–frequency map of the R-peak locked electroencephalogram (EEG), and explores its characteristics in identifying interoceptive attention states using a classification approach. HRSPs of EEG brain components specified by independent component analysis (ICA) were used for the offline and online classification of interoceptive states. A convolutional neural network (CNN) designed specifically for HRSP was applied to publicly available data from a binary-state experiment (attending to self-heartbeats and white noise) and data from our four-state classification experiment (attending to self-heartbeats, white noise, time passage, and toe) with diverse input feature conditions of HRSP. From the dynamic state perspective, we evaluated the primary frequency bands of HRSP and the minimal number of averaging epochs required to reflect changing interoceptive attention states without compromising accuracy. We also assessed the utility of group ICA and models for classifying HRSP in new participants. The CNN for trial-by-trial HRSP with actual R-peaks demonstrated significantly higher classification accuracy than HRSP with sham, i.e., randomly positioned, R-peaks. Gradient-weighted class activation mapping highlighted the prominent role of theta and alpha bands between 200–600 ms post-R-peak—features absent in classifications using sham HRSPs. Online classification benefits from employing a group ICA and classification model, ensuring reliable accuracy without individual EEG precollection. These results suggest HRSP’s potential to reflect interoceptive attention states, proposing transformative implications for clinical applications.

Significance testing for cross correlation: A critical examination of correlations between ENSO and GRACE-derived terrestrial water storage variabilities

The cross correlation has a wide range of applications in geophysical fields for measuring linear connections or relationships among physical quantities. Nonetheless, there remains a dearth of comprehensive discourse regarding its statistical significance testing, which is crucial for differentiating meaningful outcomes from those merely stemming from fortuity or pure randomness. Conventional theoretical methods for significance testing, commonly used in statistical analysis tools such as SPSS and MATLAB, are only applicable when dealing with idealized circumstances such as white noise. In discretionary application of these methods to analyze geophysical signals with, say, red noise may result in potentially unjustified conclusions. This study aims to develop a comprehensive approach based on the t-distribution within a rigorous statistical context, aiming to facilitate significance tests of cross correlation for general signals with specified time shifts or ranges. Extensive Monte Carlo experiments substantiate its robustness, thereby paving the way for accurate and expeditious identification of statistically (hence potentially physically) meaningful correlations in general. As an example, we examine critically the previously purported significant correlations between ENSO (El Niño Southern Oscillation) and global terrestrial water storage variations derived from the GRACE (Gravity Recovery and Climate Experiment) satellite mission, demonstrating that they are subject to questioning in the absence of complete significance testing.

Schrödinger-Hirota equation in birefringent fibers with cubic-quantic nonlinearity and multiplicative white noise in the ito sense: Nucci’s reductions and soliton solutions

This paper explores innovative solutions for the Stochastic Schrödinger-Hirota equation within the context of birefringent fibers with cubic-quintic nonlinearity, emphasizing incorporating multiplicative white noise in the Itô sense. Leveraging the Nucci reduction method, the study focuses on obtaining exact solutions, shedding light on the intricate interplay between quantum mechanics and stochastic processes. The Nucci reduction method is a powerful tool to facilitate the derivation of precise solutions, showcasing its efficacy in unravelling complex mathematical structures and providing valuable insights into the behaviour of quantum systems under the influence of diverse parameters. In addition, two effective and convenient procedures are employed to extract bright, dark, and unique soliton solutions, as well as their combination. Exploring these solutions contributes to a deeper understanding of the equation’s dynamics, particularly in real-world applications such as quantum optics and condensed matter physics. Additionally, this study incorporates graphical depictions of specific solutions to demonstrate the effect of white noise on solitons visually.

Predicting the incidence of rifampicin resistant tuberculosis in Yunnan, China: a seasonal time series analysis based on routine surveillance data

BackgroundRifampicin resistant tuberculosis (RR-TB) poses a growing threat to individuals and communities. This study utilized a seasonal autoregressive integrated moving average (SARIMA) model to quantitatively predict the monthly incidence of RR-TB in Yunnan Province which could guide government health administration departments and the centers for disease control and prevention (CDC) in preventing and controlling the RR-TB epidemic.MethodsThe study utilized routine surveillance reporting data from the infectious Disease Network Surveillance and Reporting System. Monthly incidence rates of RR-TB were collected from January 2019 to December 2022. A time series SARIMA model was used to predict the number of monthly RR-TB cases in Yunnan Province in 2023, and the model was validated using time series plots, seasonal and non-seasonal differencing, autocorrelation and partial autocorrelation analysis, and white noise tests.ResultsFrom 2019 to 2022, the incidence of RR-TB decreases as the incidence of all TB decreases (P < 0.05). There was no significant change in the proportion of RR-TB among all TB cases, which remained within 2.5% (P>0.05). The time series decomposition shows that it presented obvious seasonality, periodicity and randomness after being decomposed. Time series analysis was performed on the original series after 1 non-seasonal difference and 1 seasonal difference, the ADF test showed P < 0.05. According to ACF and PACF, the SARIMA (1, 1, 1) (1, 1, 0)12 model was chosen and statistically significant model parameter estimates (P < 0.05). The predicted seasonal trend of RR-TB incidence in 2019 to 2023 was similar to the actual data. The percentage accuracy in the prediction excesses 80% in 2019 to 2022 and is all within 95% CI. However there was a certain gap between the actual incidence and the predicted value in 2023, and the acutual incidence had increased by 12.4% compared to 2022. The percentage of accuracy in the prediction was only 70% in 2023.ConclusionsWe found the incidence of RR-TB was based on that of all TB in Yunnan. The SARIMA model successfully predicted the seasonal incidence trend of RR-TB in Yunnan Province in 2019 to 2023, but the prediction precision could be influenced by factors such as new infectious disease outbreaks or pandemics, social issues, environmental challenges or other unknown risks. Hence CDCs should pay special attention to the post epidemic effects of new infectious disease outbreaks or pandemics, carry out monitoring and early warning, and better optimize disease prediction models.

Effects of Auditory and Visual White Noise on Oculomotor Inhibition in Children With Attention-Deficit/Hyperactivity Disorder: Protocol for a Crossover Study.

In attention-deficit/hyperactivity disorder (ADHD), poor inhibitory control is one of the main characteristics, with oculomotor inhibition impairments being considered a potential biomarker of the disorder. While auditory white noise has demonstrated the ability to enhance working memory in this group, visual white noise is still unexplored and so are the effects of both types of white noise stimulation on oculomotor inhibition. This crossover study aims to explore the impact of auditory and visual white noise on oculomotor inhibition in children with ADHD and typically developing (TD) children. The study will investigate the impact of different noise levels (25% and 50% visual, 78 dB auditory), and performance will be evaluated both with and without noise stimulation. We hypothesize that exposure to white noise will improve performance in children with ADHD and impair the performance for TD children. Memory-guided saccades and prolonged fixations, known for their sensitivity in detecting oculomotor disinhibition in ADHD, will be used to assess performance. Children diagnosed with ADHD, withdrawing from medication for 24 hours, and TD children without psychiatric disorders were recruited for the study. Data collection was initiated in October 2023 and ended in February 2024. A total of 97 participants were enrolled, and the first results are expected between September and November 2024. This study will examine whether cross-modal sensory stimulation can enhance executive function, specifically eye movement control, in children with ADHD. In addition, the study will explore potential differences between auditory and visual noise effects in both groups. Our goal is to identify implications for understanding how noise can be used to improve cognitive performance. ClinicalTrials.gov NCT06057441; https://clinicaltrials.gov/study/NCT06057441. DERR1-10.2196/56388.

An accurate paradigm for denoising degraded ultrasound images based on artificial intelligence systems.

Ultrasound images are susceptible to various forms of quality degradation that negatively impact diagnosis. Common degradations include speckle noise, Gaussian noise, salt and pepper noise, and blurring. This research proposes an accurate ultrasound image denoising strategy based on firstly detecting the noise type, then, suitable denoising methods can be applied for each corruption. The technique depends on convolutional neural networks to categorize the type of noise affecting an input ultrasound image. Pre-trained convolutional neural network models including GoogleNet, VGG-19, AlexNet and AlexNet-support vector machine (SVM) are developed and trained to perform this classification. A dataset of 782 numerically generated ultrasound images across different diseases and noise types is utilized for model training and evaluation. Results show AlexNet-SVM achieves the highest accuracy of 99.2% in classifying noise types. The results indicate that, the present technique is considered one of the top-performing models is then applied to real ultrasound images with different noise corruptions to demonstrate efficacy of the proposed detect-then-denoise system. RESEARCH HIGHLIGHTS: Proposes an accurate ultrasound image denoising strategy based on detecting noise type first. Uses pre-trained convolutional neural networks to categorize noise type in input images. Evaluates GoogleNet, VGG-19, AlexNet, and AlexNet-support vector machine (SVM) models on a dataset of 782 synthetic ultrasound images. AlexNet-SVM achieves highest accuracy of 99.2% in classifying noise types. Demonstrates efficacy of the proposed detect-then-denoise system on real ultrasound images.

Enhancing battery pack safety against cone impact using machine learning techniques and Gaussian noise

The increasing prevalence of electric vehicles underscores the need for enhanced battery pack safety, particularly against impacts that can lead to thermal runaway and fires. This study investigates the mechanical and thermal characteristics of battery packs subjected to cone impact on the lower part. Utilizing finite element model (FEM) simulations, we examined the effects of top radius, shell condition, velocity, and angle on the battery pack's response. Five machine learning (ML) techniques were employed to predict the battery pack's behavior under impact, with training data generated from a well-planned Latin hypercube experiment based on FEM dynamic simulations. The accuracy and robustness of the ML models were evaluated under various scenarios, including the introduction of Gaussian noise. Among the models tested, BESA-ELMM (Bald eagle search algorithm-Extreme learning machine model) demonstrated exceptional speed, making it suitable for real-time assessments, while WOA-SVMM (whale optimization algorithm-Support vector machine model) exhibited superior resilience and accuracy, particularly under noisy conditions. Both models, along with the other ML techniques, showed significant effectiveness in predicting the mechanical responses of battery packs to impact. Our findings indicate that ML approaches are highly efficient in evaluating the mechanical effects on battery packs, providing crucial insights for designing safer and more durable battery packs. This study contributes to the advancement of battery safety by demonstrating the potential of integrating ML techniques with FEM simulations to enhance the resilience and impact resistance of battery packs in electric vehicles.

Optimizing Mean Fragment Size Prediction in Rock Blasting: A Synergistic Approach Combining Clustering, Hyperparameter Tuning, and Data Augmentation

Accurate estimation of the mean fragment size is crucial for optimizing open-pit mining operations. This study presents an approach that combines clustering, hyperparameter optimization, and data augmentation to enhance prediction accuracy using the Xtreme Gradient Boosting (XGBoost) regression model. A dataset of 110 blasts was divided into 97 blasts for training and testing, whereas a separate set of 13 new, unseen blasts was used to evaluate the robustness and generalization of the model. Hierarchical Agglomerative (HA) and K-means clustering algorithms were used, with HA clustering providing a higher cluster quality. To address class imbalance and improve model generalization, a synthetic minority oversampling technique for regression with Gaussian noise (SMOGN) was employed. Hyperparameter tuning was conducted using HyperOpt by comparing Random Search (RS) with the Advanced Tree-structured Parzen Estimator (ATPE). The combination of ATPE with HA clustering and SMOGN in an expanded search space produced the best results, achieving superior prediction accuracy and reliability. The proposed HAC1-SMOGN model, which integrates HA clustering, ATPE tuning, and SMOGN augmentation, achieved a mean squared error (MSE) of 0.0002 and an R2 of 0.98 on the test set. This study highlights the synergistic benefits of clustering, hyperparameter optimization, and data augmentation in enhancing machine learning models for regression tasks, particularly in scenarios with class imbalance or limited data.

Application of Odd-Order Derivatives in Fourier Transform Nuclear Magnetic Resonance Spectroscopy toward Quantitative Deconvolution.

When Fourier transform (FT) spectrum peaks are overlapped, primary maxima of odd-order derivatives can be used to evaluate their independent intensities. We studied the feasibility of higher odd-order derivatives on Lorentzian peak shape and magnitude peak shape. Simulation studies for FT nuclear magnetic resonance (NMR) spectroscopy demonstrated good results toward quantitative deconvolution of overlapping FT spectrum peaks. Although it is not so desirable to deconvolute special line shapes such as Gaussian, Voigt, and Tsallis profiles, the odd-order derivatives exhibit a bright future compared to even-order derivatives. An application example of practical NMR spectroscopy with ethylbenzene isomers is presented. White Gaussian noises were added to the simulated spectra at two different signal-to-noise ratios (20 and 40). Kauppinen's denoising and smoothing algorithms can effectively remove interference of the noise and help to have good deconvoluting results using the odd-order derivatives. We compared features of our approach with popular deconvolution sharpening algorithms and conducted a comparison study with Kauppinen's Fourier self-deconvolution. Our approach has a better dynamic range of peak intensities and is not sensitive to the sampling rates. Other common deconvolution methods are also discussed briefly.

Robust fixed‐point Kalman smoother for bilinear state‐space systems with non‐Gaussian noise and parametric uncertainties

SummaryKalman smoother is an effective algorithm to estimate the state of the dynamic systems with Gaussian noise. However, when the system is affected by non‐Gaussian noise, the traditional Kalman smoother may suffer severe performance degradation, since it is derived from the minimum mean square error criterion. By introducing the maximum correntropy criterion, which accounts for all higher order moments and has the ability to resist non‐Gaussian noise, this article studies the state estimation problem of the bilinear state‐space system with non‐Gaussian noises and parametric uncertainties. The bilinear system with parametric uncertainties is transformed into a linear time‐varying system, and a robust fixed‐point Kalman filter algorithm is derived based on the Cauchy kernel‐based correntropy criterion. To improve the state estimation accuracy, a Cauchy kernel‐based fixed‐point Kalman smoother (CK‐FPKS) algorithm is presented by introducing the backward smoothing. Simulation results show the effectiveness of the proposed algorithm.

Enhancing dementia risk screening with GAN-synthesized periodontal examination and general blood test data.

This study aimed to investigate the effectiveness of data augmentation to improve dementia risk prediction using machine learning models. Recent studies have shown that basic blood tests are cost-effective in predicting cognitive function. However, developing models that address various conditions poses challenges due to constraints associated with blood test results and cognitive assessments, including high costs, limited sample sizes, and missing data from tests not performed in certain facilities. Despite being often limited by small sample sizes, periodontal examination data have also emerged as a cost-effective screening tool. To address these challenges, this study explored the effectiveness of data augmentation using the Synthetic Minority Over-sampling Technique for Regression with Gaussian noise (SMOGN), a Generative Adversarial Network (GAN), and a Conditional Tabular GAN (CTGAN) on periodontal examination and blood test data. The datasets included parameters such as cognitive assessment results from the Mini-Mental State Examination (MMSE), demographic characteristics, periodontal examination data, and blood test results. Linear regression models, random forests, and deep neural networks were used to evaluate the effectiveness of the synthesized data. This study used measured data from 108 participants and the synthesized data generated from the measured data. External validity was evaluated using a different dataset of 41 participants with missing items. The results suggested that normal GANs have the advantage of investigating models in data diversity, whereas CTGANs preserve the data structure and linear relationships in tabular data from the measured data, which drastically improves linear regression models. Importantly, by interpolating sparse areas in the distribution, such as age, the synthesized models maintained prediction accuracy for test data with extreme inputs. These findings suggest that GAN-synthesized data can effectively address regression problems and improve dementia risk prediction.

CMBFSCNN: Cosmic Microwave Background Polarization Foreground Subtraction with a Convolutional Neural Network

In our previous study, we introduced a machine learning technique, namely Cosmic Microwave Background Foreground Subtraction with Convolutional Neural Networks (CMBFSCNN), for the removal of foreground contamination in cosmic microwave background (CMB) polarization data. This method was successfully employed on actual observational data from the Planck mission. In this study, we extend our investigation by considering the CMB lensing effect in simulated data and utilizing the CMBFSCNN approach to recover the CMB lensing B-mode power spectrum from multifrequency observational maps. Our method is first applied to simulated data with the performance of the CMB-S4 experiment. We achieve reliable recovery of the noisy CMB Q (or U) maps with a mean absolute difference of 0.016 ± 0.008 μK (or 0.021 ± 0.002 μK) for the CMB-S4 experiment. To address the residual instrumental noise in the foreground-cleaned map, we employ a “half-split maps” approach, where the entire data set is divided into two segments sharing the same sky signal but having uncorrelated noise. Using cross-correlation techniques between two recovered half-split maps, we effectively reduce instrumental noise effects at the power spectrum level. As a result, we achieve precise recovery of the CMB EE and lensing B-mode power spectra. Furthermore, we also extend our pipeline to full-sky simulated data with the performance of the LiteBIRD experiment. As expected, various foregrounds are cleanly removed from the foregrounds contamination observational maps, and recovered EE and lensing B-mode power spectra exhibit excellent agreement with the true results. Finally, we discuss the dependency of our method on the foreground models.

Corrective maintenance minimizing expected mission losses in shock exposed multistate production-storage systems

Production-storage systems are often subject to random external shocks such as storm weather and electromagnetic interference. However, most of the existing models failed to take the shock effects into consideration. This paper extends the state of the art by modeling random shocks and optimizing their mitigating corrective maintenance policy (CMP) that defines the condition triggering repair actions to restore the production subsystem to a higher performance level. The CMP can greatly impact the amount of unsupplied product as well as the maintenance and operation costs, all contributing to the expected mission losses (EML). This paper contributes by modeling and optimizing the CMP to minimize the EML. The proposed solution encompasses a new numerical algorithm that evaluates the EML of the considered production-storage system under a given CMP and the genetic algorithm realized for solving the CMP optimization problem. The proposed model is demonstrated using a case study of a multistate power generation system subject to voltage surges due to storm weather. Based on the investigation of effects of several model parameters (shock rate, storage capacity, initial amount of product in the storage, cost of unsupplied product) on the EML and optimization solutions, useful and insightful management recommendations are provided.

A 1D-CNN model for the early detection of citrus Huanglongbing disease in the sieve plate of phloem tissue using micro-FTIR

Among the most frequently diagnosed diseases in citrus, citrus Huanglongbing disease has caused severe economic losses to the citrus industry worldwide since there is no curable method and it spreads quickly. As callose accumulation in phloem is one of the early response events to Asian species Candidatus Liberibacter asiaticus (CLas) infection, the dynamic perception of the sieve plate region can be used as an indicator for the early diagnosis of citrus HLB disease. In this study, one-dimensional convolutional neural network (1D-CNN) models were established to achieve early detection of HLB disease based on spectral information in the sieve plate region using Fourier transform infrared microscopy (micro-FTIR) spectrometer. Partial least squares regression (PLSR) and the least squares support vector machine regression (LS-SVR) models are used for the prediction of callose based on the micro-FTIR information in the sieve plate region of the citrus midrib. Furthermore, an improved data augmentation method by superimposing Gaussian noise was proposed to expand the spectral amplitude. The proposed method has achieved 98.65 % classification accuracy, which was higher than that of other traditional algorithms such as the logistic model tree (LMT), linear discriminant analysis (LDA), Bayes (BS), support vector machine (SVM) and k-nearest neighbors (kNN), and also than that of the molecular detection qPCR (Quantitative real-time polymerase chain reaction) method. Finally, based on the established early detection model with laboratory samples, it can also be used to detect the citrus HLB in complex field samples by using model updating methods, and the overall detection accuracy of the model reached 91.21 %. Our approach has potential for the early diagnosis of citrus HLB disease from the microscopic scale, which would provide useful and precise guidelines to prevent and control citrus HLB disease.