Statistical Characteristics Research Articles

Exploring EEG-Based Biomarkers for Improved Early Alzheimer's Disease Detection: A Feature-Based Approach Utilizing Machine Learning

This paper presents a comprehensive investigation into Electroencephalogram (EEG) signal processing and analysis techniques aimed at enhancing early diagnosis methods for Alzheimer's Disease (AD). Leveraging a dataset that has EEG data of individuals diagnosed with Mild Cognitive Impairment (MCI), AD, Healthy Controls, and the study explores Preprocessing Methods and Feature Extraction Techniques, with machine learning model notably Support Vector Machines (SVM).In the preprocessing phase, a combination of high pass, lowpass, Savitzky–Golay, and median filters are applied, informed by a comprehensive review of filter comparison literature. Feature extraction encompasses three primary categories: ‘Statistical, ‘Frequency Domain’ and ‘Time Domain’. The scope of this work is to explore features in all these three domains and build SVM based model for efficient classification. In our investigation, we achieved a categorization accuracy of 92% through the utilization of statistical features. Employing time domain features resulted in an accuracy of 87%, while frequency domain features also yielded an 87% accuracy rate in our study. The primary objective of this study is that it aims to enhance early AD diagnosis through advanced EEG signal processing and machine learning techniques, focusing on preprocessing methods, feature extraction, and classification accuracy.

Using Decision Tree With First and Second-Order Statistical Feature Extraction for Classification of Lung Cancer

<p>The classification of CT-Scan images on images with lung cancer and normal lung has been done by improving the image quality of the median and Gabor filters, extraction of first and second-order statistical features, and decision tree classification. The data used comes from LIDC-IDRI as much as 100 training data and 40 test data. The median filter removes noise without removing edges in the image. A Gabor filter is used to facilitate texture analysis on the image. At the feature extraction stage, statistical variations of the first order, second order statistics and the merging of first and second-order statistics. The best results obtained at the testing stage are program designs with variations of feature extraction combining first and second-order statistics. The level of accuracy obtained is 97.5%, with a sensitivity of 100% and a specificity of 95%.</p>

FACSNet: Forensics aided content selection network for heterogeneous image steganalysis

The main goal of image steganalysis, as a technique of confrontation with steganography, is to determine the presence or absence of secret information in conjunction with the specific statistical characteristics of the carrier. With the development of deep learning technology in recent years, the performance of steganography has been gradually enhanced. Especially for the complex reality environment, the image content is mixed and heterogeneous, which brings great challenges to the practical application of image steganalysis technology. In order to solve this problem, we design a forensics aided content selection network (FACSNet) for heterogeneous image steganalysis. Considering the heterogeneous situation of real images, a forensics aided module is introduced to pre-categorise the images to be tested, so that the network is able to detect different categories of images in a more targeted way. The complexity of the images is also further analysed and classified using the content selection module to train a more adapted steganalyser. By doing this, the network is allowed to achieve better performance in recognising and classifying the heterogeneous images for detection. Experimental results show that our designed FACSNet is able to achieve excellent detection performance in heterogeneous environments, improving the detection accuracy by up to 7.14% points, with certain robustness and practicality.

Application of European fine-grid numerical forecasting products for deviation analysis along transmission lines

Abstract Aiming at the current problem of lack of objective prediction products for deviation prediction along transmission lines, a deviation prediction model is established based on the historical statistical characteristics of deviation of transmission lines by using European fine-grid numerical prediction products and actual observation data. The model is combined with the operation specification of transmission lines, and the European fine-grid numerical prediction product is revised by using the normalization method to obtain a more accurate deviation prediction product. By analyzing the differences between the European fine-grid numerical prediction product and the actual observation data, the deviation prediction software is established, which can effectively improve the prediction accuracy and stability of the deviation situation of transmission lines. The results show that the software has good prediction performance and can effectively reduce the false alarm rate and omission rate of transmission line deviation prediction and improve the reliability and stability of the power grid.

Color image watermarking using vector SNCM-HMT

An image watermarking scheme is typically evaluated using three main conflicting characteristics: imperceptibility, robustness, and capacity. Developing a good image watermarking method is challenging because it requires a trade-off between these three basic characteristics. In this paper, we proposed a statistical color image watermarking based on robust discrete nonseparable Shearlet transform (DNST)-fast quaternion generic polar complex exponential transform (FQGPCET) magnitude and vector skew-normal-Cauchy mixtures (SNCM)-hidden Markov tree (HMT). The proposed watermarking system consists of two main parts: watermark inserting and watermark extraction. In watermark inserting, we first perform DNST on R, G, and B components of color host image, respectively. We then compute block FQGPCET of DNST domain color components, and embed watermark signal in DNST-FQGPCET magnitudes using multiplicative approach. In watermark extraction, we first analyze the robustness and statistical characteristics of local DNST-FQGPCET magnitudes of color image. We then observe that, vector SNCM-HMT model can capture accurately the marginal distribution and multiple strong dependencies of local DNST-FQGPCET magnitudes. Meanwhile, vector SNCM-HMT parameters can be computed effectively using variational expectation–maximization (VEM) parameter estimation. Motivated by our modeling results, we finally develop a new statistical color image watermark decoder based on vector SNCM-HMT and maximum likelihood (ML) decision rule. Experimental results on extensive test images demonstrate that the proposed statistical color image watermarking provides a performance better than that of most of the state-of-the-art statistical methods and some deep learning approaches recently proposed in the literature.

A two-stage deep learning architecture for detection global coastal and offshore submesoscale ocean eddy using SDGSAT-1 multispectral imagery

Submesoscale ocean eddies are essential oceanic phenomenon that control and influence the ocean energy cascade. Most existing eddy detection methods rely on low-resolution satellite altimeter data, which fail to capture submesoscale ocean features and oceanographic phenomena in shallow water. Introducing high-resolution multispectral data can alleviate these problems, yet it has been largely overlooked. A generalized and efficient deep learning architecture that combines developments in deep learning with Sustainable Development Goals Science Satellite 1 (SDGSAT-1) multispectral data from earth observations offers a potential pathway for more fine detection of ocean eddies. Considering that oceanic eddy exhibits spatially sparse characteristics on high-resolution remote sensing scenes, the oceanic eddy detection (OED) model suitable for global coastal and offshore regions is divided into two stages: eddy information judgment and eddy position determination. Correspondingly, SDGSAT-1 multispectral data from November 2021 to December 2022 were carried out to construct two submesoscale eddy datasets for training and testing each stage model. The union validation of multiple metrics demonstrates that the proposed OED model and its stage models achieve state-of-the-art (SOTA) performance, especially in optically complex coastal and offshore waters. We applied the model to real-world scenes captured by SDGSAT-1 in 2023, and found that the detected results were mainly located at the water depth below 200 m. The authenticity of the recognition results is validated using sea surface chlorophyll concentration, temperature, and topography data, indicating that the OED model has achieved remarkable effectiveness under various sea conditions. In addition, the temporal distributions and statistical characteristics of detected submesoscale eddies are analyzed over an extended period (November 2021 to November 2023). Finally, HISEA-2, Landsat-9, and Sentinel-2 served as testing grounds to validate the generalization of the proposed methodology, with experimental results demonstrating that the OED model possesses significant developmental potential for multi-source remote sensing data. This paper presents a comprehensive deep learning framework for the global-scale detection of submesoscale eddies and underscores the pivotal role of high-resolution multispectral imagery as an innovative data source for global coastal and offshore eddy identification.

Development of mathematical models of power consumption at coal plants

The object of research is coal enterprises where powerful electrical equipment is used (underground installations up to 3000 kW, tunneling complexes of 500–1500 kW, technological complexes of 6–10/0.4 kV, etc.). The deficit of generated capacities, caused by growing energy consumption, can be reduced by regulating power consumption modes. The relevance of this issue is determined by the need to conduct a research of the electricity consumption system, to determine the qualitative and quantitative characteristics of electricity consumption using mathematical models. The lack of mathematical models makes it difficult to analyze energy intensity and consumption modes of each technological operation in the overall balance of electricity consumption of coal enterprises. The article considers the structure and classification of the main technological groups of energy consumers, the development of mathematical models for each type of load modes, as well as a generalized model of electricity consumption of coal enterprises, with the use of mathematical apparatus of probability theory and mathematical statistics. As a result of the work, mathematical models of the electricity consumption process for the main technological groups and for models of daily electricity consumption of coal enterprises as a whole were developed, and it was also established that technological objects of electricity consumption are divided into three different values, in terms of power consumption modes: constant, uniform and pulse. For each class of consumers their statistical characteristics were obtained. The work results can be applied for managing power consumption modes of coal enterprises

A Novel Approach for Glaucoma Classification by Wavelet Neural Networks Using Statistical and Graph-Based Features of Qualitatively Improved Images

A Novel Approach for Glaucoma Classification by Wavelet Neural Networks Using Statistical and Graph-Based Features of Qualitatively Improved Images

A Study on the Impact of Overtaking Lane-Changing Behaviour in Expressway Interchange Weaving Areas

This study investigates the overtaking lane-changing (OLC) behaviour in expressway interchange weaving areas, aiming to analyse these behaviours’ causes and potential impacts. Field data are utilised to analyse the statistical characteristics of lane-changing points and spatio-temporal utilisation in weaving areas. A modified NS model, which considers the distribution pattern of vehicle speeds, and a rigid lane-changing rule based on Gaussian distribution are proposed. Additionally, a cellular automaton simulation model is constructed to quantify the influence of OLC behaviour on traffic efficiency and spatio-temporal utilisation based on simulated data. The findings indicate that the imbalanced distribution of lane-changing points and spatio-temporal utilisation in weaving segments, caused by rigid lane-changing behaviour, is an objective factor that triggers OLC behaviour. When the traffic volume in weaving areas ranges from 500 to 1,100 pcu/5 min and the proportion of OLC behaviour is between 0.35 and 0.7, the behaviour will significantly enhance the average vehicle speeds of the outermost lane of the main road and normal rigid lane-changing (NRLC) vehicles, with increases of up to 48% and 51%, respectively. Moreover, OLC behaviour also improves the balance of spatio-temporal utilisation in weaving areas and reduces the average spatio-temporal utilisation. This study clarifies the positive impact of OLC behaviour on expressway interchange weaving areas and provides new research ideas for enhancing the efficiency of these areas.

Features of statistics of visits to physical sites using the example of the scientific and educational portal “Great Russian Encyclopedia” and the website of the journal Uspekhi Fizicheskikh Nauk

On February 13, 2024, the 99th anniversary of the “Great Russian Encyclopedia” (GRE) (the successor of the “Great Soviet Encyclopedia”) was celebrated. However, it was only in 2020 that work began on the scientific and educational GRE portal, which was launched in test mode on May 26, 2022 (https://bigenc.ru/). By the editorial staff of “Physical Sciences”, to date, about 2,000 articles written by outstanding physicists and selected by the representative Editorial Board have been posted on the portal. The partners of the portal are reputable scientific and educational organizations: the Russian Academy of Science (RAS), Lomonosov Moscow State University (MSU), other leading universities of the Russian Federation, and the Russian Academy of Education. The priorities of the GRE portal are reliability and accessibility. The paper presents statistics of visits to the GRE portal over the past two years. Another important electronic resource dedicated to the physical sciences and therefore analyzed jointly with the editorial board of the GRE “Physical Sciences” is the journal Uspekhi Fizicheskikh Nauk (UFN). The first issue of the UFN was published in April 1918, and the UFN website (www.ufn.ru) was opened on December 26, 1994. Since 1995, there have been statistics of visits to the UFN website, which, for the first time, allowed the UFN Editorial Board to find out how many readers it has, who they are, where they come from, what their interests and preferences are? By 2016, DOI was assigned to the entire archive of articles from the UFN in both Russian and English. By April 2024, 1075 issues of the UFN containing 11,819 articles (cited 164,216 times, data collected by DOI) written by 8,799 authors were posted on the UFN website, and 405,365,547 times visited the semantic pages of the site. Statistics of visits to the UFN website and its features in recent years will be covered in this article.The statistics of visits to the GRE Portal and the UFN website demonstrate the growing society’s request for reliable, time-tested information supported by the reputation of the editorial board and publishing houses.

Analysis of the power during machining of Inconel 718 for different geometrical profiles and the development of power prediction models using multisensor data

This article presents analyses and prediction of machining power during end milling of Inconel 718 for different geometric features namely angular slot, half slot, square pocket, rectangular pocket, and blind hole. The experimental study revealed that among the machining features examined, angular slot required the highest specific cutting energy, while blind holes consumed the least, across different machining conditions. A 40% increase in cutting speed raised specific cutting energy by 4–9%, while a similar increase in feed rate lowered specific cutting energy by 40–44% across all profiles. Doubling depth of cut reduced specific cutting energy by 50% for angular slots, half slots, square pockets, and rectangular pockets, but increased it for blind holes. Power prediction models were developed using multisensor data, employing two machine learning and two deep learning architectures. The performance of the four power prediction models was compared for all geometric profiles using both raw data and statistical feature data extracted from machining signals from force dynamometer, accelerometer, and acoustic emission (AE) sensors. Long–Short-Term Memory model outperformed other models in case of raw data for all geometric profiles. The Random Forest Regression method consistently fared better for power predictions models developed based on feature-extracted data. Predictive models trained without AE sensor data performed better than those trained with AE.

Cooperative Spacing Control of Vehicle Platoon via Relative Output Feedback Considering Analog Fading Networks

ABSTRACTThe influence of analog fading channels on platoon control performance is studied via relative output feedback. The main goal is to determine the existence of a distributed output feedback controller capable of achieving mean square stability (MSS) for the underlying vehicle platoon systems over analog fading channels. First, the conditions, closely associated with the statistical characteristics of fading channels, for achieving platoon MSS are derived for three cases: undirected information flow (UIF) topology with identical fading channels, balanced directed information flow (BDIF) topology with identical fading channels, and general information flow topology (IFT) with nonidentical fading channels, respectively. These conditions explicitly reveal how the statistical characteristics of fading channels and IFT jointly affect vehicular stability. Second, in order to mitigate the impact of fading channels on platoon MSS, some feasible dynamic observer‐based controllers by using the relative output feedback, are proposed for each one of the former two situations by solving the corresponding modified Riccati inequalities (MRIs); and in the last situation, by employing edge Laplacian to model the vehicle platoon dynamics, a sufficient condition based on the solution of an LMI, and a feasible state‐based controller based on the solution of an MRI, are provided. Finally, simulations are carried out to compare three distinct fading channels, namely the Nakagami channel, Rician channel, and Rayleigh channel. The outcomes substantiate the superior and effective performance of the implemented control methods in guaranteeing the platoon MSS.

Boosting the reconstruction performance of 3D Multi-porous media using double generative adversarial networks

With the continuous improvement of mathematical modeling technology, reconstructing the three-dimensional structure of media from two-dimensional reference images has become an important research method for the three-dimensional modeling of multi-porous media. Deep-learning-based methods are currently popular and form the focus of this research field. However, the performance of deep learning in reconstructing the three-dimensional structure of media from two-dimensional reference images still requires improvement. To enhance the diversity and generalization of network-generated three-dimensional models, this study proposed a preprocessing method that correlated two-dimensional reference images with Gaussian noise, a three-orthogonal random section constraint method, and a dual generative adversarial network (DGAN)-based model. Multiple sets of core samples, a set of building materials, and a set of battery-material samples were used to verify the performance of the proposed network. Both intuitive morphological and statistical feature comparisons showed that the DGAN model solved the problem of insufficient diversity and generalization when reconstructing three-dimensional porous media from a single image using deep-learning-based methods. The morphological and statistical features of the reconstructed three-dimensional structure also exhibited good consistency with the reference two-dimensional image, and the training efficiency of the network was greatly improved.

In silico aquatic toxicity prediction of chemicals toward Daphnia magna and fathead minnow using Monte Carlo approaches

The fast-increasing use of chemicals led to large numbers of chemical compounds entering the aquatic environment, raising concerns about their potential effects on ecosystems. Therefore, assessment of the ecotoxicological features of organic compounds on aquatic organisms is very important. Daphnia magna and Fathead minnow are two aquatic species that are commonly tested as standard test organisms for aquatic risk assessment and are typically chosen as the biological model for the ecotoxicology investigations of chemical pollutants. Herein, global quantitative structure–toxicity relationship (QSTR) models have been developed to predict the toxicity (pEC(LC)50) of a large dataset comprising 2106 chemicals toward Daphnia magna and Fathead minnow. The optimal descriptor of correlation weights (DCWs) is calculated using the notation of simplified molecular input line entry system (SMILES) and is used to construct QSTR models. Three target functions, TF1, TF2, and TF3 are utilized to generate 12 QSTR models from four splits, and their statistical characteristics are also compared. The designed QSTR models are validated using both internal and external validation criteria and are found to be reliable, robust, and excellently predictive. Among the models, those generated using the TF3 demonstrate the best statistical quality with R 2 values ranging from 0.9467 to 0.9607, Q 2 values ranging from 0.9462 to 0.9603 and RMSE values ranging from 0.3764 to 0.4413 for the validation set. The applicability domain and the mechanistic interpretations of generated models were also discussed.

Residual post-infarct myocardial inflammation detected by 68Ga-DOTATATE PET/MRI predicts long-term adverse cardiac remodelling

Abstract Background Maladaptive inflammatory responses are associated with adverse cardiac remodelling after myocardial infarction (MI), but clinical methods for detecting residual myocardial inflammation post-MI are lacking. Purpose To investigate somatostatin receptor subtype 2 (SST2) positron emission tomography (PET)/magnetic resonance imaging (MRI) using 68Ga-DOTATATE after MI. Methods In a prospective observational cohort study, infarct-related myocardial inflammation detected by 68Ga-DOTATATE PET at 2wk and 3mo post-MI was compared with MRI characteristics including left ventricular (LV) volumetric changes at 1yr, as well circulating immune cell phenotyping and serum proteomic markers. Patients with a prior history of MI or heart failure were excluded. Histological SST2 expression was assessed in myocardial biopsies. Results 38 participants (mean age 60 [SD 9] years; 84% male) with recent MI were enrolled, of whom 58% had an ST-segment elevation MI. Mean peak Troponin I was 16,665 (range 408 to >25,000) ng/L and mean post-infarct LV ejection fraction was 51 (SD 9) %. 68Ga-DOTATATE maximum standardized uptake values (SUVmax) at 10 (SD 4) days accurately localised infarcted myocardial segments defined by late-gadolinium enhancement MRI (LGE; Fig. 1); were 14.2% higher in akinetic/hypokinetic vs. normo-kinetic segments (p<0.0001); and were correlated both with peak segmental strain (r=0.47, p=0.003) and segmental T1 values (r=0.51, p=0.02). Mean infarct SUVmax was 19.7% lower on repeat PET/MRI after a mean 102 (SD 22) days (p<0.0001), and this change was in keeping with parallel reductions in T2-weighted oedema signal on MRI and serum biomarkers of cardiac injury and systemic inflammation. Residual inflammation assessed by mean infarct SUVmax at 3mo was correlated with ΔLV indexed end-diastolic volume at 369 (SD 14) days, after adjustment for baseline infarct size and other clinical variables (p=0.038). The 3mo:2wk ratio of mean infarct SUVmax was an even stronger predictor of adverse myocardial remodelling (p=0.0025). Circulating SST2+ classical monocytes were correlated with infarct 68Ga-DOTATATE signal (r=0.47, p=0.02), and SST2 was co-expressed with CD68+ macrophages in inflamed myocardial specimens of patients with recent MI and ischaemic heart failure. After statistical feature selection and multiple comparisons adjustments, among the blood markers associated with 3mo:2wk infarct SUVmax was CCL25, a chemokine involved in macrophage recruitment which has been implicated in adverse cardiac remodelling. Conclusions Here, in the first prospective clinical study of serial SST2 PET/MRI after MI, we show that 68Ga-DOTATATE can identify and track resolving infarct-related myocardial inflammation. Moreover, residual inflammation detected by 68Ga-DOTATATE is associated with long-term adverse myocardial remodelling and could provide a potential future imaging biomarker to help stratify high-risk patients for emerging immunomodulatory therapies.Figure 1.68Ga-DOTATATE PET-MRI after MI

Enhanced Hessian locally linear embedding method for rolling bearing fault diagnosis based upon novel variational mode decomposition

Due to the plenty of redundant information contained in the fault feature sets of the original vibration signals of rolling bearings, the diagnostic accuracy is reduced and computational complexity is increased, making it very difficult to achieve accurate and fast fault recognition. So as to address the hard issue, this article develops an Enhanced Hessian Locally Linear Embedding (EHLLE) method for rolling bearing fault diagnosis based upon Novel Variational Mode Decomposition (NVMD). Firstly, NVMD method is utilized to denoise sample vibration signals and the sensitive modes containing main fault information are obtained. Secondly, some time-domain and frequency-domain statistical features are used to construct sample high-dimensional features, the dimensionality of which is reduced by EHLLE. Ultimately, K-Means algorithm is employed to cluster the low-dimensional features, which are utilized to train Support Vector Machine (SVM), and then the trained SVM is applied to the recognition of testing sample low-dimensional features. Two experiments of rolling bearing fault diagnosis demonstrate the effectiveness of NVMD-EHLLE method. Additionally, the superiority of the developed method is verified by comparing with other three typical methods.

Observation of Two-Dimensional Dam Break Flow and a Gaseous Phase of Solitons in a Photon Fluid.

We report the observation of a two-dimensional (2D) dam break flow of a photon fluid in a nonlinear optical crystal. By precisely shaping the amplitude and phase of the input wave, we investigate the transition from one-dimensional (1D) to 2D nonlinear dynamics. We observe wave breaking in both transverse spatial dimensions with characteristic timescales determined by the aspect ratio of the input box-shaped field. The interaction of dispersive shock waves propagating in orthogonal directions gives rise to a 2D ensemble of solitons. Depending on the box size, we report the evidence of a dynamic phase characterized by a constant number of solitons, resembling a 1D soliton gas in integrable systems. We measure the statistical features of this gaslike phase. Our findings pave the way to the investigation of collective solitonic phenomena in two dimensions, demonstrating that the loss of integrability does not disrupt the dominant phenomenology.

Geoacoustic Digital Model for the Sea of Japan Shelf (Peter the Great Bay)

In this paper, the authors present and analyze the geoacoustic digital seabed model they developed, which is a digital description of the water column characteristics, seabed topography, and information about sediments and rocks (their composition and elastic properties) for Peter the Great Bay, the Sea of Japan. The model consists of four relief layers, a foundation and three layers of bottom sediments, and also contains the velocities of longitudinal waves in rocks and statistical characteristics of the sound velocity distribution in the water layer for three seasons. Acoustic characteristics of geological structures are based on seismoacoustic studies, sediment lithology, and laboratory measurements of rock samples collected onshore. The velocities of longitudinal and transversal waves and also the density of the sediments were calculated from their empirical dependencies on the granulometric composition of bottom sediment samples over an area of about 800 km2. In a limited area of the shelf (approximately 130 km2), high-frequency acoustic studies were carried out using echo sounders, and the longitudinal wave velocities of the top sedimentary layer were determined. Porosity, density, longitudinal, and transverse wave velocities in bottom sediments were calculated using empirical models with a normal coefficient of reflection from the seabed. A comparison was made of the results of calculating the elastic properties of the seabed using various methods.

The Parameterized Oceanic Front-Guided PIX2PIX Model: A Limited Data-Driven Approach to Oceanic Front Sound Speed Reconstruction

In response to the demand for high-precision acoustic support under the condition of limited data, this study utilized high-resolution reanalysis data and in situ observation data to extract the Kuroshio Extension Front (KEF) section through front-line identification methods. By combining the parameterized oceanic front model and the statistical features of big data, the parameterized oceanic front was reconstructed. A proxy dataset was generated using the Latin hypercube sampling method, and the sound speed reconstruction model based on the PIX2PIX model was trained and validated using single sound speed profiles at different positions of the oceanic front, combined with the parameterized oceanic front model. The experimental results show that the proposed sound speed reconstruction model can significantly improve the reconstruction accuracy by introducing the parameterized front model as an additional input, especially in the shallow-water area. The mean absolute error (MAE) of the full-depth sound speed reconstruction for this model is 0.63~0.95 m·s−1, and the structural similarity index (SSIM) is 0.76~0.78. The MAE of the sound speed section within a 1000 m depth is reduced by 6.50~37.62%, reaching 1.95~3.31 m·s−1. In addition, the acoustic support capabilities and generalization of the model were verified through ray tracing models and in situ data. This study contributes to advancing high-precision acoustic support in data-limited oceanic environments, laying a solid groundwork for future innovations in marine acoustics.

Statistical Characteristics of Wavelike Banded Convection Associated With Ducted Gravity Waves Over Southern China

AbstractWavelike banded convection occurs frequently and persistently in southern China, significantly impacting local weather. This study presents the first multi‐year investigation of wavelike banded convection associated with ducted gravity waves in southern China from 2013 to 2021 using radar mosaic maps. These convective bands are highly dependent on the wave ducting environment, which typically exhibits a three‐layer stratification structure. Out of 112 identified cases, two types were further classified based on the presence of a wave ducting vertical structure in the soundings: WaveDuct and nonWaveDuct type. Unlike nonWaveDuct type, the WaveDuct type predominantly happens on winter or spring nights. The phase speeds of WaveDuct convective bands also show a highly positive correlation with the depth of the ducting layer, consistent with wave ducting theory. This study provides a climatological understanding of the frequencies, movements, and environment conditions of wavelike banded convection related to ducted gravity waves over southern China.