Types Of Algorithms Research Articles

Monitoring of chlorophyll-a and suspended sediment concentrations in optically complex inland rivers using multisource remote sensing measurements

In recent decades, phytoplankton proliferation and sediment input to rivers (especially urban rivers) have become more dramatic under the compound pressure of climate change and human activities. Given the generally narrow width of rivers and current high spatial resolution satellites, which are limited by band settings, bandwidth, and the signal-to-noise ratio, UAVs with their exceptional spatiotemporal resolution can be used as a useful tool for river environmental monitoring and inversion uncertainty assessment. In this study, UAV-based hyperspectral (X20P) and multispectral (P4M) images, along with Sentinel-2 MultiSpectral Instrument (MSI), Landsat-8 Operational Land Imager (OLI) and Landsat-9 OLI2 data, were used to assess the uncertainty in retrieving chlorophyll-a (Chla) and suspended sediment (SS) concentrations in rivers. Chla and SS models based on UAV and satellite data were constructed using stepwise multiple regression and typical Chla and SS retrieval algorithms, respectively, and the performance of the models was the focus of our research. The results demonstrated that in the Chla concentration inversion, each sensor performed as follows: X20P > P4M > Landsat9 OLI2 > Sentinel-2 MSI > Landsat8 OLI, and the performance in the SS concentration inversion was as follows: X20P > Sentinel-2 MSI > P4M > Landsat9 OLI2 > Landsat8 OLI. In addition, the uncertainty of high spatial resolution satellite retrievals was analyzed with the assistance of the UAV-based model. Results showed that narrow bandwidths and finely tuned band settings are more essential for the Chla inversion. The typical Chla retrieval algorithm, NDCI, is only effective in certain bands (band 1 from 684 to 724 nm and band 2 from 660 to 680 nm). It is also noted that Landsat8 and Landsat9 lack some key band settings (e.g., the red-edge band of 700–710 nm), severely limiting practical application in relation to Chla. However, specific variances in different sensor bands have a relatively small impact on SS inversion, for example, the correlation between SS and the R/B (a typical SS retrieval algorithm) constructed by each sensor ranged from 0.68 to 0.77. Chla monitoring, on the other hand, necessitates a higher spatial resolution than SS monitoring. The accuracy decreased markedly when UAV images were resampled to 10 m and 30 m spatial resolution. However, it is not as crucial for the SS inversion, images with the original spatial resolution (RMSE<30cm = 6.28 mg/L) were resampled to 10 m resolution (RMSE10m = 5.85 mg/L) and 30 m resolution (RMSE30m = 4.08 mg/L) while using P4M for SS inversion, and the accuracy increased. Our results demonstrated and highlighted various options for future monitoring of Chla and SS, while exploiting the synergy between UAVs and satellites to achieve more precise observations at greater spatial and temporal scales, which will benefit aquatic environment management and protection.

Making programmable packet scheduling time-sensitive with a FIFO queue

Time-Sensitive Networking (TSN) is an emerging technology for real-time and non-real-time hybrid networked systems. TSN is standardized by IEEE 802.1 TSN Task Group and is becoming widely used in various scenarios including the cloud network. However, existing programmable packet schedulers such as PIFO, PIEO, and AIFO in programmable switches either lack the ability to express most scheduling algorithms in TSN or introduce intolerable on-chip memory overhead (e.g., strict-priority queues). This makes programmable switches and NICs incapable of providing deterministic forwarding. In this paper, we present AIAO (Admission-In-Admission-Out), a new set of programmable scheduling primitives using just a single FIFO to support typical TSN scheduling algorithms, as well as other popular work-conserving algorithms. AIAO is inspired by AIFO but improves it with a group of high-speed packet ingress/egress admission control triggered by high-precise and globally synchronized time, thus being able to support time-sensitive scheduling. We implement AIAO and evaluate it with FPGA-based TSN switches. The preliminary results show that AIAO guarantees correctness for a typical TSN scheduling algorithm with minimal logic and memory overhead.

Analysis and Design of Modified Incremental Conductance-Based MPPT Algorithm for Photovoltaic System

This study discusses the design of the Maximum Power Point Tracking (MPPT) technique for photovoltaic (PV) systems employing a modified incremental conductance (IncCond) algorithm to extract maximum power from a PV module. A PV module, a DC-DC converter, and a resistive load constitute the PV system. In the scientific literature, it is well-documented that typical MPPT algorithms have significant drawbacks, such as fluctuations around the MPP and poor tracking during a sudden change in atmospheric conditions. To solve the deficiencies of conventional methodology, a novel modified IncCond method is proposed in this study. The simulation results demonstrate that the updated IncCond algorithm presented allows for less oscillation around the maximum power point (MPP), a rapid dynamic response, and superior performance.

Convergence properties of Levenberg–Marquardt methods with generalized regularization terms

Levenberg–Marquardt methods (LMMs) are the most typical algorithms for solving nonlinear equations F(x)=0, where F:Rn→Rm is a continuously differentiable function. They sequentially solve subproblems represented as squared residual of the Newton equations with the L2 regularization to determine the search direction. However, since the subproblems of the LMMs are usually reduced to linear equations with n variables, it takes much time to solve them when m≪n.In this paper, we propose a new LMM which generalizes the L2 regularization of the subproblems of the ordinary LMMs. By virtue of the generalization, we can choose a suitable regularization term for each given problem. Moreover, we show that a sequence generated by the proposed method converges globally and quadratically under some reasonable assumptions. Finally, we conduct numerical experiments to confirm that the proposed method performs better than the existing LMMs for some problems that satisfy m≪n.

Riemannian Smoothing Gradient Type Algorithms for Nonsmooth Optimization Problem on Compact Riemannian Submanifold Embedded in Euclidean Space

Riemannian Smoothing Gradient Type Algorithms for Nonsmooth Optimization Problem on Compact Riemannian Submanifold Embedded in Euclidean Space

PB0833 VWF Expression Mostly Confirms Genetic Prediction Algorithms in Type 1 VWD Variants

PB0833 VWF Expression Mostly Confirms Genetic Prediction Algorithms in Type 1 VWD Variants

Algorithm for Enhancing the Resolution of Workshop Part Images

The resolution of the input image will affect the restoration effect of the image. In a fixed environment, obtaining high-quality images requires expensive acquisition devices, such as cameras. There are many ways to improve image quality. Instead of increasing hardware investment, it is better to find methods in image post-processing. Deep learning algorithms have obvious advantages in image processing. Based on deep learning, we propose an algorithm to convert camera captured images into high-resolution images. VDSR (Very Accurate Super Resolution) is a typical algorithm. Use residual image learning to predict accurate residual images from input images. Residual corresponds to the high-frequency information in an image, representing pixels that undergo drastic changes in the image, and can highlight the edges and contours of the target. Our proposed algorithm is more accurate than existing algorithms and improves visual effects.

Multiparticipant Federated Feature Selection Algorithm With Particle Swarm Optimization for Imbalanced Data Under Privacy Protection

In real world, data describing the same learning task may be distributed in different institutions (called participants), and these participants cannot share their own data due to the need of privacy protection. How to select an optimal feature subset on the basis of ensuring the data privacy of each participant is an important and challenging topic. At the same time, data on part participants show imbalanced or even miss some classes, further increasing the difficulty of solving this kind of problem. In view of this, by introducing a trusted third party to process and integrate optimal information from participants, this paper proposes a multi-participant federated evolutionary feature selection algorithm for imbalanced data under privacy protection. Firstly, a multi-level joint sample filling strategy with multiple participants (called sampling-rough selection-fine tuning strategy) is proposed to fill imbalanced or empty classes on each participant while ensuring data privacy. Then, a federated evolutionary feature selection method based on particle swarm optimization (PSO) is proposed by periodically sharing the optimal feature subsets obtained by PSOs on participants. Finally, the proposed algorithm is applied to 15 test datasets, and compared with several typical imbalanced feature selection algorithms and two kinds of ensemble feature selection algorithms. The experimental results show that the proposed algorithm can significantly promote the ability of each participant on processing imbalanced datasets, and improve the classification accuracy of obtained feature subsets while protecting the participants' data privacy.

Experimental Design Networks: A Paradigm for Serving Heterogeneous Learners Under Networking Constraints

Significant advances in edge computing capabilities enable learning to occur at geographically diverse locations. In general, the training data needed in those learning tasks are not only heterogeneous but also not fully generated locally. In this paper, we propose an experimental design network paradigm, wherein learner nodes train possibly different Bayesian linear regression models via consuming data streams generated by data source nodes over a network. We formulate this problem as a social welfare optimization problem in which the global objective is defined as the sum of experimental design objectives of individual learners, and the decision variables are the data transmission strategies subject to network constraints. We first show that, assuming Poisson data streams in steady state, the global objective is a continuous DR-submodular function. We then propose a Frank-Wolfe type algorithm that outputs a solution within a <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$1-1/e$</tex-math> </inline-formula> factor from the optimal. Our algorithm contains a novel gradient estimation component which is carefully designed based on Poisson tail bounds and sampling. Finally, we complement our theoretical findings through extensive experiments. Our numerical evaluation shows that the proposed algorithm outperforms several baseline algorithms both in maximizing the global objective and in the quality of the trained models.

Blind deep-learning based preprocessing method for Fourier ptychographic microscopy

Fourier ptychographic microscopy (FPM) is a technique for tackling the trade-off between the resolution and the imaging field of view by combining the techniques from aperture synthesis and phase retrieval to estimate the complex object from a series of low-resolution intensity images captured under angle-varied illumination. The captured images are commonly corrupted by multiple noise, leading to the degradation of the reconstructed image quality. Typically speaking, the noise model and noise level of the experimental images are unknown, and the traditional image denoising methods have limited effect. In this paper we model the FPM forward imaging process corrupted by noise and divide the noise in the captured images into two parts: the signal-dependent part and the signal-independent part. Based on the noise model we propose a novel blind deep-learning based Fourier ptychographic microscopy preprocessing method, termed BDFP, for removing these two components of noise. First, from a portion of the captured low-resolution images, a set of blocks corresponding to the smooth area of the object are extracted to model signal-independent noise. Second, under the assumption that the signal-dependent noise follows a Poisson distribution, we add Poisson noise and signal-independent noise blocks to clean images to form a paired training dataset, which is then used for training a deep convolutional neural network (CNN) model to reduce both signal-dependent noise and signal-independent noise. The proposed blind preprocessing method, combining with typical FPM reconstruction algorithms, is tested on simulated data and experimental images. Experimental results show that our preprocessing method can significantly reduce the noise in the captured images and bring about effective improvements in reconstructed image quality.

Feature Selection Based on Unsupervised Clustering Mechanism on Multiple-Sequence MRIs for Predicting Neoadjuvant Chemoradiation Response in Locally Advanced Rectal Cancer

Accurate response prediction allows for personalized cancer management. We developed an unsupervised clustering mechanism to improve effectiveness and efficiency in feature selection operation for accurate patient stratification. Forty-three locally advanced rectal cancer (LARC) patients underwent neoadjuvant chemoradiation were included, pre-treatment T2 and ADC MRIs were acquired for each patient. An initial feature space consisting of 200 radiomic features extracted from manually delineated GTVs from two sequences of MR images. Additional 960 high-order radiomic features extracted from a 3D convolutional neural network (CNN). To remove redundant and irrelevant features, we developed an unsupervised clustering-based feature selection operation to determine the combination of features with potential best performance. The normal process of feature selection involves searching new feature combinations and training new classifiers for evaluating their performance via an iterative process based on selected feature set, the overall time cost is tremendous. To balance the computational cost and search efficiency, firstly, we proposed an unsupervised clustering analysis metric- Comprehensive Cluster Analysis Index (CCAI) through the K-means algorithm, where the average distances between the sample points and the cluster centroids and so on, to construct a multiple linear regression model. Secondly, we extracted sample points by varying the number of features and feature ratios between radiomic features and 3D-CNN features in the output of feature selection. Thirdly, we optimized the model using the sampling points to calculate the CCAI. Two typical feature combination search algorithms, the random forest recursive feature elimination (RF-RFE) and the differential evolution (DE), were used to perform feature selection with CCAI. The accuracy, area-under-curve (AUC) and specificity, based on combined 3D-CNN and radiomic features extracted from combined T2 and ADC images, were 0.852, 0.871, and 0.735, respectively. Our experiments illustrated higher predictive power (AUC = 0.846) based on high-order abstract features extracted from the CNN on ADC and T2 images, compared to the traditional radiomic model (AUC = 0.714). Additionally, the predictive models constructed based on radiomics and CNN features extracted from ADC images were more predictable in terms of treatment responses than the radiomic and CNN imaging features extracted from T2 images. The average computational time of DE and RF-RFE were 50.5s and 128.6s in one single computation, the average computational time were 24.2s and 91.3s with CCAI, respectively. We proposed an unsupervised clustering analysis mechanism to improve the effectiveness of feature selection while decreasing its time cost markedly, which highlight the correlation and complementarity between low- and high-level imaging features, achieving better predictive accuracy.

Route Optimization in Mission Planning for Hybrid DRONE+VEHICLE Transport Systems

Introduction. In the context of modern technologies and the widespread use of unmanned aerial vehicles (UAVs) in various fields of activity, the study of optimizing their mission planning becomes increasingly relevant. This is particularly true for hybrid systems where UAVs are integrated with ground transportation ("Drone+Vehicle"). The article deals with the aspects of optimizing the mission routes of a drone that can be transported by a specialized vehicle, performing reconnaissance or maintenance missions for the presented targets. A mathematical model has been developed that allows integrating various planning stages, including determining the direction of the vehicle based on the data obtained during the drone's mission. The purpose of the paper is development and application of mathematical and software-algorithmic tools, in particular, based on the ideas of swarm intelligence, in planning operations for the inspection or maintenance of a given set of objects using hybrid systems "Drone+Vehicle". Results. A mathematical model of the problem of routing hybrid systems of the "Drone+Vehicle" type has been formed. Greedy type algorithms, deterministic local search and ant colony optimization (ACO) to solve the problem are proposed, implemented and analyzed. A computational experiment has been conducted to demonstrate the advantages of the AMC algorithm in terms of speed and efficiency, even for problems of high dimensionality. Conclusions. The proposed approach allows to cover several stages of planning the mission of a hybrid "Drone+Vehicle" system with an aggregated mathematical model. The developed mathematical model also covers the problem of choosing the direction of further movement of a vehicle located in a certain place, depending on the analysis of the results of the inspection of specified targets that may contain objects for inspection or maintenance. To solve the formulated combinatorial optimization problem, greedy type, deterministic local search, and OMC algorithms have been developed. The results of the computational experiment demonstrate the superiority of the OMC algorithm over the combined "greedy + deterministic local search" algorithm. An important future direction of research is the development and application of routing models and algorithms that take into account the obstacles present on the ground. The developed mathematical apparatus allows to move on to consider problems in which the locations of the vehicle's base on the route are not specified but are determined depending on the configuration of the targets. Keywords: unmanned aerial vehicles, hybrid systems, mission planning, route optimization, mathematcal modeling, ant colony optimization, logistics.

PROJECT METHOD IN STEM EDUCATION USING ARDUINO SOFTWARE AND HARDWARE PLATFORM

Formulation of the problem. One of the promising methods of training in STEM education is the method of projects. The projected method in STEM education determines the relevance and research nature of the topic of the project, ensuring the interconnection of theoretical knowledge with practice, practical implementation of the results of the project. The project, as a means of implementing STEM education, allows you to integrate knowledge from different subject industries when solving real tasks, the creation of existing layouts, which causes their practical use. Materials and methods. Methods of analysis and systematization of scientific and pedagogical literature were used; generalization of the results of domestic and foreign experience in the use of a prose method in the STEM education using the ARDUino software and hardware platform. The experimental method of creating an active physiotherapy laser device for treatment of the runny nose is presented. A software modeling is used to simulate a device with the design of the Arduino Uno board. Results. The example of the implementation of the STEM project "Development of a physiotherapeutic laser device for the treatment of runny nose" demonstrates how it is possible to integrate many different-level, didactic, and research tasks. A generalized description of the main structural elements of the Arduino Uno board is given. A typical algorithm for familiarizing yourself with the operation of the Arduino board is formulated. The main sections of the physics course are indicated, the knowledge of which is fundamental for implementing the project. It is shown how using a bit matrix of laser states allows the creation of cyclic irradiation modes that periodically change each other. An example of a code processing a bit matrix of laser states is provided. The sketch controls the modes of the semiconductor laser, displays the exposure time on the liquid crystal display, and emits a sound signal at the end of the exposure time set by the potentiometer. A fragment of the simulation modeling of a physiotherapy device in the Tinkercad Circuits environment is presented. Conclusions. The practical experience of using the project method in STEM education has shown that it allows students to investigate a real problem actively, apply the acquired knowledge in practice, and develop cooperation, communication, and critical thinking skills. Implementation of the project contributes to the combination of various activities, such as cognitive, creative, practical, and research, as well as the development of thinking skills, motivation, and responsibility for one's actions. Implementing the project method makes it possible to provide high-quality training for specialists in natural sciences who can effectively apply their knowledge and skills in practical situations and contribute to the further development of STEM fields in Ukraine.

Principal component analysis–artificial neural network-based model for predicting the static strength of seasonally frozen soils

Seasonally frozen soils are exposed to freeze‒thaw cycles every year, leading to mechanical property deterioration. To reasonably describe the deterioration of soil under different conditions, machine learning (ML) technology is used to establish a prediction model for soil static strength. Six key influencing factors (moisture content, compaction degree, confining pressure, freezing temperature, number of freeze‒thaw cycles and thawing duration) are included in the modelling database. The accuracy of three typical ML algorithms (support vector machine (SVM), random forest (RF) and artificial neural network (ANN)) is compared. The results show that the ANN outperforms the SVM and RF. Principal component analysis (PCA) is combined with the ANN, and the PCA–ANN algorithm is proposed, which further improves the prediction accuracy. The deterioration of soil static strength is systematically researched using the PCA–ANN algorithm. The results show that the soil static strength decreased considerably after the first several freeze‒thaw cycles before the strength plateau occurred, and the strength reduction increased significantly with increasing moisture content and compaction degree. The PCA–ANN model can generate a reasonable prediction for the static strength or other soil properties of seasonally frozen soil, which will provide a scientific reference for practical engineering.

Inertial Mann type algorithms for a finite collection of equilibrium problems and fixed point problem of demicontractive mappings

Inertial Mann type algorithms for a finite collection of equilibrium problems and fixed point problem of demicontractive mappings

SbMBR Tree—A Spatiotemporal Data Indexing and Compression Algorithm for Data Analysis and Mining

In the field of data analysis and mining, adopting efficient data indexing and compression techniques to spatiotemporal data can significantly reduce computational and storage overhead for the abilities to control the volume of data and exploit the spatiotemporal characteristics. However, traditional lossy compression techniques are hardly suitable due to their inherently random nature. They often impose unpredictable damage to scientific data, which affects the results of data mining and analysis tasks that require certain precision. In this paper, we propose a similarity-based minimum bounding rectangle (SbMBR) tree, a tree-based indexing and compression method, to address the aforementioned problem. Our method can hierarchically select appropriate minimum bounding rectangles according to the given maximum acceptable errors and use the average value contained in each selected MBR to replace the original data to achieve data compression with multi-layer loss control. This paper also provides the corresponding tree construction algorithm and range query processing algorithm for the indexing structure mentioned above. To evaluate the data quality preservation in cross-domain data analysis and mining scenarios, we use mutual information as the estimation metric. Experimental results emphasize the superiority of our method over some of the typical indexing and compression algorithms.

Energy-efficient motion planning of an autonomous forklift using deep neural networks and kinetic model

Autonomous Forklifts (AFs) play a vital role in smart factories, particularly in the transportation of heavy loads. However, their energy consumption poses a significant challenge as they need to operate for extended periods on a single battery charge. Therefore, energy-efficient motion is necessary to raise their availability. The AF’s movement is dynamically determined by a motion planning algorithm within its navigation system. In light of this, this article introduces a strategy to improve energy efficiency during the motion planning phase. This strategy involves a cooperative approach, utilizing the Deep Neural Networks (DNNs) and AF’s kinetic model to achieve this energy-saving goal. Unlike traditional methods that rely solely on the vehicle’s kinematic model, our approach considers an additional factor, incorporating the influence of the vehicle’s kinetic model for a more comprehensive and accurate energy consumption analysis. First, the kinetic model of an AF is developed by considering the effect of the front-powered wheel. Second, the kinetic model is employed within a time-energy optimization technique, aiming to find the AF’s ideal acceleration. This optimization process generates a dataset that covers a range of AF maneuvers and dynamic parameters. Third, a DNNs model is trained using this dataset to predict the optimal acceleration for the AF. Finally, the trained model is integrated into a motion planning algorithm to determine the optimal and acceptable limits for both linear and angular acceleration. Experiments illustrate that the suggested motion planning method can generate trajectories that are both feasible and optimized for energy consumption. This differs significantly from the typical algorithms which generally results in higher energy use by the AF, occasionally leading to the generation of infeasible trajectories.

A numerical approach to the optimal control of thermally convective flows

The optimal control of thermally convective flows is usually modeled by an optimization problem with constraints of Boussinesq equations that consist of the Navier-Stokes equation and an advection-diffusion equation. This optimal control problem is challenging from both theoretical analysis and algorithmic design perspectives. For example, the nonlinearity and coupling of fluid flows and energy transports prevent direct applications of gradient type algorithms in practice. In this paper, we propose an efficient numerical method to solve this problem based on the operator splitting and optimization techniques. In particular, we employ the Marchuk-Yanenko method leveraged by the L2-projection for the time discretization of the Boussinesq equations so that the Boussinesq equations are decomposed into some easier linear equations without any difficulty in deriving the corresponding adjoint system. Consequently, at each iteration, four easy linear advection-diffusion equations and two degenerated Stokes equations at each time step are needed to be solved for computing a gradient. Then, we apply the Bercovier-Pironneau finite element method for space discretization, and design a BFGS type algorithm for solving the fully discretized optimal control problem. We look into the structure of the problem, and design a meticulous strategy to seek step sizes for the BFGS efficiently. Efficiency of the numerical approach is promisingly validated by the results of some preliminary numerical experiments.

Hydrostatic pressure adaptive dual-polarized model for state of charge estimation of lithium-ion batteries

Pressure-tolerated lithium-ion batteries have been used in autonomous underwater vehicle (AUV), due to their ability to withstand pressure directly and save structural parts that protect itself. As an important component of the battery, state of charge (SOC) is critical for evaluating the reliable operation of AUV batteries. The influence of hydrostatic pressure is not considered in typical SOC estimation process, which leads to a large deviation of terminal voltage estimation, and finally the accurate estimation of SOC cannot be realized. In this paper, a dual-polarized equivalent circuit model dependent on hydrostatic pressure is established, which fully considers the influence of pressure on the internal characteristic parameters of the battery. The characteristic parameters in the equivalent circuit model are measured at hydrostatic pressure and identified by forgetting factor recursive least squares (FFRLS). Compared with the blank model without considering hydrostatic pressure, the proposed model can capture voltage and SOC, which can contribute to the estimation accuracy of terminal voltage in a wide pressure range. The typical algorithms of unscented Kalman filter (UKF), cubature Kalman filter (CKF) and adaptive cubature Kalman filter (ACKF) are used to estimate the SOC based on the two models (OCV-SOC-Pressure and OCV-SOC) at different hydrostatic pressures. The results show that the accuracy of the SOC estimation algorithm under different hydrostatic pressure environments is improved, which is attributed to the compensation correction of the original OCV-SOC model. The root mean square error (RMSE) value of the ACKF algorithm based on the hydrostatic pressure adaptive multivariate regression model is 0.94 %, which significantly improves the SOC estimation effectiveness of the OCV-SOC model without considering the pressure factor (RMSE is 7.36 %) at the hydrostatic pressure of 60 MPa. At the preset different SOC initial values, the three algorithms based on the hydrostatic pressure adaptive multivariate regression model can achieve fast convergence, and ACKF shows the best environmental adaptability.

A real-time intelligent lithology identification method based on a dynamic felling strategy weighted random forest algorithm

Real-time intelligent lithology identification while drilling is vital to realizing downhole closed-loop drilling. The complex and changeable geological environment in the drilling makes lithology identification face many challenges. This paper studies the problems of difficult feature information extraction, low precision of thin-layer identification and limited applicability of the model in intelligent lithologic identification. The author tries to improve the comprehensive performance of the lithology identification model from three aspects: data feature extraction, class balance, and model design. A new real-time intelligent lithology identification model of dynamic felling strategy weighted random forest algorithm (DFW-RF) is proposed. According to the feature selection results, gamma ray and 2 MHz phase resistivity are the logging while drilling (LWD) parameters that significantly influence lithology identification. The comprehensive performance of the DFW-RF lithology identification model has been verified in the application of 3 wells in different areas. By comparing the prediction results of five typical lithology identification algorithms, the DFW-RF model has a higher lithology identification accuracy rate and F1 score. This model improves the identification accuracy of thin-layer lithology and is effective and feasible in different geological environments. The DFW-RF model plays a truly efficient role in the real-time intelligent identification of lithologic information in closed-loop drilling and has greater applicability, which is worthy of being widely used in logging interpretation.