Data Processing Scheme Research Articles

Analisis Deformasi di Lampung dan Selat Sunda berdasarkan Data GNSS tahun 2018 hingga 2021

The Lampung Province and Sunda Strait have a seismic gap zone with the potential for major earthquakes in the future. This study analyzes the deformation occurring in this region using continuous Global Navigation Satellite System (GNSS) station data from Indonesia Continuously Operating Reference Station (InaCORS) and Sumatran GPS Array (SuGAr) from 2018 to 2021.5. The GNSS data was processed using the Bernese 5.2 scientific software, applying least squares for velocity changes and statistical tests to analyze significance. The data processing was carried out in two schemes: the first scheme covering 2018-2020, and the second covering 2019-2021. The results of the deformation analysis from 2018 to 2021, using two continuous GNSS data processing schemes, showed velocity changes relative to the Sundaland Plate ranging from ~2 mm/year to ~20 mm/year. In the eastern region of the Sumatra fault, the velocity changes were smaller, around ~5 mm/year, due to the minimal influence of tectonic activity. However, in the Sunda Strait region, the deformation was influenced by volcanic activity. The deformation occurring in Lampung Province and the Sunda Strait, based on GNSS velocity changes, significantly contributes to tectonic and volcanic activities.

Improving realty management ability based on big data and artificial intelligence decision-making.

Realty management relies on data from previous successful and failed purchase and utilization outcomes. The cumulative data at different stages are used to improve utilization efficacy. The vital problem is selecting data for analyzing the value incremental sequence and profitable utilization. This article proposes a knowledge-dependent data processing scheme (KDPS) to augment precise data analysis. This scheme operates on two levels. Data selection based on previous stagnant outcomes is performed in the first level. Different data processing is performed in the second level to mend the first level's flaws. Data processing uses knowledge acquired from the sales process, amenities, and market value. Based on the knowledge determined from successful realty sales and incremental features, further processing for new improvements and existing stagnancy mitigation is recommended. The stagnancy and realty values are used as knowledge for training the data processing system. This ensures definite profitable features meeting the amenity requirements under reduced stagnancy time. The proposed scheme improves the processing rate, stagnancy detection, success rate, and training ratio by 8.2%, 10.25%, 10.28%, and 7%, respectively. It reduces the processing time by 8.56% compared to the existing methods.

A novel EPID-based MLC QA method with log files achieving submillimeter accuracy.

The purpose of this study is to develop an electronic portal imaging device-based multi-leaf collimator calibration procedure using log files. Picket fence fields with 2-14mm nominal strip widths were performed and normalized by open field. Normalized pixel intensity profiles along the direction of leaf motion for each leaf pair were taken. Three independent algorithms and an integration method derived from them were developed according to the valley value, valley area, full-width half-maximum (FWHM) of the profile, and the abutment width of the leaf pairs obtained from the log files. Three data processing schemes (Scheme A, Scheme B, and Scheme C) were performed based on different data processing methods. To test the usefulness and robustness of the algorithm, the known leaf position errors along the direction of perpendicular leaf motion via the treatment planning system were introduced in the picket fence field with nominal 5, 8, and 11mm. Algorithm tests were performed every 2weeks over 4 months. According to the log files, about 17.628% and 1.060% of the leaves had position errors beyond ±0.1 and ±0.2mm, respectively. The absolute position errors of the algorithm tests for different data schemes were 0.062±0.067 (Scheme A), 0.041±0.045 (Scheme B), and 0.037±0.043 (Scheme C). The absolute position errors of the algorithms developed by Scheme C were 0.054±0.063 (valley depth method), 0.040±0.038 (valley area method), 0.031±0.031 (FWHM method), and 0.021±0.024 (integrated method). For the efficiency and robustness test of the algorithm, the absolute position errors of the integration method of Scheme C were 0.020±0.024 (5mm), 0.024±0.026 (8mm), and 0.018±0.024 (11mm). Different data processing schemes could affect the accuracy of the developed algorithms. The integration method could integrate the benefits of each algorithm, which improved the level of robustness and accuracy of the algorithm. The integration method can perform multi-leaf collimator (MLC) quality assurance with an accuracy of 0.1mm. This method is simple, effective, robust, quantitative, and can detect a wide range of MLC leaf position errors.

Development of a Stress-Free Algorithm for Control of Running Platforms Based on Neural Network Technologies

The article discusses the task of predicting human speed using neural network technologies and computer vision to minimize lags in treadmill control systems, which pose a health risk to the user. To solve this problem, a stress-free algorithm has been developed, including: predicting the position and speed of the user on the treadmill; calculating the treadmill speed based on the analysis of the user's position and movement characteristics; data collection and processing schemes for training neural network methods; and determining the necessary number of predicted frames to eliminate lags. The scientific novelty of the research lies in the development of a treadmill control algorithm that combines: computer vision technologies for recognizing the user's body model on the platform; neural networks; and machine learning methods to determine the final human speed based on combining data on the person's position in the frame and the current and predicted speed of the person. The proposed algorithm is implemented using Python libraries, and its validation was conducted during experimental studies analyzing the preceding 10 and 15 frames to predict the next 10 and 15 frames. Comparing machine learning algorithms (linear regression, decision tree, random forest, multilayer, convolutional, and recurrent neural networks) at different lengths of analyzed and predicted frames, the RandomForestRegressor algorithm showed the best accuracy in predicting position, while dense multilayer neural networks performed best in determining current speed. Experimental research has been conducted on applying the developed algorithm and models to determine human speed (achieving accuracy when forecasting in the range of 10-15 frames) as well as integrating them into treadmill control systems. Trials have shown the effectiveness of the proposed approach and the correctness of system operation under real conditions. The developed algorithm allows for not using noise-sensitive sensors that require attachment to the user's body but rather forecasting user actions through analyzing all points of the person's body to reduce lags in various human-machine systems.

Alignment measurement of immersed tunnels based on laser differential imaging

The precision of underwater alignment for tunnel elements directly impacts the closure state of immersed tunnels. The current global navigation satellite system measurement tower method provides centimeter-level precision; however, this is insufficient due to the tower deformation at great water depths, which fails to meet alignment requirements. In this study, a novel immersed tunnel alignment measurement method using laser differential imaging is developed. A unique sensor layout is designed to measure the axial angle and distance between tunnel elements. The system design is implemented, and its laser data processing scheme is optimized to improve performance base on this sensor layout. The experimental results demonstrate that the accuracy of underwater laser spot extraction is better than 1.16 pixels, and the precision of axial angle and axial distance alignment measurements is better than 25″ and 1.6 mm, with repeatability precision exceeding 10.55″ and 0.53 mm. The laser-based alignment measurement method is not affected by the depth of water, satisfying the required precision of immersed tunnel alignment. These results can be applied to future immersed tunnel installations without measuring towers, providing a novel method for achieving automated and unmanned intelligent construction of immersed tunnels.

A distributed data processing scheme based on Hadoop for synchrotron radiation experiments.

With the development of synchrotron radiation sources and high-frame-rate detectors, the amount of experimental data collected at synchrotron radiation beamlines has increased exponentially. As a result, data processing for synchrotron radiation experiments has entered the era of big data. It is becoming increasingly important for beamlines to have the capability to process large-scale data in parallel to keep up with the rapid growth of data. Currently, there is no set of data processing solutions based on the big data technology framework for beamlines. Apache Hadoop is a widely used distributed system architecture for solving the problem of massive data storage and computation. This paper presents a set of distributed data processing schemes for beamlines with experimental data using Hadoop. The Hadoop Distributed File System is utilized as the distributed file storage system, and Hadoop YARN serves as the resource scheduler for the distributed computing cluster. A distributed data processing pipeline that can carry out massively parallel computation is designed and developed using Hadoop Spark. The entire data processing platform adopts a distributed microservice architecture, which makes the system easy to expand, reduces module coupling and improves reliability.

Quality Control of Doppler Spectra from a Vertically Pointing, S-Band Profiling Radar

Abstract This study describes a novel combination of methods to remove spurious spectral peaks, or “spurs,” from Doppler spectra produced by a vertically pointing, S-band radar. The University of Massachusetts S-band frequency-modulated, continuous-wave radar (UMass FMCW) was deployed to monitor the growth of the CBL over northern Alabama during the VORTEX–Southeast field campaign in 2016. The Doppler spectra contained spurs caused by high-voltage switching power supplies in the traveling wave tube amplifier. In the original data-processing scheme for this radar, a median filtering method was used to eliminate most of the spurs, but the largest ones persisted, which significantly degraded the quality of derived radar moments (e.g., reflectivity, Doppler velocity, and spectrum width) and hindered further analysis of these data (e.g., hydrometeor classification and boundary layer height tracking). Our technique for removing the spurs consists of three steps: (i) a Laplacian filter identifies and masks peaks in the spectra that are characteristic of the spurs in shape and amplitude, (ii) an in-painting method then fills in the masked area based on surrounding data, and (iii) the moments data (e.g., reflectivity, Doppler velocity, and spectrum width) are then recomputed using a coherent power technique. This combination of techniques was more effective than the median filter at removing the largest spurs from the Doppler spectra and preserved more of the underlying Doppler spectral structure of the scatterers. Performance of both the median-filter and the in-painting methods is assessed through statistical analysis of the spectral power differences. Downstream products, such as boundary layer height detection, are more easily derived from the recomputed moments. Significance Statement This manuscript describes a novel combination of image and signal processing techniques used to recover meteorological observations from corrupted Doppler radar spectra. This successful recovery of meteorologically significant information illustrates the importance of retaining Doppler spectra when practical. In seeking solutions to data quality issues, the atmospheric science community should remain cognizant of promising techniques offered by other disciplines. We present this data rescue study as an example to the meteorological community.

Optimization of Data Processing Schemes for Locating Low-Frequency Oscillation Sources

The organization of data processing for measurement data arrays is one of the key factors for the effective application of synchronized phasor measurement technology (PMU) within a Wide Area Monitoring System (WAMS). This encompasses not only ensuring high computational performance and scalability but also the openness of solutions to the continually evolving data analysis methodologies. In both the scientific community and current operational-dispatching practice, there is a growing interest in the issue of power system oscillatory stability. This interest is driven by the increasing complexity of modern power systems and enhanced observability of processes due to the deployment of WAMS. One of the emerging tasks is the real-time detection of low-frequency oscillation (LFO) sources using PMU data. The dissipating energy flow (DEF) method has shown high effectiveness in addressing this task by enabling the assessment of the magnitude, speed, and direction of oscillation energy propagation. It has been previously demonstrated that, while maintaining the general computational framework of the DEF method, the time required to reach a stable decision about the LFO source depends on the choice of the combination of subtask algorithms and their parameters. This study discusses a prototype computational platform for optimizing generalized data processing schemes based on PMU data. Using the DEF method and a dataset of actual LFOs in the Russian power system as an example, the study explores mechanisms for expanding the solution space and the measurement data base. The paper presents experimental results that provide an estimation of the expected time from the onset of oscillations to the identification of their source.

Cloud Computing Based Data Processing and Automated Management of Power Dispatch

Abstract As smart grids increase, the scope of power dispatch systems has broadened, encompassing not just traditional dispatch services but also multifaceted information services, encompassing data fusion, heterogeneous system integration, and big data analytics. However, managing intricate information businesses like big data analysis poses numerous challenges for the current power dispatch system, hindering its ability to keep up with escalating business demands. We introduce a cloud computing and big data analytics-based design scheme for a power dispatch data processing and automation management system to address this. Leveraging the distributed computing prowess of cloud computing platforms, the system ensures swift processing and analysis of vast power dispatch data. Additionally, by harnessing big data analysis techniques, the system delves into historical data, uncovers potential operational patterns and risk areas, and offers insights for optimizing the Electric Power System’s (EPS) operations. Experimental outcomes demonstrate the system’s remarkable proficiency in enhancing data processing, real-time control, and automation management capabilities, thereby bolstering the growth of intelligent power dispatch systems with robust technical backing.

Simulation study on surface deformation of shallow buried coal seam mining in a gully area

Coal mining subsidence leads to frequent surface ecological and environmental problems. Due to the unique topographic conditions within gully areas, the deformation and damage characteristics, along with the evolution laws of the surface, have been difficult to analyze. To explore the surface movement and deformation law of shallow-buried coal seam mining in a gully area, this study designed a three-dimensional similar-material simulation test simulating the complete movement and deformation of the ground surface under real terrain conditions and proposed a complete data acquisition and processing scheme. Combined with the numerical simulation analysis, we utilized this scheme to analyze the dynamic influence law of coal seam mining in a gully area on the distribution of ground surface stress and displacement as well as on the dynamic characteristics of the ground surface damage. The results show that the existence of gully topography affects the stress distribution of the ground surface and the raw rock of the coal seams underneath and that there exists a stress concentration in the gully area of the ground surface. Furthermore, the mining activities of the coal seams lead to an increase in the degree of stress concentration in the gully area of the ground surface, and the slopes enter into the process of energy accumulation and sudden release, which makes the region prone to the occurrence of geological disasters such as landslides and collapses. In addition, the surface movement and deformation in the gully area are more intense, exceeding the plain area, and the surface movement is affected by the spatial location relationship between the mining area and the slope body, causing the center of the mining area to show obvious eccentricity characteristics. The results of this study provide a reference basis for the safe mining of coal mines in gully topography.

Lightweight Data Processing Scheme based on Machine Learning for 5G DMRS Index Classification

Lightweight Data Processing Scheme based on Machine Learning for 5G DMRS Index Classification

Multimode Fabry-Perot laser as a reservoir computing and extreme learning machine photonic accelerator

In this work, we introduce Fabry–Perot lasers as neuromoprhic nodes in the context of time-delayed reservoir computing and extreme learning machine (ELM) for the processing of temporal signals and the high-speed classification of images. By exploiting the multi-wavelength emission capabilities of the Fabry–Perot lasers, additional processing nodes can be introduced, thus raising the computational power without sacrificing processing speed. An experimental validation of this concept using a Fabry–Perot ELM is presented targeting a time depedent task such as channel equalization for a 50 km 28 Gbaud ‘PAM-4’ transmission, offering hard-decision forward error correction compatible performance. Additionally, the Fabry–Perot neuromorphic concept has been further strengthened by modifying the data entry technique by parallelelly assigning different samples of the input signal to different modes so as to significantly reduce speed penalty. Numerical simulations revealed that this alternative data insertion technique can offer a reduction of the processing delay and physical footprint by 75% compared to the conventional approach assigning the same symbols to all Fairy–Perot modes. Moreover, by using a similar data processing scheme in ‘MNIST’ image classification task we were able to numerically achieve a processing speed of 255.1 Mimages s−1 and a classification accuracy up to 95.95%.

An improved k-NN anomaly detection framework based on locality sensitive hashing for edge computing environment

Large deployment of wireless sensor networks in various fields bring great benefits. With the increasing volume of sensor data, traditional data collection and processing schemes gradually become unable to meet the requirements in actual scenarios. As data quality is vital to data mining and value extraction, this paper presents a distributed anomaly detection framework which combines cloud computing and edge computing. The framework consists of three major components: k-nearest neighbors, locality sensitive hashing, and cosine similarity. The traditional k-nearest neighbors algorithm is improved by locality sensitive hashing in terms of computation cost and processing time. An initial anomaly detection result is given by the combination of k-nearest neighbors and locality sensitive hashing. To further improve the accuracy of anomaly detection, a second test for anomaly is provided based on cosine similarity. Extensive experiments are conducted to evaluate the performance of our proposal. Six popular methods are used for comparison. Experimental results show that our model has advantages in the aspects of accuracy, delay, and energy consumption.

Low-Cost Particulate Matter Sensors for Monitoring Residential Wood Burning.

Conventional monitoring systems for air quality, such as reference stations, provide reliable pollution data in urban settings but only at relatively low spatial density. This study explores the potential of low-cost sensor systems (LCSs) deployed at homes of residents to enhance the monitoring of urban air pollution caused by residential wood burning. We established a network of 28 Airly (Airly-GSM-1, SP. Z o.o., Poland) LCSs in Kristiansand, Norway, over two winters (2021-2022). To assess performance, a gravimetric Kleinfiltergerät measured the fine particle mass concentration (PM2.5) in the garden of one participant's house for 4 weeks. Results showed a sensor-to-reference correlation equal to 0.86 for raw PM2.5 measurements at daily resolution (bias/RMSE: 9.45/11.65 μg m-3). High-resolution air quality maps at a 100 m resolution were produced by combining the output of an air quality model (uEMEP) using data assimilation techniques with the network data that were corrected and calibrated by using a proposed five-step network data processing scheme. Leave-one-out cross-validation demonstrated that data assimilation reduced the model's RMSE, MAE, and bias by 44-56, 38-48, and 41-52%, respectively.

Visualising flight regimes using self-organising maps

AbstractThe purpose of this paper is to group the flight data phases based on the sensor readings that are most distinctive and to create a representation of the higher-dimensional input space as a two-dimensional cluster map. The research design includes a self-organising map framework that provides spatially organised representations of flight signal features and abstractions. Flight data are mapped on a topology-preserving organisation that describes the similarity of their content. The findings reveal that there is a significant correlation between monitored flight data signals and given flight data phases. In addition, the clusters of flight regimes can be determined and observed on the maps. This suggests that further flight data processing schemes can use the same data marking and mapping themes regarding flight phases when working on a regime basis. The contribution of the research is the grouping of real data flows produced by in-flight sensors for aircraft monitoring purposes, thus visualising the evolution of the signal monitored on a real aircraft.

A novel adaptive beamforming scheme for array signal data processing

When the desired signal data exists in the array received data or the steering vector has a mismatch problem, the current traditional adaptive beamformers will suffer from the effect of the desired signal cancelation phenomenon, resulting in a sharp decline in performance. To address the occurrence of desired signal cancelation, an improved matrix projection-based efficient beamforming method is proposed. Firstly, based on spatial partitioning (SP) technology, a significant projection matrix for interference-plus-noise space (INS) is constructed. Secondly, using the constructed key projection matrix, the sample data covariance matrix is projected into the INS to achieve the goal of suppressing the desired signal data information. Finally, the weight data vector is calculated by Capon beamformer. The proposed algorithm does not require an iterative search for the optimal solution, which has the advantage of a small amount of calculation. Simulation experiments have verified that the proposed method has significant advantages in suppressing the desired data signals. Especially when the desired data signal has large power, the signal-to-interference-plus-noise ratio (SINR) of the proposed algorithm is better than that of the compared algorithms under the conditions of random directionality errors or local scattering errors between the desired signal and interference.

Image presentation and effective classification of odor intensity levels using multi-channel electronic nose technology combined with GASF and CNN

This paper proposes a novel data processing scheme for electronic noses that combines the gramian angular field (GAF) and convolutional neural network (CNN) to achieve high performance in classifying five levels of odor intensity. Specifically, a multi-channel e-nose was developed to detect various gases, including hydrogen sulfide, ammonia, sulfur dioxide, trimethylamine, and alkane gases, among others, in complex odor components. The sensor array was optimized through Spearman correlation analysis of the sensor signals and artificial olfactory odor intensity levels. Moreover, the one-dimensional temporal sensor data was converted into two-dimensional color images using the GAF (GASF/GADF) algorithm. This approach enables a more detailed presentation of deep features while retaining the time-domain dependence of the signals. To enhance the performance of classification, a multi-scale feature fusion network (MFFNet) was designed. Notably, GASF-converted images are more effective in characterizing sensor data for different odor intensity levels than GADF-converted images. Compared to classical CNN classification models such as AlexNet, GoogLeNet, and ResNet18, MFFNet achieved the highest accuracy and macro average F1-score on the test set, which were 93.75% and 93.34%, respectively. The results demonstrate the efficient classification of odor intensity levels by combining multi-channel e-nose technology, GASF, and CNN.

A novel semi-empirical model for crop leaf area index retrieval using SAR co- and cross-polarizations

The retrieval of continuous leaf area index (LAI) in space and time from remote sensing is beneficial for cropland monitoring and management. Synthetic Aperture Radar (SAR) with the advantages of all-weather operation and fine spatial resolutions has been utilized in various agricultural applications. Although the water cloud model (WCM) has been extensively used for LAI estimation over croplands, it is modified for application to crop canopies with large gaps. The requirement of prior information on soil moisture is also a hinderance for the model application. In this study, WCM is theoretically modified to consider the correlation of active microwave propagation through the canopy in downward and upward directions. Such a modification is particularly important for sparse vegetation with large gaps between crop plants in the early stage of the growing season. A parameter with explicit physical meaning, i.e. the full-vegetation backscattering coefficient, was defined to simplify our model scheme and make the model applicable for the whole growing season. In addition, a physics-based SAR data processing scheme is developed to entangle the influences of LAI and soil moisture on SAR backscatter by taking advantage of the multiple polarizations of RADARSAT-2 (R2) SAR data. In this way, LAI was estimated using modified WCM without the prior knowledge of soil moisture. To evaluate LAI retrieved from the R2 datasets (R2 LAI), ground-based LAI measurements were made at the experimental area of SMAPVEX16-MB in Canada with twenty approximately 800 m х 800 m plots in soybeans and corn. R2 LAI was well correlated to these ground-based LAI (n = 15, R2 = 0.63, RMSE = 0.99 m2·m−2 for soybeans; n = 5, R2 = 0.66, RMSE = 1.20 m2·m−2 for corn). LAI was also retrieved from optical data acquired by Sentinel-2/MSI (S2), denoted as S2 LAI. The R2 LAI and S2 LAI are well correlated and achieved coefficients of determination (R2) of 0.76 and 0.71 and root mean square errors (RMSE) of 1.1 and 1.4 m2·m−2 for soybeans and corn, respectively. The seasonal variations of R2 LAI and S2 LAI are generally similar except at the end of the growing season when S2 LAI is considerably larger than R2 LAI. S2 LAI followed the trend of the reduction in leaf chlorophyll content, while R2 LAI reduced only slightly due to the decrease in leaf water content near the end the growing season. R2 LAI represents the total standing leaf area useful for surface energy balance estimation, while S2 LAI responds to green leaf area useful for crop productivity modeling.

3D DC inversion, visualization, and processing of dense time-lapse data in fine domains applied to remediation monitoring

Using electrical direct-current (DC) data to monitor the subsurface is an efficient solution for observing changes in the shallow subsurface. Recent advances in instrumentation enable the acquisition of large data sets over 3D domains in a reasonable time. We have developed an inversion approach capable of handling very large amounts of data on a finely discretized domain, which enables the delivery of time-lapse results of dense data acquisitions in a feasible time and with high resolution. To spatially represent 3D DC data, a visualization method is introduced that formally generalizes the focusing point of a common pseudosection in three dimensions. The method physically describes subsurface properties for simple geologic scenarios. In addition, the focusing points are used to design our 3D measuring protocol. We develop a DC data processing scheme using the full time-domain induced polarization (IP) waveform data by applying two novel physics-based criteria that enforce charge buildup and steady state. These criteria are tested on DCIP field data and find that 98% of the filtered DC data have less than 1% relative error. The 3D visualization method and inversion algorithm are evaluated on synthetic scenarios of 3D DC dense borehole data. Then, we indicate time-lapse results of DC field data acquired at an uncontaminated site where a remediation agent was injected at depth. The data are acquired with a new DCIP instrument capable of measuring dense data sets at fast acquisition times. Accounting for DCIP data acquisition, signal processing, and 3D inversion of 60,000 DC measurements, our results locate in 14 h the 3D spread of the remediation agent in a [Formula: see text] volume.

Developing the GoogleNet neural network for the detection and recognition of unmanned aerial vehicles in the data Fusion System

This work reports a study into the possibility of using the GoogleNet neural network in the optoelectronic channel of the Data Fusion system. The search for the most accurate algorithms for detecting and recognizing unmanned aerial vehicles (UAVs) in Data Fusion systems has been carried out. The data processing scheme was selected (merging SVF state vectors and merging MF measurements), as well as the sensors and recognition models on each channel of the system. The Data Fusion model based on the Kalman Filter was chosen, integrating radar and optoelectronic channels. Mini-radars LPI-FMCW were used as a radar channel. Evaluation of the effectiveness of the selected Data Fusion channel model in UAV detection is based on the recognition accuracy. The main study is aimed at determining the possibility of using the GoogleNet neural network in the optoelectronic channel for UAV recognition under conditions of different range classes. The neural network for the recognition of drones was developed using transfer training technology. For training, validation, and testing of the GoogleNet neural network, a database has been built, and a special application has been developed in the MATLAB environment. The capabilities of the developed neural network were studied for 5 variants of the distance to the object. The detection objects were the Inspire 2, DJI Phantom 4 Pro, DJI F450, DU 1911 UAVs, not included in the training database. The UAV recognition accuracy by the neural network was 98.13 % at a distance of up to 5 m, 94.65 % at a distance of up to 20 m, 92.47 % at a distance of up to 20 m, 90.28 % at a distance of up to 100 m, and 88.76 % at a distance of up to 200 m. The average speed of UAV recognition by this method was 0.81 s.