基于Focal Loss改进LightGBM的供水管网毛刺数据检测

针对数据不平衡导致的管网毛刺数据检测召回率偏低问题,提出一种Focal Loss改进LightGBM的管网毛刺数据检测方法。首先,结合管网毛刺数据的特点,针对性构造邻域相关特征。其次,将Focal Loss函数引入LightGBM,提高模型对难以检测的毛刺样本的权重,并对Focal Loss不同的参数取值进行实验,以平衡精确率与召回率。最后,选择不同参数的Focal Loss进行模型融合,进一步提升模型对不平衡毛刺数据的检测性能。在某市供水管网的真实数据上进行实验,结果表明,对比基于交叉熵损失函数的单一模型,本文提出的Focal Loss改进后的融合模型在毛刺数据上召回率和F1值的提升幅度达33.3和18个百分点,但毛刺数据的精确率还有待进一步提升。本文所提方法从损失函数入手,动态调整难易样本的权重,有效地提升了不平衡数据下的毛刺数据的检测性能。

Robust state of charge estimation of lithium-ion battery via mixture kernel mean p-power error loss LSTM with heap-based-optimizer

The state of charge(SOC)estimation of lithium-ion battery is an important function in the battery management system(BMS)of electric vehicles.The long short term memory(LSTM)model can be employed for SOC estimation,which is capable of estimating the future changing states of a nonlinear system.Since the BMS usually works under complicated operating conditions,i.e the real measurement data used for model training may be corrupted by non-Gaussian noise,and thus the performance of the original LSTM with the mean square error(MSE)loss may deteriorate.Therefore,a novel LSTM with mixture kernel mean p-power error(MKMPE)loss,called MKMPE-LSTM,is developed by using the MKMPE loss to replace the MSE as the learning criterion in LSTM framework,which can achieve robust SOC estimation under the measurement data contaminated with non-Gaussian noises(or outliers)because of the MKMPE containing the p-order moments of the error distribution.In addition,a meta-heuristic algorithm,called heap-based-optimizer(HBO),is employed to optimize the hyper-parameters(mainly including learning rate,number of hidden layer neuron and value of p in MKMPE)of the proposed MKMPE-LSTM model to further improve its flexibility and generalization performance,and a novel hybrid model(HBO-MKMPE-LSTM)is established for SOC estimation under non-Gaussian noise cases.Finally,several tests are performed under various cases through a benchmark to evaluate the performance of the proposed HBO-MKMPE-LSTM model,and the results demonstrate that the proposed hybrid method can provide a good robustness and accuracy under different non-Gaussian measurement noises,and the SOC estimation results in terms of mean square error(MSE),root MSE(RMSE),mean absolute relative error(MARE),and determination coefficient R2are less than 0.05%,3%,3%,and above 99.8%at 25℃,respectively.

Prevalence of visual impairment and estimation of refractive errors among school children in Kakamega,Kenya

AIM:To investigate the prevalence of visual impairment(VI)and provide an estimation of uncorrected refractive errors in school-aged children,conducted by optometry students as a community service.METHODS:The study was cross-sectional.Totally 3343 participants were included in the study.The initial examination involved assessing the uncorrected distance visual acuity(UDVA)and visual acuity(VA)while using a+2.00 D lens.The inclusion criteria for a subsequent comprehensive cycloplegic eye examination,performed by an optometrist,were as follows:a UDVA<0.6 decimal(0.20 logMAR)and/or a VA with+2.00 D≥0.8 decimal(0.96 logMAR).RESULTS:The sample had a mean age of 10.92±2.13y(range 4 to 17y),and 51.3%of the children were female(n=1715).The majority of the children(89.7%)fell within the age range of 8 to 14y.Among the ethnic groups,the highest representation was from the Luhya group(60.6%)followed by Luo(20.4%).Mean logMAR UDVA choosing the best eye for each student was 0.29±0.17(range 1.70 to 0.22).Out of the total,246 participants(7.4%)had a full eye examination.The estimated prevalence of myopia(defined as spherical equivalent≤-0.5 D)was found to be 1.45%of the total sample.While around 0.18%of the total sample had hyperopia value exceeding+1.75 D.Refractive astigmatism(cil<-0.75 D)was found in 0.21%(7/3343)of the children.The VI prevalence was 1.26%of the total sample.Among our cases of VI,76.2%could be attributed to uncorrected refractive error.Amblyopia was detected in 0.66%(22/3343)of the screened children.There was no statistically significant correlation observed between age or gender and refractive values.CONCLUSION:The primary cause of VI is determined to be uncorrected refractive errors,with myopia being the most prevalent refractive error observed.These findings underscore the significance of early identification and correction of refractive errors in school-aged children as a means to alleviate the impact of VI.

A crosstalk-free dual-mode sweat sensing system for naked-eye sweat loss quantification via changes in structural reflectance

Sweat loss monitoring is important for understanding the body’s thermoregulation and hydration status,as well as for comprehensive sweat analysis.Despite recent advances,developing a low-cost,scalable,and universal method for the fabrication of colorimetric microfluidics designed for sweat loss monitoring remains challenging.In this study,we propose a novel laserengraved surface roughening strategy for various flexible substrates.This process permits the construction of microchannels that show distinct structural reflectance changes before and after sweat filling.By leveraging these unique optical properties,we have developed a fully laser-engraved microfluidic device for the quantification of naked-eye sweat loss.This sweat loss sensor is capable of a volume resolution of 0.5µL and a total volume capacity of 11µL,and can be customized to meet different performance requirements.Moreover,we report the development of a crosstalk-free dual-mode sweat microfluidic system that integrates an Ag/AgCl chloride sensor and a matching wireless measurement flexible printed circuit board.This integrated system enables the real-time monitoring of colorimetric sweat loss signals and potential ion concentration signals without crosstalk.Finally,we demonstrate the potential practical use of this microfluidic sweat loss sensor and its integrated system for sports medicine via on-body studies.

Genetically modified pigs:Emerging animal models for hereditary hearing loss

Hereditary hearing loss(HHL),a genetic disorder that impairs auditory function,significantly affects quality of life and incurs substantial economic losses for society.To investigate the underlying causes of HHL and evaluate therapeutic outcomes,appropriate animal models are necessary.Pigs have been extensively used as valuable large animal models in biomedical research.In this review,we highlight the advantages of pig models in terms of ear anatomy,inner ear morphology,and electrophysiological characteristics,as well as recent advancements in the development of distinct genetically modified porcine models of hearing loss.Additionally,we discuss the prospects,challenges,and recommendations regarding the use pig models in HHL research.Overall,this review provides insights and perspectives for future studies on HHL using porcine models.

Efficient unequal error protection for online fountain codes

In this paper,an efficient unequal error protection(UEP)scheme for online fountain codes is proposed.In the buildup phase,the traversing-selection strategy is proposed to select the most important symbols(MIS).Then,in the completion phase,the weighted-selection strategy is applied to provide low overhead.The performance of the proposed scheme is analyzed and compared with the existing UEP online fountain scheme.Simulation results show that in terms of MIS and the least important symbols(LIS),when the bit error ratio is 10-4,the proposed scheme can achieve 85%and 31.58%overhead reduction,respectively.

Uncertainties of landslide susceptibility prediction: Influences of random errors in landslide conditioning factors and errors reduction by low pass filter method

In the existing landslide susceptibility prediction(LSP)models,the influences of random errors in landslide conditioning factors on LSP are not considered,instead the original conditioning factors are directly taken as the model inputs,which brings uncertainties to LSP results.This study aims to reveal the influence rules of the different proportional random errors in conditioning factors on the LSP un-certainties,and further explore a method which can effectively reduce the random errors in conditioning factors.The original conditioning factors are firstly used to construct original factors-based LSP models,and then different random errors of 5%,10%,15% and 20%are added to these original factors for con-structing relevant errors-based LSP models.Secondly,low-pass filter-based LSP models are constructed by eliminating the random errors using low-pass filter method.Thirdly,the Ruijin County of China with 370 landslides and 16 conditioning factors are used as study case.Three typical machine learning models,i.e.multilayer perceptron(MLP),support vector machine(SVM)and random forest(RF),are selected as LSP models.Finally,the LSP uncertainties are discussed and results show that:(1)The low-pass filter can effectively reduce the random errors in conditioning factors to decrease the LSP uncertainties.(2)With the proportions of random errors increasing from 5%to 20%,the LSP uncertainty increases continuously.(3)The original factors-based models are feasible for LSP in the absence of more accurate conditioning factors.(4)The influence degrees of two uncertainty issues,machine learning models and different proportions of random errors,on the LSP modeling are large and basically the same.(5)The Shapley values effectively explain the internal mechanism of machine learning model predicting landslide sus-ceptibility.In conclusion,greater proportion of random errors in conditioning factors results in higher LSP uncertainty,and low-pass filter can effectively reduce these random errors.

Effect of foot reflexology on an infant with sensorineural hearing loss:A case report

BACKGROUND Our study contributes to the further understanding of the mechanism of foot reflexology.Foot reflexology has been reported to affect hearing recovery,but no physiological evidence has been provided.This lack of evidence hampers the acceptance of the technique in clinical practice.CASE SUMMARY A girl was taken to North Sichuan Medical University Affiliated Hospital for a hearing screen by her parents.Her parents reported that her hearing level was the same as when she was born.The girl was diagnosed with sensorineural hearing loss(SNHL)by a doctor in the otolaryngology department.After we introduced the foot reflexology project,the parents agreed to participate in the experiment.After 6 months of foot reflexology treatment,the hearing threshold of the girl recovered to a normal level,below 30 dB.CONCLUSION Foot reflexology should be encouraged in clinical practice and for families of infants with SNHL.

Uncertainties in landslide susceptibility prediction:Influence rule of different levels of errors in landslide spatial position

The accuracy of landslide susceptibility prediction(LSP)mainly depends on the precision of the landslide spatial position.However,the spatial position error of landslide survey is inevitable,resulting in considerable uncertainties in LSP modeling.To overcome this drawback,this study explores the influence of positional errors of landslide spatial position on LSP uncertainties,and then innovatively proposes a semi-supervised machine learning model to reduce the landslide spatial position error.This paper collected 16 environmental factors and 337 landslides with accurate spatial positions taking Shangyou County of China as an example.The 30e110 m error-based multilayer perceptron(MLP)and random forest(RF)models for LSP are established by randomly offsetting the original landslide by 30,50,70,90 and 110 m.The LSP uncertainties are analyzed by the LSP accuracy and distribution characteristics.Finally,a semi-supervised model is proposed to relieve the LSP uncertainties.Results show that:(1)The LSP accuracies of error-based RF/MLP models decrease with the increase of landslide position errors,and are lower than those of original data-based models;(2)70 m error-based models can still reflect the overall distribution characteristics of landslide susceptibility indices,thus original landslides with certain position errors are acceptable for LSP;(3)Semi-supervised machine learning model can efficiently reduce the landslide position errors and thus improve the LSP accuracies.

Relative Impacts of Sea Ice Loss and Atmospheric Internal Variability on the Winter Arctic to East Asian Surface Air Temperature Based on Large-Ensemble Simulations with NorESM2

To quantify the relative contributions of Arctic sea ice and unforced atmospheric internal variability to the “warm Arctic, cold East Asia”(WACE) teleconnection, this study analyses three sets of large-ensemble simulations carried out by the Norwegian Earth System Model with a coupled atmosphere–land surface model, forced by seasonal sea ice conditions from preindustrial, present-day, and future periods. Each ensemble member within the same set uses the same forcing but with small perturbations to the atmospheric initial state. Hence, the difference between the present-day(or future) ensemble mean and the preindustrial ensemble mean provides the ice-loss-induced response, while the difference of the individual members within the present-day(or future) set is the effect of atmospheric internal variability. Results indicate that both present-day and future sea ice loss can force a negative phase of the Arctic Oscillation with a WACE pattern in winter. The magnitude of ice-induced Arctic warming is over four(ten) times larger than the ice-induced East Asian cooling in the present-day(future) experiment;the latter having a magnitude that is about 30% of the observed cooling. Sea ice loss contributes about 60%(80%) to the Arctic winter warming in the present-day(future) experiment. Atmospheric internal variability can also induce a WACE pattern with comparable magnitudes between the Arctic and East Asia. Ice-lossinduced East Asian cooling can easily be masked by atmospheric internal variability effects because random atmospheric internal variability may induce a larger magnitude warming. The observed WACE pattern occurs as a result of both Arctic sea ice loss and atmospheric internal variability, with the former dominating Arctic warming and the latter dominating East Asian cooling.

Geometric Error Identification of Gantry-Type CNC Machine Tool Based on Multi-Station Synchronization Laser Tracers

Laser tracers are a three-dimensional coordinate measurement system that are widely used in industrial measurement.We propose a geometric error identification method based on multi-station synchronization laser tracers to enable the rapid and high-precision measurement of geometric errors for gantry-type computer numerical control(CNC)machine tools.This method also improves on the existing measurement efficiency issues in the single-base station measurement method and multi-base station time-sharing measurement method.We consider a three-axis gantry-type CNC machine tool,and the geometric error mathematical model is derived and established based on the combination of screw theory and a topological analysis of the machine kinematic chain.The four-station laser tracers position and measurement points are realized based on the multi-point positioning principle.A self-calibration algorithm is proposed for the coordinate calibration process of a laser tracer using the Levenberg-Marquardt nonlinear least squares method,and the geometric error is solved using Taylor’s first-order linearization iteration.The experimental results show that the geometric error calculated based on this modeling method is comparable to the results from the Etalon laser tracer.For a volume of 800 mm×1000 mm×350 mm,the maximum differences of the linear,angular,and spatial position errors were 2.0μm,2.7μrad,and 12.0μm,respectively,which verifies the accuracy of the proposed algorithm.This research proposes a modeling method for the precise measurement of errors in machine tools,and the applied nature of this study also makes it relevant both to researchers and those in the industrial sector.

Automated Actuarial Data Analytics-Based Inflation Adjusted Frequency Severity Loss Reserving Model

In this paper, the Automated Actuarial Loss Reserving Model is developed and extended using machine learning. The traditional actuarial reserving techniques are no longer compatible with the increase in technological advancement currently at hand. As a result, the development of the alternative Artificial Intelligence Based Automated Actuarial Loss Reserving Methodology which captures diverse risk profiles for various policyholders through augmenting the Micro Finance services, Auto Insurance Services and Both Services lines of business on the same platform through the computation of the Comprehensive Automated Actuarial Loss Reserves (CAALR) has been implemented in this paper. The introduction of the four further types of actuarial loss reserves to those existing in the actuarial literature seems to significantly reduce lapse rates, reduce the reinsurance costs as well as expenses and outgo. As a matter of consequence, this helps to bring together a combination of new and existing policyholders in the insurance company. The frequency severity models have been extended in this paper using ten machine learning algorithms which ultimately leads to the derivation of the proposed machine learning-based actuarial loss reserving model which remarkably performed well when compared to the traditional chain ladder actuarial reserving method using simulated data.

Hemoglobin loss method calculates blood loss during pancreaticoduodenectomy and predicts bleeding-related risk factors

BACKGROUND The common clinical method to evaluate blood loss during pancreaticoduoden-ectomy(PD)is visual inspection,but most scholars believe that this method is extremely subjective and inaccurate.Currently,there is no accurate,objective me-thod to evaluate the amount of blood loss in PD patients.We retrospectively analyzed the clinical data of 341 patients who underwent PD in Shandong Provincial Hospital from March 2017 to February 2019.According to different surgical methods,they were divided into an open PD(OPD)group and a laparoscopic PD(LPD)group.The differences and correlations between the in-traoperative estimation of blood loss(IEBL)obtained by visual inspection and the intraoperative calculation of blood loss(ICBL)obtained using the Hb loss method were analyzed.ICBL,IEBL and perioperative calculation of blood loss(PCBL)were compared between the two groups,and single-factor regression analysis was performed.RESULTS There was no statistically significant difference in the preoperative general patient information between the two groups(P>0.05).PD had an ICBL of 743.2(393.0,1173.1)mL and an IEBL of 100.0(50.0,300.0)mL(P<0.001).There was also a certain correlation between the two(r=0.312,P<0.001).Single-factor analysis of ICBL showed that a history of diabetes[95%confidence interval(CI):53.82-549.62;P=0.017]was an independent risk factor for ICBL.In addition,the single-factor analysis of PCBL showed that body mass index(BMI)(95%CI:0.62-76.75;P=0.046)and preoperative total bilirubin>200μmol/L(95%CI:7.09-644.26;P=0.045)were independent risk factors for PCBL.The ICBLs of the LPD group and OPD group were 767.7(435.4,1249.0)mL and 663.8(347.7,1138.2)mL,respectively(P>0.05).The IEBL of the LPD group 200.0(50.0,200.0)mL was slightly greater than that of the OPD group 100.0(50.0,300.0)mL(P>0.05).PCBL was greater in the LPD group than the OPD group[1061.6(612.3,1632.3)mL vs 806.1(375.9,1347.6)mL](P<0.05).CONCLUSION The ICBL in patients who underwent PD was greater than the IEBL,but there is a certain correlation between the two.The Hb loss method can be used to evaluate intraoperative blood loss.A history of diabetes,preoperative bilirubin>200μmol/L and high BMI increase the patient's risk of bleeding.

Inhibition of the NLRP3 inflammasome attenuates spiral ganglion neuron degeneration in aminoglycoside-induced hearing loss

Aminoglycosides are a widely used class of antibacterials renowned for their effectiveness and broad antimicrobial spectrum.However,their use leads to irreversible hearing damage by causing apoptosis of hair cells as their direct target.In addition,the hearing damage caused by aminoglycosides involves damage of spiral ganglion neurons upon exposure.To investigate the mechanisms underlying spiral ganglion neuron degeneration induced by aminoglycosides,we used a C57BL/6J mouse model treated with kanamycin.We found that the mice exhibited auditory deficits following the acute loss of outer hair cells.Spiral ganglion neurons displayed hallmarks of pyroptosis and exhibited progressive degeneration over time.Transcriptomic profiling of these neurons showed significant upregulation of genes associated with inflammation and immune response,particularly those related to the NLRP3 inflammasome.Activation of the canonical pyroptotic pathway in spiral ganglion neurons was observed,accompanied by infiltration of macrophages and the release of proinflammatory cytokines.Pharmacological intervention targeting NLRP3 using Mcc950 and genetic intervention using NLRP3 knockout ameliorated spiral ganglion neuron degeneration in the injury model.These findings suggest that NLRP3 inflammasome-mediated pyroptosis plays a role in aminoglycoside-induced spiral ganglion neuron degeneration.Inhibition of this pathway may offer a potential therapeutic strategy for treating sensorineural hearing loss by reducing spiral ganglion neuron degeneration.

Bayesian Filtering for High-Dimensional State-Space Models With State Partition and Error Compensation

In the era of exponential growth of data availability,the architecture of systems has a trend toward high dimensionality,and directly exploiting holistic information for state inference is not always computationally affordable.This paper proposes a novel Bayesian filtering algorithm that considers algorithmic computational cost and estimation accuracy for high-dimensional linear systems.The high-dimensional state vector is divided into several blocks to save computation resources by avoiding the calculation of error covariance with immense dimensions.After that,two sequential states are estimated simultaneously by introducing an auxiliary variable in the new probability space,mitigating the performance degradation caused by state segmentation.Moreover,the computational cost and error covariance of the proposed algorithm are analyzed analytically to show its distinct features compared with several existing methods.Simulation results illustrate that the proposed Bayesian filtering can maintain a higher estimation accuracy with reasonable computational cost when applied to high-dimensional linear systems.

A Combined Antenna Array Deployment with High Positioning Accuracy and Low Angular Measurement Error

In this paper,an antenna array composed of circular array and orthogonal linear array is proposed by using the design of long and short baseline“orthogonal linear array”and the circular array ambiguity resolution design of multi-group baseline clustering.The effectiveness of the antenna array in this paper is verified by sufficient simulation and experiment.After the system deviation correction work,it is found that in the L/S/C/X frequency bands,the ambiguity resolution probability is high,and the phase difference system error between each channel is basically the same.The angle measurement error is less than 0.5°,and the positioning error is less than 2.5 km.Notably,as the center frequency increases,calibration consistency improves,and the calibration frequency points become applicable over a wider frequency range.At a center frequency of 11.5 GHz,the calibration frequency point bandwidth extends to 1200 MHz.This combined antenna array deployment holds significant promise for a wide range of applications in contemporary wireless communication systems.

Evaluating foot reflexology as a proposed treatment for sensorineural hearing loss:A critical review

This editorial critically evaluates the application of foot reflexology as a treatment for sensorineural hearing loss(SNHL)in infants,as proposed in a case report published in the World of Clinical Cases.SNHL is a condition characterized by damage to the cochlea or the neural pathways that transmit auditory information to the brain.The etiology of SNHL is often complex,involving genetic mutations,prenatal factors,or perinatal insults.Reflexology,an alternative therapy involving the application of pressure to specific points on the feet,is based on the hypothesis that these points correspond to different organs and systems in the body,including the auditory system.However,the biological plausibility and clinical efficacy of foot reflexology in addressing SNHL lack empirical support.This editorial examines the pathophysiology of SNHL,assesses the clinical claims of reflexology practitioners,and emphasizes the necessity of evidence-based approaches in treating infant hearing loss.While complementary therapies may provide ancillary benefits,they should not supplant validated medical treatments in managing SNHL in infants.Further research is needed to evaluate the safety and efficacy of foot reflexology and other alternative therapies in pediatric audiology.

Numerical study of alpha particle loss with toroidal field ripple based on CFETR steady-state scenario

Effects of plasma equilibrium parameters on the alpha particle loss with the toroidal field ripple based on the CFETR steady-state scenario have been numerically investigated by the orbit-following code GYCAVA. It is found that alpha particle losses decrease and loss regions become narrower with the plasma current increasing or with the magnetic field decreasing. It is because the ripple stochastic transport and the ripple well loss of alpha particle are reduced with the safety factor decreasing. Decrease of the plasma density and temperature can reduce alpha particle losses due to enhancement of the slowing-down effect. The direction of the toroidal magnetic field can significantly affect heat loads induced by lost alpha particle. The vertical asymmetry of heat loads induced by the clockwise and counter-clockwise toroidal magnetic fields are due to the fact that the ripple distribution is asymmetric about the mid-plane, which can be explained by the typical orbits of alpha particle. The maximal heat load of alpha particle for the clockwise toroidal magnetic field is much smaller than that for the counter-clockwise one.

Acquired sensorineural hearing loss,oxidative stress,and microRNAs

Hearing loss is the third leading cause of human disability.Age-related hearing loss,one type of acquired sensorineural hearing loss,is largely responsible for this escalating global health burden.Noise-induced,ototoxic,and idiopathic sudden sensorineural are other less common types of acquired hearing loss.The etiology of these conditions is complex and multi-fa ctorial involving an interplay of genetic and environmental factors.Oxidative stress has recently been proposed as a likely linking cause in most types of acquired sensorineural hearing loss.Short non-coding RNA sequences known as microRNAs(miRNAs)have increasingly been shown to play a role in cellular hypoxia and oxidative stress responses including promoting an apoptotic response.Sensory hair cell death is a central histopathological finding in sensorineural hearing loss.As these cells do not regenerate in humans,it underlies the irreversibility of human age-related hearing loss.Ovid EMBASE,Ovid MEDLINE,Web of Science Core Collection,and ClinicalTrials.gov databases over the period August 1,2018 to July 31,2023 were searched with"hearing loss,""hypoxamiRs,""hypoxia,""microRNAs,""ischemia,"and"oxidative stress"text words for English language primary study publications or registered clinical trials.Registe red clinical trials known to the senior author we re also assessed.A total of 222studies were thus identified.After excluding duplicates,editorials,retra ctions,secondary research studies,and non-English language articles,39 primary studies and clinical trials underwent full-text screening.This resulted in 11 animal,in vitro,and/or human subject journal articles and 8 registered clinical trial database entries which form the basis of this narrative review.MiRNAs miR-34a and miR-29b levels increase with age in mice.These miRNAs were demonstrated in human neuroblastoma and murine cochlear cell lines to target Sirtuin 1/peroxisome proliferato r-activated receptor gamma coactivator-1-alpha(SIRT1/P GC-1α),SIRT1p53,and SIRT1/hypoxia-inducible factor 1-alpha signaling pathways resulting in increased apoptosis.Furthermore,hypoxia and oxidative stress had a similar adve rse apoptotic effect,which was inhibited by resve ratrol and a myocardial inhibitorassociated transcript,a miR-29b competing endogenous mRNA.Gentamicin reduced miR-182-5p levels and increased cochlear oxidative stress and cell death in mice-an effect that was corrected by inner ear stem cell-derived exosomes.There is ongoing work seeking to determine if these findings can be effectively translated to humans.

Simulation of charge-exchange induced NBI losses on EAST

The neutral beam injection is widely adopted in tokamaks as a key heating tool,playing a crucial role in generating burning plasmas.However,the loss of beam ions can damage the first wall and reduce the heating efficiency,resulting in failure to maintain steady-state conditions.In this work,the effect of neutral particles in the edge on fast ions generated by NBI in the Experimental Advanced Superconducting Tokamak(EAST)device is studied using the particle tracer code(PTC).The poloidal distribution of neutral particles is calculated by edge plasma simulation code SOLPS-ITER.In this simulation,four beam lines in EAST are considered:co-current tangential(co-tang),co-current perpendicular(co-perp),counter-current tangential(ctr-tang)and counter-current perpendicular(ctr-perp).It is shown that,in the absence of neutral particles,the loss fraction of ctr-injection is considerably higher than that of the co-injection.When considering the neutral particles,it is found that the ctr-perp injection demonstrates a significant variation in particles loss fraction(ranging from 18.56%to 25.42%)compared to the other three injection configurations.In terms of the loss fraction induced by neutral particles,ctr-injection exceeds co-injection,and perpendicular configuration exceeds tangential configuration.Furthermore,the difference of charge exchange ratios of three different energy(full energy,half energy,one third energy)of the four injections can be attributed to variations in the poloidal trajectories associated with each of these injections.Moreover,approximately half of fast ions which undergo neutralization directly lose to the first wall while the rest re-enter the bulk plasma and re-ionize.Except for the ctr-tang injection,the reionization ions from the other three injections exhibit effective confinement.