Estimation of electron density in plasma based on back propagation neural network algorithm

Purpose In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing. Design/methodology/approach In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing. Findings In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing. Originality/value In order to analyze the text complexity of Chinese and foreign academic English writings, the artificial neural network (ANN) under deep learning (DL) is applied to the study of text complexity. Firstly, the research status and existing problems of text complexity are introduced based on DL. Secondly, based on Back Propagation Neural Network (BPNN) algorithm, analyzation is made on the text complexity of Chinese and foreign academic English writings. And the research establishes a BPNN syntactic complexity evaluation system. Thirdly, MATLAB2013b is used for simulation analysis of the model. The proposed model algorithm BPANN is compared with other classical algorithms, and the weight value of each index and the model training effect are further analyzed by statistical methods. Finally, L2 Syntactic Complexity Analyzer (L2SCA) is used to calculate the syntactic complexity of the two libraries, and Mann–Whitney U test is used to compare the syntactic complexity of Chinese English learners and native English speakers. The experimental results show that compared with the shallow neural network, the deep neural network algorithm has more hidden layers and richer features, and better performance of feature extraction. BPNN algorithm shows excellent performance in the training process, and the actual output value is very close to the expected value. Meantime, the error of sample test is analyzed, and it is found that the evaluation error of BPNN algorithm is less than 1.8%, of high accuracy. However, there are significant differences in grammatical complexity among students with different English writing proficiency. Some measurement methods cannot effectively reflect the types and characteristics of written language, or may have a negative relationship with writing quality. In addition, the research also finds that the measurement of syntactic complexity is more sensitive to the language ability of writing. Therefore, BPNN algorithm can effectively analyze the text complexity of academic English writing. The results of the research provide reference for improving the evaluation system of text complexity of academic paper writing.

SPIDER (source for the production of ions of deuterium extracted from RF plasma) is the full-scale prototype of the ITER neutral beam injector ion source. The plasma heating takes place inside eight drivers via inductive coupling, through the radiofrequency (RF) coil. To achieve optimum conditions during source operation it is necessary to know the plasma behavior under various operational conditions. One of the essential parameters is the plasma electron density. It is possible to experimentally measure this parameter and, currently, different methods are being explored, such as the estimations coming from a Langmuir probe and optical emission spectroscopy. However, these methods are either available for temporary measurements or require dedicated analyses with large uncertainties. In this regard, alternative, reliable, and fast diagnostic tools will be beneficial for the estimation of the order of magnitude of electron density inside the driver. Two models for the estimation of electron density are recalled, discussed, and further modified in this work: one is based on the classical power balance equation, and the other is recently described in the literature and relies on classical plasma conductivity. Both models use equivalent electrical parameters of the driver derived from available electrical measurements at the output of the RF generator and through the knowledge of the matching network and the transmission line length. This work explicitly focuses on the application of these models to estimate the plasma electron density in a single driver of SPIDER. Furthermore, the estimations are compared with the first experimental results obtained from temporary electrostatic probe measurements and are found to be in good agreement in terms of magnitude and trends.

Measurements of spacecraft potential (V_sc) are an important tool for plasma diagnostics. High-resolution V_sc measurements can be calibrated with low-cadence observations of electron plasma frequency to derive high-resolution electron density data. We analyze V_sc measured by the Radio and Plasma Waves (RPW) instrument suite on board Solar Orbiter. We investigate the evolution of V_sc within the framework of the heliocentric distance and mission lifetime. We aim to obtain electron density estimates that are valid across a wider range of V_sc regimes, including the cases of negative V_sc. We determined V_sc by combining measurements of the probe-to-spacecraft potential, V_ps, and the probe-to-plasma potential, V_pn. Then, we used the appropriate electric current balance to find a relation between electron density and V_sc, which we calibrated to the observed electron plasma frequency. With this method, we obtained the electron density at the resolution given by the V_ps measurements. We find that V_sc reaches negative values for a larger amount of time than expected for a sunlit spacecraft immersed in a tenuous plasma such as the solar wind. We are now able to identify when these V_sc changes occur, enabling us to estimate the electron density accordingly. Solar Orbiter charges negatively during periods of high plasma density and low photoelectron emission. However, the measured V_sc is also influenced by the electrical disconnection of the solar arrays from the spacecraft ground during fuse-blowing events. This disconnection raises the local plasma potential near the probes, causing the measured V_sc to appear negative even when Solar Orbiter remains positively charged. By distinguishing between the genuine negative spacecraft charging and the apparent negative charging induced by solar panels, we can refine previous electron density estimation methods to include cases when V_ sc <0 V. This approach provides reliable, high-resolution electron density estimates across both positive and negative V_sc regimes.

Ionospheric plasma drift velocities measured by High Frequency (HF) coherent scatter radars, such as the Super Dual Auroral Radar Network (SuperDARN), are typically underestimated, sometimes significantly, because the refractive index in the scattering volume is not known. Large‐scale or background estimates of ionospheric electron density and refractive index can be made by other instruments; however, these instruments both do not cover the large field‐of‐view of the SuperDARN radars and do not provide information about the small‐scale structures which may be very important for the scattering process. A method has been developed to use different operating frequencies of the SuperDARN radars to obtain the average scattering volume electron density. These electron density measurements provide an estimate of refractive index and allow for corrections to the SuperDARN velocity data to be made. A comprehensive analysis of all SuperDARN data since its inception almost 20 years ago has provided estimates of average electron density in the scattering volume of the radars for various magnetic latitudes, solar activities, local times, and seasons. The analysis indicates that the average electron density, and therefore refractive index, in the scattering volume can vary significantly with the various parameters. Densities ranging from less than 2 × 1011 m−3 to more than 8 × 1011 m−3, result in refractive index corrections from less than 5% (not very significant) to more than 50% (extremely significant). These results provide estimates of appropriate adjustments to the drift velocities assumed by SuperDARN for various conditions. Further, this research has provided substantial insight into the physics of the coherent scattering process and provides a method by which electron density of the scattering structures can be monitored. This will be tested using in situ high‐latitude ionospheric measurements from the upcoming enhanced Polar Outflow Probe (ePOP) satellite mission.

Cross-cultural learning competence, a critical skill in our globally interconnected world, is advanced through the application of the Backpropagation (BP) neural network algorithm. This innovative approach involves leveraging neural network techniques to model and enhance individuals' abilities to navigate and understand diverse cultural contexts. The BP neural network algorithm facilitates personalized learning experiences by adapting to individuals' cultural backgrounds and preferences. This research explores a comprehensive approach for assessing and enhancing cross-cultural learning competence among Chinese college students, integrating the Word Embedding Multilingual Model with the Back Propagation Neural Network (WEMM-BPNN) algorithm. Recognizing the importance of global competencies in higher education, our study focuses on leveraging advanced neural network techniques to evaluate and elevate students' cross-cultural learning abilities. The WEMM-BPNN model combines the power of word embedding and multilingual considerations, tailoring the learning experience to individual cultural backgrounds. Through a meticulous analysis of cross-cultural data and linguistic patterns, the algorithm refines its recommendations for personalized learning strategies. The research aims not only to assess the current state of cross-cultural learning competence but also to provide targeted interventions to enhance students' intercultural understanding and adaptability. By merging linguistic models with neural network algorithms, this study offers a pioneering approach to cultivating cross-cultural competencies, contributing valuable insights to the ongoing discourse on globalized education.

From measurements of the Hα and Hβ spectral line profiles in a plasma, a method is developed which allows to separate the contributions of Doppler and Stark broadening. This method is superior to the deconvolution of Voigt profiles, in particular, when the lines are of low intensity. The electron density in the plasma can be calculated from the Stark broadening.An example is the low pressure (p ≈ 1 hPa) arc discharge of argon ion lasers which is characteristised by electron densities of approximately 1014 cm−3 at heavy particle temperatures of about 104 K. These plasma parameters lead to a broadening of the Balmer Hα and Hβ spectral lines of hydrogen, which has a low concentration within the discharge area. The spectral lines are broadened due to the electron density dependent Stark effect and the temperature responsive Doppler effect. The results are consistent with predictions of the argon ion laser modelling.

Forecasting and alert of atmospheric bioaerosol concentration profile based on adaptive genetic algorithm back propagation neural network, atmospheric parameter and fluorescence lidar

We develop a new Monte Carlo‐based inversion method for estimating electron density and effective atomic number from 3‐D dual‐energy computed tomography (CT) core scans. The method accounts for uncertainties in X‐ray attenuation coefficients resulting from the polychromatic nature of X‐ray beam sources of medical and industrial scanners, in addition to delivering uncertainty estimates of inversion products. Estimation of electron density and effective atomic number from CT core scans enables direct deterministic or statistical correlations with salient rock properties for improved petrophysical evaluation; this condition is specifically important in media such as vuggy carbonates where CT resolution better captures core heterogeneity that dominates fluid flow properties. Verification tests of the inversion method performed on a set of highly heterogeneous carbonate cores yield very good agreement with in situ borehole measurements of density and photoelectric factor.

Mapping electron density in the ionosphere: A principal component MCMC algorithm

A method for precise measurements of absolute electron density in plasma using wave cutoff is described. This method of measurement uses a network analyzer with radiating and detecting antenna A microwave signal of 10 kHZ–3 GHz frequency is introduced into the plasma from a radiating port of the network analyzer and propagates in the plasma. The transmitted wave is monitored at a distance from a radiating antenna using an antenna connected to the receiving port of the network analyzer. The transmitted wave decays rapidly at a cutoff plasma frequency, which is a direct measure of the absolute electron density. This cutoff method is free of many difficulties often encountered with a Langmuir probe, such as thin film deposition and plasma potential fluctuation. The cutoff probe can also measure the spatial distribution of the electron density. The measurement technique is analyzed theoretically and experimentally, demonstrated in density measurements of an inductively coupled radio-frequency plasma, and is compared with the double probe and a plasma oscillation methods.

Summary form only given. A THz interferometer has been constructed with the goal of directly measuring plasma electron densities in HID lamp plasmas. The system utilizes a 600 GHz source, capable of measuring plasma densities up to 4times10 <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">15</sup> cm <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">-3</sup> . Due to the short wavelength of 600 GHz radiation, the focal spot size can be less than a millimeter in diameter. These advantages will allow a THz interferometer to measure electron densities in plasmas previously unavailable to interferometric methods. In addition to the use of THz radiation for interferometry, a significant departure from typical microwave measurement will be made in the elimination of heterodyning from the system. Due to the high density and AC nature of HID lamp plasmas, the plasma is expected to recombine twice per cycle when the discharge current is equal to zero. The effect on the beam will change over time as the discharge current passes through its full AC range, allowing calculation of the density as a function of time with zero-points contained within the measurement itself. The only limitation of such a method is the bandwidth of the detector, in that the bandwidth must be higher than the frequency of the AC current in the plasma. Sensors with bandwidths of 1 kHz or greater are available and should prove sufficient for a self-heterodyning interferometer. This self-heterodyning system can eliminate the complexity associated with traditional heterodyne systems, while simultaneously providing time-dependent information on the behavior of electrons in HID plasmas, and eliminating the need for separate measurements of zero-density points for calibration.

MRI significantly improves the accuracy and reliability of target delineation in radiation therapy for certain tumors due to its superior soft tissue contrast compared to CT. A treatment planning process with MRI as the sole imaging modality will eliminate systematic CT/MRI co-registration errors, reduce cost and radiation exposure, and simplify clinical workflow. However, MRI lacks the key electron density information necessary for accurate dose calculation and generating reference images for patient setup. The purpose of this work is to develop a unifying method to derive electron density from standard T1-weighted MRI. We propose to combine both intensity and geometry information into a unifying probabilistic Bayesian framework for electron density mapping. For each voxel, we compute two conditional probability density functions (PDFs) of electron density given its: (1) T1-weighted MRI intensity, and (2) geometry in a reference anatomy, obtained by deformable image registration between the MRI of the atlas and test patient. The two conditional PDFs containing intensity and geometry information are combined into a unifying posterior PDF, whose mean value corresponds to the optimal electron density value under the mean-square error criterion. We evaluated the algorithm’s accuracy of electron density mapping and its ability to detect bone in the head for eight patients, using an additional patient as the atlas or template. Mean absolute HU error between the estimated and true CT, as well as receiver operating characteristics for bone detection (HU > 200) were calculated. The performance was compared with a global intensity approach based on T1 and no density correction (set whole head to water). The proposed technique significantly reduced the errors in electron density estimation, with a mean absolute HU error of 126, compared with 139 for deformable registration (p = 2 × 10−4), 283 for the intensity approach (p = 2 × 10−6) and 282 without density correction (p = 5 × 10−6). For 90% sensitivity in bone detection, the proposed method achieved a specificity of 86%, compared with 80, 11 and 10% using deformable registration, intensity and without density correction, respectively. Notably, the Bayesian approach was more robust against anatomical differences between patients, with a specificity of 62% in the worst case (patient), compared to 30% specificity in registration-based approach. In conclusion, the proposed unifying Bayesian method provides accurate electron density estimation and bone detection from MRI of the head with highly heterogeneous anatomy.

Pavement cracks are an important hidden danger for driving safety. Rapid and accurate detection of road crack types and effective treatment can greatly reduce the incidence of traffic accidents, which has important practical significance. Based on the advantages of scale invariant feature transform (SIFT) and back-propagation neural network (BP) algorithm, this paper proposes a method of road crack detection and recognition for four types of cracks, such as cracks, longitudinal cracks, transverse cracks and massive cracks.Firstly, the crack image is denoised and enhanced; Then scale invariant feature transform method is used to extract the feature point information of the route crack image; Finally, Back propagation neural network is used for training and recognition. The results show that this method can quickly and accurately identify the crack type, in which the accuracy of training set is 98.79%, and the accuracy of recognition set is 86.47%. The results show that the combination of scale invariant feature transform and back propagation neural network algorithm can effectively improve the efficiency of pavement crack type detection.

Electron density estimation using MPPC-based photon-counting CT for radiation therapy planning

Arc temperatures have been measured, and relative electron densities have been estimated for dc arcs in Ar, Ar-CO, He, and He-CO. Two temperatures were measured: the excitation temperature, T cxc , by means of the zinc two-line intensity ratio method, and the rotational temperature, T r , by the C 2 band method. Relative electron densities were estimated by comparing Ha line widths in each of the four arc atmospheres. These measurements were performed to gain some understanding of the influence of small amounts of CO on the excitation characteristics of low amperage arcs in argon and helium. The resulting temperatures and electron density estimates indicate that only the c in argon with CO present approaches local thermodynamic equilibrium. Tables of the measured temperatures and plots of the Hα line widths for the estimation of electron densities are given. Implications with regard to the excitation of metal impurities vaporized into these arcs are discussed.