Basis Function Neural Network Model Research Articles

Construction and Validation of Surface Soil Moisture Inversion Model Based on Remote Sensing and Neural Network

Surface soil moisture (SSM) reflects the dry and wet states of soil. Microwave remote sensing technology can accurately obtain regional SSM in real time and effectively improve the level of agricultural drought monitoring, and it is of great significance for agricultural precision irrigation and smart agriculture construction. Based on Sentinel-1, Sentinel-2, and Landsat-8 images, the effect of vegetation was removed by the water cloud model (WCM), and SSM was retrieved and validated by a radial basis function (RBF) neural network model in bare soil and vegetated areas, respectively. The normalized difference vegetation index (NDVI) calculated by Landsat-8 (NDVI_Landsat-8) had a better effect on removing the influence the of vegetation layer than that of NDVI_Sentinel-2. The RBF network model, established in a bare area (R = 0.796; RMSE = 0.029 cm3/cm3), and the RBF neural network model, established in vegetated areas (R = 0.855; RMSE = 0.024 cm3/cm3), have better simulation effects on SSM than a linear SSM inversion model with single polarization. The introduction of surface parameters to the RBF neural network model can improve the accuracy of the model and realize the high-accuracy inversion of SSM in the study area.

Online identification and feed-forward compensation of nonlinear friction in servo system based on RBF neural network model

In this paper, an online identification and compensation method of nonlinear friction based on radial basis function (RBF) neural network model is proposed for the influence of nonlinear friction on machining accuracy in the low speed process of servo feed system of CNC machine tools. First, a three-layer single-input-output RBF neural network model is established for describing the nonlinear friction of servo feeding system. Second, the neural network online learning algorithm is improved based on adaptive gain, which improves the stability and accuracy of the algorithm. Finally, experiments were carried out on a three-axis milling machine to compensate the friction in the servo feed system in real time based on the online identification results. The results show that the method can effectively improve the online identification accuracy and convergence rate, and effectively improved the low-speed performance of the servo feed system.

RBFNN-based UWB 4×4 MIMO Antenna Design with Compact Size, High Isolation, and Improved Diversity Performance for Millimeter-Wave 5G Applications

Abstract The millimeter-wave spectrum has emerged as a compelling solution to address the pressing need for high-datarate
capabilities in the development of 5G technology systems. Spanning between 20 GHz and 40 GHz, this spectrum
encompasses several prominent frequency bands crucial for advancing 5G applications. In light of this, our study
presents a thorough investigation into the design and performance of a compact cross-shaped slot broadband antenna,
complemented by a 4×4 Multiple-InputMultiple-Output (MIMO) configuration tailored for 5G operations at
28 GHz. The primary objective of this study is to develop an antenna system capable of achieving an extended bandwidth
ranging from 20 GHz to 40 GHz, effectively covering the crucial frequency bands essential for 5G millimeterwave(
mmWave) operations. To accomplish this, the optimization of antenna performance is meticulously carried out
using the Radial Basis FunctionNeuralNetworks (RBFNN) model. The RBFNNmodel serves as a robust tool for establishing
the intricate relationship between antenna dimensions, resonant frequency, and bandwidth. Subsequently,
the developed RBFNN model is employed to predict optimal antenna dimensions, ensuring resonance at 28 GHz and
meeting specified bandwidth targets. The single antenna is designed with a rectangular patch and a cross-shaped
slot and is constructed on the low loss Rogers RT Duroid 5880 substrate. This design reaches an outstanding bandwidth
of 19.5 GHz, and exhibits excellent radiation characteristics, with a high radiation efficiency of up to 99% and a
corresponding gain of 5.75 dB. The antenna’s design and performance are rigorously designed using HFSS software,
which is then compared to the results acquired using CST software. In addition, the proposed MIMO configuration
offers excellent performance in terms of key features such as small size (16 × 16.2 mm2), very wide bandwidth of 20
GHz, good gain of 6.75 high isolation exceeding 35 dB, and significant improvements in diversity performance measures
such as Envelope Correlation Coefficient (ECC), Diversity Gain (DG), Channel Capacity Loss (CCL), Total Active
Reflection Coefficient (TARC), and Mean Effective Gain (MEG). The potential of the proposed MIMO configuration
for high-speed applications is particularly remarkable. Practical verification of the MIMO configuration is carefully
carried out by fabrication andmeasurement. Experimental results strongly confirmthe effectiveness of the proposed
antenna design, establishing it as a competitive challenger for 5G technology.

Learning active subspaces and discovering important features with Gaussian radial basis functions neural networks

Providing a model that achieves a strong predictive performance and is simultaneously interpretable by humans is one of the most difficult challenges in machine learning research due to the conflicting nature of these two objectives. To address this challenge, we propose a modification of the radial basis function neural network model by equipping its Gaussian kernel with a learnable precision matrix. We show that precious information is contained in the spectrum of the precision matrix that can be extracted once the training of the model is completed. In particular, the eigenvectors explain the directions of maximum sensitivity of the model revealing the active subspace and suggesting potential applications for supervised dimensionality reduction. At the same time, the eigenvectors highlight the relationship in terms of absolute variation between the input and the latent variables, thereby allowing us to extract a ranking of the input variables based on their importance to the prediction task enhancing the model interpretability. We conducted numerical experiments for regression, classification, and feature selection tasks, comparing our model against popular machine learning models, the state-of-the-art deep learning-based embedding feature selection techniques, and a transformer model for tabular data. Our results demonstrate that the proposed model does not only yield an attractive prediction performance compared to the competitors but also provides meaningful and interpretable results that potentially could assist the decision-making process in real-world applications. A PyTorch implementation of the model is available on GitHub at the following link.11https://github.com/dannyzx/Gaussian-RBFNN.

Thermal resistance optimization of ultra-thin vapor chamber based on data-driven model and metaheuristic algorithm

The ultra-thin vapor chamber(UTVC) is extensively utilized across various fields due to its excellent heat dissipation performance and good temperature uniformity. The data-driven modeling approach is well suited to predict the thermal resistance of the UTVC due to its great flexibility and accuracy. In this paper, a novel approach is proposed to optimize the UTVC thermal resistance, which combines the radial basis function neural network(RBFNN) model with an improved adaptive differential fish swarm evolution algorithm(ADFEA). The mean square error of the RBFNN model was 0.00016 on the training set and 0.00027 on the test sets, which indicates that the model is able to accurately predict the thermal resistance of the UTVC. The data are obtained from experiments on a mesh wick UTVC with dimensions of 124 × 14 × 1 mm. A novel optimization algorithm, ADFEA, has been designed to enhance optimization capability and convergence accuracy. This algorithm combines differential algorithm and artificial fish swarm algorithm, incorporating a parameter adaptation mechanism. The optimal operating parameters of the UTVC are obtained by ADFEA optimization and the accuracy of the optimized results is verified by experiment. The proposed optimization method provides new insights for the design and optimization of UTVC.

Research on thermal efficiency and weld forming coefficient prediction of ultra-high strength steel welded joint under different energy inputs

As an ultra-high strength steel, Al–Si coated 22MnB5 hot stamping steel is widely used in the manufacturing of body-in-white structural parts. Compared with traditional welding technology, laser welding is widely used in the field of automobile body-in-white manufacturing due to its high energy density, small heat affected zone, and high weld quality. For ultra-high strength steel laser welded joints, the weld forming coefficient is an important index to reflect the welding quality. In order to investigate the influence of weld forming coefficient on the Al content and the thermal efficiency, laser welding experiments of ultra-high strength steel under different laser energy inputs are carried out. The melting of the base metal and coating under different laser energy inputs is also considered. Particle swarm optimization (PSO) algorithm is introduced into radial basis function (RBF) neural network model to optimize the central parameters as the RBF neural network model alone is not sufficient in predicting the outcomes. The results shows that if the laser power density is constant (7 × 105 W/cm2), when laser energy inputs are 400 J/cm to 1200 J/cm, the Al content in welded joints is 1.458%–1.886%, the melting efficiency of welded joints is 0.23–0.26, the energy conversion efficiency of welded joints is 0.45–0.46. When the laser energy inputs are lower than 522 J/cm, the Al content of the laser welded joint increases gradually. When the laser energy inputs are higher than 522 J/cm, the Al content of the laser welded joint decreases. The root mean square error(RMSE) of PSO-optimized RBF neural network testing sets prediction results is 0.1551, R-square (R2) is 0.771 and mean absolute percentage error (MAPE) is 2.758%. The prediction accuracy of the PSO-optimized RBF neural network model for the upper surface weld width, waist weld width, and lower surface weld width is 93.9%, 91.1%, and 92.2%.

Multiple-input multiple-output Radial Basis Function Neural Network modeling and model predictive control of a biomass boiler

This study presents a model predictive control of a 4 × 3 Multiple-Input Multiple-Output (MIMO) biomass control system that uses radial basis function (RBF) as an activation function to enhance the control performance. The biomass boiler model is developed from the system identification box in MATLAB by collecting measured input and output data from the 31.5 MW Wonji sugar mill and analyzing the data using black box modeling approach. The major goal of this study is to improve the MIMO control performance of a biomass boiler by utilizing Radial Basis Function Neural Network (RBFNN) to increase model accuracy which ultimately enhances the overall control system. Biomass boilers have four inputs and three outputs. The inputs are airflow 1, airflow 2, water flow and stocker speed (the speed of the motor which feeds bagasse or sugarcane pulp) and outputs are temperature, pressure and drum level. The RBFNN model was programmed using MATLAB R2021a software with system identification toolbox. Shorter settling times of 0.286 s, 1.873 s, and 0.637 s, as well as tolerable overshoots of 0.505%, 1.5%, and 15.698% for temperature, pressure, and level respectively, were achieved with the suggested model predictive controller using RBFNN model. However, when utilizing the identical controller and state space model, the settling times are 2.318 s, 5.461 s, and 6.147 s, with overshoots of 4.737%, 8.152%, and 38.194% for the three variables respectively. The suggested method was compared to the model predictive control (MPC) biomass boiler state space model, which can be considered as a model without RBFNN. The simulation results indicate that the RBFNN-based MPC performed better than the state space model-based MPC. This is because, the state space model is always constant, in contrast to the neural network's active monitoring of boiler dynamics.

Application of pipeline leakage detection based on distributed optical fiber acoustic sensor system and convolutional neural network

Underwater pipelines are exposed to harsh environments, including high salinity, multi-modal vortex corrosion, and severe wave interference. Their safety is essential for the development and transportation of marine energy. Therefore, real-time safety monitoring of long-distance energy pipelines is of great strategic importance for ensuring the safety of life and property and energy security. With the rapid development of energy development, the corrosion and leakage mechanisms of natural gas pipelines, as well as their identification and early warning, have become the focus of attention. Optical fiber sensing technology has been applied to various energy safety monitoring fields. However, the mechanism of sound source fluctuations in pipeline leakage and the mutual coupling mechanism between distributed optical fiber sensing technology and leakage sound waves are not yet clear. This paper establishes a model based on sound wave propagation and leakage noise response, derives a quadratic fitting relationship between pipeline pressure fluctuations and leakage orifices and a relationship between leakage noise source standard deviation and orifices, and proposes a complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) permutation entropy underwater natural gas pipeline leakage signal recognition method based on distributed optical fiber acoustic sensing technology. The results of theoretical analysis are verified by experiments. It shows that the signal processing method of CEEMDAN permutation entropy is superior to traditional noise reduction methods, which can better preserve the features of the original signal; the radial basis function (RBF) neural network model can accurately identify four different leakage features with an accuracy of 88.15%, and its recognition stability and generalization ability are superior to convolutional neural network, backpropagation, and random forest. Therefore, the research results of this paper provide a new method for safety monitoring in the application of energy pipeline transportation engineering, and expand the potential application scenarios of distributed acoustic sensing sensor systems and RBF neural networks.

Eligibility of village fund direct cash assistance recipients using artificial neural network

<p>Bantuan Langsung Tunai Dana Desa (BLT-DD), or known as Village Fund Direct Cash Assistance is assistance from the Indonesian government which causes problems and conflicts in the community when the assistance is not on target. The classification algorithm is proven to use in determining BLT-DD recipients. In this study, the radial basis function (RBF) and elman recurrent neural network (ERNN) models compare to classify the eligibility of BLTDD recipients. In the experiment, the optimal performance of the RBF and ERNN compare in determining the eligibility of BLT-DD recipients. Also, it’s compared with the classification algorithm that implements the same data, namely BLT-DD data for Kubu Raya District. The experimental results show the effectiveness of the RBF model in recognizing test data, while the ERNN model is effective in identifying test data. The RBF and ERNN models can achieve the same total accuracy of 98.10%.</p>

Application of WCA-RBF Neural Network in Fault Diagnosis of Analog Circuits

With the fast growth of electronic technology today, the hybrid circuit of analog and digital circuits has become a trend in the growth of electronic technology. To address fault diagnosis in analog circuits, Haar wavelet is applied for fault feature extraction. The K-means clustering method and pseudoinverse algorithm were used to optimize the center value and weight value of the radial basis function neural network, respectively. The adaptive step size was improved in the wolf pack algorithm, the parameters of the radial basis function neural network were optimized based on the wolf pack algorithm, and a wolf pack algorithm optimized radial basis function neural network model was constructed. The test results show that this model converges after 40 times of training, with an error value of 10−3 and an average value of the mean squared error of 0.45. Comparing the fault diagnosis rates of the original model, genetic algorithm optimized radial basis function neural network model, and wolf colony algorithm optimized radial basis function neural network model, the last model has the best fault diagnosis rate, reaching 95.52%. The wolf colony algorithm is utilized to optimize the radial basis function neural network model to diagnose the faults in the standard filter circuit, and the fault diagnosis rate reaches 96.17%. The findings express that the radial basis function neural network model optimized by the wolf colony algorithm has a good diagnosis effect for different faults in the analog circuit.

Short-term solar radiation forecasting using machine learning models under different sky conditions: evaluations and comparisons.

Forecasting short-term solar radiation is crucial for many solar energy applications. Additionally, solar energy has a lower environmental impact than conventional sources like fossil fuels and can be used for investment purposes through the construction of large solar farm facilities. To test, evaluate, and compare various solar radiation models, short-term observations of meteorological, astronomical, computational, and geographical data were collected at two distinct locations from 2012 to 2015. In this study, seven machine learning models were employed: multi-layer perceptron (MLP), feedforward backpropagation algorithm (FFBP), autoregressive integrated moving average (ARIMA), linear regression (LR), radial basis function neural network (RBFNN), random forest (RF), and Gaussian process regression (GPR) models. These models were used to forecast hourly global solar radiation (GSR) using the aforementioned data as model input. The performance of the selected models' forecast accuracy was thoroughly examined by assessing it for a typical day, for four seasons, and under three sky conditions. The RF model can forecast GSR with satisfactory accuracy, and MLP and GPR models provide better accuracy than LR, FFBP, RBF, and ARIMA models. For example, the R2 value range of RF are 0.9621 for Tetuan site and 0.9534 for Tangier site, respectively. Meanwhile, RF, MLP, and GPR models under-forecast few high radiation values on clear days, which may due to the differences in training and testing data ranges and distributions of the sky conditions. Finally, the obtained result of this study indicate that the proposed RF model is a reliable alternative for short-term global solar radiation forecasting due to its high forecast accuracy.

Surface Roughness Prediction of Titanium Alloy during Abrasive Belt Grinding Based on an Improved Radial Basis Function (RBF) Neural Network.

Titanium alloys have become an indispensable material for all walks of life because of their excellent strength and corrosion resistance. However, grinding titanium alloy is exceedingly challenging due to its pronounced material characteristics. Therefore, it is crucial to create a theoretical roughness prediction model, serving to modify the machining parameters in real time. To forecast the surface roughness of titanium alloy grinding, an improved radial basis function neural network model based on particle swarm optimization combined with the grey wolf optimization method (GWO-PSO-RBF) was developed in this study. The results demonstrate that the improved neural network developed in this research outperforms the classical models in terms of all prediction parameters, with a model-fitting R2 value of 0.919.

Integrating discrete wavelet transform with neural networks and machine learning for fault detection in microgrids

Microgrids are essential for integrating renewable energy sources into the power grid. However, fault detection is challenging due to bidirectional energy flow. Traditional relay-based systems struggle in microgrids, primarily because of limited fault currents from grid-connected renewable energy inverters. To address these challenges, this paper proposes a new methodology for fault detection and classification in a renewable microgrid. The main contributions encompass two key aspects. Firstly, it enhances fault detection performance in microgrids characterized by nonlinear relationships, including photovoltaic, hydrokinetic, and variable electric load systems. Secondly, the combination of the discrete wavelet transform with various types of neural networks and supervised learning techniques provides a robust methodology for fault detection and classification. The proposed approach is evaluated using an IEEE-5 feeder test bed representing a realistic ring network configuration. The results show that the radial basis function neural network model exhibited promising outcomes, yielding a low prediction error of 1.31 e-31, highlighting its practical potential for enhancing system reliability and performance. Furthermore, various test cases were conducted by altering the ground resistance to train the neural networks, demonstrating the effectiveness of this neural network in accurately identifying fault conditions. Additionally, this research achieved promising outcomes with other models, including support vector machine and nonlinear autoregressive with external input, emphasizing the adaptability of these models in fault detection.

Dynamic event-triggered attitude synchronization of multi-spacecraft formation via a learning neural network control approach

This paper addresses the robust attitude synchronization issue in a multi-spacecraft formation system subjected to limited communication, space disturbances, modeling uncertainties, and actuator faults. To accommodate limited inter-spacecraft communication, a dynamic event-triggered mechanism is designed to reduce the communication trigger frequency by dynamically adjusting the trigger threshold. Moreover, an event-based distributed self-learning neural-network control (SLN2C) law is developed to guarantee robust attitude synchronization during multi-spacecraft formation. In the SLN2C scheme, a learning radial basis function neural network (RBFNN) model is proposed to online approximate and compensate for lumped disturbances, in which an iterative learning algorithm with a variable learning intensity is adopted to update the weight matrix of the RBFNN model. Compared with the traditional fixed learning intensity, a variable one can reduce initial oscillation and weaken the saturation response. Numerical simulations and comparisons are performed to illustrate the effectiveness and superiority of the proposed event-based spacecraft attitude synchronization control method.

Research on rainfall prediction based on RBF neural network model and stormwater inundation risk in scenic areas: A case study of the Yesanpo Scenic Area, Baoding, China

Research on stormwater inundation risk and rainwater management in scenic areas has a lot to do with rainfall during the flood season. When the measured rainfall data is limited, an artificial network model with nonlinear mapping capability can be applied to predict rainfall data during the flood season, which increases the sample size of rainfall data and improves the accuracy of research results. Based on a radial basis function (RBF)neural network model, this paper takes the Yesanpo Scenic Area in Baoding City, Hebei Province as an example to estimate the monthly maximum rainfall data during the flood season (July–September) of 2022, 2023, and 2024 in the study area. On this basis, the Pearson III frequency curve is used to calculate the design rainfall corresponding to the rainfall frequency of 20%, 5%, and 2%. With the help of SCS-CN model and ArcGIS spatial analysis tools, the stormwater inundation areas are simulated in the study area, which are divided into three risk levels: high, medium, and low, providing a reference for the stormwater management in the Yesanpo Scenic Area.

Prediction of mechanical properties for typical pressure vessel steels by small punch test combined with machine learning

To understand the fitness of different machine learning methods to small punch test (SPT), three machine learning methods, namely, back propagation (BP) neural network, radial basis function (RBF) neural network and random forest (RF) regression model were used to establish machine learning-based correlation models of SPT load–displacement and uniaxial tensile test true stress–strain curves. Five typical pressure vessel steels were tested to reveal the prediction accuracies of different machine learning methods. Statistical analysis, unveiled the following order of prediction accuracy for pressure vessel steels: BP > RBF > RF. However, the differences in the mean absolute percentage erros between BP and RF decreased from 5.64% to 1.59%, with the training data volume increasing from 50 data sets to 629 data sets. Therefore, if a large training data volume is used, then the three machine learning methods can provide acceptable prediction results. However, if the training data volume is insufficient, then the BP, and RBF neural networks are better choices.

MOPSO-based structure optimization on RPV sealing performance with machine learning method

The structure integrity of reactor pressure vessels (RPV) plays an important role in the safety of nuclear power plants, which mainly concerns the risk of sealing failure. In the present work, a hybrid method consisting of an artificial neural network (ANN) and multi-objective particle swarm optimization (MOPSO) is proposed, aiming to find an optimized RPV structure with improved sealing performance. The ANN model provides a more accurate prediction of sealing performance than the radial basis function neural network (RBFNN) model. There is also a better generalization ability in the ANN model with R2 above 0.96 and RMSE below 0.06 in the test set. With ANN as a surrogate model, multi-objective optimization is applied in RPV structure design. Compared with that of the original RPV structure, the sealing performance can be improved by even over 25% in the optimized structure. The application of ANN surrogate models can save more than 99% computation cost, compared with optimization based on finite element analysis (FEA).

Predicting quality of the whole egg powder during storage: Based on Arrhenius and radial basis function model

The quality of whole egg powder (WEP) deteriorates during long-term storage due to oxidation, which causes caking, discoloration and reduction of functional properties. The purpose of this study is to investigate the changes in lipid oxidation, protein oxidation, and functional characteristics of WEP during accelerated storage and to establish an Arrhenius model and radial basis function neural network (RBFNN) model to predict the oxidative changes in WEP. During storage, the peroxide value (PV) and thiobarbituric acid reactive substances (TBARS) of lipid oxidation significantly increased, and the Fourier transform infrared spectroscopy results showed an increasing trend in the characteristic absorption peaks of lipid hydroperoxides, free fatty acids, and cis fatty acids. The carbonyl groups, surface hydrophobicity, and fluorescence intensity significantly decreased, and the functional characteristics showed a decreasing trend in the solubility, foaming, and emulsifying properties of WEP. Most importantly, compared to the Arrhenius model, the RBFNN model could predict and assess the lipid and protein quality of WEP more accurately, with a small mean squared error (MSE) (0.00048) for storage at 20–60 °C.

Experimental and numerical investigation of heat transfer and flow of water-based graphene oxide nanofluid in a double pipe heat exchanger using different artificial neural network models

In this study, a water-based graphene oxide nanofluid was utilized in a counter-current flow double pipe heat exchanger (DPHE). The inner pipe carried the hot fluid (deionized water-based fluid). In the outer pipe, the cold fluid was flown, in which the experiments were performed once for deionized water-based fluid and once for graphene oxide nanofluid. These experiments were conducted at various inlet hot fluid temperatures of 35, 45, and 55 °C, volumetric concentrations of 0.01, 0.055, and 0.1% for nanofluid, and cold fluid flow rates of 14.4, 18.9, and 23.4 ml/s to evaluate the thermohydraulics of the DPHE. The results demonstrated that an increase in the flow rate and concentration of nanoparticles led to an improvement in the heat transfer coefficient (HTC) . It is also observed that inlet hot fluid temperature had a negligible effect on this coefficient compared to the concentration and flow rate. Additionally, the results showed that the friction factor and pressure drop of nanofluid were higher than those of the basefluid and their values were increased by increasing the concentration. The maximum increase compared to the basefluid was 72% for the friction factor and 111%, for the pressure drop. Besides, radial basis function neural network (RBFNN) and multi-layer perceptron neural network (MLPNN) models were designed for estimating the HTC. Both models accurately predicted the coefficient, but the RBFNN model exhibited higher accuracy than the MLPNN model. The results further indicated that the nanofluid outperformed the basefluid in terms of HTC. Due to the exceptionally high thermal conductivity of graphene nanoparticles, the HTC of the nanofluid was improved by up to 85% compared to the basefluid. The optimum value of HTC was achieved at a temperature of 55 °C, a volume concentration of 0.1%, and a flow rate of 23.4 ml/s.

Discrimination of internal browning in pineapple during storage based on changes in volatile compounds

Internal browning (IB) is a physiological disorder without external symptoms of postharvest pineapples, but whether and how IB influences pineapple volatiles remain unknown. We examined eigenvalues of volatiles in ‘Comte de Paris’ pineapples with or without IB using electronic nose (E-nose) and gas chromatography-mass spectrometry (GC–MS). Correlation coefficients between the responses of E-nose sensors S7 and S9 and IB were 0.836 and 0.804, respectively. The multilayer perceptron neural network and radial basis function neural network models classified IB degree with accuracy of 94.77% and 91.67%. GC–MS analysis revealed 30 volatile substances upregulated in pineapple with IB compared to those without, of which 15 were esters. IB regulated volatile compound synthesis through the lipoxygenase pathway which involved lipoxygenase, pyruvate decarboxylase 1, alcohol dehydrogenases, acyl-CoA oxidase 1, and alcohol acyltransferase genes and their related enzymes. These results suggested that volatiles regulated by IB could be used to discriminate IB severity in pineapples.