Hybrid Identification Method Research Articles

Convolutional neural network-support vector machine-based approach for identification of wheat hybrids

Selecting wheat hybrids is vital for enhancing crop yield, adapting to changing climates, and ensuring food security. These hybrids align with market demands and sustainable farming practices, contributing to efficient crop management. Traditional methods for wheat hybrid selection, such as molecular techniques, are costly and time-consuming, and are prone to human error. However, advancements in artificial intelligence and machine learning offer non-destructive, objective, and more efficient solutions. This study is explored the classification of wheat varieties and hybrids using two deep learning models, MobileNetv2 and GoogleNet. These models are achieved impressive classification accuracy, with MobileNetv2 reaching 99.26% and GoogleNet achieving 97.41%. In the second scenario, the deep features obtained from these models are classified with Support Vector Machine (SVM). In the classification made with the MobileNetv2-SVM hybrid model, an accuracy of 99.91% is achieved. This study is provided rapid and accurate wheat variety and hybrid identification method, as well as contributing to breeding programs and crop management.

Suggesting a prospect for melatonin-mediated orchid flowering under extreme conditions

Abiotic stress is a major constraint in the successful growth and development of ornamental plants under severe conditions. Since antiquity, melatonin homeostasis has been an effective contrivance in the strategies of abiotic stress tolerance in plants, although it is completely neglected in orchids, the champagne of flowers. Orchids with exceptionally long vegetative phase face a number of stresses and, therefore, stress alleviation has been a hot topic in orchid cultivation. The in-vitro flowering is a useful method for early identification of hybrids in crop improvement programs. We successfully achieved in-vitro leafless flowering in three Cymbidium orchids (C. sinense, C. goeringii and C. ensifolium), which are elite flowers in terms of versatile flower shapes, esthetic preference and price. Transcriptomic analysis was performed to compare the leafless flowers with leaves to identify genes related to tryptophan pathway and melatonin biosynthesis. More than 50 differentially expressed genes (DEGs) were identified in each species with contrasting expressions in the leafless flowers and leaves. The important melatonin pathway genes included serotonin N-acetyltransferase (SNAT), caffeic acid 3-O-methyltransferase (CAMT) and tryptophan decarboxylase (TDC). Moreover, clustering analysis pointed out the significant abiotic stress tolerance-related genes. This opening report, thus, provides a robust cradle to idealize the melatonin as an effective abiotic stress regulator to aid the long journey of vegetative growth and then flowering in precious orchids.

Identification of Asymmetric Bouc–Wen Hysteresis Under Intense Noise by Only Measuring Acceleration

Abstract Parameter identification of hysteretic models is significant for predicting structural dynamic response in vibration isolation structures. However, quasi-static testing and displacement measurement methods are not convenient for assembly structures and sensor layouts. Moreover, the methods based on evolutionary optimization need to provide appropriate boundary conditions for convergence and efficiency. Therefore, a novel hybrid identification method that takes the advantage of physics-informed parameter constraints and only acceleration measurement is proposed to identify the asymmetric Bouc–Wen hysteresis model. The restoring force surface is constructed for hysteretic force extraction based on the measurement of base excitation and isolated mass acceleration. The polynomial fitting and limit cycle approach are utilized for physical information given of an improved Bouc–Wen model. Furthermore, the evolutionary algorithm based on parameter constraints is implemented for final parameter estimation. A numerical simulation of an asymmetric Bouc–Wen model shows that the proposed method can keep an normalized mean square error (NMSE) of 0.19% under the noise level of 30 dB. The reconstructed hysteresis loop keeps in good agreement with the theoretical one.

Hybrid identification method of material parameters based on genetic algorithm and improved homotopy algorithm

This paper proposes a hybrid identification method of material parameters based on genetic algorithm and improved homotopy algorithm. In this method, genetic algorithm is first used to perform a preliminary identification of the model parameters. Then, the results of the preliminary identification are used as the initial values for more precise parameter identification using the improved homotopy algorithm. Based on the Euler prediction-Newton correction homotopy algorithm, a curve prediction-Newton correction homotopy algorithm is proposed to improve the calculation accuracy and efficiency. The effectiveness and accuracy of the hybrid identification method are verified by numerical examples. The hybrid identification method is applied successfully to determine material characteristic parameters of FGH97. The results indicate that based on experimental data and numerical simulations, the hybrid identification method can rapidly obtain effective and reliable material parameters. This method reduces the calculation amount, avoids dependence on the selection of the initial population, and has a high calculation accuracy and efficiency for the inverse problem of parameter identification. It provides an effective method to accurately identify material parameters and can also be applied to parameter identification of other materials. • A hybrid identification method of material parameters based on genetic algorithm and improved homotopy algorithm is proposed. • Curve prediction-Newton correction homotopy algorithm is proposed to improve the calculation accuracy and efficiency. • The effectiveness and accuracy of the hybrid identification method are verified by numerical examples. • The hybrid identification method is applied successfully to determine material characteristic parameters of FGH97 • Hybrid identification method can also be applied to parameter identification of other materials.

Hybrid identification method for fractional-order nonlinear systems based on the multi-innovation principle

Hybrid identification method for fractional-order nonlinear systems based on the multi-innovation principle

Output-only structural damage identification using hybrid Jaya and differential evolution algorithm with reference-free correlation functions

To solve the optimization-based structural damage identification problem, a novel hybrid algorithm based on Jaya and differential evolution algorithm (HJDEA) is proposed to detect, locate and quantify structural damages by effectively incorporating the powerful local exploitation capacity of Jaya algorithm and global exploration capability of differential evolution. Meanwhile, Hammersley sequence initialization and Lévy flight search mechanism are introduced into HJDEA to further improve convergence rate and refining the quality of the best solution. Four different algorithms, genetic algorithm, particle swarm optimization, Jaya and the proposed HJDEA are employed for comparative study. In addition, the objective function is established by adjacent acceleration correlation function so as to avoid false identification caused by defining improper reference point. The performance of the proposed damage identification strategy based on HJDEA and adjacent acceleration correlation function is investigated with numerical examples involving an 8-DOF lumped mass model and a cantilever beam, as well as an experimental study of the ASCE benchmark structure under white noise excitation. Results show that the proposed hybrid identification method is accurate, efficient and robust in the identification of the damage existence, location and severity of stiffness and mass parameters even with partial output-only responses and 20% noise-polluted measurements.

MILM hybrid identification method of fractional order neural-fuzzy Hammerstein model

MILM hybrid identification method of fractional order neural-fuzzy Hammerstein model

Hybrid identification method of coupled viscoplastic-damage constitutive parameters based on BP neural network and genetic algorithm

The constitutive model based on the theoretical framework of coupled viscoplastic-damage involves calibration of multiple and high coupling parameters. The inverse calibration by genetic algorithm (GA) with global search ability has some challenges as the dependence on the selection of the initial population, massive computation, and convergence inconsistency. To obtain statistical knowledge from state data to avoid subjective experience, a hybrid identification method based on the BP neural network and GA is proposed. A coupled viscoplastic-damage constitutive model based on the thermal deformation and microstructure evolution is established. The parameters in the model are determined based on the hybrid identification method. Two types of aluminum alloy sheets are selected to test the generalization, and mean square errors (RMSE) are 2.46 and 4.89, respectively. The results indicate that this method has higher accuracy than the inverse calibration method based on single optimization algorithm.

Kinematic Calibration of Industrial Robots Based on Distance Information Using a Hybrid Identification Method

To improve the positioning accuracy of industrial robots and avoid using the coordinates of the end effector, a novel kinematic calibration method based on the distance information is proposed. The kinematic model of an industrial robot is established. The relationship between the moving distance of the end effector and the kinematic parameters is analyzed. Based on the results of the analysis and the kinematic model of the robot, the error model with displacements as the reference is built, which is linearized for the convenience of the following identification. The singular value decomposition (SVD) is used to eliminate the redundant parameters of the error model. To solve the problem that traditional optimization algorithms are easily affected by data noise in high dimension identification, a novel extended Kalman filter (EKF) and regularized particle filter (RPF) hybrid identification method is presented. EKF is used in the preidentification of the linearized error model. With the preidentification results as the initial parameters, RPF is used to identify the kinematic parameters of the linearized error model. Simulations are carried out to validate the effectiveness of the proposed method, which shows that the method can identify the error of the parameters and after compensation the accuracy of the robot is improved.

Online probabilistic model class selection and joint estimation of structures for post-disaster monitoring

Online selection of the appropriate model and identifying its parameters based on measured vibrational data are among the challenging issues in dynamic system identification. After a severe earthquake, quick monitoring and assessment of structural health status play a crucial role in effective critical risk management for the building owners and decision-makers. The Bayesian multiple modeling approach is a suitable tool for optimal model class selection, which is used in this article mainly for improving data fitting precision, decreasing dimensions of structural unknown vector through removing unnecessary parameters, detecting the occurrence and type of predominant phenomenon related to degradation and pinching, and finally increasing stability and convergence rate of the used identification algorithm. In this study, a reliable and effective time-domain method is proposed for online probabilistic model class selection and joint estimation of structures using the central difference Kalman filter and Bayesian multiple modeling approach. Also, in contrast to existing studies, the performance and efficiency of the proposed algorithm are investigated in nonlinear system identification with a large number of unknowns. The proposed algorithm is implemented on three moment-frame buildings with 8, 54, and 60 unknowns. In addition, a numerical example is provided to analyze the case in which the exact model is not among the plausible models. To verify the performance of the hybrid identification method, robust simulations with synthetic measurement noises and modeling errors were generated using the Monte Carlo random simulation method. The result shows the method can be used to simultaneously select the optimal model class and identify its unknown states and parameters in an online manner.

A hybrid identification method on butterfly optimization and differential evolution algorithm

Modern swarm intelligence heuristic search methods are widely applied in the field of structural health monitoring due to their advantages of excellent global search capacity, loose requirement of initial guess and ease of computational implementation etc. To this end, a hybrid strategy is proposed based on butterfly optimization algorithm (BOA) and differential evolution (DE) with purpose of effective combination of their merits. In the proposed identification strategy, two improvements including mutation and crossover operations of DE, and dynamic adaptive operators are introduced into original BOA to reduce the risk to be trapped in local optimum and increase global search capability. The performance of the proposed algorithm, hybrid butterfly optimization and differential evolution algorithm (HBODEA) is evaluated by two numerical examples of a simply supported beam and a 37-bar truss structure, as well as an experimental test of 8-story shear-type steel frame structure in the laboratory. Compared with BOA and DE, the numerical and experimental results show that the proposed HBODEA is more robust to detect the reduction of stiffness with limited sensors and contaminated measurements. In addition, the effect of search space, two dynamic operators, population size on identification accuracy and efficiency of the proposed identification strategy are further investigated.

Research on tobacco foreign body detection device based on machine vision

Foreign body detection is an important aspect that affects the quality of tobacco production. This paper describes a direct foreign body detection scheme using machine vision, which uses three cameras arranged around a tobacco bale to record its multiple surfaces and directly identify foreign bodies. In this study, color sorting table method (CSTM) was first used to identify and remove color-sensitive foreign bodies; thereafter, gray threshold method and double threshold method were used to further identify and remove foreign bodies with similar colors. The experimental results indicate that the multi-step hybrid identification method proposed herein can effectively identify and remove various foreign bodies in the production process of tobacco packs, with an accuracy rate of 97.8%, which meets the industrial requirements for foreign body detection. Compared with various existing devices and methods, it has the advantages of high detection efficiency and low cost.

Inverse identification of graphite damage properties under complex stress states

As a key material in high-temperature gas-cooled reactors (HTGR), nuclear graphite is a type of quasi-brittle material with complex damage mechanisms. However, it is difficult to characterise the damage properties of nuclear graphite under complex stress states using conventional testing approaches or inverse methods. In this study, a hybrid identification method based on 8-node quadrilateral element digital image correlation (Q8-DIC), a double iterative finite element model updating (FEMU) technique, and artificial neural networks (ANNs) is presented to characterise the damage properties of IG11 graphite material under complex stress states. First, this method is verified using simulated tests on a ring under diametrical compression, then applied to actual mechanical testing of graphite material to evaluate its damage properties. Finally, factors affecting the evolution of damage are discussed. The results indicate that the first principal strain has the most significant effect on the damage evolution of the graphite material.

A Hybrid Estimation and Identification Method for Online Calculation of Voltage-Dependent Load Parameters

This paper presents a hybrid estimation and identification (HEI) method for identifying the load model parameters of voltage-dependent loads along with estimating the system states. The parameters of voltage-dependent load models are identified using multiple snapshots consecutively gathered through supervisory control and data acquisition system. The proposed HEI method imposes no additional cost to the installed metering devices or communication network. Mathematical aspects of the proposed HEI method are analytically proved and a four-step approach is presented for implementing it. Comprehensive numerical experiments and statistical analysis are presented to demonstrate the effectiveness of the proposed method for both load model identification and state estimation.

A Novel Adaptive Weighted Least Square Support Vector Regression Algorithm-Based Identification of the Ship Dynamic Model

This study contributes to developing a novel hybrid identification method based on intelligent algorithms, i.e. the least support vector regression algorithm (LS-SVR) and the artificial bee colony algorithm (ABC), to deal with the identification of the simplified ship dynamic model while the outliers exist in the measurements. The ship dynamic model is directly derived from our previous work which has been well verified and validated. The outliers are detected by introducing the robust estimation method namely the $3\sigma $ principle and then deleted from the training data. The weighted version of LS-SVR (WLS-SVR) with spareness and robustness ability is used as the fundamental identification approach. To improve the performance of the WLS-SVR, the structural parameters involved in it are optimized by utilizing the artificial bee colony algorithm (ABC), and the weights of it are adaptively set with the use of the adaptive weight method. Two case studies including the simulation study on a container ship and the experimental study on an Unmanned Surface Vessel (USV) are carried out to test the proposed hybrid intelligent identification method. The simulation study demonstrates the effectiveness and the acceptable time complexity in terms of the engineering application of the proposed identification method through the comparison with the cross-validation method and particle swarm optimization algorithm optimized LS-SVR. In the experimental study, ABC-LSSVR, ABC-LSSVR with the $3\sigma $ principle (D-ABC-LSSVR), ABC-LSSVR with the adaptive weight (ABC-AWLSSVR), and ABC-LSSVR with both the $3\sigma $ principle and the adaptive weight (D-ABC-AWLSSVR) are applied to identify the steering model for the USV. The results indicate that the influence of the outliers on model identification is effectively diminished by the robust $3\sigma $ principle and the adaptive weight method and that the D-ABC-AWLSSVR outperforms over the other three identification methods in terms of the mean squared error (MSE) of the model predictions.

Establishment of co-infection and hybridization of Haemonchus contortus and Haemonchus placei in sheep.

This study aimed to evaluate the simultaneous infections of Haemonchus contortus and Haemonchus placei in sheep, as well as the production of hybrids. A parental group of lambs (n = 6) were mix-infected with 2000 infective larvae (L3) of H. placei and 2000 L3 of H. contortus. Faecal samples were taken from each of these six lambs to produce the first generation of L3 (F1-L3) in individual cultures. These F1-L3 were used to infect 12 lambs; six of them were euthanized at 42 days (Group F1-42) and six at 84 days (Group F1-84) post infection. Polymerase chain reaction (PCR) analysis, using species-specific primer pairs, was the gold standard method for identification of Haemonchus adult species and hybrids. The establishment rate of both species was similar in the parental group: 51.7% H. contortus and 48.3% H. placei. Of the 219 adult specimens from groups F1-42 and F1-84 analysed by PCR, eight (3.65%) were hybrids, 111 were H. contortus and 100 were H. placei. The morphological evaluation of the F1-L3 from the parental group showed a predominance of larvae with H. contortus size (51.5%) in comparison with H. placei (42.8%). In the second generation of L3 (F2-L3) produced by the F1-lambs, larvae with H. contortus morphology predominated, with 81.5% in the F1-42 group and 84.0% in the F1-84 group. In conclusion, an artificial mixed infection by H. contortus and H. placei was established in lambs and resulted in the production of a small number of hybrids among their offspring.

Decoding natural images from evoked brain activities using encoding models with invertible mapping

Recent studies have built encoding models in the early visual cortex, and reliable mappings have been made between the low-level visual features of stimuli and brain activities. However, these mappings are irreversible, so that the features cannot be directly decoded. To solve this problem, we designed a sparse framework-based encoding model that predicted brain activities from a complete feature representation. Moreover, according to the distribution and activation rules of neurons in the primary visual cortex (V1), three key transformations were introduced into the basic feature to improve the model performance. In this setting, the mapping was simple enough that it could be inverted using a closed-form formula. Using this mapping, we designed a hybrid identification method based on the support vector machine (SVM), and tested it on a published functional magnetic resonance imaging (fMRI) dataset. The experiments confirmed the rationality of our encoding model, and the identification accuracies for 2 subjects increased from 92% and 72% to 98% and 92% with the chance level only 0.8%.

Computational fluid dynamics modeling and parameterization of the visible light photocatalytic oxidation process of toluene for indoor building material

Poor indoor environmental conditions caused by the presence of gas-phase/aerosol-phase contaminants are thought to be potential triggers of illnesses, leading to productivity losses. In recent decades, the photocatalytic oxidation (PCO) process has attracted attention because of its potential to purify indoor air polluted with volatile organic compounds (VOCs), especially at low concentration levels. Titanium-dioxide (TiO2)-bound building materials have been extensively studied for the oxidation of indoor VOCs. In this study, kinetic studies were carried out to evaluate the PCO of toluene in the gas phase, over TiO2-bound building materials, using a 20l small test chamber. A Langmuir–Hinshelwood (L–H)-type model, for reproducing the PCO process over TiO2-bound building materials, was developed as a function of the toluene concentration, illumination intensity, and humidity levels. The parameters of the L–H model were determined using the hybrid identification procedure of computational fluid dynamics (CFD) simulations and a 20l small test chamber experiment. By using this hybrid identification method, PCO kinetic parameters were estimated with reference to the concentration in viscous-sub layer. Finally, CFD simulations were also carried out under the same boundary conditions as those used in the chamber experiments to evaluate the prediction accuracy.

Embedded system for staff access control using NFC and MIFARE technologies

This paper presents the analysis and performance evaluation of an embedded prototype to control the access of people to companies or institutions by using short range wireless technologies, like NFC and RFID. The developed system proposes a hybrid identification method between MIFARE cards and smartphones with Android operating system. It integrates a web platform in charge of the processing of the system data and increase the use of the technology through services where the gathering of people and objects register and authentication is required. With this proposal, we seek to optimize the time in the identification transactions and improve the security in places where the manual access is carried out. This work is an answer to the need of an adequate management of the access control of the Technological Faculty personnel in the Universidad Distrital Francisco José de Caldas in Bogotá: the chosen scenario for testing our proposal.

A reliable and cost-effective method for the early identification of citrus rootstock hybrids using high resolution melting analysis

A reliable and cost-effective method for the early identification of citrus rootstock hybrids using high resolution melting analysis