ABSTRACT
Objective To compare the principles and performance of three Hough transform algorithms(standard Hough transform,gradient based Hough transform,and random Hough transform)in order to establish a suitable control basis for precise and rapid recognition of targets and acquisition of target center coordinates for craniocerebral puncture robots.Methods A simulation environment in MATLAB software was built to study and analyze image feature recognition,filtering,edge detection,cumulative voting and other processing engineering.Contour recognition and fitting of target circles were achieved in multiple scenarios before their center coordinates were obtained.The recognition and fitting performance of these algorithms was quantitatively compared.Finally,a better detection algorithm based on the actual environment of the craniocerebral puncture robot was determined.Results The standard Hough transform algorithm had the largest error between the mark circle and the target circle,and the running time of this algorithm was the longest due to large computation.The detection speed of the random Hough transform algorithm was lower than that of the gradient-based Hough transform algorithm,but the fitting accuracy was slightly better than that of the standard Hough transform algorithm.The speed and accuracy of circle fitting based on the gradient Hough transform algorithm had significant advantages over the other two.Conclusion The gradient based Hough transform algorithm is more suitable for obtaining the target center coordinates of the craniocerebral puncture robot system.
ABSTRACT
RESUMEN Introducción: Las irregularidades en los movimientos oculares constituyen un indicador importante para diagnosticar determinadas enfermedades neurodegenerativas. La electrooculografía es la técnica más difundida para medir dichos movimientos oculares. Durante la realización de una prueba visual, el paciente puede realizar movimientos de cabeza indeseados que añaden perturbaciones a la señal electrooculográfica, modificando su morfología y, por tanto, alterando determinados parámetros diagnósticos. Objetivo: Desarrollar un método para corregir el efecto del desplazamiento angular horizontal de la cabeza en la señal electrooculográfica. Método: Se detalla un modelo matemático utilizado en la Universidad de Oriente desde marzo de 2021 a diciembre de 2021, para la implementación de la corrección en dos tipos de señales electrooculográficas artificiales con diferentes movimientos de cabeza horizontales. Resultados: Se evalúo cualitativamente el comportamiento del método utilizado a través de su implementación en señales generadas artificialmente en MATLAB. Finalmente se caracterizaron los efectos de la corrección en los parámetros diagnósticos de la señal electrooculográfica. Conclusiones: El método implementado demostró su validez para casos específicos, en el que se logra para dos tipos de señales eliminar los errores introducidos por el desplazamiento de la cabeza. La corrección mejora el error introducido en la amplitud de la señal electrooculográfica sin corregir y mantiene inalterables, a falta de un análisis más profundo, los demás parámetros diagnósticos.
ABSTRACT Introduction: Eye movement disorders are an important indicator for the diagnosis of certain neurodegenerative diseases. Electrooculography is the most widespread technique for measuring such eye movements. During the performance of the eye test, patients may forge unwanted head movements that add disturbances to the electrooculographic signal, modifying its morphological characteristic and, therefore, changing certain diagnostic parameters. Objective: To develop a method for the correction of the effect of the horizontal and angular head displacement by the electrooculographic signal. Method: It is detailed the use of a mathematical model for the correction of two types of artificial electrooculographic signals with different horizontal head movements at the Universidad de Oriente, from March 2021 to December 2021. Results: The behavior of the method used was evaluated qualitatively through its implementation in the signals generated artificially in MATLAB. Finally, the correction effects on the diagnostic parameters of the electrooculographic signal were characterized. Conclusions: The implemented method proved its validity for specific cases, in which it is possible to eliminate the errors caused by head displacement in two types of signals. The correction minimizes the error introduced in the uncorrected electrooculographic signal amplitude and keeps unchanged the other diagnostic parameters in absence of further analyses.
RESUMO Introdução: As irregularidades nos movimentos oculares são um importante indicador para diagnosticar certas doenças neurodegenerativas. A eletrooculografia é a técnica mais difundida para medir esses movimentos oculares. Durante um teste visual, o paciente pode realizar movimentos involuntários da cabeça que adicionam distúrbios ao sinal eletrooculográfico, modificando sua morfologia e, portanto, alterando alguns parâmetros diagnósticos. Objetivo: Desenvolver um método para corrigir o efeito do deslocamento angular horizontal da cabeça no sinal eletrooculográfico. Método: Um modelo matemático usado na Universidade de Oriente de março de 2021 a dezembro de 2021 é detalhado para a implementação da correção em dois tipos de sinais eletrooculográficos artificiais com diferentes movimentos horizontais da cabeça. Resultados: O comportamento do método utilizado foi avaliado qualitativamente através de sua implementação em sinais gerados artificialmente no MATLAB. Por fim, foram caracterizados os efeitos da correção sobre os parâmetros diagnósticos do sinal eletrooculográfico. Conclusões: O método implementado demonstrou sua validade para casos específicos, nos quais é possível eliminar os erros introduzidos pelo deslocamento da cabeça para dois tipos de sinais. A correção melhora o erro introduzido na amplitude do sinal eletrooculográfico não corrigido e mantém os demais parâmetros diagnósticos inalterados, na ausência de uma análise mais profunda.
ABSTRACT
Objective:To study the value of autoregressive integrated moving average (ARIMA) and autoregressive (AR) models in predicting the daily number of ambulances in prehospital emergency medical services demand in Guangzhou.Methods:Matlab simulation software was used to analyze the emergency dispatching departure records in Guangzhou from January 1, 2021 to December 31, 2021. A time series for the number of ambulances per day was calculated. After identifying the time series prediction model, ARIMA(1,1,1), AR(4) and AR(7) models were obtained. These models were used to predict the number of ambulances per day. ARIMA(1,1,1) model divided the time series into the training set and test set. Prony method was used for parameter calculation, and the demands of number of ambulances of the next few months were forecasted. AR(4) and AR(7) models used uniformity coefficient to forecast the demands of number of ambulances on that very day.Results:ARIMA(1,1,1), AR(4) and AR(7) can effectively predict the number of ambulances per day. The prediction fitting error of ARIMA (1,1,1) decreased with the extension of prediction time. The mean absolute percentage error (MAPE) of forecast results of daily vehicle output of emergency dispatching within two months was less than 6% and the predicted results were almost within the 95% confidence interval. The residual analysis of the model verified that the model was significantly effective.Conclusions:ARIMA model can make a long-term within two months and effective prediction fitting of the daily vehicle output of emergency dispatching, and AR model can make a short-term and effective prediction of the daily vehicle output of emergency dispatching.
ABSTRACT
A software platform for AI-ECG algorithm research is designed and implemented to better serve the research of ECG artificial intelligence classification algorithm and to solve the problem of subjects data information management. Matlab R2019b and MySQL Sever 8.0 are used to design the software platform. The software platform is divided into three modules including data management module, data receiving module and data processing module. The software platform can be used to query and set the subjects information. It has realized the functions of data receiving, signal processing and the display, analysis and storage of ECG data. The software platform is easy to operate and meets the basic needs of scientific research. It is of great significance to the research of AI-ECG algorithm.
Subject(s)
Humans , Algorithms , Artificial Intelligence , Electrocardiography , Signal Processing, Computer-Assisted , SoftwareABSTRACT
Objective:To establish a motion planning method for avoiding singularities for manipulator-assisted puncture surgery navigation, and design the corresponding computer program.Methods:According to the actual operation and the need of clinicians, the puncture needle sleeve installed at the end of the UR3 robotic arm was designed, and the kinematics analysis and simulation verification of the robotic arm were performed. A calculation program for solving the movement pose when the puncture needle at the end of the robotic arm reaches the target position, and a motion planning program for avoiding singularities through small-angle rotation were programmed.Results:Six groups of joint angles were randomly selected, and the theoretical coordinates calculated by the program were compared with the actual coordinates. The result showed that the error between the theoretical value and the actual value was small, which proved the correctness of the kinematics model. In the verification experiment, 3 sets of initial poses at random were simulated, the best pose was obtained by the program. Then the pose was transmitted into the control system to control the movement of the robotic arm. The verification experiment results showed that the puncture needle can reach the target point, and the singularity can be effectively avoid by the small-angle rotation of the fixed central axis.Conclusions:The singular point avoidance method based on end posture rotation can effectively avoid the failure of initial target posture motion planning, and it has reference value for the application of manipulator in puncture surgery.
ABSTRACT
Introduction: Posture analysis software Matlab 7.11 R2010b is commonly used as a tool for postural assessment. It is easy to use. Nonetheless, reliability studies are lacking. Methods: The study sample consisted of 25 pictures from 25 subjects, and each subject was assessed (1 day interval) by 3 blinded raters and by 1 blind rater for 3 times. Photographs of subject were coded and two variables (Lumbar lordosis and Pelvic tilt) were analyzed. Inter- and intra-rater reliabilities were calculated using intra-class correlation coefficient. Results: The intra-class correlation coefficient (ICC) was calculated. We found excellent inter-rater reliability and intra-rater reliability of Posture analysis software Matlab7.11 R2010b for both variables. Discussion: Observation posture analysis is easy but it is less reliable method. It cannot be used to measure progression of posture corrections and for research purpose. Photography method is most reliable method to evaluate posture. There are many softwares available for analysis of posture and Matlab 7.11 R2010b is one of them. In this study we found excellent inter-rater reliability and intra-rater reliability of the software. Conclusion: The postural assessment software Matlab 7.11 R2010b is having excellent inter-rater reliability and intra-rater reliability and should be considered as a reliable tool for postural assessment.
ABSTRACT
Objective::To construct the color matching template irrelevant to size and rotation according to the types and distribution characteristics of colors in images of Chinese herbal pieces, in order to establish color characterization and image identification methods for Chinese herbal pieces. Method::Totally 20 types of Chinese herbal pieces were selected, including rhizomes, flowers, seeds and fruits.For each sample, two observation surfaces were selected to extract color parameters in foreground through image processing such as image segmentation, model transformation from RGB to L*a*b*.Color vectors of the two observation surfaces were sequenced in a descending order, scaled to a certain size by interpolating, and combined into an integrated color vector in a weight ratio of 1∶1.As for centripetally distributed observation surface images(e.g.transverse section), corrosion operation was conducted to extract the color components of each ring from outer to inner by circles, which were then ordered and scaled.The integrated color vector was used as initial template for training, the correlation coefficient between each sample and the template was calculated, and the interval estimation of positive samples were carried out by t test.With the total recognition rate as an indicator, the optimal template dimensions, width of ring and training volume were ultimately determined. Result::The visualization results of the trained templates of the varied herbal pieces were easy to be visually distinguished.After 260 samples of the herbal pieces were tested, the template of a and b components was better than that of L*, a* and b* in terms of recognition performance, with a* recognition accuracy of 95.8%(249/200). Conclusion::Color characteristics of images from two observation surfaces of Chinese herbal pieces are integrated to obtain the combined color feature vector, so as to achieve preferable recognition results for samples from both the same and different medicinal parts.This method boasts a strong anti-interference ability of random variation of sample shape, sampling part and color.
ABSTRACT
OBJECTIVE: To establish the elimination method of outliers based on Grubbs rule and MATLAB language, and to evaluate the effects of it on drug bitterness evaluation. METHODS: Referring to Grubbs rule, the automatic cyclic outliers elimination method based on MATLAB language was established. Totally 20 volunteers were included in single oral taste test (Tetrapanax papyrifer) and multiple oral taste test (10 kinds of medicinal material as T. papyrifer, Changium smyrnioides, Poria cocos, etc.). Seven sensors were selected for electronic tongue test (Clematis armandii). The data of bitterness evaluation in above tests (oral taste test as bitterness value, electronic tongue test as response value of sensors) were used as the data source. Five researchers were selected and adopted table-by-table elimination method based on Grubbs rule (method one), Excel software elimination method based on Grubbs rule (method two) and automatic cyclic outliers elimination method based on Grubbs rule and MATLAB language (method three) to judge and eliminate the outliers. The effects of above three methods were evaluated with the removal time and error rate of outliers as indexes. RESULTS: There were two outliers in the data of bitterness evaluation in single oral taste test; the elimination time of the three methods were(745.400 0±25.904 4),(288.333 3±31.253 1)and(0.000 3±0.000 0)s, respectively; error rates were 20.0%, 0 and 0, respectively. There were six outliers in the data of bitterness evaluation in multiple oral taste test; the elimination time of three methods were (3 693.107 7±75.023 3), (1 494.761 4±53.826 9), (0.005 2±0.000 0)s, respectively; error rates were 10.0%, 4.0%, 0, respectively. There were three outliers in the data of bitterness evaluation in electronic tongue test; the elimination time of three methods were (2 992.673 3±84.117 6), (1 276.367 1±55.024 5), (0.002 3±0.000 0)s, respectively; error rates were 5.7%, 2.9%, 0, respectively. The elimination results of the three methods were consistent. The elimination time of method two was significantly shorter than that of method one (P<0.01); the elimination time of method three was significantly shorter than those of method one and method two (P<0.01). There was no significant difference in error rate of 3 methods (P>0.05). CONCLUSIONS: The automatic cyclic elimination method of outliers based on Grubbs rule and MATLAB language can significantly shorten the elimination time of outliers in data of drug bitterness evaluation, improve the efficiency of data processing, and is suitable for drug bitterness evaluation.
ABSTRACT
Resumen Introducción: tradicionalmente, los pólipos colónicos se miden empíricamente por estimación visual y con las pinzas de biopsia, aunque dichos métodos son inexactos. Diferentes métodos han sido investigados, pero no tienen la exactitud esperada. Por lo anterior, se realizó este trabajo para construir un algoritmo que permitiera medir los pólipos a partir de fotografías tomadas con el colonoscopio. Materiales y métodos: el trabajo se realizó en tres fases. En la primera, se construyó un algoritmo en el programa MATLAB. Se capturaron fotos en formato JPG con el colonoscopio. En la segunda fase, con el algoritmo se midieron imágenes de objetos con tamaños conocidos para verificar la exactitud del algoritmo. Después de verificar la exactitud, fue sometida al algoritmo la fotografía de los pólipos del colon. En la tercera fase, se utilizaron imágenes de pólipos previamente enviadas a tres expertos. Todas las fotografías fueron tomadas con el colonoscopio Olympus Exera II. Resultados: en los objetos menores de 5 mm, el algoritmo sobreestimó el tamaño entre 0,11 y 0,08 mm; en los mayores de 5 mm, sobreestimó el tamaño entre 0,25 mm y 1,76 mm en los de 22 mm. Los expertos sobrestimaron los tamaños de manera importante. En los pólipos de 7, 8 y 9 mm, los expertos dijeron que medían 12, 15 y 18 mm, respectivamente. Conclusión: el algoritmo desarrollado tiene adecuada exactitud para medir pólipos colónicos. Por su fácil consecución y utilización, podría ser una herramienta para solucionar la dificultad de medir pólipos durante una colonoscopia.
Abstract Introduction: Traditionally, colon polyps' measurements have been empirically estimated visually and with biopsy forceps, but neither method is inaccurate. Other methods have been studied but have not had the accuracy expected. The research reported here was undertaken to address this issue by building an algorithm for measure polyps from photographs taken through a colonoscope. Materials and methods: The study was done in three phases. First, an algorithm was built in MATLAB, and photos taken with a colonoscope were stored in the JPG format. In the second phase, images of objects with known sizes were checked against the algorithm to verify its accuracy. After verification of the algorithm's accuracy, photographs of colon polyps were measured using the algorithm. In phase 3, images of polyps previously sent to three experts were measured with the algorithm. All photographs were taken with an Olympus Exera II Colonoscope. Results: For objects smaller than 5 mm, the algorithm overestimated sizes by 0.11 to 0.08 mm. For those greater than 5 mm, it overestimated sizes by 0.25 mm to 1.76 mm in those of 22 mm. The experts seriously overestimated sizes. They estimated that 7 mm polyps measured 12 mm, 8 mm polyps measured 15 mm, and 9 mm polyps measured 18mm. Conclusion: The algorithm developed is sufficiently accurate for measuring colon polyps and is easy to obtain and relatively easy to use. It could become a tool for overcoming the difficulty of measuring polyps during a colonoscopy.
Subject(s)
Humans , Colonic Polyps , Colonoscopy , Colonoscopes , Surgical InstrumentsABSTRACT
ABSTRACT This paper presents standalone solar photovoltaic (PV) powered fed actuation system employing a switched reluctance motor (SRM) particularly used in remote and rural areas. The converter efficiency is achieved by changing ON and OFF state of solar PV drive. An electronic commutation drives SRM drive with achieved by position hall sensor and encoder. The modified boost converter is proposed in single stage to conversion of PV fed power and inverter with reduced switching losses. Further proposed system is designed to reduce cost of system using simple design and control. This paper also proposes the speed control strategy of SRM motor with an artificial intelligent based Adaptive neuro fuzzy inference (ANFIS) system to achieve desired motor velocity as stated in reference velocity in farm lands. The system proposed is subjected to analysis the performance of drive and controller in both load and no-load conditions. Initially, a simulation model is modeled in MATLAB-SIMULINK with corresponding environments. The experimental setup for proposed system is developed using FPGA based SPEEDGOAT real time target machine. The simulation and hardware results suggest feasibility of proposed system in real time.
ABSTRACT
Numerical simulation is a powerful technology for photoacoustic imaging (PAI) in both theory studies and practical applications. In this paper, a simulation platform for PAI was designed and implemented based on Matlab. The simulation platform utilized finite element method (FEM) and -space pseudospectral method to calculate the forward and inverse problem of PAI. And a graphical user interface (GUI) was realized. Structural design, work process and other operating details of the platform was also provided. By compared with theoretical temporal waveform of photoacoustic signal and reconstruction results of COMSOL, the validity and reliability was verified. And a reliable simulation tool was proposed for PAI.
Subject(s)
Algorithms , Computer Simulation , Finite Element Analysis , Photoacoustic Techniques , Reproducibility of ResultsABSTRACT
Objective To determine the relationship between the theory and actual displacement of the urine flow rate meter calibration device gear pump, and to construct a model between actual and theory displacement, in order to obtain actual displacement via theory displacement. Methods The weight of the standard water flow in each flow rate was measured by B2000S digital scales,and the scatter plot between the theory displacement and actual displacement was drawn to find the best fitted curve;then the MATLAB Curve Fitting Tool was used to obtain the best quasi relational equation. Results The error between the fitted displacement and the actual displacement of the gear bump was 1.494% in maximum and-0.010% in minimum, far less than 5% of the requirements for urinary flow meter measurement. Conclusion Based on regression analysis, the relationship between the theoretical displacement and actual displacement of the flow rate meter calibration device is established,the fitting error is small,and the method is simple and easy to achieve.
ABSTRACT
In view of the main problems of Matlab teaching of biomedical engineering profession,the paper proposes main measures for teaching reforming,including the adjustment of teaching hours,teaching content,teaching materials and other aspects,as well as reform of teaching methods and examination.The investigation result shows that the reform has a positive meaning on the improvement of students' learning quality.
ABSTRACT
Objective:To design a automatic classification system for leukocytes in order to increase detection speed of manual microscope inspection and reduce the inaccurate detected results in clinical laboratory; and to evaluate this system.Methods: In this system, the image processing and algorithm classifying were achieved by MATLAB software consisted of digital image processing module and automatic classification module. Classification decision for discrimination function and simulated detection for this system were achieved by using automatic classification module.Results: In the simulation experiments, the detection results for sample cell demonstrated the recognition accuracy can achieve to 93% and the speed can achieve to 97.8 cells per second for this system.Conclusion: The automatic recognition and classification system for leukocyte not only reduces human consumption, but also improves the detection accuracy and detection speed for leukocyte, and it has some significant in clinical application.
ABSTRACT
Objective To design and implement an automatic analysis and evaluation system for the image parameters of medical MRI quality testing.Methods The system was developed and debugged by the study on MRI image quality parameters,the image denoising,integration,extraction and etc by MATLAB processing platform as well as the comparison and comparative calculation of the obtained data.Results The system replaced manual operation by auto processing and parameters analysis of MRI quality inspection image.Conclusion The system enhances the efficiency and avoids artificial error,and has a promising prospect in the future.
ABSTRACT
Objective To design and implement an automatic analysis and evaluation system for the image parameters of medical MRI quality testing.Methods The system was developed and debugged by the study on MRI image quality parameters,the image denoising,integration,extraction and etc by MATLAB processing platform as well as the comparison and comparative calculation of the obtained data.Results The system replaced manual operation by auto processing and parameters analysis of MRI quality inspection image.Conclusion The system enhances the efficiency and avoids artificial error,and has a promising prospect in the future.
ABSTRACT
OBJECTIVE:To extract the feature of Achyranthes bidentata and Cyathula officinalis,and to establish image recog-nition method. METHODS:The microscopic image stitching of A. bidentata and C. officinalis was implemented by MATLAB. The color,invariant moment,stripes and the features of vascular bundle in cross section were extracted. The data was organized into da-ta matrix,and then data matrix was standardized by Zscore function;principal components were analyzed through Princomp func-tion. BP nerve network recognition mode was adopted. RESULTS:The microstructures in the micro images of the samples were kept integrated. The measured data of 27 characteristics were acquired in each group of sample. Through principal component analy-sis,the parameters of 11 main components were selected to establish BP never network. The average recognition rate of BP nerve network was 100% between 2 medicinal material relatives (n=50). CONCLUSIONS:The method can be used for micro-image auto Stitching of Chinese medicinal materials and image recognition of A. bidentata and C. officinalis.
ABSTRACT
Basic Requirements of Teaching Basic Courses of Computer in Universities proposed pro-moting reforms to universities' computer basic education, whose core was to cultivate the students' computational thinking ability, infiltrating the essential thinking method of computational science in content and design of the course. Tianjin Medical University distinguished different levels of students according to a proficiency test, implemented graded teaching, introduced MATLAB in the course of program design, and performed modular teaching according to the students' specialties. All courses implemented small class teaching to strengthen the students' ability to apply computational thinking and computer technology to medical practice and introduced network-based test, in order to provide ideas for the teaching reform of computer basic courses in medical col-leges and universities.
ABSTRACT
El efecto auxin-like consiste en la promoción del crecimiento vegetal por ácidos húmicos (AH). En este trabajo, se evaluó el efecto auxin-like de ácidos húmicos, mediante la determinación del área foliar y la superficie radicular de plántulas de maíz. Los AH fueron obtenidos por solubilización alcalina de carbón, denominados AH-NaOH y mediante solubilización bacteriana de carbón, designados AH-BSC3 y AH-BSC25. Se probó la aplicación de AH, mediante inmersión de semillas en soluciones de 20, 80 y 150mgAH/L y por aspersión foliar sobre plántulas de dos semanas. El ensayo, se desarrolló bajo condiciones de casa de malla y constó de cinco repeticiones por tratamiento; 30 días después de la siembra en suelo, se determinó el área foliar, utilizando el software ImageJ y la superficie total de raíces, mediante un algoritmo desarrollado en Matlab. Se registraron incrementos significativos en el área foliar de plantas tratadas mediante la inmersión de semillas, en soluciones de AH-BSC-3-80mg/L y 150mg/L, AH-BSC-25-20mg/L y 150mg/L, y AH-NaOH-80mg/L y plantas tratadas mediante aspersión foliar de AH-BSC-3-150mg/L, AH-BSC-25-150mg/L y AH-NaOH-150mg/L. También, se evidenciaron incrementos significativos en la superficie total de raíces de plántulas tratadas con AH-BSC25-150mg/L, AH-NaOH-80mg/L y AH-BSC3-80mg/L y todos los tratamientos de AH por aspersión. Se presentó el efecto auxin-like de AH sobre el desarrollo radicular y foliar de plántulas de maíz, a través del análisis digital de imágenes; esta herramienta puede producir información precisa para medir algunos parámetros del proceso vegetal.
The auxin-like effect consists in plant growth promotion by humic acids (HA). In this research the auxin-like effect was determined by digital image processing, both foliar and root surface of corn plants were assessed. The HA were obtained through alcaline solubilization coal, HA-NaOH and through coal bacterial solubilization, HA-CSB3 and HA-CSB25. The application of the HA solutions of 20, 80 and 150mgHA/L was evaluated through seed immersion and foliar spray on two week-old plants. The experiment was carried out under shade cloth with five replicates by treatments; 30 days after planting in soil, leaf area was measured using ImageJ software and total root surface through an algorithm of Matlab. Significant increase in leaf area of plants treated by immersion of seeds in HA-BSC3-80mg/L and 150mg/L, AH-CSB25-20mg/L and 150mg/L, and HA-NaOH-80mg/L was found, as well as in plants treated by foliar aspersion of HA-CSB3-150mg/L, AH-CSB 25-150mg/L and HA-NaOH-150mg/L. Moreover significant increase in total root surface of plants treated with HA-CSB25-150mg/L, HA-NaOH-80mg/L and HA-CSB3-80mg/L and all treatments of HA by aspersion was found. The auxin-like effect of humic acids on maize plants was evidenced through digital image analysis; this tool can produce accurate information to measure some plant development parameters.
ABSTRACT
Objective To realize rapid and non-destructive drug classification and improve the accuracy of drug classification.Methods A model for drug classification based on the combination of principal components analysis and artificial neural network (PCA-ANN) method was introduced.The software for drugs classification was then developed with the utility of MATLAB language.The near infra-red spectrum (NIRS) detection technique was executed on five kinds of drugs (a total of 120 batch samples) and the detection data was collected within the range of 1 350-1 800 nm of excitation wavelength and 0.5 nm of wavelength interval.Results The network training mean square error (MSE) was 5.91e-03,and the prediction error (β) was 2.469% when the number of the interfering drugs number was less than 5.Conclusions The classification of drugs by NIRS combined with PCA-ANN is feasible and the classification accuracy can be increased.