Classification Of Test Samples Research Articles

Classification of Kudoa thyrsites infected and uninfected fish using a handheld near-infrared spectrophotometer, SIMCA and PLS-DA.

Kudoa thyrsites infection of marine fish typically results in myoliquefaction, which is only apparent 24 to 56 h post-mortem. The traditional methods for the detection of K. thyrsites infected fish are time-consuming and destructive, reducing its marketability. This poses a challenge for the fish industry to remove infected fish before it reaches the market or further processing activities. This study investigated the use of near-infrared (NIR) spectroscopy, in combination with soft independent modelling of class analogy (SIMCA) and partial least square discriminant analysis (PLS-DA), for discriminating K. thyrsites infected fish from uninfected fish. Performance of the classification models was evaluated by calculating the sensitivity, specificity and precision. A total of 334 fish samples (200 sardine, 64 hake and 70 kingklip) were used for this study. Infection of K. thyrsites was determined with the use of qPCR assays. Ninety per cent (90%) of the sardine samples, 78% of the hake samples and 37% of the kingklip samples were infected. Class groups of infected and uninfected fish samples were created for the purpose of generating SIMCA and PLS-DA classification models for each species of fish, as well as for a species independent data set. Principal component analysis (PCA) of NIR spectra did not show any clustering for infected and uninfected samples. Calibration and test sample sets were generated for the purpose of building and testing the SIMCA and PLD-DA classification models. SIMCA and PLS-DA were unable to classify test samples correctly into the two classes. The number of misclassifications (NMC) was higher for the SIMCA models than for the PLS-DA models, with more than 60% incorrectly classified. SIMCA classified most of the test samples into both classes. The precision for PLS-DA were 89% for sardine, 81% for hake, 0% for kingklip and 87% for species independent models, however, most samples were classified at infected. The use of NIR spectroscopy and classification models such as SIMCA and PLS-DA showed limited use as a method to distinguish between K. thyrsites infected and uninfected fish samples. Textural and chemical changes during extended frozen storage of the fish samples may have masked the effects associated with K. thyrsites infection. Further studies are suggested where NIR spectroscopy is used in combination with texture analysis and image spectroscopy.

Self-organizing maps for exploration and classification of nuclear magnetic resonance spectra for untargeted metabolomics of breast cancer

Metabolomics has emerged as a powerful tool for identifying biomarkers of disease, and nuclear magnetic resonance (NMR) spectroscopy allows for the simultaneous detection of a wide range of metabolites. However, due to complex interactions within metabolic networks, metabolites often exhibit high correlation and collinearity. To address this challenge, self-organizing maps (SOMs) of Kohonen maps and counter propagation-artificial neural networks (CP-ANN) were employed in this study to model proton nuclear magnetic resonance spectroscopic (1HNMR) data from control samples and breast cancer (BC) patients. Blood serum samples from a control group (n=24) and BC patients (n=18) were used to extract metabolites using methanol and chloroform solvents in optimum extraction conditions. The 1HNMR data was preprocessed by performing phase, baseline, and shift corrections. Subsequently, the preprocessed data was modeled using Kohonen network as an unsupervised technique and CP-ANN as a supervised technique. In this regard, the model built with CP-ANN successfully distinguished between the two classes with an accuracy of 100 % for both group and sensitivity of 96 % and 100 % for control group and BC patients, respectively. Additionally, CP-ANN algorithm demonstrated predictive capabilities by accurately classifying test samples with 90 % sensitivity, 98 % specificity, and 96 % accuracy for control group and 100 % sensitivity, 90 % specificity, and 96 % accuracy for BC patients. Furthermore, analysis of the resulting topological map revealed 14 significant variables (biomarkers) such as sarcosine, lysine, trehalose, tryptophan, and betaine that effectively differentiated between healthy individuals and BC patients.

Data augmentation via variational mode reconstruction and its application in few-shot fault diagnosis of rolling bearings

Currently, the popular fault diagnosis methods based on deep learning encounter a common limitation in that their accuracy heavily relies on an adequate number of training samples. However, collecting fault samples in real-world scenarios is often challenging. To overcome this challenge, this paper develops a novel data augmentation method named variational mode reconstruction (VMR) to generate augmented samples with similar features to the original samples. The first key point is the random weighting of a certain randomly chosen intrinsic mode function (IMF). Another key point is that the mean values and standard deviations of the augmented samples remain consistent with the original samples. Next, the augmented balanced dataset is utilized to train a deep residual shrinkage network (DRSN), which is then employed for the classification of test samples. Finally, the effectiveness and superiority of the developed VMR in few-shot fault diagnosis are verified through a series of experiments.

Fault diagnosis for rotor based on multi-sensor information and progressive strategies

Fault diagnosis is an effective tool to ensure safe operation of machinery and avoid serious accidents. As most currently used fault diagnosis methods usually employ mapping relationship established by training samples and their labels to achieve classification of testing samples, it is difficult for them to achieve fault diagnosis under the condition of incomplete training sample types. In addition, previous studies usually focus on feature extraction of single-channel vibration signal, which cannot get complete fault feature information. To solve the above problems, a progressive fault diagnosis method is investigated in this paper. First, the preliminary fault detection for the rotor is performed by studying reconstruction error of a sparse auto-encoder. Second, if a fault exists in the rotor, the outlier detection is implemented by the support vector data description method. Finally, if there are no outlier samples, the well -trained support vector machine is used to confirm the type of fault samples and complete the diagnosis. The performance of the proposed method was verified using the data obtained from a rotor laboratory bench. The types of rotor states investigated include normal, contact-rubbing, unbalance and misalignment. The experimental results verify the effectiveness and superiority of the proposed method in reducing the incidents of fault omission and fault misunderstanding.

Open-set recognition of breast cancer treatments

Open-set recognition generalizes a classification task by classifying test samples as one of the known classes from training or “unknown.” As novel cancer drug cocktails with improved treatment are continually discovered, classifying patients by treatments can naturally be formulated in terms of an open-set recognition problem. Drawbacks, due to modeling unknown samples during training, arise from straightforward implementations of prior work in healthcare open-set learning. Accordingly, we reframe the problem methodology and apply a recent Gaussian mixture variational autoencoder model, which achieves state-of-the-art results for image datasets, to breast cancer patient data. Not only do we obtain more accurate and robust classification results (14% average F1 increase compared to recent methods), but we also reexamine open-set recognition in terms of deployability to a clinical setting.

Improved Brain-Computer Interface Signal Recognition Algorithm Based on Few-Channel Motor Imagery.

Common spatial pattern (CSP) is an effective algorithm for extracting electroencephalogram (EEG) features of motor imagery (MI); however, CSP mainly aims at multichannel EEG signals, and its effect in extracting EEG features with fewer channels is poor—even worse than before using CSP. To solve the above problem, a new combined feature extraction method has been proposed in this study. For EEG signals from fewer channels (three channels), wavelet packet transform, fast ensemble empirical mode decomposition, and local mean decomposition were used to decompose the band-pass filtered EEG into multiple time–frequency components, and the corresponding components were selected according to the frequency characteristics of MI or the correlation coefficient between its time–frequency components and the original EEG signal. Furthermore, phase space reconstruction (PSR) was performed on the selected components after the three time-frequency decompositions, the maximum Lyapunov index was calculated, and the features were reconstructed; then, CSP projection mapping was used for the reconstructed features. The support vector machine probability output model was trained by the obtained three mappings. Probability outputs by three different support vector machines were then obtained. Finally, the classification of test samples was determined by the fusion of the Dempster–Shafer evidence theory at the decision level. The results showed that the accuracy of the proposed method was 95.71% on data set III of BCI competition II (left- and right-hand MI), which was 2.88% higher than the existing methods. On data set IIb of BCI competition IV, the average accuracy was 86.60%, which was 2.3% higher than the existing methods. This study verified the effectiveness of the proposed method and provided an approach for the research and development of the MI-BCI system based on fewer channels.

Characterization and classification of numerical data patterns using Annotated Paraconsistent Logic and the effect of contradiction

This work describes the development of a computational mathematical model that uses Annotated Paraconsistent Logic - APL and a concept derived from it, the effect of contradiction, to identify patterns in numerical data for pattern classification purposes. The APL admits paraconsistent and paracomplete logical principles, which allow the manipulation of inconsistent and contradictory data, and its use allowed the identification and quantization of the attribute related to the contradiction. To validate the model, series of Raman spectroscopies obtained after exposure of proteins, lipids and nucleic acids, collected from cutaneous tissue cell samples previously examined for the detection of cancerous lesions, identified as basal carcinoma, melanoma and normal, were used. Initially, the attributes related to contradiction, derivative and median obtained from spectroscopies were identified and quantified. A machine learning process with approximately 31.6% of each type of samples detects a sequence of spectroscopies capable of characterizing and classifying the type of lesion through the chosen attributes. Approximately 68.4% of the samples are used for classification tests. The proposed model identified a segment of spectroscopies where the classification of test samples had a hit rate of 76.92%. As a differential and innovation of this work, the use of APL principles in a complete process of training, learning and classification of patterns for numerical data sets stands out, with flexibility to choose the attributes used for the characterization of patterns, and a quantity of samples of about one third of the total required for characterization.

Using carbonate absorbance peak to select the most suitable regression model before predicting soil inorganic carbon concentration by mid-infrared reflectance spectroscopy

Mid-Infrared reflectance spectroscopy (MIRS, 4000–400 cm−1) is being considered to provide accurate estimations of soil inorganic carbon (SIC) contents, based on prediction models when the test dataset is well represented by the calibration set, with similar SIC range and distribution and pedological context. This work addresses the case where the test dataset, here originating from France, is poorly represented by the calibration set, here originating from Tunisia, with different SIC distributions and pedological contexts. It aimed to demonstrate the usefulness of 1) classifying test samples according to SIC level based on the height of the carbonate absorbance peak at 2510 cm−1, and then 2) selecting a suitable prediction model according to SIC level. Two regression methods were tested: Linear Regression using the height of the carbonate peak at 2510 cm−1, called Peak-LR model; and Partial Least Squares Regression using the entire MIR spectrum, called Full-PLSR model. First, our results showed that Full-PLSR was 1) more accurate than Peak-LR on the Tunisian validation set (R2val = 0.99 vs. 0.86 and RMSEval = 3.0 vs. 9.7 g kg−1, respectively), but 2) less accurate than Peak-LR when applied on the French dataset (R2test = 0.70 vs. 0.91 and RMSEtest = 13.7 vs. 4.9 g kg−1, respectively). Secondly, on the French dataset, predictions on SIC-poor samples tended to be more accurate using Peak-LR, while predictions on SIC-rich samples tended to be more accurate using Full-PLSR. Thirdly, the height of the carbonate absorbance peak at 2510 cm−1 might be used to discriminate SIC-poor and SIC-rich test samples (<5 vs. > 5 g kg−1): when this height was > 0, Full-PLSR was applied; otherwise Peak-LR was applied. Coupling Peak-LR and Full-PLSR models depending on the carbonate peak yielded the best predictions on the French dataset (R2test = 0.95 and RMSEtest = 3.7 g kg−1). This study underlined the interest of using a carbonate peak to select suitable regression approach for predicting SIC content in a database with different distribution than the calibration database.

Cooperative classification method for multi-fault diagnosis of machinery based on parameterized wavelet kernel extreme learning and sparse representation

Owing to complicated manual design and feature extraction processes of mechanical multi-fault classification and recognition methods, single-class classifiers do not adapt well to the high dimensionality and high self-similarity among mechanical vibration signals with nonlinear characteristics, resulting in insufficient classification accuracy. Combining the adaptive learning and feature extraction capabilities of the wavelet kernel-based extreme learning machine (WKELM) with the sparse representation classifier (SRC), this paper proposes a hybrid artificial bee colony (ABC)-optimized Morlet wavelet kernel-based extreme learning machine (ABC-MWKELM) with SRC. The two-level classifier is capable of cooperatively classifying multiple mechanical faults. First, a Morlet wavelet kernel-based extreme learning machine (MWKELM) model that matches the kernel function construction condition is presented. An ABC optimization algorithm is adopted to optimize critical parameters of the MWKELM model, thereby improving the accuracy and generalization ability of the model. In addition, the ABC algorithm is used to optimize the MWKELM model as a pre-classifier for classifying test samples. According to the posterior probability of each training sample category output, the threshold decision method selects candidate categories with a high confidence coefficient. When the preset meets the threshold, the classification result of the ABC-optimized MWKELM is directly adopted. Otherwise, the candidate training samples are used to construct a dictionary and the SRC is used to classify the test samples further. The experimental results demonstrate that compared with the ELM, WKELM, (ELM-SRC), and radial basis function (RBF)-KELM and SRC (RBFKELM-SRC), the method presented in this paper has significant advantages in terms of accuracy of mechanical multi-fault classification. The validity and applicability of this method in mechanical multi-fault classification were verified.

A fast and low-cost approach to quality control of alcohol-based hand sanitizer using a portable near infrared spectrometer and chemometrics

The use of alcohol-based hand sanitizers is recommended as one of several strategies to minimize contamination and spread of the COVID-19 disease. Current reports suggest that the virucidal potential of ethanol occurs at concentrations close to 70%. Traditional methods of verifying the ethanol concentration in such products invite potential errors due to the viscosity of chemical components or may be prohibitively expensive to undertake in large demand. Near infrared (NIR) spectroscopy and chemometrics have already been used for the determination of ethanol in other matrices and present an alternative fast and reliable approach to quality control of alcohol-based hand sanitizers. In this study, a portable NIR spectrometer combined with classification chemometric tools, i.e., partial least square discriminant analysis (PLS–DA) and linear discriminant analysis with successive algorithm projection (SPA–LDA) were used to construct models to identify conforming and non-conforming commercial and laboratory synthesized hand sanitizer samples. Principal component analysis (PCA) was applied in an exploratory data study. Three principal components accounted for 99% of data variance and demonstrate clustering of conforming and non-conforming samples. The PLS–DA and SPA–LDA classification models presented 77 and 100% of accuracy in cross/internal validation respectively and 100% of accuracy in the classification of test samples. A total of 43% commercial samples evaluated using the PLS–DA and SPA–LDA presented ethanol content non-conforming for hand sanitizer gel. These results indicate that use of NIR spectroscopy and chemometrics is a promising strategy, yielding a method that is fast, portable, and reliable for discrimination of alcohol-based hand sanitizers with respect to conforming and non-conforming ethanol concentrations.

The local-balanced model for improved machine learning outcomes on mass spectrometry data sets and other instrumental data.

One unifying challenge when classifying biological samples with mass spectrometry data is overcoming the obstacle of sample-to-sample variability so that differences between groups, such as between a healthy set and a disease set, can be identified. Similarly, when the same sample is re-analyzed under identical conditions, instrument signals can fluctuate by more than 10%. This signal inconsistency imposes difficulties in identifying subtle differences across a set of samples, and it weakens the mass spectrometrist’s ability to effectively leverage data in domains as diverse as proteomics, metabolomics, glycomics, and imaging. We selected challenging data sets in the fields of glycomics, mass spectrometry imaging, and bacterial typing to study the problem of within-group signal variability and adapted a 30 year old statistical approach to address the problem. The solution, “local-balanced model,” relies on using balanced subsets of training data to classify test samples. This analysis strategy was assessed on ESI-MS data of IgG-based glycopeptides and MALDI-MS imaging data of endogenous lipids, and MALDI-MS data of bacterial proteins. Two preliminary examples on non-mass spectrometry data sets are also included to show the potential generality of the method outside the field of MS analysis. We demonstrate that this approach is superior to simple normalization methods, generalizable to multiple mass spectrometry domains, and potentially appropriate in fields as diverse as physics and satellite imaging. In some cases, improvements in classification can be dramatic, with accuracy escalating from 60% with normalization alone to over 90% with the additional development described herein.

Robust unsupervised small area change detection from SAR imagery using deep learning

Small area change detection using synthetic aperture radar (SAR) imagery is a highly challenging task, due to speckle noise and imbalance between classes (changed and unchanged). In this paper, a robust unsupervised approach is proposed for small area change detection using deep learning techniques. First, a multi-scale superpixel reconstruction method is developed to generate a difference image (DI), which can suppress the speckle noise effectively and enhance edges by exploiting local, spatially homogeneous information. Second, a two-stage centre-constrained fuzzy c-means clustering algorithm is proposed to divide the pixels of the DI into changed, unchanged and intermediate classes with a parallel clustering strategy. Image patches belonging to the first two classes are then constructed as pseudo-label training samples, and image patches of the intermediate class are treated as testing samples. Finally, a convolutional wavelet neural network (CWNN) is designed and trained to classify testing samples into changed or unchanged classes, coupled with a deep convolutional generative adversarial network (DCGAN) to increase the number of changed class within the pseudo-label training samples. Numerical experiments on four real SAR datasets demonstrate the validity and robustness of the proposed approach, achieving up to 99.61% accuracy for small area change detection.

Binary classification with ambiguous training data

In supervised learning, we often face with ambiguous (A) samples that are difficult to label even by domain experts. In this paper, we consider a binary classification problem in the presence of such A samples. This problem is substantially different from semi-supervised learning since unlabeled samples are not necessarily difficult samples. Also, it is different from 3-class classification with the positive (P), negative (N), and A classes since we do not want to classify test samples into the A class. Our proposed method extends binary classification with reject option, which trains a classifier and a rejector simultaneously using P and N samples based on the 0-1-$c$ loss with rejection cost $c$. More specifically, we propose to train a classifier and a rejector under the 0-1-$c$-$d$ loss using P, N, and A samples, where $d$ is the misclassification penalty for ambiguous samples. In our practical implementation, we use a convex upper bound of the 0-1-$c$-$d$ loss for computational tractability. Numerical experiments demonstrate that our method can successfully utilize the additional information brought by such A training data.

Rapid detection and quantification of sucrose adulteration in cow milk using Attenuated total reflectance-Fourier transform infrared spectroscopy coupled with multivariate analysis.

Adulteration of milk to gain economic benefit has become a common practice in recent years. Sucrose is illegally added in milk to reconstitute its compositional requirement by improving the total solid contents. The present study is aimed to use FTIR spectroscopy in combination with multivariate chemometric modelling for the differentiation and quantification of sucrose in cow milk. Pure milk and adulterated milk spectra (0.5-7.5% w/v) were observed in the spectral region 4000-400cm-1. Principal component analysis (PCA) was used for the discrimination of pure milk and adulterated milk. Soft independent modelling of class analogy (SIMCA) was able to classify test samples with a classification efficiency of 100%. Partial least square regression (PLS-R) and principle component regression (PCR) models were established for normal spectra, 1st derivative and 2nd derivative for the quantification of sucrose in milk. PLS-R model (normal spectra) in the combined wavenumber range of 1070-980cm-1 showed the best prediction based on parameters like coefficient of determination (R2) (Cal: 0.996; Val: 0.993), RMSE (Cal: 0.15% w/v; Val: 0.20% w/v), RE% (Cal: 4.9% w/v; Val: 5.1% w/v) and RPD (13.40). This method has a detection level of 0.5% w/v sucrose adulteration.

A novel method for sentiment classification of drug reviews using fusion of deep and machine learning techniques

Nowadays, the development of new computer-based technologies has led to rapid increase in the volume of user-generated textual content on the website. Patient-written medical and health-care reviews are among the most valuable and useful textual content on social media which have not been studied extensively by researchers in the fields of natural language processing (NLP) and data mining. These reviews offer insights into the interaction of patients with doctors, treatment, and their satisfaction or frustration with the delivery of healthcare services. In this study, we propose two deep fusion models based on three-way decision theory to analyze the drug reviews. The first fusion model, 3-way fusion of one deep model with a traditional learning algorithm (3W1DT) developed using a deep learning method as a primary classifier and a traditional learning method as the secondary method that is used when the confidence of the deep method during classification of test samples is low. In the second proposed deep fusion model, 3-way fusion of three deep models with a traditional model (3W3DT), three deep and one traditional models are trained on the entire training data and each classifies the test sample individually. Then, the most confident classifier is selected to classify the test drug review. Our results on the reviews based on Drugs.com dataset show that both proposed 3W1DT and 3W3DT methods outperformed the traditional and deep learning methods by 4% and the 3W3DT outperformed 3W1DT by 2% in terms of accuracy and F1-measure.

Evaluation of machine learning methods for organic apple authentication based on diffraction grating and image processing

Optical measuring technologies coupled with machine learning algorithms can be used to build a home-made sensor system. We built such a sensor system using a smartphone and a diffraction grating sheet. Diffraction images were captured under white light illumination and converted into a data matrix for data analysis. In this paper we present a systematic evaluation of this sensor system on the task of differentiating organic apples from conventional ones. We used the sensor system to measure 150 organic and conventional apples as rainbow images. We processed the rainbow images using computer vision techniques, built machine learning and chemometrics models, and used the resultant models to classify testing samples. Moreover, a comparative study was conducted where the same set of apples were scanned by a commercial spectrometer resulting in spectral data of the apple samples and classification was undertaken using partial least squares discriminant analysis (PLS-DA). Experimental results show that state of the art machine learning algorithms such as support vector machine (SVM) and locally weighted partial least squares classifier (LW-PLSC) are effective in handling low-quality image data with classification accuracies of 93 − 100%. These results suggest that the sensor system is convenient and low-cost, and provides a fast, effective, non-destructive and viable solution for in-line food authentication.

Application of Attenuated Total Reflectance-Fourier Transform Infrared (ATR-FTIR) spectroscopy coupled with chemometrics for detection and quantification of formalin in cow milk

Milk is the best and cheapest source of nutrition and hence adulteration in milk is done to gain economic benefit. Formalin has been added illegitimately in order to increase the shelf life of milk. Fourier transform infrared (FTIR) spectroscopy coupled with multivariate chemometrics was evaluated as a quick quality monitoring method for the qualitative and quantitative analysis of formalin in cow milk. Spectra of pure and adulterated milk (0.5–5 % v/v) were acquired in the wavenumber range of 4000−400 cm−1 using ATR-FTIR. Principal component analysis (PCA) showed well separated clusters allowing discrimination of pure samples from adulterated samples. Soft Independent Modelling of Class Analogy (SIMCA) approach was applied for the classification of test samples which showed 100 % classification efficiency. Partial least squares (PLS) regression and Principle component regression (PCR) models were established to quantify the level of formalin in milk using normal, 1st derivative and 2nd derivative spectra. PLSR model for normal spectra showed best prediction as compared to PCR with coefficient of determination (R2) of 0.977 for calibration and 0.985 for validation. This method has a sensitivity of 0.5 % level of formalin adulteration.

A New Fuzzy Logic Classifier Based on Multiscale Permutation Entropy and Its Application in Bearing Fault Diagnosis.

The self-organizing fuzzy (SOF) logic classifier is an efficient and non-parametric classifier. Its classification process is divided into an offline training stage, an online training stage, and a testing stage. Representative samples of different categories are obtained through the first two stages, and these representative samples are called prototypes. However, in the testing stage, the classification of testing samples is completely dependent on the prototype with the maximum similarity, without considering the influence of other prototypes on the classification decision of testing samples. Aiming at the testing stage, this paper proposed a new SOF classifier based on the harmonic mean difference (HMDSOF). In the testing stage of HMDSOF, firstly, each prototype was sorted in descending order according to the similarity between each prototype in the same category and the testing sample. Secondly, multiple local mean vectors of the prototypes after sorting were calculated. Finally, the testing sample was classified into the category with the smallest harmonic mean difference. Based on the above new method, in this paper, the multiscale permutation entropy (MPE) was used to extract fault features, linear discriminant analysis (LDA) was used to reduce the dimension of fault features, and the proposed HMDSOF was further used to classify the features. At the end of this paper, the proposed fault diagnosis method was applied to the diagnosis examples of two groups of different rolling bearings. The results verify the superiority and generalization of the proposed fault diagnosis method.

Parameter self-tuning schemes for the two phase test sample sparse representation classifier

Sparse Representation Classifier (SRC) and its variants were considered as powerful classifiers in the domains of computer vision and pattern recognition. However, classifying test samples is computationally expensive due to the $$\ell _1$$ norm minimization problem that should be solved in order to get the sparse code. Therefore, these classifiers could not be the right choice for scenarios requiring fast classification. In order to overcome the expensive computational cost of SRC, a two-phase coding classifier based on classic Regularized Least Square was proposed. This classifier is more efficient than SRC. A significant limitation of this classifier is the fact that the number of the samples that should be handed over to the next coding phase should be specified a priori. This paper overcomes this main limitation and proposes five data-driven schemes allowing an automatic estimation of the optimal size of the local samples. These schemes handle the three cases that are encountered in any learning system: supervised, unsupervised, and semi-supervised. Experiments are conducted on five image datasets. These experiments show that the introduced learning schemes can improve the performance of the two-phase linear coding classifier adopting ad-hoc choices for the number of local samples.

Make Intelligent of Gastric Cancer Diagnosis Error in Qazvin's Medical Centers: Using Data Mining Method.

Objective:Gastric cancer is one of the most common types of cancers, which will result in irreparable harm in the case of misdiagnosis or late diagnosis. The purpose of this study is to investigate the capability of data mining techniques and disease risk factor characteristics to predict and diagnose the gastric cancer. Methods:In this retrospective descriptive-analytic study, we selected 405 samples from two groups of patient and healthy participants. A total of 11 characteristics and risk factors were examined. we used four Machine learning methods, Include support vector machine (SVM), decision tree (DT), naive Bayesian model, and k nearest neighborhood (KNN) to classify the patients with gastric cancer. The evaluation criteria to investigate the model on the database of patients with gastric cancer included Recall, Precision, F-score, and Accuracy. Data was analyzed using MATLAB® software, version 3.2 (Mathworks Inc., Natick, MA, USA). Results:Based on the results achieved from the evaluation of four methods, the accuracy rates of SVM, DT, naive Bayesian model, and KNN algorithms were 90.08, 87.89, 87.60, and 87.60 percent, respectively. The findings showed that the highest level of F-Score was related to the SVM (91.99); whereas, the lowest rate was associated with the KNN algorithm (87.17). Conclusion:According to the findings, the SVM algorithm showed the best results in classification of Test samples. So, this intelligent system can be used as a physician assistant in medical education hospitals, where the diagnosis processes are performed by medical students.