scholarly journals A Transfer Learning Architecture Based on a Support Vector Machine for Histopathology Image Classification

2021 ◽  
Vol 11 (14) ◽  
pp. 6380
Author(s):  
Jiayi Fan ◽  
JangHyeon Lee ◽  
YongKeun Lee
Keyword(s):  
Support Vector Machine ◽  
Transfer Learning ◽  
Classification Accuracy ◽  
Support Vector ◽  
Svm Classifier ◽  
Breast Cancer Dataset ◽  
Classification Problems ◽  
Cancer Dataset ◽  
Softmax Classifier ◽  
Histopathology Images

Recently, digital pathology is an essential application for clinical practice and medical research. Due to the lack of large annotated datasets, the deep transfer learning technique is often used to classify histopathology images. A softmax classifier is often used to perform classification tasks. Besides, a Support Vector Machine (SVM) classifier is also popularly employed, especially for binary classification problems. Accurately determining the category of the histopathology images is vital for the diagnosis of diseases. In this paper, the conventional softmax classifier and the SVM classifier-based transfer learning approach are evaluated to classify histopathology cancer images in a binary breast cancer dataset and a multiclass lung and colon cancer dataset. In order to achieve better classification accuracy, a methodology that attaches SVM classifier to the fully-connected (FC) layer of the softmax-based transfer learning model is proposed. The proposed architecture involves a first step training the newly added FC layer on the target dataset using the softmax-based model and a second step training the SVM classifier with the newly trained FC layer. Cross-validation is used to ensure no bias for the evaluation of the performance of the models. Experimental results reveal that the conventional SVM classifier-based model is the least accurate on either binary or multiclass cancer datasets. The conventional softmax-based model shows moderate classification accuracy, while the proposed synthetic architecture achieves the best classification accuracy.

scholarly journals Weed Detection and Classification using ICA Based SVM Classifier

2020 ◽  
Vol 8 (5) ◽  
pp. 1557-1560
Keyword(s):  
Support Vector Machine ◽  
Classification Accuracy ◽  
Learning Algorithm ◽  
Feature Weighting ◽  
Training Data ◽  
Support Vector ◽  
Svm Classifier ◽  
Classification Problems ◽  
Weed Detection ◽  
Data Set

Support vector machine (SVM) is a commonly known efficient supervised learning algorithm for classification problems. However, the classification accuracy of the SVM classifier depends on its training parameters and the training data set as well. The main objective of this paper is to optimize its parameters and feature weighting in order to improve the strength of the SVM simultaneously. In this paper, the Imperialist Competitive Algorithm based Support Vector Machine (ICA-SVM) classifier is proposed to classify the efficient weed detection. This enhanced ICA-SVM classifier is able to select the appropriate input features and to optimize the parameters of SVM and is improving the classification accuracy. Experimental results show that the ICA-SVM classification algorithm reduces the computational complexity tremendously and improves classification Accuracy.

Shape-restricted support vector machine (SR-SVM): a SVM classifier taking supplementary shape information of input

2021 ◽  
Vol 40 (1) ◽  
pp. 1481-1494
Author(s):  
Geng Deng ◽  
Yaoguo Xie ◽  
Xindong Wang ◽  
Qiang Fu
Keyword(s):  
Support Vector Machine ◽  
Classification Performance ◽  
Research Literature ◽  
Support Vector ◽  
Svm Classifier ◽  
Classification Problems ◽  
Active Set ◽  
Shape Information ◽  
Convex Optimization Problem ◽  
Shape Restrictions

Many classification problems contain shape information from input features, such as monotonic, convex, and concave. In this research, we propose a new classifier, called Shape-Restricted Support Vector Machine (SR-SVM), which takes the component-wise shape information to enhance classification accuracy. There exists vast research literature on monotonic classification covering monotonic or ordinal shapes. Our proposed classifier extends to handle convex and concave types of features, and combinations of these types. While standard SVM uses linear separating hyperplanes, our novel SR-SVM essentially constructs non-parametric and nonlinear separating planes subject to component-wise shape restrictions. We formulate SR-SVM classifier as a convex optimization problem and solve it using an active-set algorithm. The approach applies basis function expansions on the input and effectively utilizes the standard SVM solver. We illustrate our methodology using simulation and real world examples, and show that SR-SVM improves the classification performance with additional shape information of input.

Feature Selection Method Based on Mutual Information and Support Vector Machine

2021 ◽  
pp. 2150021
Author(s):  
Gang Liu ◽  
Chunlei Yang ◽  
Sen Liu ◽  
Chunbao Xiao ◽  
Bin Song
Keyword(s):  
Support Vector Machine ◽  
Feature Selection ◽  
Mutual Information ◽  
Classification Accuracy ◽  
Feature Selection Method ◽  
Selection Method ◽  
Support Vector ◽  
Svm Classifier ◽  
Standard Data ◽  
Feature Dimension

A feature selection method based on mutual information and support vector machine (SVM) is proposed in order to eliminate redundant feature and improve classification accuracy. First, local correlation between features and overall correlation is calculated by mutual information. The correlation reflects the information inclusion relationship between features, so the features are evaluated and redundant features are eliminated with analyzing the correlation. Subsequently, the concept of mean impact value (MIV) is defined and the influence degree of input variables on output variables for SVM network based on MIV is calculated. The importance weights of the features described with MIV are sorted by descending order. Finally, the SVM classifier is used to implement feature selection according to the classification accuracy of feature combination which takes MIV order of feature as a reference. The simulation experiments are carried out with three standard data sets of UCI, and the results show that this method can not only effectively reduce the feature dimension and high classification accuracy, but also ensure good robustness.

scholarly journals Eye-Tracking Analysis for Emotion Recognition

2020 ◽  
Vol 2020 ◽  
pp. 1-13
Author(s):  
Paweł Tarnowski ◽  
Marcin Kołodziej ◽  
Andrzej Majkowski ◽  
Remigiusz Jan Rak
Keyword(s):  
Support Vector Machine ◽  
Eye Movements ◽  
Eye Tracking ◽  
Emotion Recognition ◽  
Classification Accuracy ◽  
Pupil Diameter ◽  
Support Vector ◽  
Svm Classifier ◽  
High Arousal ◽  
Validation Method

This article reports the results of the study related to emotion recognition by using eye-tracking. Emotions were evoked by presenting a dynamic movie material in the form of 21 video fragments. Eye-tracking signals recorded from 30 participants were used to calculate 18 features associated with eye movements (fixations and saccades) and pupil diameter. To ensure that the features were related to emotions, we investigated the influence of luminance and the dynamics of the presented movies. Three classes of emotions were considered: high arousal and low valence, low arousal and moderate valence, and high arousal and high valence. A maximum of 80% classification accuracy was obtained using the support vector machine (SVM) classifier and leave-one-subject-out validation method.

scholarly journals Feature Extraction and Classification of MRI Using Hybrid RBF Kernel and SVM

2021 ◽  
pp. 418-426
Author(s):  
Suhas S ◽  
Dr. C. R. Venugopal
Keyword(s):  
Support Vector Machine ◽  
Image Retrieval ◽  
Classification Accuracy ◽  
Kernel Functions ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Svm Classifier ◽  
Mr Images ◽  
Rbf Kernel

An enhanced classification system for classification of MR images using association of kernels with support vector machine is developed and presented in this paper along with the design and development of content-based image retrieval (CBIR) system. Content of image retrieval is the process of finding relevant image from large collection of image database using visual queries. Medical images have led to growth in large image collection. Oriented Rician Noise Reduction Anisotropic Diffusion filter is used for image denoising. A modified hybrid Otsu algorithm termed is used for image segmentation. The texture features are extracted using GLCM method. Genetic algorithm with Joint entropy is adopted for feature selection. The classification is done by support vector machine along with various kernels and the performance is validated. A classification accuracy of 98.83% is obtained using SVM with GRBF kernel. Various features have been extracted and these features are used to classify MR images into five different categories. Performance of the MC-SVM classifier is compared with different kernel functions. From the analysis and performance measures like classification accuracy, it is inferred that the brain and spinal cord MRI classification is best done using MC- SVM with Gaussian RBF kernel function than linear and polynomial kernel functions. The proposed system can provide best classification performance with high accuracy and low error rate.

scholarly journals SVM-RFE Based Feature Selection and Taguchi Parameters Optimization for Multiclass SVM Classifier

2014 ◽  
Vol 2014 ◽  
pp. 1-10 ◽  
Author(s):  
Mei-Ling Huang ◽  
Yung-Hsiang Hung ◽  
W. M. Lee ◽  
R. K. Li ◽  
Bo-Ru Jiang
Keyword(s):  
Feature Selection ◽  
Classification Accuracy ◽  
Explanatory Power ◽  
Disease Diagnosis ◽  
Parameters Optimization ◽  
Recursive Feature Elimination ◽  
Support Vector ◽  
Svm Classifier ◽  
Classification Problems ◽  
Class Variable

Recently, support vector machine (SVM) has excellent performance on classification and prediction and is widely used on disease diagnosis or medical assistance. However, SVM only functions well on two-group classification problems. This study combines feature selection and SVM recursive feature elimination (SVM-RFE) to investigate the classification accuracy of multiclass problems for Dermatology and Zoo databases. Dermatology dataset contains 33 feature variables, 1 class variable, and 366 testing instances; and the Zoo dataset contains 16 feature variables, 1 class variable, and 101 testing instances. The feature variables in the two datasets were sorted in descending order by explanatory power, and different feature sets were selected by SVM-RFE to explore classification accuracy. Meanwhile, Taguchi method was jointly combined with SVM classifier in order to optimize parametersCandγto increase classification accuracy for multiclass classification. The experimental results show that the classification accuracy can be more than 95% after SVM-RFE feature selection and Taguchi parameter optimization for Dermatology and Zoo databases.

Texture-Based Evolutionary Method for Cancer Classification in Histopathology

2016 ◽  
pp. 55-69
Author(s):  
Kiran Fatima ◽  
Hammad Majeed
Keyword(s):  
Classification Accuracy ◽  
Malignant Tumors ◽  
Svm Classifier ◽  
Breast Cancer Dataset ◽  
Cancer Dataset ◽  
Tissue Samples ◽  
Diagnostic And Prognostic Value

Real-world histology tissue textures owing to non-homogeneous nature and unorganized spatial intensity variations are complex to analyze and classify. The major challenge in solving pathological problems is inherent complexity due to high intra-class variability and low inter-class variation in texture of histology samples. The development of computational methods to assists pathologists in characterization of these tissue samples would have great diagnostic and prognostic value. In this chapter, an optimized texture-based evolutionary framework is proposed to provide assistance to pathologists for classification of benign and pre-malignant tumors. The proposed framework investigates the imperative role of RGB color channels for discrimination of cancer grades or subtypes, explores higher-order statistical features at image-level, and implements an evolution-based optimization scheme for feature selection and classification. The highest classification accuracy of 99.06% is achieved on meningioma dataset and 90% on breast cancer dataset through Quadratic SVM classifier.

Design of a Power Aware Systolic Array based Support Vector Machine Classifier

2015 ◽  
pp. 96-138
Author(s):  
Bhaswati Mandal ◽  
Manash Pratim Sarma ◽  
Kandarpa Kumar Sarma
Keyword(s):  
Support Vector Machine ◽  
Systolic Array ◽  
Support Vector ◽  
Svm Classifier ◽  
Classification Problems ◽  
Processing Elements ◽  
Array Architecture ◽  
Multiclass Support Vector Machine ◽  
Kernel Operation

This chapter presents a method for generating binary and multiclass Support Vector Machine (SVM) classifier with multiplierless kernel function. This design provides reduced power, area and reduced cost due to the use of multiplierless kernel operation. Binary SVM classifier classifies two groups of linearly or nonlinearly separable data while the multiclass classification provides classification of three nonlinearly separable data. Here, at first SVM classifier is trained for different classification problems and then the extracted training parameters are used in the testing phase of the same. The dataflow from all the processing elements (PEs) are parallely supported by systolic array. This systolic array architecture provides faster processing of the whole system design.

Spectral-Spatial Classification of Hyperspectral Image Based on Support Vector Machine

2021 ◽  
Vol 16 (1) ◽  
pp. 56-74
Author(s):  
Weiwei Yang ◽  
Haifeng Song
Keyword(s):  
Support Vector Machine ◽  
Classification Accuracy ◽  
Spatial Information ◽  
Hyperspectral Image ◽  
State Of The Art ◽  
Support Vector ◽  
Svm Classifier ◽  
Spatial Classification ◽  
Homogeneous Regions

Recent research has shown that integration of spatial information has emerged as a powerful tool in improving the classification accuracy of hyperspectral image (HSI). However, partitioning homogeneous regions of the HSI remains a challenging task. This paper proposes a novel spectral-spatial classification method inspired by the support vector machine (SVM). The model consists of spectral-spatial feature extraction channel (SSC) and SVM classifier. SSC is mainly used to extract spatial-spectral features of HSI. SVM is mainly used to classify the extracted features. The model can automatically extract the features of HSI and classify them. Experiments are conducted on benchmark HSI dataset (Indian Pines). It is found that the proposed method yields more accurate classification results compared to the state-of-the-art techniques.

Cancer Detection Using Aritifical Neural Network and Support Vector Machine: A Comparative Study

2013 ◽  
Vol 65 (1) ◽  
Author(s):  
Sharifah Hafizah Sy Ahmad Ubaidillah ◽  
Roselina Sallehuddin ◽  
Nor Azizah Ali
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Human Life ◽  
Support Vector ◽  
Svm Classifier ◽  
Malignant Tumours ◽  
Cancer Dataset ◽  
Cancer Data ◽  
Standard Data ◽  
Artificial Neural Network Ann

Accurate diagnosis of cancer plays an importance role in order to save human life. The results of the diagnosis indicate by the medical experts are mostly differentiated based on the experience of different medical experts. This problem could risk the life of the cancer patients. From the literature, it has been found that Artificial Intelligence (AI) machine learning classifiers such as an Artificial Neural Network (ANN) and Support Vector Machine (SVM) can help doctors in diagnosing cancer more precisely. Both of them have been proven to produce good performance of cancer classification accuracy. The aim of this study is to compare the performance of the ANN and SVM classifiers on four different cancer datasets. For breast cancer and liver cancer dataset, the features of the data are based on the condition of the organs  which is also called as standard data while for prostate cancer and ovarian cancer; both of these datasets are in the form of gene expression data. The datasets including benign and malignant tumours is specified to classify with proposed methods. The performance of both classifiers is evaluated using four different measuring tools which are accuracy, sensitivity, specificity and Area under Curve (AUC). This research has shown that the SVM classifier can obtain good performance in classifying cancer data compare to ANN classifier.

Sign in / Sign up

Export Citation Format

Share Document