scholarly journals Ultrasound Image Classification of Thyroid Nodules Using Machine Learning Techniques

Medicina ◽  
2021 ◽  
Vol 57 (6) ◽  
pp. 527
Author(s):  
Vijay Vyas Vadhiraj ◽  
Andrew Simpkin ◽  
James O’Connell ◽  
Naykky Singh Singh Ospina ◽  
Spyridoula Maraka ◽  
...  
Keyword(s):  
Decision Making ◽  
Sensitivity And Specificity ◽  
Thyroid Nodules ◽  
Median Filter ◽  
Ultrasound Image ◽  
Multiple Instance Learning ◽  
Image Features ◽  
Classification Model ◽  
Support Vector ◽  
Accuracy Score

Background and Objectives: Thyroid nodules are lumps of solid or liquid-filled tumors that form inside the thyroid gland, which can be malignant or benign. Our aim was to test whether the described features of the Thyroid Imaging Reporting and Data System (TI-RADS) could improve radiologists’ decision making when integrated into a computer system. In this study, we developed a computer-aided diagnosis system integrated into multiple-instance learning (MIL) that would focus on benign–malignant classification. Data were available from the Universidad Nacional de Colombia. Materials and Methods: There were 99 cases (33 Benign and 66 malignant). In this study, the median filter and image binarization were used for image pre-processing and segmentation. The grey level co-occurrence matrix (GLCM) was used to extract seven ultrasound image features. These data were divided into 87% training and 13% validation sets. We compared the support vector machine (SVM) and artificial neural network (ANN) classification algorithms based on their accuracy score, sensitivity, and specificity. The outcome measure was whether the thyroid nodule was benign or malignant. We also developed a graphic user interface (GUI) to display the image features that would help radiologists with decision making. Results: ANN and SVM achieved an accuracy of 75% and 96% respectively. SVM outperformed all the other models on all performance metrics, achieving higher accuracy, sensitivity, and specificity score. Conclusions: Our study suggests promising results from MIL in thyroid cancer detection. Further testing with external data is required before our classification model can be employed in practice.

scholarly journals An Image Detection Method Based on Parameter Optimization of Support Vector Machine

2021 ◽  
Vol 15 ◽  
pp. 306-314
Author(s):  
Zhanshen Feng
Keyword(s):  
Image Processing ◽  
Computer Vision ◽  
Support Vector Machine ◽  
Parameter Optimization ◽  
Visual Processing ◽  
Image Data ◽  
Image Features ◽  
Classification Model ◽  
Support Vector ◽  
Image Detection

With the progress and development of multimedia image processing technology, and the rapid growth of image data, how to efficiently extract the interesting and valuable information from the huge image data, and effectively filter out the redundant data, these have become an urgent problem in the field of image processing and computer vision. In recent years, as one of the important branches of computer vision, image detection can assist and improve a series of visual processing tasks. It has been widely used in many fields, such as scene classification, visual tracking, object redirection, semantic segmentation and so on. Intelligent algorithms have strong non-linear mapping capability, data processing capacity and generalization ability. Support vector machine (SVM) by using the structural risk minimization principle constructs the optimal classification hyper-plane in the attribute space to make the classifier get the global optimum and has the expected risk meet a certain upper bound at a certain probability in the entire sample space. This paper combines SVM and artificial fish swarm algorithm (AFSA) for parameter optimization, builds AFSA-SVM classification model to achieve the intelligent identification of image features, and provides reliable technological means to accelerate sensing technology. The experiment result proves that AFSA-SVM has better classification accuracy and indicates that the algorithm of this paper can effectively realize the intelligent identification of image features.

scholarly journals Support Vector Machine And K-Nearest Neighbor Based Liver Disease Classification Model

2021 ◽  
Vol 3 (1) ◽  
pp. 9-14
Author(s):  
Tsehay Admassu Assegie
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Liver Disease ◽  
Classification Model ◽  
Support Vector ◽  
Disease Prediction ◽  
Accuracy Score ◽  
Learning Models ◽  
Accuracy And Precision ◽  
Machine Learning Models

Machine-learning approaches have become greatly applicable in disease diagnosis and prediction process. This is because of the accuracy and better precision of the machine learning models in disease prediction. However, different machine learning models have different accuracy and precision on disease prediction. Selecting the better model that would result in better disease prediction accuracy and precision is an open research problem. In this study, we have proposed machine learning model for liver disease prediction using Support Vector Machine (SVM) and K-Nearest Neighbors (KNN) learning algorithms and we have evaluated the accuracy and precision of the models on liver disease prediction using the Indian liver disease data repository. The analysis of result showed 82.90% accuracy for SVM and 72.64% accuracy for the KNN algorithm. Based on the accuracy score of SVM and KNN on experimental test results, the SVM is better in performance on the liver disease prediction than the KNN algorithm.  

scholarly journals Support Vector Machine Based Feature Extraction For Gender Recognition From Objects Using Lasso Classifier

2020 ◽  
Author(s):  
Damodara Krishna Kishore Galla ◽  
BabuReddy Mukamalla ◽  
Rama Prakasha Reddy Chegireddy
Keyword(s):  
Support Vector Machine ◽  
Feature Selection ◽  
Face Recognition ◽  
Selection Process ◽  
Recognition System ◽  
Classification Model ◽  
Support Vector ◽  
Gender Classification ◽  
Accuracy Score ◽  
Lasso Regression

Abstract The blind people has their difficulty to identify the object moving around them, therefore with a high accuracy score object detection and human face recognition system will helps them in identifying the things around them with ease. Facial record images are immobile an difficult assignment for biometric authentication systems due to various types of characteristics are dimensions, pose, expressions, illustrations and age etc. In facial and other united images includes different objects classifications. In this research article, a minimum distance trainer for feature selection by accessing SVM feature optimization process. For feature selection process SVM (support vector machine) was considered for improving its feature interpretability and computational efficiency., then LASSO classifier applied to perform object recognition and gender classification. Original face image database used for the gender classification. This approach was implemented with dual classification model (1) Recognizing or classifying human faces from various objects and (2) Classifying gender through face recognition] is made possible with the help of combining modified SIFT feature in combination with ridge regression (RR), elastic net (EN), lasso regression(LR) and lasso regression with Gaussian Support Vector Machines (LRGS) based classification.

Big Cats Classification Based on Body Covering

2021 ◽  
Vol 5 (5) ◽  
pp. 984-991
Author(s):  
Fernanda Januar Pratama ◽  
Wikky Fawwaz Al Maki ◽  
Febryanti Sthevanie
Keyword(s):  
Median Filter ◽  
Computation Time ◽  
Optimal Level ◽  
Input Image ◽  
The Body ◽  
Classification Model ◽  
Support Vector ◽  
Feature Extraction Method ◽  
Animal Populations ◽  
Segmentation Image

The reduced habitat owned by an animal has a very bad impact on the survival of the animal, resulting in a continuous decrease in the number of animal populations especially in animals belonging to the big cat family such as tigers, cheetahs, jaguars, and others. To overcome the decline in the animal population, a classification model was built to classify images that focuses on the pattern of body covering possessed by animals. However, in designing an accurate classification model with an optimal level of accuracy, it is necessary to consider many aspects such as the dataset used, the number of parameters, and computation time. In this study, we propose an animal image classification model that focuses on animal body covering by combining the Pyramid Histogram of Oriented Gradient (PHOG) as the feature extraction method and the Support Vector Machine (SVM) as the classifier. Initially, the input image is processed to take the body covering pattern of the animal and converted it into a grayscale image. Then, the image is segmented by employing the median filter and the Otsu method. Therefore, the noise contained in the image can be removed and the image can be segmented. The results of the segmentation image are then extracted by using the PHOG and then proceed with the classification process by implementing the SVM. The experimental results showed that the classification model has an accuracy of 91.07%.  

Intelligent decision-making with bird-strike risk assessment for airport bird repellent

2018 ◽  
Vol 122 (1252) ◽  
pp. 988-1002 ◽  
Author(s):  
Weishi Chen ◽  
Jie Zhang ◽  
Jing Li
Keyword(s):  
Risk Assessment ◽  
Decision Making ◽  
Real Time ◽  
Expert Knowledge ◽  
Assessment Model ◽  
Classification Model ◽  
Support Vector ◽  
Bird Strike ◽  
Intelligent Decision Making ◽  
Intelligent Decision

ABSTRACTAn intelligent decision-making method was proposed for airport bird-repelling based on a Support Vector Machine (SVM) and bird-strike risk assessment. The bird-strike risk assessment model is established with two exponential functions to separate the risk levels, while the SVM method includes two steps of training and testing. After the risk assessment, the Bird-Repelling Strategy Classification Model (BRSCM) was trained based on the expert knowledge and large amount of historical bird information collected by the airport linkage system for bird detection, surveillance and repelling. Then, in the testing step, the BRSCM was continuously optimised according to the real-time intelligent bird-repelling strategy results. Through several bird-repelling examples of a certain airport, it is demonstrated that the decision accuracy of BRSCM is relatively high, and it could solve new problems by self-correction. The proposed method achieved the optimised operation of multiple bird-repelling devices against real-time bird information with great improvement of bird-repelling effects, overcoming the tolerance of birds to the bird-repelling devices due to their long-term repeated operation.

scholarly journals Support Vector Machine Based Feature Extraction for Gender Recognition From Objects Using Lasso Classifier

2020 ◽  
Author(s):  
Damodara Krishna Kishore Galla ◽  
BabuReddy Mukamalla ◽  
Rama Prakasha Reddy Chegireddy
Keyword(s):  
Face Recognition ◽  
Recognition System ◽  
Classification Model ◽  
Support Vector ◽  
Gender Classification ◽  
Accuracy Score ◽  
Lasso Regression ◽  
Vehicle Recognition ◽  
And Gender ◽  
Human Faces

Abstract The blind people has their difficulty to identify the object moving around them, therefore with a high accuracy score object detection and human face recognition system will helps them in identifying the things around them with ease. In this research article,a minimum distance trainer for feature selection by accessing SVM feature optimization process, then LASSO classifier applied to perform object recognition and gender classification. Database of 100 images (50 male and 50 female face images considered from 5 different databases) and 10 categories of vehicle types are used for gender and vehicle recognition and classification. Original face image database used for the gender classification. This approach was implemented with dual classification model [(1) Recognizing or classifying human faces from various objects and (2) Classifying gender through face recognition] is made possible with the help of combining modified SIFT feature in combination with ridge regression (RR), elastic net (EN), lasso regression(LR) and lasso regression with Gaussian Support Vector Machines (LRGS) based classificatioins. The final classification results accurate are as follows RR- 89.6%, EN- 93.5%, LR-93.2% and the proposed approach is LRGS with 98.4% accurate detection rate with rediction names.

Quantitative inspection for identifying broken coal mine wire rope based on wavelet packet sparse representation

2021 ◽  
Vol 63 (2) ◽  
pp. 102-110
Author(s):  
Junying Zhou ◽  
Jie Tian ◽  
Peng Cheng ◽  
Xu Li ◽  
Decheng Wang
Keyword(s):  
Sparse Representation ◽  
Matching Pursuit ◽  
Wavelet Packet ◽  
Median Filter ◽  
Recognition Rate ◽  
Wire Rope ◽  
Classification Model ◽  
Filter Method ◽  
Support Vector ◽  
Reconstructed Signal

The magnetic flux leakage (MFL) signal of steel wire rope is easily affected by background noise, rope strands and so on. A preprocessing method for the damage signal based on wavelet packet sparse representation is proposed. This method is suitable for the damage signal of the wire rope. The original signal is decomposed into three layers of wavelet packets and the wavelet packet coefficients are sparsely represented by the matching pursuit (MP) and orthogonal matching pursuit (OMP) algorithms. The signal-to-noise ratio (SNR) of the reconstructed signal is much higher than that obtained through the wavelet threshold shrinkage method, the median filter method and the singular value difference spectrum method. The proposed method can significantly improve the noise reduction effect of the damage signal. A principal component analysis (PCA)-based particle swarm optimisation support vector machine (PSO-SVM) model for quantitative recognition is proposed. Seven global eigenvalues and wavelet packet energy entropy details of damage signals are extracted as effective eigenvalues. The eight eigenvalues are used as the input for the SVM that is designed and trained. A PSO-SVM classification model based on PCA is proposed. The results show that the recognition rate of the SVM is 94.73%. The quantitative recognition accuracy is improved.

Wearable IoT based diagnosis of prostate cancer using GLCM-multiclass SVM and SIFT-multiclass SVM feature extraction strategies

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Swetha Parvatha Reddy Chandrasekhara ◽  
Mohan G. Kabadi ◽  
Srivinay Srivinay
Keyword(s):  
Prostate Cancer ◽  
Image Processing ◽  
Feature Extraction ◽  
Sensitivity And Specificity ◽  
Early Stage ◽  
Classification Model ◽  
Support Vector ◽  
Data Set ◽  
Content Type ◽  
Multiclass Svm

Purpose This study has mainly aimed to compare and contrast two completely different image processing algorithms that are very adaptive for detecting prostate cancer using wearable Internet of Things (IoT) devices. Cancer in these modern times is still considered as one of the most dreaded disease, which is continuously pestering the mankind over a past few decades. According to Indian Council of Medical Research, India alone registers about 11.5 lakh cancer related cases every year and closely up to 8 lakh people die with cancer related issues each year. Earlier the incidence of prostate cancer was commonly seen in men aged above 60 years, but a recent study has revealed that this type of cancer has been on rise even in men between the age groups of 35 and 60 years as well. These findings make it even more necessary to prioritize the research on diagnosing the prostate cancer at an early stage, so that the patients can be cured and can lead a normal life. Design/methodology/approach The research focuses on two types of feature extraction algorithms, namely, scale invariant feature transform (SIFT) and gray level co-occurrence matrix (GLCM) that are commonly used in medical image processing, in an attempt to discover and improve the gap present in the potential detection of prostate cancer in medical IoT. Later the results obtained by these two strategies are classified separately using a machine learning based classification model called multi-class support vector machine (SVM). Owing to the advantage of better tissue discrimination and contrast resolution, magnetic resonance imaging images have been considered for this study. The classification results obtained for both the SIFT as well as GLCM methods are then compared to check, which feature extraction strategy provides the most accurate results for diagnosing the prostate cancer. Findings The potential of both the models has been evaluated in terms of three aspects, namely, accuracy, sensitivity and specificity. Each model’s result was checked against diversified ranges of training and test data set. It was found that the SIFT-multiclass SVM model achieved a highest performance rate of 99.9451% accuracy, 100% sensitivity and 99% specificity at 40:60 ratio of the training and testing data set. Originality/value The SIFT-multi SVM versus GLCM-multi SVM based comparison has been introduced for the first time to perceive the best model to be used for the accurate diagnosis of prostate cancer. The performance of the classification for each of the feature extraction strategies is enumerated in terms of accuracy, sensitivity and specificity.

scholarly journals Covid-19 Detection using Deep Learning

2021 ◽  
Vol 9 (VI) ◽  
pp. 3835-3540
Author(s):  
M. Srilekha Reddy
Keyword(s):  
Global Economy ◽  
Transmission Rate ◽  
False Negative ◽  
Image Features ◽  
Diagnostic Methods ◽  
Classification Model ◽  
Support Vector ◽  
Classification Rate ◽  
X Ray ◽  
Chest X Ray

Recently, the virus (COVID-19) has spread widely throughout the world and has led to the examination of large numbers of suspected cases using standard COVID-19 tests and has become pandemic. Everyday life, public health and the global economy have been destroyed. The pathogenic laboratory tests such as Polymerase chain reaction (PCR) take a long time with false negative results and are considered the gold standard for diagnosis. Therefore, there was an urgent need for rapid and accurate diagnostic methods to detect COVID-19 cases as soon as possible to prevent the spread of this epidemic and combat it. Applying advanced artificial intelligence techniques along with radiography may be helpful in detecting this disease. In this study, we propose a classification model that detect the infected condition through the chest X-ray images. A dataset containing chest x-ray images of normal people, people with pneumonia such as SARS, streptococcus and pneumococcus and other patients with COVID- 19 were collected. Histogram of oriented gradients (HOG) is used for image features extraction. The images are then classified using Support Vector Machines (SVM), random forests and K- nearest neighbours (KNN), with classification rate 98.14%, 96.29% and 88.89% respectively. These results may contribute efficiently in detecting COVID-19 disease. The input dataset is taken from Kaggle which provides the dataset to analyse and helps to get the best possible solutions from the set of problems. Kaggle is launching a companion COVID-19 forecasting challenges to help answer a subset of the NASEM/WHO questions. While the challenge involves forecasting confirmed cases and fatalities between April 1 and April 30 by region, the primary goal isn't only to produce accurate forecasts. It’s also to identify factors that appear to impact the transmission rate of COVID-19.

AUTOMATED CLASSIFICATION FOR BRAIN MRIS BASED ON 2D MF-DFA METHOD

Fractals ◽  
2020 ◽  
Vol 28 (06) ◽  
pp. 2050109
Author(s):  
JIAN WANG ◽  
WEI SHAO ◽  
JUNSEOK KIM
Keyword(s):  
Sensitivity And Specificity ◽  
Nearest Neighbor ◽  
Binary Classification ◽  
Brain Mri ◽  
Image Features ◽  
Support Vector ◽  
Fluctuation Analysis ◽  
Automated Classification ◽  
Multifractal Detrended Fluctuation Analysis ◽  
Hurst Exponents

Magnetic resonance image (MRI) is an important tool to diagnose human diseases effectively. It is very important for research and clinical application to classify the normal and abnormal human brain MRI images automatically. In this paper, an accurate and efficient technique is proposed to extract features of MRIs and classify these images into normal and abnormal categories. We use two-dimensional multifractal detrended fluctuation analysis (2D MF-DFA) to obtain image features. These features are the local generalized Hurst exponents calculated by 2D MF-DFA. In this regard, the values of Hurst exponents are given as the training input vector and are taken to the classifiers. We use [Formula: see text]-nearest neighbor ([Formula: see text]-NN) and support vector machine (SVM) to classify a specific brain MRI as normal or glioma affected. For SVM, we apply the leave-one-out cross-validation method for experimental verification. The 2D MF-DFA-SVM system achieved accuracy, sensitivity, and specificity of [Formula: see text] ±[Formula: see text], [Formula: see text], and [Formula: see text] ±[Formula: see text], respectively. The 2D MF-DFA-[Formula: see text]-NN system achieved accuracy, sensitivity, and specificity of [Formula: see text], [Formula: see text], and [Formula: see text], respectively. We find that when performing binary classification for brain MRIs, the SVM is superior to [Formula: see text]-NN. In addition, our experimental results indicate that the proposed 2D MF-DFA-SVM achieved excellent outcomes compared to those of the previous works. The proposed system is a promising system to clinical use.

Sign in / Sign up

Export Citation Format

Share Document