scholarly journals Internet of things mathematical approach for detecting brain tumor

2018 ◽  
Vol 7 (4) ◽  
pp. 2779
Author(s):  
Noor Kareem Jumaa ◽  
Auday A.H Mohamad ◽  
Sameer Hameed Majeed
Keyword(s):  
Brain Tumor ◽  
Internet Of Things ◽  
Support Vector ◽  
Medical Field ◽  
Brain Functions ◽  
Svm Algorithm ◽  
Magnetic Resonance Imaging Mri ◽  
The Right ◽  
Computerized System ◽  
Program Version

Brain is highly important organ which makes us able to walk, breath, and all other activities; without brain lives can’t do all of that. The importance of brain functions made it critical to make any not precisely measured medical action. Currently; computer vision is very important in medical field, where it helps specialists to precisely diagnose and take the right decision before making surgeries. This article worked on accommodating the technology of internet of things (IoT) for serving brain medicine specialist in the field of identifying the need of making surgeries depending on magnetic resonance imaging (MRI) images. Support Vector Machine (SVM) algorithm is used to detect brain tumor and segment it from MRI morphological images. Putting SVM on IoT Thingspeak platform will help brain specialist to diagnose MRI images that are received from MRI computerized system online. The obtained results are compared with same algorithm implemented locally with assist of Matlab program version R2017a.  

scholarly journals SVM-Based Normal Pressure Hydrocephalus Detection

2021 ◽  
Author(s):  
Alexander Rau ◽  
Suam Kim ◽  
Shan Yang ◽  
Marco Reisert ◽  
Elias Kellner ◽  
...  
Keyword(s):  
Support Vector Machine ◽  
Normal Pressure Hydrocephalus ◽  
Clinical Symptoms ◽  
Normal Pressure ◽  
Support Vector ◽  
Asymptomatic Patients ◽  
Svm Algorithm ◽  
Magnetic Resonance Imaging Mri ◽  
The Right ◽  
Work Up

Abstract Background and Purpose As magnetic resonance imaging (MRI) signs of normal pressure hydrocephalus (NPH) may precede clinical symptoms we sought to evaluate an algorithm that automatically detects this pattern. Methods A support vector machine (SVM) was trained in 30 NPH patients treated with ventriculoperitoneal shunts and 30 healthy controls. For comparison, four neuroradiologists visually assessed sagittal MPRAGE images and graded them as no NPH pattern, possible NPH pattern, or definite NPH pattern. Results Human accuracy to visually detect a NPH was between 0.85 and 0.97. Interobserver agreement was substantial (κ = 0.656). Accuracy of the SVM algorithm was 0.93 and AUROC 0.99. Among 272 prespecified regions, gray matter and CSF volumes of both caudate, the right parietal operculum, the left basal forebrain, and the 4th ventricle showed the highest discriminative power to separate a NPH and a no NPH pattern. Conclusion A NPH pattern can be reliably detected using a support vector machine (SVM). Its role in the work-up of asymptomatic patients or neurodegenerative disease has to be evaluated.

scholarly journals Recognition of brain cancer and cerebrospinal fluid due to the usage of different MRI image by utilizing support vector machine

2020 ◽  
Vol 9 (2) ◽  
Author(s):  
Soobia Saeed ◽  
Afnizanfaizal Abdullah
Keyword(s):  
Support Vector Machine ◽  
Cerebrospinal Fluid ◽  
Brain Tumor ◽  
Brain Cancer ◽  
The Body ◽  
Csf Leak ◽  
Support Vector ◽  
The Future ◽  
Tumor Region ◽  
The Right

Medicinal images assume an important part in the diagnosis of tumors as well as Cerebrospinal fluid (CSF) leak. Similarly, MRI could be the cutting-edge regenerative imaging technology that allows for a sectional angle perspective of the body that gives specialists convenience and will inspect the person-concerned. In this paper, the author has attempted the strategy to classify MRI images at the beginning of production to have a tumor or recognition. The study aims to address the aforementioned problems associated with brain cancer with a CSF leak. This research, the author focuses on brain tumor and applies the statistical model for the testing and also discusses the images of a brain tumor. They can judge the tumor region by conducting a comparative image analysis and applying Histogram function afterwards to construct a classifier that could be prepared to predict tumor and non-tumor MRI examinees based on the support vector machine. Our system is capable of detecting the right region that a pathologist also highlights. In the future, this should be more driven with the objective that tumors can be arranged and describe the solution in the medical terms implementation with gives some predictions about the future generated by modified technology. 

scholarly journals Prediction of Successful Elearning Based on Activity Logs with Selection of Support Vector Machine based on Particle Swarm Optimization

2019 ◽  
Vol 2 (1) ◽  
Author(s):  
Elin Panca Saputra ◽  
Sukmawati Angreani Putri ◽  
Indriyanti Indriyanti
Keyword(s):  
Support Vector Machine ◽  
Particle Swarm Optimization ◽  
Particle Swarm ◽  
Attribute Selection ◽  
Support Vector ◽  
Swarm Optimization ◽  
Student Activities ◽  
Svm Algorithm ◽  
The Right ◽  
Selection Of

Prediction is a systematic estimate that identifies past and future information, we predict the success of learning with elearning based on a log of student activities. In our current study we use the Support vector machine (SVM) method which is comparable with Particle Swarm Optimization. It is known that SVM has a very good generalization that can solve a problem. however, some of the attributes in the data can reduce accuracy and add complexity to the Support Vector Machine (SVM) algorithm. It is necessary for existing tribute selection, therefore using the Particle swarm optimization (PSO) method is applied to the right attribute selection in determining the success of elearning learning based on student activity logs, because with the Swarm Optimization (PSO) method can increase accuracy in determining selection of attributes.

The Application of an Improved Integration Algorithm of Support Vector Machine to the Prediction of Network Security Situation

2014 ◽  
Vol 513-517 ◽  
pp. 2285-2288 ◽  
Author(s):  
Shao Min Zhang ◽  
Bing Xia Li ◽  
Bao Yi Wang
Keyword(s):  
Support Vector Machine ◽  
Network Security ◽  
Prediction Error ◽  
Bootstrap Method ◽  
Learning Theories ◽  
Support Vector ◽  
Integration Algorithm ◽  
Optimal Weights ◽  
Svm Algorithm ◽  
The Right

In order to grasp the security situation of the network accurately and provide effective information for managers of network.GeesePSOSEN-SVM algorithm is proposed in this paper. It can produce and train multiple independent SVM through Bootstrap method and increase the degree of difference among SVM based on learning theories of negative correlation to construct the fitness function.GeesePSO algorithm is used to calculate the optimal weights of SVM.The algorithm chooses the high weights of SVM to integrate. At last, through the experiment on MATLAB for network security situational prediction,the results show that the absolute prediction error is smaller ,and the right trend rate is higher.

scholarly journals Ring enhanced aneurysm due to vasa vasorum of aneurysm wall mimicking a metastatic brain tumor

2021 ◽  
Vol 12 ◽  
pp. 64
Author(s):  
Yu Shimizu ◽  
Katsuyoshi Miyashita ◽  
Nozomu Oikawa ◽  
Masaaki Kobayashi ◽  
Yasuo Tohma
Keyword(s):  
Differential Diagnosis ◽  
Brain Tumor ◽  
Metastatic Brain Tumor ◽  
Vasa Vasorum ◽  
Neurological Deficits ◽  
Peripheral Edema ◽  
Thrombosed Aneurysm ◽  
Aneurysm Wall ◽  
Magnetic Resonance Imaging Mri ◽  
The Right

Background: A spherical intracranial mass can be occasionally misdiagnosed due to the lack of typical radiographic features. Completely thrombosed intracranial aneurysms (CTIA) are uncommon, but a possible differential diagnosis must be considered to guarantee the best surgical approach for these lesions. Case Description: Here, we report an extremely rare case of a right frontal mass mimicking a brain tumor, in which the surgery unveiled a CTIA of the right middle cerebral artery (MCA). A 56-year-old woman presented with right hemiparesis and mild headache. Magnetic resonance imaging (MRI) revealed a right frontal mass with peripheral edema. The lesion enhanced on initial and follow-up MRI of the brain. Subsequent vascular studies and metastatic workup were negative. A temporal craniotomy with neuronavigation (Brain Lab AG, Germany) was performed and an intraoperative diagnosis of a thrombosed aneurysm along the branch of the MCA was established. The aneurysm was successfully trapped and resected. The patient did not exhibit any postoperative neurological deficits. Conclusion: This is the rare report of a ring enhanced completely thrombosed aneurysm due to vasa vasorum which is misdiagnosed as metastatic brain tumor. In case of an intracranial ring enhanced mass with signs of intralesional hemorrhage and peripheral edema, CTIA should be considered as a possible differential diagnosis.

scholarly journals SVM Optimization Based on PSO and AdaBoost to Increasing Accuracy of CKD Diagnosis

2019 ◽  
pp. 119
Author(s):  
Amanah Febrian Indriani ◽  
Much Aziz Muslim
Keyword(s):  
Data Mining ◽  
Chronic Kidney Disease ◽  
Support Vector Machine ◽  
High Accuracy ◽  
Classification Algorithm ◽  
High Dimensional ◽  
Support Vector ◽  
Medical Field ◽  
Swarm Optimization ◽  
Svm Algorithm

Classification is data mining techniques which used for the purposes of diagnosis in the medical field as measured by the high accuracy produced. The accuracy of classification algorithm is influenced by the use of features and dimensions in dataset. In this study, Chronic Kidney Disease (CKD) dataset was used where the data is one of the high dimension datasets. Support Vector Machine (SVM) algorithm is used because its ability to handle high-dimensional data. In the dataset, it consists of 24 attributes and 1 class which if all are used results accuracy of classification will be diminished. Method for selecting features with Particle Swarm Optimization (PSO) is applied to reduce redundant features and produce optimal features. In addition, ensemble AdaBoost also applied in this research to increase performance of entirety classification algorithm. The results showed that the optimization of SVM algorithm by using PSO as a selection and ensemble feature of AdaBoost with an average of selected features of 18 features could increase the accuracy of 36.20% to 99.50% in the diagnosis of CKD compared to the SVM algorithm without optimization only resulting in accuracy 63.30%. This research can be used as a reference for further research in focusing on the preprocessing stage.

scholarly journals Brain Tumor Detection and Classification Using Image Processing Techniques

2021 ◽  
pp. 32-38
Author(s):  
P. Sankar Ganesh ◽  
T. Selva Kumar ◽  
Mukesh Kumar ◽  
Mr. S. Rajesh Kumar
Keyword(s):  
Image Processing ◽  
Image Segmentation ◽  
Brain Tumor ◽  
Human Body ◽  
Brain Mri ◽  
X Rays ◽  
Abnormal Growth ◽  
Brain Functions ◽  
Magnetic Resonance Imaging Mri ◽  
The Brain

At present, processing of medical images is a developing and important field. It includes many different types of imaging methods. Some of them are Computed Tomography scans (CT scans), X-rays and Magnetic Resonance Imaging (MRI) etc. These technologies allow us to detect even the smallest defects in the human body. Abnormal growth of tissues in the brain which affect proper brain functions is considered as a brain tumor. The main goal of medical image processing is to identify accurate and meaningful information using images with the minimum error possible. MRI is mainly used to get images of the human body and cancerous tissues because of its high resolution and better quality images compared with other imaging technologies. Brain tumor identifications through MRI images is a difficult task because of the complexity of the brain. MRI images can be processed and the brain tumor can be segmented. These tumors can be segmented using various image segmentation techniques. The process of identifying brain tumors through MRI images can be categorized into four different sections; pre-processing, image segmentation, feature extraction and image classification.

scholarly journals A Unique Six Sigma Based Segmentation Technique for Brain Tumor Detection and Classification using Hybrid CNN-SVM Model

2019 ◽  
Vol 8 (2) ◽  
pp. 35-40
Keyword(s):  
Brain Tumor ◽  
Six Sigma ◽  
Machine Learning Algorithms ◽  
Support Vector ◽  
Classification Rate ◽  
Segmentation Technique ◽  
Svm Model ◽  
Tumor Region ◽  
Magnetic Resonance Imaging Mri ◽  
Feature Mining

An intelligent organizing scheme to detect and classify normal, abnormal MRI brain sequences has been illustrated here. At present, handling of brain tumors disease and decision is based on radiological appearance and its symptoms. Magnetic-Resonance-Imaging (MRI) is a powerful substantial precise instrument for functional conclusion of brain tumorous. In existing study, broad range of methods is used for brain cancer detection and classification. Under this methods viz., image pre-processing, enhancement, segmentation, feature mining and resulting classification is efficiently conducted. Furthermore, when various machine learning algorithms like: Six Sigma, Convolutional Neural Network (CNN), Support Vector Machine (SVM), are employed to detect and extract the tumor region and classify numerous sequence of imageries, it is witnessed from our results that this Hybrid CNN-SVM model gives maximum classification accuracy rate of 99.33% compared to previous models. The foremost aim of this research is to get an effective result for detecting type of brain tumor using six sigma based segmentation technique, and to achieve efficient classification rate, using hybrid CNN-SVM model.

scholarly journals Exploring Statistical Parameters of Machine Learning Techniques for Detection and Classification of Brain Tumor

2019 ◽  
Vol 8 (10) ◽  
pp. 4118-4124
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Brain Tumor ◽  
Random Forest ◽  
Machine Learning Techniques ◽  
Support Vector ◽  
Learning Techniques ◽  
Artificial Neural ◽  
Computerized System ◽  
The Brain

A computerized system can improve the disease identifying abilities of doctor and also reduce the time needed for the identification and decision-making in healthcare. Gliomas are the brain tumors that can be labeled as Benign (non- cancerous) or Malignant (cancerous) tumor. Hence, the different stages of the tumor are extremely important for identification of appropriate medication. In this paper, a system has been proposed to detect brain tumor of different stages by MR images. The proposed system uses Fuzzy C-Mean (FCM) as a clustering technique for better outcome. The main focus in this paper is to refine the required features in two steps with the help of Discrete Wavelet Transform (DWT) and Independent Component Analysis (ICA) using three machine learning techniques i.e. Random Forest (RF), Artificial Neural Network (ANN) and Support Vector Machine (SVM). The final outcome of our experiment indicated that the proposed computerized system identifies the brain tumor using RF, ANN and SVM with 100%, 91.6% and 95.8%, accuracy respectively. We have also calculated Sensitivity, Specificity, Matthews’s Correlation Coefficient and AUC-ROC curve. Random forest shows the highest accuracy as compared to Support Vector Machine and Artificial Neural Networks.

scholarly journals Penerapan Algoritma Support Vector Machine Untuk Model Prediksi Kelulusan Mahasiswa Tepat Waktu

2021 ◽  
Vol 5 (2) ◽  
pp. 386-392
Author(s):  
Emy Haryatmi ◽  
Sheila Pramita Hervianti
Keyword(s):  
Data Mining ◽  
Support Vector Machine ◽  
Support Vector ◽  
Time Data ◽  
Data Mining Technique ◽  
Student Data ◽  
Industry Standard ◽  
Svm Algorithm ◽  
Student Graduation ◽  
The Right

A University can have many student data in their database because many students did not graduate on time. Data mining technique can be used to process student data to predict student graduation on time. Support Vector Machine (SVM) algorithm is one of data mining techniques. Objectives of this research was implementation of SVM algorithm to model the prediction of student graduation on time in private university in Indonesia. This research was conducted using CRISP-DM (Cross Industry Standard Process for Data Mining) method. There are five steps in that method such as understanding business to predict student graduation in time which is not available, data understanding by choosing the right attribute for the next step, data preparation includes cleaning the null data and transforming data into category which has been specified, modeling was used by implementing data training and data testing on SVM algorithm and evaluation to validate and measure the accuracy of the model. The result of this research shown that accuracy value of data testing was 94,4% using 90% data training and 10% data testing. This concluded SVM algorithm can be used to model the prediction of student graduation on time.  

Sign in / Sign up

Export Citation Format

Share Document