Acute sinusitis classification using support and fuzzy support vector machines

Rustam, Zuherman; Angie, N.; Pandelaki, Jacub; Yunus, Reyhan Eddy

doi:10.1088/1742-6596/1490/1/012029

Cited by 6 publications

(5 citation statements)

References 8 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It has been documented that affected maxillary anatomic sites are hyperthermic (warmer) in comparison to healthy contralateral sites [2] [3]. In addition to its use as a diagnostic method, it has also been applied to the task of determining the effectiveness of acute sinusitis treatments and therapies [4].…”

Section: Related Workmentioning

confidence: 99%

See 1 more Smart Citation

Sinusitis Detection Using Neural Network Fusion of Different Classifiers on Thermal Images.

Katual

Kaul

2023

Preprint

View full text Add to dashboard Cite

Inflammation or swelling of the tissue lining on the sinuses is known as sinusitis, due to an inflammatory response, or an infection brought on by a virus, bacteria, or fungus. An unchecked sinus infection can spread to the eyes and brain, causing blindness and brain abscess respectively. In this work, a non-invasive technique developed for the detection of sinusitis from thermal images has been presented. CNN, KNN, and SVM have been used as classifiers. For KNN and SVM features were extracted from cropped thermal face images by taking the output of the first fully connected layer of Alexnet and VGGNet. The fusion of these classifiers has been done to improve the detection performance of the individual classifiers. The algorithm has been tested on a publicly available dataset. The performance evaluation has been carried out on the basis of five indices. Based on the results, fusion with neural network illustrates the highest accuracy of 99.59% irrespective of the feature extraction method, followed by the majority voting technique with an accuracy of 99.18% for features extracted by Alexnet and 98.78% for features extracted by VGGNet.

show abstract

Section: Related Workmentioning

confidence: 99%

“…In this work, linear kernels were used for the classification of the thermal images of sinusitis-affected persons as there were only two classes. In different studies, SVM has been presented as the classifier for sinusitis thermogram classification [4].…”

Section: Support Vector Machinementioning

confidence: 99%

Sinusitis Detection Using Neural Network Fusion of Different Classifiers on Thermal Images.

Katual

Kaul

2023

Preprint

View full text Add to dashboard Cite

show abstract

“…Many applications exist for classification and regression, including image classification, character recognition, pattern classification, function identification. Another definition of the SVM is a system for efficiently training linear learning machines [18].…”

Section: Support Vector Machines (Svms)mentioning

confidence: 99%

Computed Tomography (Ct) Scan Assisted Machine Learning in the Management of Artifacts Related to Paranasal Sinuses and Anterior Cranial Fossa

Musleh

2022

Computational Intelligence and Neuroscience

View full text Add to dashboard Cite

Computed tomography (CT), through the use of ionizing radiation, allows us to assess the different parts of the body. It is made up of an X-ray tube that rotates rapidly around the patient generating the radiation beam. This is attenuated with the patient producing information, which is collected by the detectors that are opposite to the tube located in the gantry (part of the tomography equipment); finally, these collected data are sent to the computer that will reconstruct the information obtained and will represent it as an image on the monitor. In the practice of a study, artifices or artifacts may appear regardless of their origin, which limits the scan examination; this leads to stopping the examination and starting again, and added to this with the contrast media, they have to apply these drugs again. State-of-the-art scanners allow complete reconstructions to be performed with few projections, limiting radiation doses, by means of statistical algebraic reconstruction methods. The present work shows the simulation of artifacts in sinusitis diagnosis computed tomography images, the extraction of features from each image, and an automatic classification algorithm for the differentiation of artifacts. The results show that the algorithm is able to classify the simulated artifacts with a percentage of 90%.

show abstract

“…The random forest is a tree-based ensemble which is a combination of each decision tree depending on a collection of random variables [19]. The decision tree is a flowchart shaped like vector [20]. For adimensional, the random vector = ( 1 , 2 , … , ) represents the predictor variables and a random variable represents the real-valued response [20].…”

Section: Random Forestmentioning

confidence: 99%

“…The decision tree is a flowchart shaped like vector [20]. For adimensional, the random vector = ( 1 , 2 , … , ) represents the predictor variables and a random variable represents the real-valued response [20]. Figure 2 is an illustration of random forest [20].…”

Section: Random Forestmentioning

confidence: 99%

Hepatitis classification using support vector machines and random forest

Aurelia

Rustam

Wirasati

et al. 2021

IJ-AI

View full text Add to dashboard Cite

<span id="docs-internal-guid-e57881bf-7fff-62db-2c1e-192664c8e8a8"><span>Hepatitis is a medical condition defined by inflammation of the liver. It can be caused by infection of the liver by hepatitis viruses or is of unknown aetiology. There are 5 main hepatitis viruses, such as virus types A, B, C, D and E. The infection may occur with limited or no symptoms, but also may include some symptoms like abdominal pain, dark urine, extreme fatigue, jaundice, nausea or vomiting. Because Indonesia is a large archipelago, the prevalence of viral infections varies greatly by region of acute hepatitis patients. This research uses data of hepatitis examination result with amount of 113 data and 5 features. The method that used is support vector machines (SVM) and random forest method. SVM is the classification method that uses discriminant hyper-plane, dividing to classes. meanwhile, random forest is a tree-based ensemble depending on a collection of random variables. SVM and random forest (RF) are applied to predict hepatitis data, and then the results will be compared.</span></span>

show abstract

Acute sinusitis classification using support and fuzzy support vector machines

Cited by 6 publications

References 8 publications

Sinusitis Detection Using Neural Network Fusion of Different Classifiers on Thermal Images.

Sinusitis Detection Using Neural Network Fusion of Different Classifiers on Thermal Images.

Computed Tomography (Ct) Scan Assisted Machine Learning in the Management of Artifacts Related to Paranasal Sinuses and Anterior Cranial Fossa

Hepatitis classification using support vector machines and random forest

Contact Info

Product

Resources

About