C, Ganesh Babu, Rajaguru, Harikumar, M, Kalaiyarasi
Die vorgeschlagene Arbeit wurde entwickelt, um das Risiko einer hochdimensionalen Datendarstellung in Form einer niedrigdimensionalen Datendarstellung zu verringern. Die Reduzierung der Dimensionalität wird durch die Auswahl der richtigen Merkmale erreicht, wobei die Dimensionen reduziert werden und ein geeignetes Modell erstellt wird, um die richtige Wahl zu treffen. In diesem Bericht werden die Verfahren zur Dimensionalitätsreduzierung wie Hauptkomponentenanalyse (PCA), Kernel-PCA und Locally Linear Embedded (LLE) vorgestellt.
Die vorgeschlagene Arbeit wurde entwickelt, um das Risiko einer hochdimensionalen Datendarstellung in Form einer niedrigdimensionalen Datendarstellung...
C, Ganesh Babu, Rajaguru, Harikumar, M, Kalaiyarasi
Arrhythmia occurs when there is no proper working of electrical impulses present in the heart. An earlier detection of irregular heart rhythm is necessary in order to rescue ones survival. Classification of arrhythmia is needed for diagnosis. This report confers the Principle component analysis as feature reduction process to reduce high dimensional input without influencing classification methods and two feature selection techniques such as Grey wolf optimizer (GWO), Particle swarm optimization (PSO), and Support Vector Machine (SVM) helpful in choosing features with arrhythmia and...
Arrhythmia occurs when there is no proper working of electrical impulses present in the heart. An earlier detection of irregular heart rhythm is neces...
In the world, there are many rare and incurable diseases that need to be detected. The manual detection of those diseases requires more cost and time. Autism is one of the main diseases that are increasing at a higher rate and its detection techniques are very challenging. But the early detection of autism can save a patient or increase their lifetime. So this work concentrates on developing machine learning algorithms to detect autism. Our project's main aim is to detect whether the patient is having autism or not. The appropriate dataset is used with eight machine learning algorithm and...
In the world, there are many rare and incurable diseases that need to be detected. The manual detection of those diseases requires more cost and time....
Using deep learning techniques lung ultrasonography (LUS) images are analyzed instead of CT scan images for COVID-19 detection. The severity of the disease is found at the pixel level and frame level. Every pixel of image will be classified with the help of semantic segmentation network, resulting in the detection of COVID part in the input image. When compared to the existing method, this proposed method can give better classification.
Using deep learning techniques lung ultrasonography (LUS) images are analyzed instead of CT scan images for COVID-19 detection. The severity of the di...
C, Ganesh Babu, Rajaguru, Harikumar, M, Kalaiyarasi
The proposed work developed to reduce the risk of high dimensional data representation in the form of low dimensional data representation. Reduction in dimensionality is achieved by choosing the right features where the dimensions get reduced, it build a right model to achieve right choice. This report presents the dimensionality reduction practices such as Principal Component Analysis (PCA), Kernel PCA and Locally Linear Embedded (LLE).
The proposed work developed to reduce the risk of high dimensional data representation in the form of low dimensional data representation. Reduction i...
Mithilfe von Deep-Learning-Techniken werden Lungenultraschallbilder (LUS) anstelle von CT-Scan-Bildern zur Erkennung von COVID-19 analysiert. Der Schweregrad der Krankheit wird auf Pixel- und Bildebene ermittelt. Jedes Pixel des Bildes wird mit Hilfe eines semantischen Segmentierungsnetzwerks klassifiziert, was zur Erkennung des COVID-Anteils im Eingabebild führt. Im Vergleich zur bestehenden Methode kann diese vorgeschlagene Methode eine bessere Klassifizierung liefern.
Mithilfe von Deep-Learning-Techniken werden Lungenultraschallbilder (LUS) anstelle von CT-Scan-Bildern zur Erkennung von COVID-19 analysiert. Der Schw...
En utilisant des techniques d'apprentissage profond, les images d'échographie pulmonaire (LUS) sont analysées au lieu des images de tomodensitométrie pour la détection du COVID-19. La gravité de la maladie est trouvée au niveau du pixel et de l'image. Chaque pixel de l'image sera classé à l'aide d'un réseau de segmentation sémantique, ce qui permettra de détecter la partie COVID dans l'image d'entrée. Comparée à la méthode existante, la méthode proposée permet une meilleure classification.
En utilisant des techniques d'apprentissage profond, les images d'échographie pulmonaire (LUS) sont analysées au lieu des images de tomodensitométr...