Purpose
The purpose of this paper is to predict future diseases based on existing health status using link prediction and explores how long the link survives.
Design/methodology/approach
The authors aimed to compare SULP with other approaches of link prediction especially DLS and try to find which one is better on parameters like AUROC and precision over disease–disease network data set. The implementation is done over MATLAB.
Findings
The authors have found that on the parameters such as AUROC and precision, SULP performs better. The AUROC value of SULP is 0.9805 and lies in between the standard value of 0.5 and 1 and precision value is 0.76.
Originality/value
The approach is novel and is applicable on almost every type of network model.
Brain cancer is a rare and deadly disease with a slim chance of survival. One of the most important tasks for neurologists and radiologists is to detect brain tumors early. Recent claims have been made that computer-aided diagnosis-based systems can diagnose brain tumors by employing magnetic resonance imaging (MRI) as a supporting technology. We propose transfer learning approaches for a deep learning model to detect malignant tumors, such as glioblastoma, using MRI scans in this study. This paper presents a deep learning-based approach for brain tumor identification and classification using the state-of-the-art object detection framework YOLO (You Only Look Once). The YOLOv5 is a novel object detection deep learning technique that requires limited computational architecture than its competing models. The study used the Brats 2021 dataset from the RSNA-MICCAI brain tumor radio genomic classification. The dataset has images annotated from RSNA-MICCAI brain tumor radio genomic competition dataset using the make sense an AI online tool for labeling dataset. The preprocessed data is then divided into testing and training for the model. The YOLOv5 model provides a precision of 88 percent. Finally, our model is tested across the whole dataset, and it is concluded that it is able to detect brain tumors successfully.
The existing work on unsupervised segmentation frequently does not present any statistical extent to estimating and equating procedures, gratifying a qualitative calculation. Furthermore, regardless of the datum that enormous research is dedicated to the advancement of a novel segmentation approach and upgrading the deep learning techniques, there is an absence of research comprehending the assessment of eminent conventional segmentation methodologies for HSI. In this paper, to moderately fill this gap, we propose a direct method that diminishes the issues to some extent with the deep learning methods in the arena of a HSI space and evaluate the proposed segmentation techniques based on the method of the clustering-based profound iterating deep learning model for HSI segmentation termed as CPIDM. The proposed model is an unsupervised HSI clustering technique centered on the density of pixels in the spectral interplanetary space and the distance concerning the pixels. Furthermore, CPIDM is a fully convolutional neural network. In general, fully convolutional nets remain spatially invariant preventing them from modeling position-reliant outlines. The proposed network maneuvers this by encompassing an innovative position inclined convolutional stratum. The anticipated unique edifice of deep unsupervised segmentation deciphers the delinquency of oversegmentation and nonlinearity of data due to noise and outliers. The spectrum efficacy is erudite and incidental from united feedback via deep hierarchy with pooling and convolutional strata; as a consequence, it formulates an affiliation among class dissemination and spectra along with three-dimensional features. Moreover, the anticipated deep learning model has revealed that it is conceivable to expressively accelerate the segmentation process without substantive quality loss due to the existence of noise and outliers. The proposed CPIDM approach outperforms many state-of-the-art segmentation approaches that include watershed transform and neuro-fuzzy approach as validated by the experimental consequences.
With the growth of social networks, the problem of linking the isolated or missing nodes appears. Thus, link prediction comes into existence to resolve this problem. Link prediction may be defined as an approach to predict an optimistic relationship that may exist or is likely to exist between nodes. Predicting the prospect link formed in future between nodes either in a dense or sparse network, the number of techniques exist intending to establish a link based on a certain similarity between the nodes. After conducting in-depth research on almost every link prediction technique, we reach the conclusion that every technique evaluates the probability score to predict future links. This research work discusses almost every previous technique and puts forward a comparatively similar technique for link prediction. The proposed technique is named Shabaz–Urvashi Link Prediction (SULP), which is based on a formula derived from an empirical theory after making a node matrix and altering the position of the neighbouring nodes, which states, ‘A node is predicted to establish a friendship if it has a maximum degree in its common neighbouring row and a minimum degree in its common neighbouring column’. SULP is tested using established datasets and compared with other link prediction techniques on the statistical measures such as Area Under Receiver Operating characteristic Curve (AUROC), precision and recall. SULP performs better as compared to other link prediction techniques on most of the testing datasets.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.