Visual Cryptography encrypts the secret or key into 'n' shares or portions and distributes them to a group of 'n' participants. The secret is recovered only when shares of all the participants in the group are stacked upon one another depending on the method used. This technique eliminates complex computations during decryption. It uses simple OR or XOR Boolean operations. Once the secret is revealed, it is no more a secret. So, a new secret acts as a key, that is to be again shared confidentially. The same process is performed and new shares are generated and distributed. The generation and distribution of shares must be done every time when a new secret or a combinational key is shared. In this paper, a trusted third party generates the shares and distributes it to the group of participants. It also generates an extra share for itself. To reveal the secret, the third party's share is also used along with other participants shares. Every time when the secret is to be changed, the third party regenerates its share only, instead of generating shares for all participants. This method reduces the overhead of regeneration and redistribution of shares to all participants with every change of the secret or key. This method of key management also retains the perfect contrast and security. The OR based method leads to noise during recovery. XOR based operations during recovery recovers lossless image. So, XOR operation is more preferable during recovery of the secret.
Intracranial hemorrhage (ICH) is a serious medical condition that necessitates a prompt and exhaustive medical diagnosis. This paper presents a multi-label ICH classification issue with six different types of hemorrhages, namely epidural (EPD), intraparenchymal (ITP), intraventricular (ITV), subarachnoid (SBC), subdural (SBD), and Some. A patient may experience numerous hemorrhages at the same time in some situations. A CT scan of a patient’s skull is used to detect and classify the type of ICH hemorrhage(s) present. First, our model determines whether there is a hemorrhage or not; if there is a hemorrhage, the model attempts to identify the type of hemorrhage(s). In this paper, we present a hybrid deep learning approach that combines convolutional neural network (CNN) and Long-Short Term Memory (LSTM) approaches (Conv-LSTM). In addition, to propose viable solutions for the problem, we used a Systematic Windowing technique with a Conv-LSTM. To ensure the efficacy of the proposed model, experiments are conducted on the RSNA dataset. The suggested model provides higher sensitivity (93.87%), specificity (96.45%), precision (95.21%), and accuracy (95.14%). In addition, the obtained F1 score results outperform existing deep neural network-based algorithms.
The success of machine learning models is subjected to the availability of sufficient amounts of training data. Avail-ability of large amounts of labeled data is difficult especially in the domains of image, speech, video etc. Semi-supervised learning is an approach that uses additionally available unlabeled data to improve performance of a model with limited data. To gain better performance with limited training data we suggest semisupervised SVM models for EEG Signal classification and image classification tasks. We explore multiple approaches to semi-supervised learning based on Support vector machines: Semi-supervised Support vector machines (S 3 VM), S 3 VM light , SVM-light and label switching based Support Vector Machine (Lap-SVM) for different tasks. Our experiments show that semi-supervised approaches when trained with sufficient unlabeled data can significantly improve performance of the model when compared with its counterpart supervised model. The proposed models are verified on 3 different benchmark data sets. Proposed semi-supervised approach for image classification task show a remarkable 20% improvement over baseline SVM model.
Many vulnerable, heinous acts that are coming about in the society especially at Roads, most specifically affecting women in the society, are more in recent days. Though new technologies are developing day by day, the fatality rate is not in control to date. Without proper guidance to the people about the particular place where there is a big scope of occurrence of a greater number of accidents, this menace cannot be regulated. It is required to highlight the District-wise data and Roads where the accidents and fatalities are more. The data would help the policymakers to put in place Focused Initiatives regarding those top dangerous roads to address the menace of rising road accidents and resultant fatalities. In this, we created a dataset in Andhra Pradesh where we include those attributes that are helpful for our analysis to predict which road is the most dangerous one. We applied various Machine Learning models such as Logistic regression, Random forest classifier, Gradient Boosting Classifier, Gaussian Naive Bayes, Decision Tree Classifier, K- Nearest Neighbour Classifier and SVM to predict the dangerous roads. It is observed that Logistic Regression provides good accuracy with 87.14.
Sorting is a huge demand research area in computer science. Sorting is a process of arranging the elements in an order. In practical application computing requires things to be in order. A comparative study is done in this study and performed the comparison for both positive and negative numbers by taking the random numbers as input. In this study, different algorithms like UNH Sort, Selection Sort, Bubble Sort, Insertion Sort, Merge Sort, Quick Sort are considered for the experimentation. From the obtained results we can conclude that, Initially when the input size is less UNH Sort is giving best when it is compared with bubble sort. When the input size increases bubble sort takes long time to perform sorting. And Quick sort takes less time to perform sorting.
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.
customersupport@researchsolutions.com
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.