Search

Our eyes are undoubtedly the most precious gift we have and play a significant part in our daily life. We are fortunate to have sight, so we can see this world. However, some individuals struggle to visualize these things. Because of this, moving around in strange public settings presents several difficulties for those with vision impairment. 39 million individuals are blind and 246 have limited vision, making up the estimated 285 million visually impaired persons globally. Wearable technology should be created with these people's visual impairments in mind. Smart shoes are a wearable technology created to give persons with vision impairments navigational information. In this study, a sophisticated electronic assistive device for the blind prototype model and system design are given. This system's components—a microprocessor, an ultrasonic sensor, and a Bluetooth headphone—are made to provide general measures for object detection, human detection, and real-time help. A pair of smart shoes equipped with water and ultrasonic sensors. A Bluetooth connection between the shoe and an Android application will enable voice control support for the user. The user will be assisted in moving about autonomously by the Smart Shoes and the Android application.

Automatic detection of glaucoma from retinal fundus images is a major area of research in Computer aided diagnostics. In this paper, we propose a novel methodology to detect glaucoma by using energy of graph concepts. The retinal fundus image is first segmented to get the structure of the retinal vasculature using various image processing techniques. The retinal vasculature is then modeled into two graphs based on the position of branchpoints and the crossover points in the image. The graphs thus formed are simplified and 6 different energies are extracted from it. These energies are then used as features to a machine learning model i.e., quadratic support vector machine after performing principal component analysis. The methodology was tested out on the G1020 dataset and the results obtained show that energy of graphs does contain discriminating information regarding disease detection.

Face-on-Face interaction constitutes an integral part of the classroom atmosphere as it provides teachers with an opportunity to understand their students intimately. Hence, this study deals with attribute based double bounded rough neutrosophic set driven random forests using Gini Impurity based split to arrive at a decision regarding the teaching-learning efficiency. A mathematical model is constructed using double bounded rough neutrosophic set which is utilised to evaluate the expression of the students with the help of a real-time data by capturing the images of the students against different subjects. The decisions made are then used to fit a random forest model to establish inferences regarding the teaching-learning efficiency for different subjects. The constructed model is then validated using newly added test objects.

Encryption and decryption are the two processes in cryptography to conceal and convey important information to an authorized person without third-party interruption in a network. Cryptography is a branch of computer science in which the system has to be updated every second. It mainly depends on mathematical concepts like number theory and algebra. Recently, graph theory concepts are employed in cryptography to make it stronger. The usage of complex graphs in cryptosystems makes it difficult to hack. In this paper, we proposed a cryptosystem using the Turan graph which has a complex graph structure. The advantage of using a Turan graph is that it is a unique multipartite complete graph with more edges than other multipartite complete graphs. This adds robustness to the cryptosystem. The novelty of this paper is the decomposition of the Turan graph into paths and stars and applying edge labeling to them to encrypt and decrypt a sentence of k words. The algorithms for encryption and decryption are also proposed in this paper.

In this paper, a hybrid intelligent structure called “Double Bounded Rough Neutrosophic Sets” is defined, which is a combination of Neutrosophic sets theory and Rough sets theory. Further, the Attribute based Double Bounded Rough Neutrosophic Sets was implemented using this hybrid intelligent structure for Facial Expression Detection on real time data. Facial expression detection is becoming increasingly important to understand one’s emotion automatically and efficiently and is rich in applications. This paper implements some of these applications of facial expression such as: differentiating between Genuine and Fake smiles, prediction of Depression, determining the Degree of Closeness to a particular Attribute/Expression and detection of fake expression during an examination. With the onset of COVID – 19 pandemic, majority of people are choosing to wear masks. A suitable method to detect Facial Expression with and without mask is also implemented. Double Bounded Rough Neutrosophic Sets proposed in this paper is found to yield better results as compared to that of individual structures (Neutrosophic sets theory or Rough sets theory)

In this paper, we define the Total graph and the complemented graph of a rough semiring (T, ∆, ∇). We prove that the existence theorem of the total graph and the complemented graph on (T, ∆, ∇) for X ⊆ U where U is the finite universal set on the set of all rough sets for the given information system I = (U, A) together with the operations praba ∆ and praba ∇. We illustrate these concepts through examples.