1. Ontology based Security Model for SIoT using Block Chain Technology { Master’s Thesis }
In the realm of technological innovation, the Social Internet of Things (SIoT) device represents the convergence of IoT devices and Smart objects, aiming to establish meaningful relationships within a specified set of objects. This fusion creates a dynamic interplay between interconnected devices, facilitating a more comprehensive understanding of their relationships and interactions. The SIoT device stands as a testament to the evolving landscape of the Internet of Things, emphasizing the importance of connectivity and shared intelligence among various objects in our digital ecosystem.
To ensure the integrity of data flows within the network, a robust ontological model is employed. This model serves as a foundational representation of the shared device, incorporating conceptualization for a clearer understanding. To further enhance security, the device data undergoes encryption using the Fernet module—a cryptographic function embedded in the Python programming language. This meticulous approach not only validates the data flow but also fortifies the overall architecture of the SIoT device, underscoring the significance of security measures in the ever-expanding domain of interconnected technologies.
2. Blockchain implementation for securing the heterogeneous data
● The aim of this project is to distribute the ledger technology, where peers can participate, interact, and execute a transaction without any centralized entity with a key feature.
● It utilizes crypto currency algorithms to ensure data security in a Blockchain network
3. Real time Drowsiness detection using Alarm System
● The aim of this project is to develop a prototype drowsiness detection system.
● The focus will be placed on designing a system that will accurately monitor the open or closed state of the driver’s eyes in real time.
4. Django Application for Smart Air Pollution Control
The aim of this project is to develop a system that input the data from the sensors and helps to monitor Air
pollution of the plant.
5. Twitter Sentiment Analysis using Machine learning approaches
The aim of this project is to analyze Twitter data from the Kaggle database. The system helps in identifying
people’s well-being, categories as positive, negative, or objective, by using their tweet.
6. Crowd Behavior Analysis Using Machine Learning Techniques
The aim is to conduct accurate crowd counting from an arbitrary still image, with an arbitrary camera perspective and crowd density. To estimate the number of people in each image via the Convolutional Neural Networks (CNNs).