Blockchain Scalability Analysis and Improvement of Bitcoin Network through Enhanced Transaction Adjournment Techniques
Data Lake System for Essay-Based Questions: A Scenario for the Computer Science Curriculum
Creating Secure Passwords through Personalized User Inputs
Optimizing B-Cell Epitope Prediction: A Novel Approach using Support Vector Machine Enhanced with Genetic Algorithm
Gesture Language Translator using Morse Code
Efficient Agent Based Priority Scheduling and LoadBalancing Using Fuzzy Logic in Grid Computing
A Survey of Various Task Scheduling Algorithms In Cloud Computing
Integrated Atlas Based Localisation Features in Lungs Images
A Computational Intelligence Technique for Effective Medical Diagnosis Using Decision Tree Algorithm
A Viable Solution to Prevent SQL Injection Attack Using SQL Injection
The novel coronavirus disease (COVID-19) has currently affected millions of people, claiming more than 4,000,000 lives all over the world. Several dashboards have been created to analyze the present situation and get a better grasp of the current status of COVID-19. As the situation unfolded, infections caused by species of fungi, Mucormycosis (commonly called black fungus), have affected patients treated for COVID-19. Therefore, to facilitate information and to create awareness, it would be better to have a dashboard that display trends and data on COVID-19 and associated related diseases. In the proposed work, a dashboard has been created to visualize how COVID-19 epidemic has an impact in the global scenario. With the present work, the spread of diseases associated with COVID-19 (fungi variants) can be visualized. The data visualization is performed using Python. The tool kits and packages used for this purpose is Dash by Plotly. The acquired data is classified and filtered with interesting criteria in the ranging process stage. Using specific tools, data representations like line chart, bubble map, heat map, choropleths, tree map and, folium map are plotted to visualize the data.
This paper proposes a self-driving car model also called autonomous, robotic or driverless car, which is the one that operates and navigates using its intelligence. The primary objective of our prototype is to navigate safely, quickly, efficiently and comfortably through our virtual environment using computer vision. Detection of lanes, traffic cars, obstacles, signals have been performed.
There is an increased tendency to copy another person's content blatantly from the information available in the Internet. The act of plagiarism is using someone else's idea and written work without their knowledge or acknowledgment; this is intellectual theft, and is a crime. To address this issue, it is necessary to maintain a plagiarism reporting system to keep track of text recycling. The objective of this paper, is to develop an application where texts are compared to detect plagiarism, even if the text is uploaded in image format. The text from images is extracted with the help of Optical Character Recognition (OCR). Similarity, analysis is calculated through machine learning techniques of word to vector conversion and cosine similarity. Dataset for comparison is taken from text scripts from the internet and manuscripts of journals or essays of students. The key concept behind this paper is to discourage academic plagiarism among the student community and to stimulate the practice of writing originally.
Nowadays, phishing attacks can be launched from anywhere in the world at insignificant costs by people with little to no technical skills. As the technical skills and costs associated with deploying phishing attacks decline, there is an unprecedented level of scam that is driving the need for more effective methods of proactively detecting phishing threats. In our proposed work, the use of URLs as input has been explored for machine learning models applied for phishing site prediction. In this way, a feature engineering approach has been compared followed by a random forest classifier against a novel method based on recurrent neural networks. The recurrent neural network approach has been determined which provides an accuracy rate even without the need of manual feature creation.
Rapid advancements in the field of computer networking and information storage has spread through many aspects of business and, thus have prompted an expansion in improvements to prevent powerful attacks on computers through the networks. Intrusion Detection Systems (IDS) have turned into a necessary way to guarantee the security of managing computer systems. IDS look to identify intrusions before networks can be influenced by malicious activities. It is achieved by logging the legitimate values on the network beforehand and scanning for any attempt in changing the values. The aim of this paper is to make a light-weight Network Intrusion Detection System (NIDS) to keep running at an ideal spot with the least system prerequisites. It guards against man-in-the-middle attacks on network systems. At the point when an attacker is found spoofing the Address Resolution Protocols (ARPs), defensive ARPs are manually created and sent to 'depoison' the victim using their unique logged L2 addresses. Given the increasing complexity of the current system environment, an everincreasing number of hosts are becoming vulnerable to attack vectors, and therefore methodological, productive and mechanized intrusion detection methodologies need to be carefully examined.
