smjajoo Goto Github PK

big-data-credit-card-fraud-detection

In this project, three prospective approaches are demonstrated for pre-processing large data sets in practical time-frames, that can attempt to address the class imbalance by improving the running time of the relevant SMOTE+ENN oversampling techniques, with the aim of improving or enabling classifier performance. The focus of our study was to implement a divide and conquer based implementation that leveraged clustering as a more intelligent division measure.

big-data-pyspark

browsermate

Browser Mate is a customizable web extension that sends a text message to a responsible adult when the browser reaches a specific URL (i.e., age-inappropriate). This text message contains the link to that URL and the summary of the content of the URL.

chess-positions

data-modeling-and-analysis-projects

Data modeling and analysis of a few datasets

educational-chatbot

The automated, intelligent tutoring system, which provides a dedicated learning environment for students to study in and then analyses their reactions and patterns of engagement with artificially intelligent learning content, is the most valuable use of AI. Similarly, AI chatbots can assist students in learning through a sequence of messages based on a study material.

healthcare-logistic-robot-simulation

In this project, a robot system is introduced into a healthcare environment for a logistic purpose. The robot system takes care of all the workflow management by itself. The prime guiding question of this report is “How the healthcare service robots affect the efficiency of workflow management in the healthcare environment?”

kaggle-projects

linear-models

pima-data-modeling-and-analysis

This project looks at the effectiveness of SICE imputation technique in supporting binary classification performance of the Logisitic Regression in the context of decision support for the healthcare sector where accurate predictive models have the potential to improve patient outcomes by promoting access to care. Processing methodologies are assesed with reference to the relevant Accuracy and False Positive metrics. Analysis and comparison of the results suggest that imputation alone can likely impact classifier performance only marginally in situations where the data set is of sufficient size.

social-media-portfolio

Welcome to my GitHub Profile Feel free to check out anything -- some of this stuff is temporary or testing, and mainly kept for my own purposes. Some of my i

travelling-salesman

voice-recognition-sports-center

The expanding popularity of voice interface is used here to reenact the feeling of conversation between virtual assistant of the Sports Centre and user. With thorough research and observations, multiple sports activities and many types of equipment have been added to this prototype such as activities like Basketball, Volleyball, Swimming and equipment like Climbing shoes, Netballs etc. This prototype is a conversational VUI where the system does not have to give any indicator to speak. And uses a more natural turn-taking approach.