# iu-projects

**Repository Path**: mazaiting/iu-projects

## Basic Information

- **Project Name**: iu-projects
- **Description**: 效率参数分析
- **Primary Language**: Python
- **License**: Not specified
- **Default Branch**: main
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2025-04-07
- **Last Updated**: 2025-05-09

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

# IU Projects
## DLBDSOOFPP01 — Object-Oriented and Functional Programming with Python
### Habit-Tracking Application 
Stay on track with your goals and build positive routines effortlessly. The habit-tracking app empowers you to monitor and manage your daily habits, fostering a path to a healthier, more productive lifestyle.

**Grade:** 97 out of 100

## DLBDSMLUSL — Machine Learning - Unsupervised Learning and Feature Engineering
### Task 2: Policing Equity
This task aims to evaluate a large dataset of policing activities collected over a few years to discover patterns and find homogeneous categories of incidents. Also, it aims to reduce the dataset's complexity, produce meaningful visualizations that capture its key features, and provide descriptive statistics for each cluster.

**Grade:** 94 out of 100

## DLBSEPCP01_E — Cloud Programming
### Task 1: Host a simple webpage on AWS
Design and implement a highly available, low-latency website on AWS using Amazon S3 bucket for hosting and CloudFront for content delivery using Infrastructure as Code (IaC) tools like Terraform for reproducibility. The goal of the task is to host an “index” HTML file, guaranteeing high availability, minimizing latency, and enabling auto-scaling for optimal performance.

**Grade:** 100 out of 100

## DLBAIPCV01 — Project: Computer Vision
### Task 2: Recognizing Objects in Video Sequences
This project aims to develop a computer vision system that accurately detects and segments objects in video. I used state-of-the-art object detection and segmentation algorithms. Firstly, I implemented three SoA approaches: YOLO, SSD, and Faster R-CNN and evaluated their performance. Then, I analysed the results visually and highlighted their strengths and weaknesses. Next, I determined the best-performing approach based on evaluation and analysis. Link: https://drive.google.com/drive/folders/1NdpVsZzHaaUc4d0PXXzEveJfNaLGTQd4?usp=sharing 

**Grade:** 87 out 100

## DLBAIPNLP01 — Project: NLP
### Task 2: Sentiment Analysis on Movie Reviews
A sentiment analysis project on movie reviews compares Logistic Regression, SVM, Random Forest, and LSTM. It covers text preprocessing and model evaluation to provide an overview of machine learning and deep learning methods for binary classification. 
Links: https://medium.com/@fatimakhongulomova/from-logistic-regression-to-lstm-a-sentiment-analysis-case-study-on-movie-reviews-66fabd8cfaaf; https://www.kaggle.com/code/fotimakhongulomova/sentiment-analysis-on-movie-reviews