Zekun Wang's Blog | Data Science

K-Means based Anomalous Email Detection in PySpark

Anomaly detection for emails based on Minhash and K-Means, implemented by PySpark and Colab.

K-Means is known as a common unsupervised learning clustering method. But in fact, K-Means algorithm can be applied to more scenarios. This time, I will use a K-Means-based approach to complete ano...

Posted by Zekun on May 5, 2021

WearMask - Face Mask Detection Project Details

Low-cost solution for small businesses and public places

The paper has been published on arXiv. Background In the last November, the COVID-19 epidemic in the United States reached a new wave of peaks. During Thanksgiving week alone, there were 1,147,48...

Posted by Zekun on December 1, 2020

Super fast In-browser FaceMask Detection

Open the webpage, then you have it!

facemask-detection.com 👈👈 This is an AI that detects masks super fast: No installation or registration. No need to buy expensive devices. You don’t even need a continuous internet connectio...

Posted by Zekun on November 27, 2020

Tutorial for compiling NCNN with WASM

The second step to deploy a deep learning model in the browser.

The content of this tutorial is an extension of the Tutorial for compiling NCNN library. When we successfully compile the NCNN library normally, we can use the tools in it to convert our models in...

Posted by Zekun on November 15, 2020

Tutorial for compiling NCNN library

The first step to deploy a deep learning model.

This is a tutorial to helping compile NCNN library. The content comes from my attempts to complete the Mask-Detection project, so the operation is based on the Yolo-Fastest model. I hope it will he...

Posted by Zekun on November 10, 2020

Darknet to Keras - Model Transformation

New version based on TensorFlow 2.0

In the process of completing the mask detection project recently, I tried to convert Darknet into a Keras model. In other words, to convert the .cfg file and the .weights file into a .h5 file. The...

Posted by Zekun on October 25, 2020

How to get information from IP address?

Note - geoip2 module introduction

The process of getting IP address information is done based on GeoIP2 Databases. I Used the MaxMind GeoIP2 Python API for IP information queries. The Github page for the API is GeoIP2-python. You ...

Posted by Zekun on July 20, 2020

COVID-19 Data Exploration (Unfinished)

Exploration and visualization of COVID-19 related data

Note: The content of this article is based on the data what was collected by the project team of Professor Ziqi Chen, School of Mathematics and Statistics, Central South University(China). The data...

Posted by Zekun on March 19, 2020

LAPOP Data Dashboard

A dashboard prototype based on Shiny R

This project is designed a data visualization dashboard to help non-professional users for Latin American Public Opinion Project (LAPOP). Due to copyright issues and confidentiality agreements, th...

Posted by Zekun on February 19, 2020

Cashbox Magazine Song Chart Analysis

A simple example of a data analysis pipeline

This article mainly introduces the full picture of a data analysis pipeline by showing the simple data import, feature engineering, and exploratory data analysis processes. The data used this tim...

Posted by Zekun on February 15, 2020

Zekun Blog