menghonghan
Algorithm Engineer in Healthcare Industry menghonghan@brandeis.edu
Brandeis UniversityGreat Boston Area
Pinned Repositories
chatgpt-on-wechat
COVID-19-Tracker
GUI designed by Plotly Dash
Grocery-Shopping-Behavior-Big-Data-Analysis
Processed over 30 million observations; conducted inactive customer diagnosis and loyalism analysis using MySQL; visualized consumer behavior on private labeled product with Python (matplot, seaborn)
Healthcare-Data-Mining-Projects
Data mining projects include predicting risk score of chronic diseases with NHANES data and analysis of patient and insurance claim data.
k-Means-Clustering
K-Means clustering revision with silhouette score
Massive-Data-Mining
Codes for COSI-120A Massive Data Mining
MetaCost
P. Domingos proposed a principled method for making an arbitrary classifier cost-sensitive by wrapping a cost-minimizing procedure around it. The procedure, called MetaCost, treats the underlying classifier as a black box, requiring no knowledge of its functioning or change to it.
Predict-small-hydro-production-in-California
Using regression (multi-linear regression), classification (KNN, Random Forest, Logistic regression, LGBTree), clustering (k-means) models to predict the production of small hydro and try to find out main impactors and certain patterns using R.
Tansfer-Feature-Learing-with-JDA-implementation-
The introduction and code implementation of the paper "Transfer Feature Learning with Joint Distribution Adaptation"
Urban-Sound-Classification
Using UrbanSound8K dataset from Kaggle, conducted feature extraction by MFCC, MEL-Spectrogram and Chroma_stft, trained a 2D CNN, achieved accuracy of 92.8 %, using Python (tensorflow, kera, librosa)
menghonghan's Repositories
menghonghan/Tansfer-Feature-Learing-with-JDA-implementation-
The introduction and code implementation of the paper "Transfer Feature Learning with Joint Distribution Adaptation"
menghonghan/Healthcare-Data-Mining-Projects
Data mining projects include predicting risk score of chronic diseases with NHANES data and analysis of patient and insurance claim data.
menghonghan/Urban-Sound-Classification
Using UrbanSound8K dataset from Kaggle, conducted feature extraction by MFCC, MEL-Spectrogram and Chroma_stft, trained a 2D CNN, achieved accuracy of 92.8 %, using Python (tensorflow, kera, librosa)
menghonghan/chatgpt-on-wechat
menghonghan/COVID-19-Tracker
GUI designed by Plotly Dash
menghonghan/Grocery-Shopping-Behavior-Big-Data-Analysis
Processed over 30 million observations; conducted inactive customer diagnosis and loyalism analysis using MySQL; visualized consumer behavior on private labeled product with Python (matplot, seaborn)
menghonghan/k-Means-Clustering
K-Means clustering revision with silhouette score
menghonghan/Massive-Data-Mining
Codes for COSI-120A Massive Data Mining
menghonghan/MetaCost
P. Domingos proposed a principled method for making an arbitrary classifier cost-sensitive by wrapping a cost-minimizing procedure around it. The procedure, called MetaCost, treats the underlying classifier as a black box, requiring no knowledge of its functioning or change to it.
menghonghan/Predict-small-hydro-production-in-California
Using regression (multi-linear regression), classification (KNN, Random Forest, Logistic regression, LGBTree), clustering (k-means) models to predict the production of small hydro and try to find out main impactors and certain patterns using R.
menghonghan/Pypeteer-QiChacha
Using Pypeteer crawled basic information and Administrative penalty information
menghonghan/sturmgang
menghonghan/transferlearning
Everything about Transfer Learning and Domain Adaptation--迁移学习