Name: Md Junayed Hasan
Type: User
Company: National Subsea Centre
Bio: đ§ Expert in AI, ML/DL, Computer Vision, Data Modelling | ⥠Committed to Reliability, Safety, and Sustainable Energy
Twitter: drjunayedhasan
Location: Aberdeen
Md Junayed Hasan's Projects
All my R&D Jupyter Notebooks regarding Deep Learning
Implementation of DeepJDOT in Keras
Deep Learning tutorial
DeepSleepNet: a Model for Automatic Sleep Stage Scoring based on Raw Single-Channel EEG
Discriminative Feature Alignment for Unsupervised Domain Adaptation
å°æĨ常åĻäš äŊŋį¨įįŽæŗæģįģåŊįąģ
Repository to maintain code for my internship on Domain Adaptation
Domain adaptation segmentation for volume EM imaging
engie-wind-turbine-power-prediction
This methods can be used for event identification to detect first arrival time of Vp and Vs. These methods are Akaike Information Criterion, MER and S/L kurt
Slides, code and resources for model interpretation methods in machine learning and deep learning
Sometimes it might happen that we considered only precision score from the computed model. We saved the confusion matrix for multiclass, and we have calculated the precision score. However, after some time, you might be needing to calculate the Recall, and F1 score from that confusion matrix. It is possible to calculate through the equations. You can easily see the description of precision, recall and F1 score from this link: https://en.wikipedia.org/wiki/Precision_and_recall. However, for multiclass classification, it is often very tough to back calculate all the things. So in this code, I have attempted to find out a way to calculate all the measurement paramters from the confusion matrix. You just need to provide the confusion matrix to the code, and it will calculate the rest for you.
FastAI Model Interpretation with LIME
Draft of the fastai book
The code repository for "Few-Shot Learning via Embedding Adaptation with Set-to-Set Functions"
Tips for Advanced Feature Engineering
A Guide for Feature Engineering and Feature Selection, with implementations and examples in Python.
Code repo for the book "Feature Engineering for Machine Learning," by Alice Zheng and Amanda Casari, O'Reilly 2018
Python code source for features selection đ¨âđŦ series on medium website. đ°
Contains code and presentation for my interactive hack session, 'Effective Feature Engineering: A Structured Approach to Building Better Machine Learning Models' where we look at two interesting case studies on how to effectively leverage feature engineering and use a structured approach to build good machine learning models. This is created for the purpose of being presented in Analytics Vidhya's DataHack Summit 2018
Spark - Bearing RUL Predictions
MATLAB GIfTI Library
Python notebooks for Optimal Transport between Gaussian Mixture Models
A Simple pytorch implementation of GradCAM and GradCAM++
Code associated with our paper "Graph2Speak: Improving Speaker Identification with Network Knowledge in Criminal Conversational Data"