mohit-bags

Active-Learning-on-Regression

Regression problems are pervasive in real-world applications. Generally a substantial amount of labeled samples are needed to build a regression model with good general- ization ability. However, many times it is relatively easy to collect a large number of un- labeled samples, but time-consuming or expensive to label them. Active learning for re- gression (ALR) is a methodology to reduce the number of labeled samples, by selecting the most beneficial ones to label, instead of random selection. This paper proposes two new ALR approaches based on greedy sampling (GS). The first approach (GSy) selects new samples to increase the diversity in the output space, and the second (iGS) selects new samples to increase the diversity in both input and output spaces. Extensive experiments on 10 UCI and CMU StatLib datasets from various domains, and on 15 subjects on EEG- based driver drowsiness estimation, verified their effectiveness and robustness.

Arrhythmia-Detection

Arrhythmia Detection into three classes AFL,AFIB,NSR(Normal Sinus Rythum) using ECG/PPG data based on RR interval Extraction

AWS-SageMaker-Docker-

Now you can train and build custom ML models on AWS Sagemaker using Docker

BERT-Notebooks

Fine tuned pre-trained BERT Model for recognition of Technological and Organizations entities

Budget-Optimization

covid19india-cluster

:microscope: COVID19 India Cluster Network

DSA-questions

Fall-Detection-using-Accelerometer

Predicting-Sales-on-a-Time-Series-Data

Used ARIMA Model for Forecasting.

XAI_ECG

Code to generate ECG figures from MIT BIH arrhythmia database, train CNN models (RESNET-50) on those images and produce explainability using 3 different methods.

mohit-bags/A-to-Z-Resources-for-Students

A to Z Resources for students as well as working proffessionals

mohit-bags/ab-test-RL

Using reinforcement learning for AB test

mohit-bags/Job-Recommendation-Engine

Job prediciton based on NLP models.

mohit-bags/SleepStaging

Sleep staging using single lead ECG

mohit-bags/Speaker_Recognition_MFCC_GMM

The program uses Mel-frequency cepstrum coefficients for feature extraction, then generates Gaussian Mixture Models for each subject. The models predict the subject for a given test sample by comparing its extracted features to the trained models.