sakibsourav019 Goto Github PK

ai-ducation-analytics-comp-6721--fall2023-ak_7-

This is the official repository of group AK_7 for the project of AI Ducation Analytics needed for the Fall 2023's course Applied AI

comp-6751-natural-language-analysis-projects-fall-2023

These are the projects on Natural Language Analysis instructed by prof. Sabine Bergler of Concordia University. Building Context-free feature grammar to do text analysis and operations such as: Tokenizer, Sentence Splitting (SS), POS Tagging, Gazetteer, Named Entity Recognition (NER) and Measured Entity Detection (MET).

creating-preprocessing-new-dataclass-using-search-engine

For building image dataset of rare dataclass we can use this python script to scrap images of our interest, augment the data and train our deep learning models

day-and-night-time-classifier-based-on-image

This code classifies between daytime and night time based on image pixel values

google-images-download

Python Script to download hundreds of images from 'Google Images'. It is a ready-to-run code!

image-classification-with-transfer-learning-vgg16

Here, I implemented VGG-16 transfer learning CNN architecture to classify Cats and Dogs images in a large dataset using ImageNet, which has more than 20,000 data classes. I wrote the code on Google Colab and uploaded the dataset of 2000 images in google drive.

inse6220-pca-analysis

Course project for INSE6220

jute-insect-classification-using-transfer-learning-and-deployment-in-android-app

We developed an intelligent model for jute pests identification based on transfer learning (TL) and deep convolutional neural networks (DCNN) to solve this practical problem. The proposed DCNN model can realize fast and accurate automatic identification of jute pests based on photographs.

piano-as-music-accompaniment

Here, we are working to build a framework using python where it receives acoustic signals from guitars and create music accompaniment by generating piano tones in real time.

presearch

streetlight_control_multiclass_segmentation_-camvid-_unet_keras

We trained the U-net model based with ResNet-34 as backbone to accomplish the tasks. The validity of the models is ensured through corresponding evaluation matrices. The proposed model is much simpler, cost effective, durable and robust than the conventional, physical sensor-based existing intelligent solutions.

ubmec-unified-bangla-multi-class-emotion-corpus-

UBMEC is a new, larger, unified 6-class (anger, disgust, fear, joy, sadness, and surprise) emotion dataset for Bangla language based on user reviews. It amalgamates two recently published publicly available Bangla emotion corpuses BNEmo and BEmoC, as well as with additional manually tagged corpus by us those results in a adequately developed Bangla emotion corpus.