basharbme

2048-console

A clone of the game 2048 in the console written in vanilla python without any imports.

2048-DeepQLearning

Implementation of an agent able to play 2048. Report, evaluation and implementation details in the GitHub repository. During the project I gained experience with Reinforcement learning technologies such as the gym framework and the Keras-rl library.

3D-Bioprinter-parts-and-accessories

A collection of STL files used for building or modifying a FDM printer to print gels

bone-segmentation

Source code behind the paper Fully automatic and fast segmentation of the femur bone

EEG_Classification_Deeplearning

EEG Signal Classification using LSTM on various datasets

Health_Discernment_System

An efficient and user-friendly application with GUI based (Tkinter) front-end and various custom CNN models as back-end which detects various human diseases such as Malaria, Pneumonia, Breast Cancer and Skin Cancer using cell, tissue, x-ray or skin images.

Intelligent-Estimation-of-Speed-of-Induction-Motor

speed tracking capability of model reference adaptive system (MRAS) with model-based flux/speed observers and artificial neural network (ANN)-based adaptive speed estimators for sensorless induction motor (IM) drives has been analyzed. In model-based technique, mathematical model of IM is used to estimate the rotor speed. The current and flux observers are used as the reference model to estimate the rotor flux. The estimated rotor flux signals are used as the input signal for the adaptive observer to estimate the speed. In ANN-based method, adaptive model is constructed with a feedforward neural network to estimate the rotor speed. Feedforward ANN algorithm is used to train the network. The training algorithm decides the learning speed, stability, and dynamic performance of the system. Both methods have good speed tracking capability. Simulation results are presented to know the accuracy of the proposed methods. The proposed speed estimation techniques have great potential in industrial applications.

MONAILabel

MONAI Label is an intelligent open source image labeling and learning tool.

SmileToCast-Blender

Blender console easily convert dentist planning smile to 3D printable customized cast for veneers \ or cosmetics procedure planning .. Cast to be then scaled to real size impression.

TMJ-prosthesis-Blender

Open source TMJ Prosthesis Customizable to patient anatomy

basharbme/3D-unet-1

basharbme/Biomolecular-Blender

Scripts to import, manipulate and visualise biomolecule-files into blender

basharbme/bone-cancer-classifier

Diseases Prediction from MRI-CT data

basharbme/Classification-of-Brain-tumor-Using-CNN-in-Deep-Learning-approach

This project is being done as a part of 1nd semester ME curriculum. The major objective of this project is to detect if the brain tumour is present or not by training the machine using pre-processed Magnetic resonance imaging (MRI) using Deep Learning. The segmentation, detection, and extraction of infected tumor area from magnetic resonance(MR) scan.We estimate the brain tumor severity using Convolutional Neural Network algorithm which gives us accurate results.

basharbme/CTPelvic1K

Resources of the paper “Deep Learning to Segment Pelvic Bones: Large-scale CT Datasets and Baseline Models”.

basharbme/Deep-Mind

A Brain Tumour Classifier

basharbme/EEG-Based-Emotion-Recognition-on-DEAP

basharbme/Emotion-Recognition-from-brain-EEG-signals-

Emotion recognition can be achieved by obtaining signals from the brain by EEG . This test records the activity of the brain in form of waves. We have used DEAP dataset on which we are classifying the emotion as valance, likeness/dislike, arousal, dominance. We have used LSTM and CNN classifier which gives 88.60 % accuracy to predict the model successfully.

basharbme/image_segmentation_using_opencv

Implement Watershed Algorithm using OpenCV for image segmentation.

basharbme/openCV-Learning

Contains codes and Mini project made while learning OpenCV

basharbme/Radiology-and-AI

Training and applying AI models for segmenting and characterizing brain tumours given 3D neuroimaging data

basharbme/Skin-Diseases-Detection-Hackbash

Dermatological Issues/disorders are most commonly spread worldwide. This can be caused by various fungal, bacterial, or skin allergies. Effective use of Emerging technologies like AI/ML can recognize such diseases. Computer Vision is one such platform that made the possibility of detecting the cause accurately through Images.The problem here is to develop an Application Programming Interface which can be easily integrated with Android app to detect the skin disease without any physical interaction with a Dermatologist.

basharbme/smop

Small Matlab to Python compiler

basharbme/Vehicle-Detection-Image-Set

basharbme/watershed-segmentation-Python-OpenCV

Watershed Segmentation with Python and OpenCV

basharbme/3DUnet_pytorch

basharbme/Bitcoin-Price-Prediction-Using-RNN---LSTM

This repo consist the code for Predicting Bitcoin Price using Deep Learning Method like RNN-LSTM

basharbme/Can-You-Find-The-Tumour

Identifying tumours in breast mammograms using semantic segmentation in Tensorflow 2.0.

basharbme/DentAid

FYP Fall 2108

basharbme/Dental-Biometrics

Person Identification based on dental records using Deep Neural Networks. My Btech final year project.

basharbme/face_mask_detection

Face mask detection system using Deep learning.

basharbme/Huffman_Coding_Images

basharbme/Matching-3D-Models

In oral and maxillofacial surgery, there is the situation that the lower jaw, the mandible, is partially destroyed, e.g. by tumor or accident, and must be replaced. For this purpose, a piece of bone is taken from the iliac crest. The question now is, which piece is best suited. In addition to the many medical constraints (trauma, vascularization, muscle insertion, access, etc.), one aspect is of great importance: the accuracy of fit. So find the best piece on the iliac crest to replace the mandibular piece.

basharbme/placental-segmentation-2dunet

Jupyter notebooks for training of a 2d Unet on placental tissue followed by segmentation of a 3d block of image data through combination of 2d segmentation outputs

basharbme/pneumonia_classifier_project

ML project classifing xray images

basharbme/reactor-modelling

MATLAB/COMSOL reactor modelling & optimisation

basharbme/Routing-on-Resource-Allocation-in-Free-Space-Optical-Network

basharbme/Stegnography

basharbme/student-accomodation-finder

The Bournemouth Student Property Finder is a web application created using React for my User Centered Web Development Unit

basharbme/swin-transformer-pytorch

Implementation of the Swin Transformer in PyTorch.