improving safety on drivers for
NS2 Projects

Improving Safety on Drivers for Vehicular Ad Hoc Networks

Improving Safety on Drivers for Vehicular Ad Hoc Networks

Need for individualizing vehicular communications in order to improve safety for a highway scenario. Adapting a vehicular ad hoc network to both its individual driver’s characteristic and traffic conditions enables it to transmit in a smart manner to other vehicles. This radical improvement is now possible due to the progress that is being made in vehicular ad hoc networks (VANET). Packet success probability is derived for a chain of vehicles by taking multi-user interference, path loss, and fading into account. Then, by considering the delay constraints and types of potential collisions, we approximate the optimal channel access probabilities.

NS2 Demo

Improving Safety on Drivers for Vehicular Ad Hoc Networks
heart disease prediction using k
Python Projects , Machine Learning Projects

Heart Disease Prediction using K-means clustering algorithm and Logistics regression

Implementation Details:
Heart Disease Prediction using K-Means clustering and Logistics Regression

1. We are taken dataset data.csv

2. Input data.csv is split into three cluster

Cluster 0, Cluster1, Cluster2

3. Every cluster data is taken for getting trainset and test set

Trainset contains 14 columns, whereas testset contains 13 column

4. Every cluster testset is predicted for heart disease

Accuracy is arrived
5. Logistics regression is performed and accuracy arrived

Python Demo

 

 

Heart Disease Prediction using K-means clustering algorithm and Logistics regression-Python
convolutional neural networks fo
Deep Learning Projects , Python Projects

Convolutional Neural Networks for Diabetic Retinopathy

Convolutional Neural Networks for Diabetic Retinopathy

The diagnosis of diabetic retinopathy (DR) through colour fundus images requires experienced clinicians to identify the presence and significance of many small features which, along with a complex grading system, makes this a dicult and time consuming task. In this paper, we propose a CNN approach to diagnosing DR from digital fundus images and accurately classifying its severity. We develop a network with CNN architecture and data augmentation which can identify the intricate features involved in the classification task such as micro-aneurysms, exudate and haemorrhages on the retina and consequently provide a diagnosis automatically and without user input. We train this network using a high-end graphics processor unit (GPU) on the publicly available Kaggle dataset and demonstrate impressive results, particularly for a high-level classification task.

Techniques Used

  • Convolutional Neural Networks  (CNN)
  • Logistic regression
  • Random Forest

Python Deep Learning project demo

 

Convolutional Neural Networks for Diabetic Retinopathy
face detection and recognition a
Python Projects , Machine Learning Projects

Face detection and recognition and attendance using machine learning and deep learning

This project is proposed for real time face detection and recognition. The project is implemented in both machine learning and deep learning.

Implementation step:

Face is detected in real time, detected face is trained with atleast 1000 frames for good accuracy.

The training the collected data

Face recognition with input and mark attendance

Software used: Python

Python Project Demo

 

Face recognition and Identification with attendance in python