Prediction of Breast Cancer Data Science Project in Python

The Prediction of Breast Cancer is a data science project and its dataset includes the measurements from the digitized images of needle aspirate of breast mass tissue.

The data has 100 examples of cancer biopsies with 32 features. From these features, we can predict whether the tumors are benign or malignant.

The steps to be done are:

  • Data Preparation by checking the target variable and removing the ID variable.
  • Visualization of the frequency of the type variable.
  • Normalizing the variables by using min-max normalizations and z-score methods.
  • Bifurcation of the train and test sets.
  • Prediction of the type of tumors using the classification algorithm.
  • Improving the models using different values of k and other methods of normalizations.

Other data Science Projects using python below:

1) Marketing Campaigns Prediction of the clientele subscribing to services in Bank.
2) Market Basket Analysis for the creation of Online Recommender System for Grocery Supermarket.
3) Movie Review Analysis using Natural Language Processing (NLP).
4) Analysis of Most Connected Hubs in Socially Connected People.
5) Analysis of Loan Sanction for particular customers in a Bank.
6) Prediction of Medical Expenses of Incoming Patients in a Particular Hospital.
7) Cluster Analysis of Collection of People impacting a Social Networking Site.
8) Text Mining with Predictive Analysis of Spam Filtration in Incoming Mails.
9) Expectation Maximization Analysis for Digit Classification.
10) Exploration of Murders according to Investigation Team Uniform Crime Reports.

Art Auction Houses Data Science Project in Python

Art Auction Case Study:

Art auction application provides buying and selling of artworks. The normal way of sale of an artwork is auction places buy artworks from the art owners and sell it to the customers who bid more. The bidder bids a maximum price based on the art’s Naturality, quality, and artist value.
The dataset provided contains details of art auctions from various art houses and the details about the art piece auctioned and the other details about the auction

Task:

We would like you to perform an exploratory analysis on the dataset provided. Please take a shot at analyzing this dataset using any tool of your choice and create a summary of key insights and analysis charts.
The questions to be solved are:
a) How many art pieces were auctioned in zip codes mentioned?
b) Which country has contributed most in the auction?
c) Highlight the states which have sold most of the paintings?
d) How many paintings were made between the year 1947-1950?
e) Which artist has sold the most number of paintings?
f) Which dimensions of the art were used the most?
g) Categorize according to the sales of art in terms of year in which they were made?
h) List out the top 10 buyers.
i) Distribution of Acquisition price of art over the country.
j) How many arts are insured above the average minimum insurance price?
k) How much difference is there for actual cost and buyers cost?
l) How many arts were sold online according to year?
m) Which artist got the highest rating below 5?
n) In which year most of the arts were the good purchase?
o) Design out a predictive model to show whether the purchases were good purchases or not?
You can use your own way of visualization and Modelling.

Handwritten Character Recognition using Deep Learning Approach

ABSTRACT:

Deep learning is a new area of machine learning research which has been introduced with the objective of moving machine learning closer to one of it’s goal i.e artificial intelligence.

There are various applications of deep learning. In this project we use deep learning for hand-written character  recognition.

The challenges associated with hand-written character recognition are- word and line seperation,segmentation of words into  characters, recognition of words when lexicons are large, and the use of the language models in aiding preprocessing and recognition, character extraction , types of hand writing, number of scriptors, size  of vocabulary and spatial layout.

We would like to attempt them with deep learning. Multi-layer with layer wise abstraction will be used for this purpose.

SOFTWARE REQUIREMENTS:

Python

Digit Recognition Python Project

Project Domain: Image processing and Machine learning

Project Title: Digit Recognition

DESCRIPTION:

Digit recognition is one of the active research topics in digital image processing. It is a classic machine learning problem. The goal of this project is to take an image of handwritten digits and determine what those digits are. The principal task in digit recognition is to extract HOG features from the database of handwritten digits and to build a classifier on it. Then we predict the digits of the database using this classifier. To build the classifier we write python scripts.

EXISTING SYSTEM:

The current systems use resource intensive image processing methods and algorithms with varying accuracies and rejections.

PROPOSED SYSTEM:

The proposed system uses efficient pattern classification and machine learning approach to improve overall performance of predicting the digits.

FUTURE EXPANSION:

This digit recognition can be further scaled to achieve big data processing levels.

Hardware and software requirements:

Hardware Requirements:

  • RAM : 1 GB and above
  • OS : Linux, Windows

Software Requirements:

  • Python 2.7

Smart Traffic Management System Project

Traffic management is the problem that most of the countries are taking special steps. Smart traffic management system project is a hardware and software application which will use latest technologies to calculate traffic and provide information to traffic police for taking steps.

Project category:

Traffic Management System

Project Introduction:

This application is designed by using PLC and SCADA technology.  Compare to existing method, in this project density of vehicles at each lane and their weight and then take required steps to control traffic. This system is useful for managing traffic in highways.

Working:

Sensors will detect weight of every vehicle and if vehicle weight is more than 80 sensors will send signals to PLC , PLC will guide vehicles to move to other lane by sending information to barricading.

Similarly if the weight of vehicle is less than 80 sensors will send message to PLC which will help vehicles to pass to respective LANE.

Download Smart Traffic Management System Project Source Code