Disaster_Or_Not: Tweet Sentiment Analysis

Last Updated on May 3, 2021


In this project, the objective was to perform analysis on data and to build a model to predict if the tweet is real or not about disaster statement.

I started with data cleaning processes like dealing with null values, outliers, stop-words etc.

Then, I perform analytics on the cleaned data and verified with visualization.

Then, tested some hypothesis like disaster statement may include words like fire, rain and the checked their significance with respect to data.

Then, I created some predictive models starting with Machine Learning Algorithm ' Ridge classifier' after vectorization.

Then, to improve the performance I used RNN, Bidirectional LSTMs and got perfect score with bidirectional LSTM.

Then, I created a web app using Flask and HTML-CSS.

More Details: Disaster_or_not: Tweet Sentiment Analysis

Submitted By

Share with someone who needs it

Encrypt And Decrypt Strings And Images Using Python

Last Updated on May 3, 2021


Encrypt and Decrypt Strings

Encryption is the process of encoding the data. i.e converting plain text into

ciphertext. This process is the encryption. And Decryption is a process of decoding the encoded data. Converting the ciphertext into plain text. This process requires a key that we used for


We require a key for encryption. There two main types of keys used for encryption and decryption. They are Symmetric-key and Asymmetric-key.

In symmetric-key encryption, the data is encoded and decoded with the same key. This is the easiest way of encryption, but also less secure. The receiver needs the key for decryption, so a safe way need for transferring keys. Anyone with the key can read the data in the middle.

Asymmetric-key Encryption, we use two keys a public key and private key. The public key is used to encrypt the data and the private key is used to decrypt the data. By the name, the public key can be public (can be sent to anyone who needs to send data). No one has your private key, so no one the middle can read your data.

Encrypt and Decrypt images

simple process in which we convert our data or information into secrete code to prevent it from unauthorized access and keep it private and secure.

First, we will select an image, and then we will convert that image into a byte array due to which the image data will be totally converted into numeric form, and then we can easily apply the XOR operation on it. Now, whenever we will apply the XOR function on each value of the byte array then the data will be changed due to which we will be unable to access it. But we should remember one thing that here our encryption key plays a very important role without that key we can not decrypt our image. It acts as a password to decrypt it

More Details: Encrypt And Decrypt Strings and Images using Python

Submitted By

Human Computer Interaction Using Iris,Head And Eye Detection

Last Updated on May 3, 2021


HCI stands for the human computer interaction which means the interaction between the humans and the computer.

We need to improve it because then only it would improve the user interaction and usability. A richer design would encourage users and a poor design would keep the users at bay.

We also need to design for different categories of people having different age,color,gender etc. We need to make them accessible to older people.

It is our moral responsibility to make it accessible to disabled people.

So this project tracks our head ,eye and iris to detect the eye movement by using the viola Jones algorithm.But this algorithm does not work with our masks on as it calculated the facial features to calculate the distance.

It uses the eucledian distance to calculate the distance between the previous frame and the next frame and actually plots a graph.

It also uses the formula theta equals tan inverse of b/a to calculate the deviation.

Here we are using ANN algorithm because ANN can work with incomplete data. Here we are using constructive or generative neural networks which means it starts capturing our individual images at the beginning to create our individual patterns and track the eye.

Here we actually build the neural network and train it to predict

Finally we convert it to mouse direction and clicks and double clicks on icons and the virtual keyboard.

As a contributing or moral individuals it is our duty to make devices compatible with all age groups and differently abled persons.

More Details: Human Computer Interaction using iris,head and eye detection

Submitted By

Smart Bag Tracker

Last Updated on May 3, 2021


Smart bag is an application-specific design that can be useful for almost everyone in the

society. The loss or mishandling of luggage in airports is increasing nowadays,

tremendously raising its associated costs. It is expected that the constant monitoring

detects possible errors in a timely manner, allowing a proactive attitude when correcting

this kind of situations. There are several devices in the market but all have some

problems such as power consumption, location, portability, etc. The current research

provides a novel idea to track the luggage in real time with the help of a microcontroller

system, which is wearable and handy. Using wireless communication techniques, the

proposed system has been designed.

The system consists of GPS module which will fetch the current latitude and longitude and

using advanced Wi-Fi enabled microcontroller which will connect to the 4G

hotspot internet and transmit the current location of the bag to the central server. Using an

Android App the user can view the current position of the bag in google maps.

There are a lot of applications to the luggage but all of them are not controlled from the luggage, instead the commands are sent from the mobile phone to the luggage via Machine to Machine communication. The mobile phone has a pre-installed application software with a pre-installed set of instructions. They wait for the user to send the commands. This can either be for tracking its location.

More Details: Smart Bag Tracker

Submitted By

Utilising Blockchain Technology In Control And Distribution Of Pharmaceutical Supplies

Last Updated on May 3, 2021


In a recent report by the world health Organisation, drug counterfeiting has been identified as a global problem. It estimates that in low- and middle-income countries, every 10th drug in market circulation is counterfeit or has a poor quality. The use of such substandard products may have a negative impact on the mortality rate. Medicines move through a supply chain in which several participants participate. These usually include the manufacturer, wholesaler and retailer. They are engaged in the production, transportation and sale of these products. Also in these systems, there is a key participant - the regulating authority responsible for each stage of the movement of batches of products throughout the chain. In particular, at the state level, this participant may be some authorised body of the state apparatus, for example, a special Agency for the control of turnover of medicinal products. Its main task is to delegate the rights to manufacture medicines according to state standards, as well as to control the movement of all units of goods ever produced. As for the consumer, there is another problem - the control of drugs, issued only by prescription. Dispensing without a prescription is illegal, however, the control of honesty of retailers, as well as with counterfeit medicines, is not easy and requiring a special approach.

This project is still in progress and is expected to be completed by Nov 2021.

More Details: Utilising Blockchain Technology in Control and Distribution of Pharmaceutical supplies

Submitted By

Loan Prediction

Last Updated on May 3, 2021


A Company wants to automate the loan eligibility process (real time) based on customer detail provided while filling online application form. These details are Gender, Marital Status, Education, Number of Dependents, Income, Loan Amount, Credit History and others. To automate this process, they have provided a dataset to identify the customers segments that are eligible for loan amount so that they can specifically target these customers. So in this project our main objective is to predict whether a individual is eligible for loan or not based on given dataset.

For simplicity i divided my projects into small parts-

  1. Data Collection :- I collected data from 'Anylitical Vidhya' as a CSV file. We have two CSV file one is train data which is used for training the data and other is test data which is used for prediction based on training of model.
  2. Import Libraries:- I import differnt Sklearn package for algorithm and different tasks.
  3. Reading data:- i read the data using pandas 'read csv()' function.
  4. Data Preprocessing -: In this part i first found missing values then i remove a column or imputed some value (mean, mode, median) According to the amount of data missing for a particular column.

I checked the unique value in each column. Then i did label encoding to convert all string types data to integer value. I used dummie function to convert each unique value to different columns . I find out correlation matrix which shows the correlation between columns to each other.

Then i split the data. I did analysis on each column and row of dataset.

Here i selected a classifier algorithm because it is a classification problem i.e. in this problem target value is of categorial datatype.

Then i create a model . I trained that model using Logistic regression Algorithm , which is a classification algorithm. I feed training dataset to model using Logistic regression algorithm. After creating model i did similiar data preprocessing to test dataset . And then i feed test dataset to trained model which predict the values of this test dataset. And then i found accuracy of this model using actual target value which is given in training dataset. and predict target value which we predict from test dataset.

After this i used another algorithm which is random forest classifier. i did traied the model using random forest classifier and then calculate the accuracy.

I compared the accuracy of both algorithm and i preffered algorithm which had better accuracy.

In this project i got 78.03% accuracy when i create model using random forest classifier and got 80.06% when i create model using logistic regression.

More Details: Loan prediction

Submitted By