PORTFOLIO
-
News Classification using Machine Learning and Deeplearning
With the burgeoing growth of online news, it is now inevitable to classify the news automatically according to its category. In this project, we used multiple dataset and perform multiclass classification using classifcal machine learning and also we have used transformer based techniques. Two datasets are used BBC and AG News Dataset
Explore the complete project:
AG News Classification project code
BBC_News_Classification using classical machine learning -project code
BBC_News_Classification using Deep Learning
​
​
-
Github Bugs Prediction- Automating the customer support for Software tool companies
In Software products companies, we have teams which are specialized in certain technical and business skills. It is the internal business process through which task get assigned to different teams. Generally , when customer queries comes,they go to the first line tech-support teams. Then it goes to the next line support teams where they review the issues and based on a technical analysis the customer emails get routed to the concerned department. For example,If there is a bug in the released software it goes to R&D or It goes to sales department, if it is an inquiry . As the product grows, managing huge number of supports tickets and differentiating them takes significant time.Only way to go towards customer delight is the quick response to customer's queries.
Through machine learning created a classification system which can classify the tickets into bugs and inquiry by doing text analysis and hence can reduce the routing time.
Explore the complete project code and case study:
-
Predicting the price of second hand cars in India
In India second cars is a big market and generally it involves lot of middle man in the value chain. In this project we have a used publicaly available data from cardekho data set to predict the second hand car price.
​
-
Fake Job and Real Job prediction
The burgeoning fake job rackets are alarming. During this unprecedented times, when the world is suffering through a covid19 Pandemic and the economies seeing a negative growth with the increase in unemployement. Fake job rackets are extremely dangerous. According to the Word Economic forum(https://www.weforum.org/), in the week of 25 April,2020, 3.8 million Americans made an unemployment claim. During this time when people are desperate to get a job, it is very easy for these rackets to tap people. One of the most efficient solution to this problem will be to identify the fake jobs when they are posted. Identification is one of the key steps to eradicate this rackets.
Applying machine learning, we can classify the fake jobs and reals job. Using RamdomForest Classifier, achieved decent performance.
​
​
-
Indentification of attacks in IOT based ICU healthcare system
Internet of things has emerged as a key area of research in both academic and industrial communinity. IOT in a nutshell is a collection of objects which are connected to the internet and has the ability to communicate with each other. In IOT, we are deallng with the connectivity of objects which has contraints on power,compute and secuirity. Smart systems are made by combining the power of these embedded objects with the power of analytics in edge or cloud. our smart cities,smart watch etc. are nothing but bunch of connected devices with analytical capabilities.
With the increase of the IOT devices, security is one of the most activate area of research. In recent times the malacious attacks on the IOT newtwork has become very popular. As these IOT devices operates in constrainted power,bandwidth, memory environment, traditional IT network security or Intrution Detection systems(IDS) can't be implemented for IOT networks. Hence there is a need for IDS
In this project, we are going to train a machine learning/deep learning model which can detect a malacous attack on the IOT network.