My Expertise
As an avid Engineer, I know how to achieve Efficiency, Optimization and Performance according to hardware and software environment. From Assembly Language to the Python, excellent experience in C/C++. Areas of Interest - Computer Graphics, Cyber Security, Data Science, Machine Learning and Deep Learning.
Featured Projects
News Article + Trading
- VADER, NLTK, BackTrader
It's true that News article affects mindset of the people and we read news evveryday. This is where Behavioural Economics comes in place! Leveraging Human-Emotions for Trading. Voila! I didn't expected the results to be damn Accurate.
No Link
Train Tracks
- Geo Spatial Analysis (GIS)
Using Census and Consumer data to analyze consumer behavior in particular dissemination areas. First step was to map Census data on map than implemented train routes and train stations. After that creating Buffer radius of 10km to cover the area around the station. Performed intersection between the Dissemiination areas and assigned them the station id.
No Link
Fish Spices Detection
- Assembled Model, Faster R-CNN, RPN
This project is in possession of a pretty good object detector that can locate and crop out the fishes with reasonable robustness. next was train a good classifier that can accurately identify the fish species. I fine-tuned several different ConvNet models, including VGG-16/19, ResNet-50/152, Inception-V1, Inception-V3/V4, Xception, DenseNet-121, ResNeXt-50/152. Stochastic Gradient Descent was used as the optimizer. The fine-tune procedure was also used.
No Link
Article Classification using ML
- Natural Language Processing
Text classification is one of the imperative and typical task in Machine Learning. Assigning categories to documents, which can be a web page, library book, media articles, news etc. has many applications like spam filtering, email channeling, sentiment analysis, finding reader’s interest and Article Classification.
Check it out
Automobile Price Prediction
- Data cleansing, Linear expr, KNN
Car's messy data with features including make, model, year, engine, and 12 other properties of the car is used to find co-relation between attributes and to predict its price with less properties and less error-rate.How effects of features on the price?, How does the brand affect the price? What cars can be considered expensive? Price vs. popularity!
Check it out
Fraud Classification and Detection
- Numpy, Pandas, SQL
Machines are much better at dealing with and processing large datasets than humans are. They are able to detect and recognize thousands of features on a user’s purchasing journey instead of the few that can be captured by creating rules. This ability to see deep into the data and make concrete predictions for large volumes of transactions is the main advantage.
Check it out