my projects
DYNAMIC PIPELINE
APACHE-AIRFLOW (orchestration tool)
Developed dynamic pipelines which are specific to user and multiple job schedulings for analytics of data at a particular interval of time and based on output, sending the email alerts to the user with the snipit of charts and data tables. Other than this, I have build multiple projects which interact with multiple databases and also Databricks to trigger spark jobs to load tons of data.
HArmony
This is a "game-changing" digital analytics capability for the client, largest pharmaceutical company. It brings 3 corporate functions (R&D, Procurement, and Finance) within one platform. It has two major functionalities - traceability through Genealogy, and Cost Simulation. It is structured with all 4 layers – UI/ visualization, logic/analytics services, data, technology infrastructure for a complete digital analytics platform. It brings data from diverse ERP systems across global regions as well as unstructured data within one platform, and facilitates seamless collaboration across the above-mentioned corporate functions to perform the necessary analytics.
Intelliwat
(IOT +.NET)
Designed developed an IoT product for Govt. of Andhra Pradesh, capable of detecting and providing real-time data of underground water leakage over a web-based platform. Fabricated a 3-m long POC and integrated the ESP-8266 module as well as other sensors to acquire and send real-time data to firebase. Developed an online monitoring system and showcased all the data to provide meaningful insights that can be understood by any layman. Finalists and 1st Runner-up out of 295 teams who participated from all over India.
Disney chatbot (AI)
A chatbot is trained and capable of replying in a unique way using Disney’s dialogue involving emoticons while judging the emotions of the user using ML practices. The chatbot can converse both with text-based systems as well as voice-based systems. This chatboat helps a person to get out of their emotions and try to make them happy and can also act as friend who is always ready to chat with them.
face mask detector
(ML)
An intelligent tool, that can recognize if a person is wearing a mask or not. In addition to that, the tool can also suggest the suitable size of the face mask that the person will require. And is capable for detecting in a group or large crowd.
Autopense
This project is filed for patent and AutoPense will be an automatic medicine dispenser which will help the community and civil hospitals to fetch the patient record automatically and provide them their daily medices. This comes with alarms, GPS and notification. Technologies we have used: - IoT, Database, Firebase and some AI algorithms Role: - Team leader for this project in a team size of 6 members (including me)
anomaly detection with timeseries in keras
(data Science)
Build an anomaly detection model using deep learning. Specifically, we will be designing and training an LSTM autoencoder using the Keras API with Tensorflow 2 as the backend to detect anomalies (sudden price changes) in the S&P 500 index. Also created, interactive charts and plots using Plotly Python and Seaborn for data visualization and display our results in Jupyter notebooks.
predict the future product prices using facebook prophet
(data science)
This project was to train time-series prediction models to predict future product prices. This project could be practically applied in the banking, retail, and healthcare sectors. Also, used Facebook Prophet library which is very powerfull in preparing the future dataset and is more accurate.
Hidden world
(python + javascript)
We have create a web app in NASA SPACE APPS CHALLENGE 2019, in a team of 6 members and my role was a python developer. In this we built an app in which is a complete environmental education website, which is very user friendly (have voice commands to perform the operations, using python) and through our website we prepared a platform in which we connect the user to NASA directly. All the daily updates regarding NASA were provided.