I am a technology agnostic developer boasting a diverse experience of over 2 years in the field. My proficiency spans across Python and Dart, with Python being my primary language of expertise. I find immense joy in turning conceptual ideas into tangible realities, a passion that drives my work every day. One of my standout skills is my expertise in code debugging. In my free time at work, I enjoy delving into library code, abstracted code, and exploring the intricacies of the proverbial black box. Unraveling complexities and understanding the inner workings of the code is not just a task but a gratifying endeavor for me.
Moreover, I am a staunch advocate for writing tests. I firmly believe that tests play a pivotal role in any project, instilling confidence in the code we produce. This commitment to testing reflects my dedication to delivering robust and reliable solutions in every project I undertake.
Languages: Python, Dart
Frameworks: Django, Django REST, Wagtail, Flutter
Database: PostgreSQL
Others: Celery, Elasticsearch, Git, HTML, CSS, Object Oriented Programming, Data Structures and Algorithms
Plant Classification through computer vision can be a method to reduce human errors and produce accurate results. The objective of this project is to implement a mobile application that can identify plant as well as classify it from a given image. The project was divided into two parts, i.e. Leaf Segmentation and Leaf Classification. Leaf Segmentation was done using the Detectron2 algorithm, where each leaf from a mobile captured image was extracted and was passed on to the Leaf Classification block for classification which was trained on a neural network with InceptionV3 as feature extractor. Segmentation model achieved a mean Average Precision score of 71% and classification achieved an accuracy of 79%.
We propose a deep learning-based model for individually extracting all 12 leads from 12-lead ECG images captured using a camera. To simplify the analysis of the ECG and the calculation of complex parameters, we also propose a method to convert the paper ECG format into a storable digital format. The You Only Look Once, Version 3 (YOLOv3) algorithm has been used to extract the leads present in the image. These leads are then passed on to another deep learning model which separates the ECG signal and background from the single-lead image. After that, vertical scanning is performed on the ECG signal to convert it into a 1-Dimensional (1D) digital form. To perform the task of digitalization, we used the pix-2-pix deep learning model and binarized the ECG signals. Our proposed method was able to achieve an accuracy of 97.4 %.
There are nearly 350,000 plant species in the world with various sizes, different leaf shapes, texture and edges and identifying all these plants is not an easy task for humans and might induce errors. Plant Classification through computer vision can be a method to reduce human errors and produce accurate results. There have been various studies on this problem and many research papers are published on the topic. In this project we study 27 research papers and analyze the datasets and methods used in these papers. After summarize some findings observed through this analysis.
Built a Home appliances controlling system which can be used to turn ON and OFF any home appliances connected through it from anywhere in the world. The system was built using ESP8266-01 to which maximum two devices can be connected and watch was designed with an ESP8266-12E module which has in-built WiFi. The watch was capable control appliances, display Time, Date, Temperature and Humidity of a particular city. Time was displayed using NTPClient API and weather using OpenWeatherAPI. The system and watch were connected using Blynk IOT server