Bishal Kharal | Student Researcher

Hi, I'm Bishal Kharal

A

A student Researcher who is passionate about AI, deep learning, physics and mathematics.

About

I'm a graduate student in high school who is interested in deep learning and data engineering. I've opted to use cutting-edge technology and research in to locate the ideal answers to challenges the physical universe faces.

Languages: Python, JavaScript, C, C++, HTML/CSS, Bash
Databases: PostgreSQL, MongoDB
Libraries: NumPy, Pandas, OpenCV, FastAPI
Frameworks: Flask, Django, Node.js, Keras, TensorFlow, PyTorch, Scrapy
Tools & Technologies: Git, Docker, AWS, GCP, Heroku, JIRA

Looking for an opportunity to work in a challenging position combining my skills in Deep learning and Research, which provides professional development, interesting experiences and personal growth.

Experience

DRCFS

Co-Founder & President

Ideated and disseminated a unique pictographic, storytelling format via social media to an audience of 1000+ professionals.
Responsible for event planning with board members on a bi-weekly basis, managed over 10 events like school outreach programs, hour of code, research paper reviews and webinars impacting over 600 students.
Supervised and mentored a remote team of 6 interns working across marketing, graphic design and content creation.
Involved in group projects, building ’Project Pahiro’ with over 400+ unique users and worked on human computer interaction research papers.
Tools: Python, Flask, OpenCV, Keras, Tensorflow, PyTorch, Django, ExpressJS

Nov 2021 - PRESENT | Kathmandu, Nepal

Reduct Nepal

Data scientist

Worked on a data science project for the team involving training of a machine learning model using Python. Created chart visualizations of model results in matplotlib.
Researched and worked on feasibility of Machine Learning models to detect human voice under HIPAA Compliance.
Collaborated with fellow interns for code optimization and saved hours of time by automating manual tasks.
Built and refactored data visualization dashboard for interncal company data.
Tools: Python, Flask, PostgresSQL, Tensorflow, Django, R

Feb 2022 - April 2022 | Kathmandu, Nepal

Padamna Pvt. Ltd

Co-founder & backend Developer

Hired and built cross-functional team of seven people across marketing, tech and operations.
Led the GoProcure (Freight Negotiation Tool) team of 6 cross-funtional engineers, 2 marketeers, and 2 UI/UX desginers; helped solve poor sprint efficiency by tracking developer metrics which increased the sprint completion rate from 55 to 80 percentage.
Tools: Javascript, Python, Git, Docker, JIRA

July 2022 - PRESENT | Kathmandu, Nepal

Global AI Hub

Core member

Worked with other fellow core members to conduct different AI sessions.
Collaborating with a diverse research team to collect, code, and write technical reports.
Participated in different sessions on programming and computer science.

Feb 2022 - PRESENT | Zurich, Switzerland

Projects

Frida
A mobile application that is powered with AI to detect landslides and other climate related features.
AccomplishmentsTools: Deep learning, Python, FastAPI, Flutter, Google Firebase
Register/login from mobile application.
View latest climate related news.
Monitor water levels and get alerts about flood
Get notified about landslides near your location 1 day before prior occuring it.





JOVAI NASA Spaceapp
JOVAI is an web-application that uses deeplearning and GAN to edit Jupiter images taken by JunoCam.
AccomplishmentsTools: Deep learning, StyleGAN, Python, JupyterNotebook, Javascript, HTML, CSS
Colorize raw image taken by JunoCam into detailed colored image.
Generate new detailed image of Jupiter with StyleGAN.





EaseMed
A mobile app to reduce the mental health illness.
AccomplishmentsTools:Python, Deep learning, Flutter, RESTAPI
Users can chat with chat bot powered with AI to talk about their mental health issues.
Users can get nearest hospital, doctors contact info and ambulance live location..





Visual Question Answering
An attention-based classification model that aims at generating an answer for a given input image.
AccomplishmentsIncorporated Convolution Neural Networks (CNN) for extracting image features and Long Short Term
Memory for extracting question
embeddings.
Tested the model on the COCO dataset, abstract scenes images, and got 69% overall accuracy on the
VQA evaluation metric.




Video Summarizer
A Seq2Seq model that generates a short summary of the given input video.
AccomplishmentsIncorporated CNN to detect and classify objects in the video frames and Long Short Term Memory for
generating a summary.
Evaluated the model on MSVD (Microsoft Video Description Corpus) dataset; achieved 0.77, 0.71,
0.52 scores respectively on ROGUE,
BLEU, METEOR evaluation metrics.




Image Generator
An image generator based on the concept of adversarial networks (GANs)
AccomplishmentsDeveloped system was tested on a human-face database and loss was calculated by comparing the PCAs
of generated and original image.
Calculated difference in PCA was less than 10%, depicting the successful generation of an image by
the generator.




Head Counting System
A system that calculates the attendance of the class from a panoramic image of a live classroom.
AccomplishmentsUsed Singular Value Decomposition for image compression; applied various image processing
techniques and morphological operations to
detect the number of heads.