Hi There,
I'm Priyanshu Kumar Saw !!
i am into
About Me
🚀 Currently doing internship at Nokia and completed my Bachelor of Engineering (Computer Science and Engineering) (Hons.) with a Specialization in Artificial Intelligence and Machine Learning (In association with IBM) at Chandigarh University.
💻 Coding isn't just a skill—it's a passion. With 5-star ratings in C++ and Python on HackerRank and a strong command of Object-Oriented Programming, I love crafting clean, efficient solutions to tough problems.
🎓 I've been selected for the prestigious IndiaAI Fellowship, launched under the IndiaAI Mission — an initiative by the Ministry of Electronics and Information Technology (MeitY), Government of India.
🧠 I've solved over 2500 DSA problems across platforms like LeetCode, GfG, CodeChef, CodeStudio, and HackerRank—always pushing myself to improve, one problem at a time.
🏆 Hackathon Highlights:
🥇 1st Prize @ HackWithIndia Hackathon (Microsoft Office, Gurugram) – out of 5000+ teams!
🏅 Top 6 @ Smart India Hackathon 2023 – chosen from 50,000+ ideas.
🌍 Global Nominee @ NASA Space App Challenge 2023 – we built a space debris mitigation solution in just 35 hours.
🥈 2nd Place @ Electrothon 5.0 (NIT Hamirpur) – we built iHelp, a transparent giving experience platform to collaborate with NGOs.
📚 With a deep curiosity for exploring cutting-edge technology, I've published 6 research papers in prestigious platforms like Springer, IEEE, and others.
🎖️ Proud to have received:
• Super Achiever Award
• Researcher of the Year
• Academic Excellence Award
• Engineer’s Day Award
from Chandigarh University. Each one represents hours of dedication, teamwork, and a genuine love for tech.
🌌 A finalist in the National Engineering Olympiad, and top performer in the International Space Science Competition. Always driven to explore, build, and challenge limits.
👨✈️ A proud alumnus of Sainik School Tilaiya, with NCC A & B certificates—the roots of my discipline, leadership, and resilience.
🔍 Forever excited about emerging technologies, I thrive on the challenge of staying at the forefront of the ever-evolving tech landscape. Explore my digital badges and achievements here.
💬 Always up for a conversation about tech, innovation, or a great idea. Whether you're looking to collaborate, brainstorm, or just connect—let’s make it happen.
🚀 Let’s build the future together.
email : priyanshukumar7470@gmail.com
place : Hazaribagh, Jharkhand, India - 825406
Education is not the learning of facts, but the training of the mind to think.
Chandigarh University
Sainik School Tilaiya | CBSE
Munam Public School | CBSE
August 2024 - Ongoing
July 2024 - July 2024
May 2024 - July 2024
February 2024 - March 2024
April 2023 - May 2024
September 2023 - October 2023
June 2023 - July 2023
January 2023 - April 2023
January 2023 - March 2023
June 2022 - August 2022
Held at Microsoft Office Gurugram with a prize money of $2000.
New accomplishments have contributed widely to game development especially with respect to production of intelligent game playing entities. Most of the archetypal approaches for designing AI in games fail to work properly in complex and real-time environments with huge action space. This research addresses these challenges by utilizing reinforcement learning (RL) techniques to design AI models for two well-known games: Snake and Mario. The main challenge in the Snake game is to find the best action within a given state in a discrete state-action space. To solve this, we apply Q-learning, an uncomplicated, but highly effective RL algorithm that aims to accumulate the maximum reward by learning from previous experiences. The reason for Mario being more challenging than the other one is that Mario has a high dimensional input space and a continuous action space. For this, we use Proximal Policy Optimization (PPO), one of the most effective methods of reinforcement learning applicable in environments with the continuous decision space and stochastic nonlinear differential equations. This paper describes the design, deployment, and evaluation of these Reinforcement Learning agents where the major difficulties and the rectified methodologies are described. This study compares the efficiency of the application of Q-learning and PPO and shows how these approaches are more effective than the classical AI technologies in the context of gaming environments and bring valuable contributions toward further enhancement of game AI.
Authors: Priyanshu Kumar Saw, Nancy, Shivam Gupta, Atul Raj, Kushagra Agrawal, Amit Kumar
Published in: IEEE Xplore
Date: October 2024
Link: View Publication
This study presents a pioneering approach in machine learning for detecting sign language, merging the capabilities of computer vision with cutting-edge deep learning methods. The primary aim of this model is the precise conversion of sign language gestures into textual or spoken forms, greatly improving communicative access for individuals with hearing impairments. This method is underpinned by advanced neural network frameworks, notably recurrent neural networks (RNNs) and convolutional neural networks (CNNs), which are adept at processing complex visual data in real-time. Utilizing a robust and diverse dataset, the proposed system showcases its efficacy in real-time sign language recognition, demonstrating high accuracy and efficiency. The results indicate the system's adaptability in varied environmental conditions, underscoring its practical utility. This research signifies a significant advancement in assistive communication technologies, underscoring the powerful impact of sophisticated machine learning techniques in catering to the distinct communication requirements of the hearing-impaired population. By achieving this milestone, the project not only tackles a crucial accessibility issue but also establishes a foundation for subsequent breakthroughs in the realm of inclusive communication solutions.
Authors: Priyanshu Kumar Saw, Nancy, Shivam Gupta, Atul Raj, Kushagra Agrawal, Shweta Chauhan
Published in: IEEE Xplore
Date: June 2024
Link: View Publication
The abundance of user-generated images online presents an invaluable resource for understanding our world. While Structure from Motion (SfM) excels in controlled settings, applying it to diverse internet image collections faces challenges due to variability. This paper explores innovative algorithms for crafting precise 3D models from these diverse sets. It evaluates feature extraction, matching techniques, and reconstruction, addressing issues like resolution disparities and shadows. Robust SfM algorithms have implications in computer vision, machine learning, and robotics, enhancing object recognition, scene understanding, and navigation. This could impact autonomous vehicles, augmented reality, and virtual tourism. SfM shows promise in extracting accurate 3D models from unstructured image collections, offering insights into our world and aiding exploration, comprehension, and preservation.
Authors: Priyanshu Kumar Saw, Nancy, Shivam Gupta, Ganesh Kumar Jha, Shweta Chauhan
Published in: Springer
Date: December 2023
Link: View Publication
There has been an ever growing demand for a better music recommendation system which beats the traditional ones. Before recommending any song it is crucial that a prior classification of songs is achieved with the highest level of accuracy. This research paper is primarily focussed on categorizing the songs based on its genre.In order to achieve this, the sequential Neural network model with several layers of densely connected neurons, dropout regularization, and a Softmax output layer is trained on large dataset containing the features extracted from the audio files. With the help of CNN deep learning model, the existing model has been improved.
Authors: Priyanshu Kumar Saw, Nancy, Amit Kumar, Harashleen Kour
Published in: IEEE Xplore
Date: July 2023
Link: View Publication
In all nations across the world, the demand for safe, rapid, and dependable train services continues to be a source of worry. Safety, operational inefficiency and reliability of old railway systems and operations, as well as safety and security concerns that haunt many countries for changing rail infrastructure that exist the worldwide train sector is battling to stay afloat. to accommodate the rising freight and passenger demand because of the inefficient utilization of the rail network and Rail assets are being used inefficiently. This is predicted to cause train congestion. executives to design better and more efficient train systems efficiently. Indian Railways' passenger reservation system is one of the most extensive in the world. Approximately one million passengers travel with Indian Airlines every day in reserved accommodations. Another sixteen million passengers use unreserved flights. Railways in India It are a huge job to navigate this large structure. We have investigated several aspects of implementing smart computing in reservation models for railway networks.
Authors: Priyanshu Kumar Saw, Nancy
Published in: International Journal of Scientific Research in Science, Engineering and Technology
Date: May 2023
Link: View Publication
Bank management governs various concerns associated with banks in order to maximize profits. The concerns broadly include liquidity management, asset management, liability management and capital management. But still there might be some flaws in this system. These flaws may be holes in rules and regulations, bribery, excuses of lunch, bank’s slow server, employees’ attitude towards work, long waiting times in customer services etc. So, these issues can be solved by an interface connected directly to the bank’s administration through which a person can do their daily minimal banking jobs not through an ATM but through their smartphone. Here comes our project BMS which is a CLI program scripted through python, and data managed by DBMS. The user can perform transactions between accounts of the same bank, check balance, create or delete accounts, deposit or withdraw amounts.
Authors: Priyanshu Kumar Saw, Nancy
Published in: International Journal of Scientific Research in Science, Engineering and Technology
Date: May 2023
Link: View Publication
