Auto Recovered

Nathan
Joseph Savio pereiranathan501@gmail.com

+91 8766434810
Linkedin Pereira nathanpereira1234 (github.com)
Education
Bhopal, Madya Pradesh,India VIT Bhopal University Oct 2022- Present

B-Tech Computer Science and Engineering
• Engineering GPA: 8.37/10
Mapusa, Goa ,India St. Xavier’s Higher Secondary School Mar 2020- Mar 2022
Goa state Board of education (Class XII)
• Percentage 79.5%
Mapusa, Goa, India St. Britto’s Higher Secondary School Mar 2011- Mar 2020
Goa state Board of education (Class X)
• Percentage 86.3%
Work Experience
Data Analyst Quantium May 2023 – June 2023
• Ensured payment platform security compliance while collaborating across teams for feature delivery and code quality
maintenance.
Extra Curriculars
• Open-Source Contributor (2020-Present)
o Applied proficient Python and C++ expertise to actively contribute to impactful open-source projects, driving code
enhancements and adeptly resolving intricate technical issues.
• Freelance Work
(Jan 2024- Present)
o Pioneered a sustainable e-commerce platform, utilizing HTML, CSS, and JavaScript for a visually appealing and user-friendly
experience.
o Engineered TensorFlow models for a predictive analytics tool, predicting user preferences and behaviors.
o Completed 12+ diverse freelance projects, demonstrating excellence in web development and machine learning.
Personal Projects
• Top down Car Racing Game
The Game was programmed in C#. Using car images and integrating it with sound incase the car collides with a incoming
car producing an explosion.The game track was put in motion facilitating the movement of the car while being stationary ,
all that the player has to do is to move it left or right.
• Crack detection using Resnet18 model

Crack detection using Resnet18 model involves using a deep learning approach to identify cracks or defects in images.
Resnet18 is a convolutional neural network (CNN) architecture that has proven to be effective for various image
recognition tasks, including crack detection. By leveraging Resnet18, the model can learn features from the input images
and accurately classify whether a crack is present or not.
• Hotel Website
Designed and developed a dynamic and user-friendly hotel website, integrating essential features such as online booking.
Implemented responsive design principles to ensure seamless user experience across devices, resulting in increased user
engagement and booking conversions. Utilized HTML, CSS, JavaScript, and Bootstrap framework to create visually
appealing and functional web pages.
• Taxi Tip Prediction using Scikit and Snap ML
Developed a robust taxi tip prediction system using Scikit-learn and Snap ML, leveraging machine learning algorithms to
accurately forecast tip amounts for taxi rides. Implemented data preprocessing techniques, feature engineering, and model
selection to optimize predictive performance. Collaborated with data engineers to integrate real-time data streams, ensuring
up-to-date predictions for taxi drivers and passengers. Achieved high accuracy and reliability in tip prediction, contributing
to improved driver earnings and customer satisfaction. Documented the project's workflow, including data exploration,
model training, and evaluation, demonstrating strong analytical and problem-solving skills in a collaborative environment.
• RFID Door Lock System

Designed and implemented an RFID door lock system utilizing advanced technologies for access control and security
management. Integrated RFID technology with electronic locking mechanisms to provide secure and efficient entry
management solutions. Developed software interfaces for RFID reader communication, user authentication, and access
logs tracking. Implemented encryption protocols to safeguard sensitive data and ensure system integrity. Conducted
thorough testing and validation to ensure reliable performance and seamless integration with existing infrastructure.
Contributed to enhancing security measures and access control protocols, demonstrating proficiency in IoT and security
systems development.
• Movie Recommendation System

Implemented a Movie Recommendation System in C++ utilizing a singly linked list data structure for efficient storage and
retrieval of movie data. Developed algorithms to analyze user preferences and movie ratings, incorporating collaborative
filtering techniques to generate personalized recommendations. Utilized object-oriented programming principles to design
classes for movies, users, and recommendation algorithms, ensuring modularity and code reusability. Implemented features
such as adding new movies, updating ratings, and generating recommendations based on user input. Conducted thorough
testing and performance optimization to enhance system responsiveness and scalability. Contributed to improving user
satisfaction by providing accurate and relevant movie suggestions tailored to individual preference
• Classification of Handwritten digits from MNIST database using Tensorflow

Developed a robust handwritten digit classification system using TensorFlow and the MNIST database, a benchmark
dataset in machine learning. Designed and trained deep learning models, such as convolutional neural networks (CNNs), to
accurately classify digits from handwritten images with high precision. Implemented data preprocessing techniques,
including normalization and augmentation, to enhance model performance and generalization. Utilized TensorFlow's APIs
for model construction, training, and evaluation, optimizing hyperparameters to achieve optimal accuracy. Collaborated
with a team to deploy the classification system in production, ensuring real-time inference capabilities for digit recognition
applications. Contributed to advancing image recognition technology and demonstrated expertise in deep learning and
TensorFlow framework.
• Violence detection using CNN

Developed a robust violence detection system using Convolutional Neural Networks (CNNs), a state-of-the-art deep
learning architecture, to analyze video frames and identify violent actions. Utilized Python and deep learning frameworks
such as TensorFlow or PyTorch to build and train the CNN models. Implemented data preprocessing techniques, including
frame extraction and augmentation, to enhance model performance and generalization. Collaborated with domain experts
to annotate and curate datasets for training and testing the violence detection models. Conducted thorough model
evaluation and optimization to achieve high accuracy and real-time inference capabilities. Contributed to enhancing public
safety and security by deploying the violence detection system in real-world applications.
• Data Science Project

SpaceX, a leader in the space industry, strives to make space travel affordable for everyone. Its accomplishments include
sending spacecraft to the international space station, launching a satellite constellation that provides internet access and
sending manned missions to space. SpaceX can do this because the rocket launches are relatively inexpensive ($62 million
per launch) due to its novel reuse of the first stage of its Falcon 9 rocket. Other providers, which are not able to reuse the
first stage, cost upwards of $165 million each. By determining if the first stage will land, we can determine the price of the
launch. To do this, we can use public data and machine learning models to predict whether SpaceX – or a competing
company – can reuse the first stage.
• Drowsiness Detection System for vehicle safety using Heart rate and eye tracking
Developed a cutting-edge Drowsiness Detection System leveraging heart rate monitoring and eye tracking technologies to
enhance vehicle safety. Designed and implemented algorithms to analyze heart rate variability and eye movement patterns,
detecting signs of drowsiness and fatigue in real-time. Integrated hardware sensors and software interfaces for seamless
data acquisition and processing. Utilized machine learning techniques, such as deep neural networks and support vector
machines, to classify drowsiness levels and trigger alerts or interventions when necessary. Collaborated with
interdisciplinary teams including engineers and medical experts to validate system accuracy and reliability. Contributed to
improving road safety and preventing accidents by implementing advanced drowsiness detection capabilities in vehicles.
Awards and Recognitions

• 1st place in International Mathematics Olympiad in class XII
Participated in many Hackathons conducted by university and online and received certificates
Skills
• Java (Object Oriented Programming), Python, C , C++, C# ,HTML/CSS, Javascript , Matlab,Kotlin
• Data Structures, Algorithms, TensorFlow, Machine Learning, Deep Learning , Cloud Computing, RESTful API, Data Collection
and Web Scraping, Data Wrangling, Data Engineering, Data Visualization, Advanced Computer vision, Generative AI, Custom
layer and distributed layers, Natural Language processing, Penetration testing, Cloud Computing, Full Stack Web development,
Game Development, Competitive Coding
Languages
1. English
2. Hindi
3. Portuguese
4. German

Auto Recovered

Uploaded by

Copyright:

Available Formats

Auto Recovered

Uploaded by

Document Information

Original Title

Copyright

Available Formats

Share this document

Share or Embed Document

Sharing Options

Did you find this document useful?

Is this content inappropriate?

Copyright:

Available Formats

Auto Recovered

Uploaded by

Copyright:

Available Formats

Nathan

Joseph Savio pereiranathan501@gmail.com

Bhopal, Madya Pradesh,India VIT Bhopal University Oct 2022- Present

• Crack detection using Resnet18 model

• RFID Door Lock System

• Movie Recommendation System

• Classification of Handwritten digits from MNIST database using Tensorflow

• Violence detection using CNN

• Data Science Project

Awards and Recognitions

You might also like