Machine Learning Node Js
Resume:
Skills
Programming Languages: C, C++, Java, Python, Node.js, React.js, Angular.js, JavaScript, Julia, Go Database Languages: PostgreSQL, SQL, MongoDB
Cloud & DevOps: Amazon Web Services (AWS), Kubernetes, Jenkins, Docker Data Analysis & Visualization: Power BI, MATLAB
Development Tools: npm, Git, Postman
Inductive Automation: Ignition Vision, Ignition Perspective Software Testing: Jest, Selenium, Karma, Mocha Chai, SonarQube Authentication & Security: Key cloak, Google Authenticator Soft Skills: Project Management, Cross-functional Collaboration, Problem-solving, Continuous Learning Education
Michigan, USA
2022 - 2024
Masters of Computer Science (with Distinction). Coursework included Data Structures and Algorithms, Artificial Intelligence, Machine Learning, Human Computer Interaction, Computer Security, Network Security.
SAVITRIBAI PHULE PUNE UNIVERSITY Maharashtra, India 2016 - 2020
Bachelor of Computer Engineering (with Distinction). Coursework included Database Management Systems, Web Technology, Data Analytics, Data Mining, Cloud Computing, Computer Networks. Work Experience
MERCURY MARINE: SOFTWARE ENGINEERING INTERN Wisconsin, USA May 2023 – Dec 2023
• Integrated real-time PLC sensor data from Automatic Guided Carts using OPC tags.
• Redesigned dashboards, significantly enhancing production efficiency, resulting in a 40% increase in throughput per shift.
• Created and configured Memory tags, Expression tags, and Boolean tags to monitor and control production line aspects.
• Bound tags to UI components for real-time updates and controls within Ignition Vision screens.
• Implemented tag change scripts to automate responses to tag value changes.
• Utilized Alarm tags to trigger alerts for issues with PLC sensor data.
• Stored shift-end data to Microsoft SQL using Python scripting and Historian tags.
• Retrieved data from Microsoft SQL using Query Tags.
• Developed a standalone Perspective project to display all internal projects and their statuses for a prestigious year-end event.
• Created a Perspective project to monitor employee training attendance and statuses.
• Developed a Perspective project to fetch NOAA temperature and humidity data via a Node API.
• Displayed environmental data in the plant and triggered alarms if conditions were suboptimal for marine engines.
Vrushali
Shinde
********@***.***
https://www.linkedin.com/in/vrushali-shinde-a0437b260/ Michigan, United States (Self-funded Relocation)
MICHIGAN TECHNOLOGICAL UNIVERSITY
CAPGEMINI: SENIOR SOFTWARE ENGINEER Maharashtra, India Aug 2020 - Aug 2022
• Developed backend solutions using Node.js, integrated with Java Spring Boot.
• Created RESTful APIs and microservices for the recruitment portal.
• Enhanced authentication with Key cloak and Google Authenticator.
• Used Amazon S3, and PostgreSQL for data management.
• Maintained project schedules, ensuring timely feature delivery.
• Automated resume analysis and scoring with a Python API.
• Stored the resume score with candidate information in Amazon DynamoDB
• The Python API was integrated with the backend developed using Java Spring Boot, and it interacted with AWS services for data storage and retrieval (AWS DynamoDB). This integration
• Developed Angular frontend for project customization and access.
•
• Managed and deployed EC2 instances.
• Delivered live production project, enhancing recruitment efficiency at Capgemini.
• Agile Methodology implementation.
Academic Projects (Python focused)
Brain Tumor Segmentation (2023)
Key aspects of the project included:
• Model Architecture: Implemented a U-Net model, which is highly effective for image segmentation tasks. The model was trained to identify and delineate tumor regions within brain x-rays.
• Data Handling: Utilized a dataset from Kaggle, performing preprocessing steps such as resizing images, normalization, and data augmentation to improve model performance.
• Evaluation Metrics: Assessed the model's accuracy using metrics like Intersection over Union
(IoU) and pixel-wise accuracy to ensure precise tumor detection and segmentation. Emotion-Based Music Recommendation System (2022)
Key aspects of the project included:
• Natural Language Processing (NLP): Employed Python libraries such as NLTK and Scikit-learn to analyze text data from a Twitter dataset. Techniques like Count Vectorizer and TF-IDF were used for text representation.
• Machine Learning Models: Applied multiple classifiers including Multinomial Naive Bayes (MNB), Logistic Regression, Support Vector Machine (SVM), K-Nearest Neighbors (KNN), Decision Tree Classifier, and XGBoost Classifier. After evaluation, Random Forest Classifier was found to perform the best for emotion prediction.
• System Integration: Developed a pipeline that processes input text, predicts the emotion, and then recommends a music playlist based on the detected emotion. This involved integrating various machine learning models and ensuring seamless data flow through the system. Django Platform:
• Data Analysis: Conducted a thorough survey and analysis of ECG signals from a Kaggle dataset. This involved preprocessing the data to remove noise and artifacts to improve the accuracy of subsequent analysis.
• Machine Learning Implementation: Utilized Python to implement machine learning algorithms for classifying ECG signals. Techniques included feature extraction, dimensionality reduction, and classification using models like Support Vector Machines (SVM) and Neural Networks.
• Early Detection: The primary objective was to detect cardiovascular diseases at an early stage by analyzing the ECG patterns. The model's performance was evaluated using metrics such as accuracy, precision, and recall to ensure reliable detection. streamlined the resume processing workflow and enhanced the efficiency of the recruitment portal.
Provided a time-saving solution for package extraction.
Contact this candidate