Vamsicharan Petluru

Innovative software developer with experience in designing, developing, and implementing software solutions to address complex business issues. Skilled in multiple programming languages and frameworks, with a strong ability to adapt to new technologies quickly. Demonstrated success in improving system performance and enhancing functionality through strategic updates and modifications. Committed to collaborating closely with team members to achieve project goals and meet deadlines efficiently.

• Certification in Advanced Software Engineering in Cloud and Crypto technologies, link
• AWS Certified Developer Associate, link
• Certified MuleSoft Developer

Melody Mapper,

• Developed and trained music genre classification algorithms including SVM, MLP, Logistic Regression, Decision Tree, and Naive Bayes, achieving an average accuracy of 85%.
• Generated classification precision by 20% through rigorous feature engineering and selection techniques applied to a comprehensive Spotify dataset comprising 115,000 tracks categorized into 20 distinct genres.

Stock Pricing Anomaly Detection and Notification

• Crafted a system using Yahoo Finance APIs and AWS Lambda for real-time stock pricing, improving data accuracy by 20% over manual input.
• Established an automated notification system using Amazon SNS for stock price alerts, reducing response time by 30% and improving decision-making efficiency.
• Leveraged AWS CloudFormation & AWS CodeDeploy to implement an anomaly detection service, reducing deployment time by 40% and increasing system scalability.

IoT Health Guardian: Smart Healthcare Monitoring System

• Engineered a healthcare monitoring system using an ARM microcontroller, tracking vital signs and environmental conditions.
• Enhanced system scalability, enabling the integration of 50% more IoT devices and users while maintaining high performance metrics in real-time data processing environments across healthcare monitoring applications.
• Resolved interoperability challenges by achieving a 95% compatibility rate among IoT devices, ensuring seamless integration and data exchange.

Smart Leaf Disease Detection through Image Analysis, 2320-2882

• Programmed and constructed a self-navigating robot with cameras and sensors to gather real-time images of tomato leaves, culminating in a dataset of over 5,000 samples.
• A Recurrent Neural Network (RNN) model was developed and executed, achieving an accuracy rate exceeding 80% in the detection of predefined plant conditions.
• Incorporated DeepSORT which led to a notable 30% reduction in false alarms, attaining precision and recall rates of 95% and 92%, respectively.