Manasa Gourishetty

Methodical Quality Assurance Analyst known for high productivity and efficient task completion. Possess specialized skills in automated testing tools, defect tracking systems, and test case management, ensuring thorough software quality checks. Excel in critical thinking, problem-solving, and communication, facilitating seamless collaboration with development teams to identify and resolve software issues promptly. Highly skilled Quality Assurance Analyst with significant experience in software testing, bug tracking and resolution. Strong understanding of diverse QA methodologies and tools, demonstrating capability to implement comprehensive testing strategies. Proven ability to work collaboratively with development teams to improve overall product quality and performance. Exceptional problem-solving skills leading to successful project completion within stringent deadlines.

Lane Line Detection
Skilled in developing and implementing Lane Line Detection systems, leveraging computer vision techniques to identify road lanes in real-time. Proficient in using image processing algorithms, such as edge detection and Hough Transform, to enhance vehicle navigation and safety. Experienced in working with Python, OpenCV, and machine learning models to optimize lane detection accuracy and performance.

Fake Online Reviews Detection using NLP
In a variety of ways, detecting and removing fake reviews from a dataset using various Natural Language Processing (NLP) techniques is critical. To train the false review dataset and evaluate the accuracy of how real the reviews in the dataset are, this paper employs two Machine Learning (ML) models. When relying on product reviews for items obtained online on various websites and applications, the number of bogus reviews in the e-commerce industry, as well as other platforms, is rising drastically. The merchandise of the firm was trusted prior to making a purchase. As a result, the fake review problem must be addressed so that significant e-commerce companies like Flipkart, Amazon, and others can solve the issue and eradicate phony reviewers and spammers, preventing people from losing faith in online buying platforms. This algorithm might be used by websites and apps with tens of thousands of users to predict the validity of reviews, allowing company owners to take action. The XGBoost and Random Forest approaches were used to create this model. These models may be used to immediately determine the quantity of spam reviews on a website or application. To combat such spammers, a sophisticated model that has been trained on millions of reviews is necessary. The "Amazon Yelp dataset" is used to train the models in this study, and it is a fairly small dataset that may be expanded to achieve great accuracy and flexibility.

Automated Fire Detection and Surveillance System
The main aim of this project is to design an Automatic Fire Detection and Surveillance System. This will detect the fire during surveillance using convolutional neural networks (CNNs). However, such methods generally need more computational time and memory, restricting its implementation in surveillance networks. In this project, we propose a cost-effective fire detection CNN architecture for surveillance videos. This mainly focuses on the computational complexity and detection accuracy. To balance the efficiency and accuracy, the model is fine-tuned considering the nature of the target problem and fire data. This system takes the image file or the video file as input and detects the fire and the fire percentage, which is accurate enough to control fire accidents and save human lives. The development of this project is done by using Python libraries and some machine learning and deep learning algorithms. This project is useful to reduce major fire accidents and helps people, especially disabled people, children, and elderly individuals, escape from deadly accidents in time.