Waddepally Naggasai

Role : Webpage and Prototype design.
Introduced a barcode scanning application streamlining transactions with minimal internet dependency. The web platform, dedicated to the college canteen's counter, manages user deposits and deducts costs per order. The user scans the barcode that's imprinted on the back of the college identity card to open his portal, this shall be used to view the balance and the total amount in deposit. This system innovatively revamps the classic 'khaata' method, providing a convenient cashless experience customized for the college environment.
The proposed system for streamlining transactions at the college canteen addresses several key issues encountered in the existing system while introducing innovative features to enhance efficiency and convenience. Let's break down the components and benefits:
1. Introduction of AGLET Application:
AGLET serves as the platform for managing user accounts and transactions. It utilizes the existing college identity card, transforming it into a multipurpose tool for accessing various services on campus. Through AGLET, users can access their credentials, check their syllabus, and manage their canteen deposit seamlessly. 2. Barcode Scanning Mechanism:
Users simply scan the barcode on their college identity card to access their portal on AGLET. This eliminates the need for manual login procedures and reduces reliance on internet connectivity, as basic functionalities can be accessed offline.
3. Minimal Internet Dependency: By utilizing the available internet connectivity on campus efficiently, AGLET minimizes the need for constant internet access. This is particularly advantageous in environments where internet connectivity may be unreliable or limited.
4. Canteen Deposit System: The system allows users to deposit funds at the beginning of each week, ensuring they have sufficient balance for their transactions. Transactions at the canteen are expedited as users only need to scan their ID card and place their orders, with the amount deducted directly from their deposit.
5. Streamlined Transactions: The system reduces waiting times at the canteen by eliminating the need for manual payment processing and order taking. It minimizes data consumption and eliminates the hassle of remembering passwords associated with traditional web-based systems.
Benefits of the Proposed System: Efficient utilization of available internet resources.
Faster order placement and transaction processing.
Convenient access to syllabus information.
User-friendly barcode scanning mechanism.
Individualized barcodes for enhanced security and tracking.
Overall, the proposed system offers a comprehensive solution to the challenges faced by the existing system, providing a seamless and efficient experience for users accessing canteen services and other campus-related functionalities.

Role : Website front-end and Prototype design.
A prediction model for the farmers to predict crop prices accurately so that they get the optimum value for their yield. The project uses three prediction algorithms; KNN, Decision tree and Naive-Bayes, and the prediction model is generated upon the government data that's existing of a particular region. Inclusion of provision of new Government aided schemes to the farmers is made for their benefit.
Proposed System:
Machine Learning Algorithms: Various machine learning algorithms such as Random Forest, Decision Tree, and KNN are utilized for predicting crop prices. These algorithms are trained on a crop prices dataset, which includes crop details, market prices, and rainfall data.
Benefits of the Proposed System: The system provides farmers with advance forecasts of crop prices, enabling them to make informed decisions and mitigate losses. It also integrates other modules such as weather forecasting, crop recommendation, and fertilizer recommendation to offer a comprehensive solution for agricultural management. The existing system primarily focuses on providing farmers with tools and information to optimize crop production and manage agricultural resources efficiently. It includes features such as crop recommendation based on machine learning models, fertilizer recommendation, and weather forecasting to aid farmers in making informed decisions.
In contrast, the proposed system expands upon this foundation by introducing advanced machine learning algorithms for predicting crop prices. By utilizing techniques such as Random Forest, Decision Tree, and KNN, the system enhances the accuracy of price predictions, thereby empowering farmers to anticipate market trends and optimize their agricultural practices accordingly.
Furthermore, the system's integration of various modules such as weather forecasting and crop recommendation enhances its utility and effectiveness. Farmers can access comprehensive information and insights to make informed decisions about crop selection, fertilization, and resource management.
Overall, the proposed system represents a significant advancement in agricultural technology, offering farmers a powerful toolset for improving productivity, profitability, and sustainability in their operations.