AR powered home garden measuring app
Ceilão.Grid is a smart Android-based mobile application developed to revolutionize small-scale gardening and promote sustainable agriculture in Sri Lanka. The core idea is to empower individuals—especially urban dwellers and small-scale farmers—to grow their own food effectively, even in limited spaces, while reducing reliance on chemically grown commercial produce. The app leverages advanced technologies like Augmented Reality (AR), Artificial Intelligence (AI), and real-time weather APIs to deliver a personalized and practical gardening experience.
Using AR, Ceilão.Grid allows users to scan and measure their available land accurately, offering optimal layout plans for planting. Based on the scanned data, location, and soil type, the app recommends suitable crops and intercropping methods. It also provides cost estimations, revenue predictions, watering schedules based on weather forecasts, and guidance on pest control using an AI chatbot.
Furthermore, with offline accessibility and a simple UI, Ceilão.Grid is designed to be inclusive and user-friendly for a wide audience. The app’s modular design, developed using Kotlin and Node.js, ensures maintainability and scalability.
Ceilão.Grid isn’t just a gardening tool—it’s a lifestyle companion that encourages eco-conscious living, community development, and food independence. It addresses real-world problems with a blend of technology and empathy, making sustainable gardening achievable for all.
A Novel Approach of Airbag anticipation detection before a crash incident
An Intelligent Airbag Deployment System has been developed to address the suboptimal performance of current airbag systems, particularly in budget-friendly vehicles, which often suffer from unexpected deployments or failures to deploy during critical incidents. These issues typically arise from a reliance on predefined crash algorithms and sensor data that may not adequately capture complex real-world collision dynamics, thereby compromising passenger safety.
This research introduces a novel approach that leverages machine learning and computer vision to overcome these limitations. The system integrates the YOLOv8 object detection model with a Logistic Regression classifier to anticipate accidents in real-time by analyzing live dashcam footage. Key visual data features are extracted, preprocessed, and used to train the model to predict the necessity of airbag deployment. The model’s performance was fine-tuned through hyperparameter optimization and assessed using standard metrics like accuracy, precision, recall, and F1-score.
Testing in both simulated and real-world environments demonstrated significant improvements in deployment precision and a reduction in false activations compared to conventional systems. Initial evaluations showed the system’s capability to differentiate between crash and non-crash events, achieving an accuracy of 60.8%, a precision of 57.1%, and an F1 score of 26.1% in predicting correct airbag deployment events. This system aims to enhance passenger safety and mitigate economic burdens associated with unnecessary deployments