Palntify: Indoor plant monitoring with integration of automatic drip irrigation and artificial UV lighting system using deep learning and IoT technologies [

ABSTRACT: STATEMENT OF THE PROBLEM: The study aims to address the challenges associated with urban gardening and improve the quality control plant growth through the development of an advanced indoor plant monitoring system. This system will incorporate automatic drip irrigation and artificial UV lighting, combined with deep learning and Internet of Things (IoT) technologies. A multitude of factors contribute to the challenges faced by plant owners and gardeners, such as limited time, lack of knowledge, inadequate urban spaces for gardening activities, as well as environmental stressors and the looming concerns of climate change. By integrating automation technologies with deep learning algorithms, the monitoring system can deliver precise measurements of crucial environmental elements surrounding the plants. This, in turn, contributes to optimizing their growth processes for increased productivity while simultaneously reducing the need for constant human supervision. RESEARCH METHODOLOGY: The study utilized an experimental research design in conjunction with a quantitative approach to investigate the possible cause-and-effect relationship between the independent and dependent variables. Data will be collected through various instruments, including surveys, observations, interviews, and an IoT device, to thoroughly evaluate the accuracy and effectiveness of the plant monitoring with automated drip irrigation and artificial lighting system in supporting the growth of indoor plants. The study will be conducted for seven weeks or 35 school days, and the locale will be in Imus City, Cavite, in a controlled room environment at an urban house. Data analysis will be done using statistical treatments such as Intraclass Correlation Coefficient (ICC) and Pearson Correlation Coefficient. This study will be significant in examining the effects of the integrated system on a range of different plant species that are commonly found in urban environments and will be relevant for indoor plant cultivation in various settings. SUMMARY OF FINDINGS: The purpose of this study was to develop Plantify, an indoor plant monitoring system with automatic drip irrigation and artificial UV lighting, using deep learning and IoT technologies. The researchers tested the effectiveness and reliability of Plantify by gathering data on plant height, leaf color, temperature, humidity level, and soil moisture level, and comparing the results with a control group using traditional planting methods. The study found that Plantify was able to accurately showed the same parameters for users to monitor. The researchers discovered several intervening variables that could hinder plant growth and found that Plantify could mitigate these variables to sustain plant health. To determine the significant relationship between Plantify and the control group, the researchers tabulated and computed the hypotheses. The analysis showed a very strong positive correlation between lettuce and basil height when using Plantify compared to traditional planting methods. The T-test also revealed a significant relationship between plant height and Plantify. In terms of leaf color, there was a little significant relationship between traditional planting and Plantify for lettuce and basil, with some bad ratings observed under the integrated deep learning to detect the health of the plants for both methods. However, Plantify received a good overall rating for leaf color, particularly during weeks 1 to 5. The study also assessed the reliability of the mobile application by comparing the accuracy of the measurement of the application with all the Pods for temperature, humidity, and soil moisture. The intraclass correlation coefficient showed excellent reliability, with a 100% agreement rate between Plantify and the mobile application. CONCLUSION: The proponents successfully developed an indoor plant monitoring system called Plantify using deep learning and IoT technologies, which integrates automatic drip irrigation and artificial UV lighting to provide real-time data on the current state of the plant and automatic the provision of essential resources. Plantify demonstrated reliable results for Lettuce and Basil leaf color ratings and was effective in promoting plant growth. The mobile application was highly reliable and accurate for users, with a 100% accuracy rate and minimal delay in real-time scenarios. The study concludes that Plantify is an accurate and efficient tool for automating and monitoring plant growth, demonstrating the potential of deep learning and IoT technologies in the agriculture industry. RECOMMENDATION: The proponents recommend improving the watering system, expanding the capacity of the current system, using high-quality cameras for monitoring plant growth, adding a disease detection feature, conducing more testing with various plant species and environmental factors such as temperature and humidity for optimal plant growth and health.

000-099 General References or Works