The LeafQuest app is built to merge augmented reality (AR) and artificial intelligence (AI) in order to help users

choose and visualize plants that is appropriate for their space available and given environmental conditions.

Through the use of an artificial intelligence as a recommendation system, this will improve decision-making and

recommendations, and how mobile application can turn traditional plant care into dynamic, learning experience.

The applications are meant to close the gap between knowledge of plant care and users’ accessibility. The study

gathered 80 survey responses from plant hobbyists, enthusiasts, and lovers in Metro Manila. It aimed to evaluate

the quality of LeafQuest in terms of performance, ease of use, reliability, and overall system quality as a mobile-

based augmented reality tool for plant placement, discovery, and development. Findings revealed that all criteria

fell within the “Excellent” range (3.50–4.49), with weighted means between 4.12 and 4.24, indicating strong

acceptance and positive reception from the respondents.

Keywords: Agile methodology, Artificial intelligence (AI), Augmented reality (AR), Gamification

Recommendation system

With the help of augmented reality (AR) and gamification, LeafQuest is a mobile application that combines

digital and natural strategies to create an immersive, interactive platform for virtual plant placement, discovery,

and growth. It allows mobile devices to incorporate real plants in order to create a shared area composed of

virtual plants and the real-world environment via the platform and the immersion. Through this app, users can

discover the rich world of botany and create their own virtual gardens. This application of plant design not only

fosters the user's creativity but also helps them learn as they can arrange the plants otherwise, find out about the

short history and plant characteristics of different kinds, and see the effect of time on them.

The goal of this system is to build a dynamic and educational platform allowing people to cherish the natural

world by engaging in virtual plant placement and discovering the different species of plants. The app, which

uses augmented reality (AR) technology as a tool, allows users to easily associate virtual plants with their real

This section describes the process used to develop LeafQuest, a mobile-based augmented reality application for

finding, planting, and maintaining plants. The Agile methodology was selected as the development framework,

allowing for flexibility and iterative improvements throughout planning, design, development, testing, and

deployment. Data were collected through surveys, interviews, observations, user feedback, and previous studies

to identify requirements as well as evaluate the system's quality and performance. This section also discusses

research design, data collection, sampling, analysis, and the ethical considerations that ensures the study is valid,

reliable, and meets academic rigor.

The development of LeafQuest utilized the Agile Methodology. Agile is based on a progressive and iterative

Figure 4.1: Agile Methodology

Planning

During the planning stage, the proposers worked as a team to establish objectives, requirements, and the scope

of the project. They agreed on the needs LeafQuest would have to meet, as well as a list of the main features that

should be included, such as gamified learning components to make the app fun and engaging to the learner, AI

recommenders to suggest plants, plant identification features for the user to discover new plants, and modules

for user interaction. The work was organized by assigning tasks and scheduling when to do the work.

The requirements developed during `design` were translated into an explicit system design. The user interface,

layout, and system architecture were designed to help ensure the application was user-friendly and functional.

Once developed, the app was tested for functionality and quality. Usability testing was one type of testing that

was conducted, which allowed us to check if the app was easy to use. Compatibility testing was next in line,

enabling us to test the app on different Android devices. Performance testing was also carried out to confirm the

app was stable and would work as expected while in use. Functionality testing allowed us to check that all

features of the app were working correctly and user acceptance testing allowed us to assess whether the app met

user needs and expectations once developed.

After testing was finished, LeafQuest was made available to the intended users in Manila. The deployment phase

meant that the app was available for real-world use; plant enthusiasts and hobbyists could now evaluate the

develop and ensure that the app remained true to its goals.

In order to inform the development and improvement of LeafQuest, a variety of data collection methods were

utilized. Feedback was collected from users during the development process and once in use to assess overall

satisfaction, usability, and suggestions for improvement. Surveys consisting of both closed and open-ended

responses were conducted to gain an overview of user experiences and expectations for plant enthusiasts,

hobbyists, and lovers. Interviews were then used to obtain richer detail about user expertise, experiences,

challenges, and recommendations for LeafQuest. Observational studies enabled the researcher to observe how

participants used the application and to identify any usability issues. Finally, related literature was reviewed in

order to identify gaps and areas for possible improvement. This ensured that LeafQuest was built on both user

The processes of data analysis required the collation and analysis of data gathered through surveys, interviews,

observations, and user feedback. As part of the analysis process, responses were examined for similar themes,

patterns, and issues relative to care of plants and the use of the LeafQuest application. The results were then

interpreted based on the identification and assessment of user needs and the measured performance of the system,

as well as identifying opportunities for improvement. This examination helped ensure findings were made based

on reliable measurement and directly informed adaptations of the application.

As a demonstration of the validity of the LeafQuest study, the investigators will use data obtained from reliable

procedures followed across participants and cross-checking results from particular methods. These measures of

informed of the purpose of the study. The research team also engaged in fair and just use of the data, honestly

reported the results of the research, and relied on ethical standards when conducting this study.

Bawingan et al. (2024) carried out a study to examine the experiences of users with mobile plant identification

applications. Four of the most used apps were LeafSnap, PictureThis, Pl@ntNet, and PlantSnap. The apps were

utilized by students, teachers, and hobbyists, who identified plants by snapping and uploading pictures. The

study collected feedback using questionnaires, highlighting the difficulties and perceptions of users of the apps.

Barra et al. (2024) developed BotanicAR as a cooperative AR game based on the Meta Quest 3 headset. The

research skills by providing dashboards to track approvals and document status. This digital archive can help

create an academic setting that is more collaborative, accessible, efficient, and driven by technology for the

names and caring tips are reliable. The plant tracking and growth functions performed as expected, while the

easy to understand.

Figure 5.5: Bar Graph of the Responses in Usability of LeafQuest

felt comfortable with children, or other people using the app, without concern for data safety or misuse.

Figure 5.6: Bar Graph of the Responses in Maintainability of LeafQuest

Figure 5.6 illustrates that users found that the app performed without any visible bugs or incomplete

functionality. The overall structure and organization of the app added to a reliable environment. There were no

broken links or missing elements while using the app. In addition, most users thought the app would be easy to

update, and they would be willing to use an improved version in the future.

This criterion measured the smoothness of the app on the devices, usability offline, functionality of all features,