| Summary: | Pineapple (Ananas comosus) is a tropical fruit that is widely distributed throughout the world. The cultivation of pineapples, which holds great economic importance in the field of agriculture, encounters ongoing difficulties regarding the detection and control of diseases that affect both the quantity and quality of the yield. Manual disease detection in pineapple crops is challenging due to subjective evaluations, laborious processes, and financial losses. Manual methods can lead to delayed disease identification and specialised knowledge, limiting precise disease diagnosis. The need for effective disease detection tools has prompted the investigation of mobile applications as an ideal solution. To address these issues, automated disease scanning technology systems utilising computer vision and machine learning are essential. The Successive Approximation Model (SAM) was used for instructional design that emphasises a rapid and iterative development process. The development process involves three phases: design, development, and evaluation. The developed mobile application was then evaluated using a questionnaire to get user's feedback and evaluate the accuracy of information provided by the application. Reporting on the result from Likert Scale, most of the score showed values four and above which indicated positive response on the usability and accuracy of disease detection by the mobile application. As a conclusion, the development of this mobile application gives a positive response to users to promptly detect and control diseases, thereby reducing the possibility of crop damage. © 2024 Institute of Physics Publishing. All rights reserved.
|
|---|