PET PARADISE : Aplikasi Adopsi Hewan Peliharaan Berbasis Android Menggunakan Convolutional Neural Network

Dery, Sudrjat (2021) PET PARADISE : Aplikasi Adopsi Hewan Peliharaan Berbasis Android Menggunakan Convolutional Neural Network. Undergraduate Thesis thesis, Institut Teknologi Telkom Purwokerto.

	Text Cover.pdf Download (429kB)
	Text Abstract.pdf Download (5kB)
	Text Abstrak.pdf Download (6kB)
	Text BAB I.pdf Download (139kB)
	Text BAB II.pdf Download (1MB)
	Text BAB III.pdf Download (1MB)
	Text BAB IV.pdf Restricted to Registered users only Download (2MB) | Request a copy
	Text BAB V.pdf Download (31kB)
	Text Daftar Pustaka.pdf Download (146kB)
	Text Lampiran.pdf Restricted to Registered users only Download (2MB) | Request a copy

Abstract

According to DKPKP, it describes how the increase in abandoned animals, especially cats, continues to increase every year. The adoption process also still has obstacles for ordinary people who are not used to the adoption process, one of the problems is in recognizing the type of animal that will be proposed for adoption later. Survey data conducted on random respondents resulted in an average of respondents only being able to guess three types of animals from the 8 types given. This study aims to design and build applications that can help the animal adoption process with the help of machine learning technology from the Firebase ML-Kit library to identify Android-based animal types. The development method used to build applications in this study is the Mobile Application Development Lifecycle (MADLC) which includes several phases, namely identification, design, development, prototyping, testing, deployment, and maintenance. The results of the validation of the machine learning model created using the confusion matrix resulted in 41% and 21% accuracy for cats and dogs, which were less than optimal because the dataset used was not good. While the results of application testing using thinking aloud in two task scenarios, namely scenarios of potential adopters and animal owners, resulted in 95% and 92% of the user's success in carrying out the given task, respectively. This shows that the application can provide good functionality in the animal adoption process. Keywords: Adoption, Android, Convolutional Neural Network, Machine Learning, Mobile Application Development Lifecycle

Actions (login required)

View Item