Claim Missing Document
Check
Articles

Found 3 Documents
Search

Deteksi Penyakit pada Tanaman Padi Menggunakan MobileNet Transfer Learning Berbasis Android Herwina; Ashabul Kahfi Ash Shiddiq; Theddy Dzikrullah Syahputra; Darmatasia
AGENTS: Journal of Artificial Intelligence and Data Science Vol 2 No 2 (2022): Maret - Agustus
Publisher : Prodi Teknik Informatika Universitas Islam Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1556.62 KB) | DOI: 10.24252/jagti.v2i2.41

Abstract

Rice is a staple food in several countries, including Indonesia. To produce quality rice, maintenance of rice plants is required from planting to harvest. One of the problems often experienced by farmers is the presence of diseases that attack rice plants. The limited knowledge of some farmers means that farmers do not understand the condition of their plants, resulting in delays in handling when the plants are attacked by disease. This research aims to build an application that can detect diseases in rice plants that attack rice leaves. The types of diseases that will be detected are Leaf Smut, Brown Spot, and Bacterial Leaf Blight. This research uses a transfer learning approach with the Convolutional Neural Network algorithm to detect diseases in rice leaves. The architecture used is MobileNetV1 with an accuracy of 94% and MobileNetV2 with an accuracy of 95%. The input image used is 224x224 pixels in size. The trained model is then integrated into an Android-based application. Test results on the Android application show that the model can detect diseases on rice leaves.
IMPLEMENTASI JARINGAN SARAF TIRUAN UNTUK MENENTUKAN KELAYAKAN MAHASISWA DALAM MENDAPATKAN PEKERJAAN Ayu Azhari Zainal; Azizah Salsabila Azizah Salsabila; Hastuti Hastuti; Darmatasia
AGENTS: Journal of Artificial Intelligence and Data Science Vol 3 No 1 (2023): September - Februari
Publisher : Prodi Teknik Informatika Universitas Islam Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1233.462 KB) | DOI: 10.24252/jagti.v3i1.58

Abstract

Job recruitment selection is one of the processes carried out by agencies or companies to determine whether a person is eligible for a certain job position or not. The selection process is often carried out in a subjective manner so that it can be detrimental to companies or job applicants. In the process of determining a person's eligibility to be accepted or get a particular job, a company usually has set certain criteria. In addition, a company also often holds regular employee recruitment. This study aims to implement one of the machine learning algorithms, namely an Artificial Neural Network to build a model that can assist companies in predicting a person's eligibility for employment. The model is built with reference to certain criteria data that has been set by the company such as educational history, work experience, and capabilities. The best accuracy result of 91.18% is obtained from a model built using a learning rate parameter of 0.1 and the number of hidden layers is 10.
SISTEM MANEJEMEN DAN MONITORING BIMBINGAN TUGAS AKHIR BERBASIS WEB Salmi; Darmatasia
AGENTS: Journal of Artificial Intelligence and Data Science Vol 3 No 1 (2023): September - Februari
Publisher : Prodi Teknik Informatika Universitas Islam Negeri Makassar

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (832.897 KB) | DOI: 10.24252/jagti.v3i1.59

Abstract

The process of supervising student final assignments experiences many obstacles that can hinder the process of completing the final assignment itself. In addition, lecturers also carry out other tri-dharma activities, namely research and community service which require lecturers to carry out activities outside the campus. Differences in activity and liveliness between lecturers and students can be one of the obstacles in the final assignment guidance process. The purpose of this research is to design a system that can manage and monitor processes as well as provide advice related to web-based graduation projects, to facilitate processes, suggestions and assurance of information at any time and the accuracy of work processes in improving student graduation performance, especially in the final project process. The results of the accuracy test conducted on respondents and the level of satisfaction of respondents on the feasibility of the system is 80%. Keywords: Management, Guidance, Monitoring, Final Project..   Keywords: Management, Guidance, Monitoring, thesis