Claim Missing Document
Check
Articles

Found 2 Documents
Search

Classification of Eye Diseases Using the AlexNet Convolutional Neural Network Model Algorithm Moch Deny Pratama; Royal Fajar Sultoni; Adil Sandy Wardhani; Maulana Hassan Sechuti; Yerezqy Bagus; Dina Zatusiva Haq; Yoga Ari Tofan
IJCONSIST JOURNALS Vol 7 No 1 (2025): September
Publisher : International Journal of Computer, Network Security and Information System

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33005/ijconsist.v7i1.160

Abstract

This study uses the Convolutional Neural Network (CNN) method with the AlexNet model to classify eye diseases based on medical images. The dataset includes labeled images of three types of eye diseases: cataract, glaucoma, and diabetic retinopathy. The experimental results show that the model achieved an accuracy of 75.18%, which indicates that CNN with the AlexNet architecture can classify eye diseases quite well. This research shows that deep learning can be used to help doctors or health professionals in diagnosing eye diseases through automatic image analysis. Although the accuracy still needs to be improved, this study can serve as a reference for developing an automated diagnostic system in the future. Further research is expected to increase accuracy, expand the dataset, and apply other deep learning techniques to improve the performance of eye disease detection.
Penerapan Chatbot Assistant Berbasis Kecerdasan Buatan untuk Mendukung Transformasi Digital pada Mitra Usaha Agribisnis: TelurKita Angga Lisdiyanto; Agussalim Agussalim; Ani Dijah Rahajoe; Rizky Parlika; Budi Nugroho; Taufikurrahman Taufikurrahman; Rangga Laksana Aryananda; Addien Haniefardy; Dina Zatusiva Haq; Yerezqy Bagus; Vinza Hedi Satria; Yoga Ari Tofan
Mestaka: Jurnal Pengabdian Kepada Masyarakat Vol. 5 No. 5 (2026): Oktober 2026
Publisher : Pakis Journal Institute

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.58184/mestaka.v5i5.1209

Abstract

Many micro, small, and medium businesses (UMKM) believe that using information technology needs a lot of money, a long build time, and a special information technology team. This belief often slows down their digital change. This community service activity aimed to help the partner understand how to use information technology to support digital change. It focused on a chatbot assistant based on artificial intelligence, because this tool is cheap and fast to set up. The activity took place at the office of PT Assasta Sampoerna Indonesia (TelurKita) in Ngasem, Kediri Regency. The partner's leaders and staff joined it. The method had five steps: studying what the partner needed, preparing the material, explaining the main ideas, showing how the system works, and holding a guided talk that linked the partner's work needs with the technology. The material showed that going digital means joining people, process, data, and technology. It also introduced a chatbot design that uses standard operating procedure documents as its knowledge base. The system takes the text out, cuts it into small parts, and sends it to an API (Application Programming Interface) of an LLM (Large Language Model). The team measured the result in a descriptive and qualitative way, by watching the participants and studying their questions. The result shows that the participants understood more. They could point out work steps that a machine can do, and their view about the cost and difficulty of this technology changed.