Accepted: 06-04-2023 | Received in revised: 11-07-2023 | Published: 12-08-2023 940 Accredited Ranking SINTA 2 Decree of the Director General of Higher Education, Research and Technology, No. 158/E/KPT/2021 Validity period from Volume 5 Number 2 of 2021 to Volume 10 Number 1 of 2026 Published online on: http://jurnal.iaii.or.id JURNAL RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol. 7 No. 4 (2023) 940 – 946 ISSN Media Electronic: 2580-0760 Performance Comparison of Convolutional Neural Network and MobileNetV2 for Chili Diseases Classification Achmad Naila Muna Ramadhani 1 , Galuh Wilujeng Saraswati 2 , Rama Tri Agung 3 , Heru Agus Santoso 4 1,2,4 Informatics Engineering, Faculty of Computer Sciemce, Dian Nuswantoro University, Semarang, Indonesia 3 Informatics Engineering, Faculty of Computer Science, Pembangunan Nasional Veteran Yogyakarta University, Yogyakarta, Indonesia 1 111201912206@mhs.dinus.ac.id, 2 galuhwilujengs@dsn.dinus.ac.id, 3 123180053@student.upnyk.ac.id, 4 heru.agus.santoso@dsn.dinus.ac.id Abstract Chili is an important agricultural commodity in Indonesia and plays a significant role in the nation's economic growth. Its demand by households and industries reaches up to 61%. However, this high demand also means that monitoring efforts need to be intensified, particularly for chili plant diseases that can greatly impact yields. If these diseases are not promptly addressed, they can lead to a decrease in production levels, which can negatively affect the economy. With technological advancements, automatic monitoring using image processing is now highly feasible, making monitoring more efficient and effective. Common chili plant diseases include Chili leaf yellowing disease, Chili leaf curling disease, and cercospora leaf spots and Magnesium Deficiency with symptoms that can be observed through the shape and color of the leaves. This research aims to classify chili plant diseases by comparing the CNN algorithm and the pre-trained MobileNetV2 based model performance using Confussion Matrix. The study shows that the MobileNetV2 model, trained with a learning rate of 0.001, produces a more optimal model with an accuracy of 90% and based on the calculation of the confusion matrix, the average percentage values for recall, precision, and F1 score are 92%. These findings highlight the potential of image processing and pre-trained models to support efforts to monitor plant diseases and improve chili production. Keywords: chili; comparison; CNN; mobilenetV2 1. Introduction Indonesia is known as an agrarian country, so its people still rely on the agricultural sector. Chili is one of the largest agricultural commodities in Indonesia. Based on data from the Badan Pusat Statistik (2022), chili production in Indonesia over the past three years has produced a total of 7.09 tons. The annual breakdown shows that in 2019, chili commodities produced around 1.37 tons, in 2020 produced 1.5 tons, and in the last year, 2021, chili commodities were able to produce 1.39 tons. In this data, the amount of chili production increases every year, such as in 2020, which reached 1.51 million tons. This amount increased by 9.76% compared to the previous year. Chili plants also get the title as a determinant of national economic growth in Indonesia because the demand for chili in households and industries reaches as much as 61%. The high demand for chili makes the price of chili very fluctuating and is one of the reasons for high inflation rates in Indonesia [1]. Various factors that can cause an increase in chili prices due to a decrease in chili production levels include poor seed quality, worsening soil fertility levels, inadequate chili plant cultivation techniques, and common problems that occur in plants such as pests and diseases [2]. One of the causes of the decline in chili production rates is due to pests and diseases that can cause losses in both the quantity and quality of chili plants. Some diseases that often affect chili production rates in Indonesia are yellowing and curling diseases [2]. If chili harvest production rates decrease in both quality and quantity due to pests and diseases, it will have an impact on the economy. Therefore, early detection of plant diseases is essential in plant maintenance and care. Diseases that are not detected and allowed to develop will result in damage to the plants. This is what can cause a decrease in the quality and quantity of chili harvests, which can affect the country's economy [3]. Based on the problem, a solution is needed to improve the maximum level of chili production. As science advances, innovations have been made to detect plant