Claim Missing Document
Check
Articles

Found 1 Documents
Search
Journal : JOIV : International Journal on Informatics Visualization

Modified Alexnet Architecture for Classification of Cassava Based on Leaf Images Sholihin, Miftahus; Md Fudzee, Mohd Farhan; Ismail, Mohd Norasri; Wati, Efi Neo; Arshad, Mohamad Syafwan; Gusman, Taufik
JOIV : International Journal on Informatics Visualization Vol 8, No 3 (2024)
Publisher : Society of Visual Informatics

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.62527/joiv.8.3.2966

Abstract

The objective of this study is to address the drawbacks of conventional classification approaches through the implementation of deep learning, specifically a modified AlexNet. The primary aim of this study is to precisely categorize the four distinct varieties of cassava, namely Manggu, Gajah, Beracun, and Kapok. The cassava dataset was obtained from farmers in Lamongan, Indonesia, and was used as a source of information. Data collection on cassava leaves was carried out with agricultural research specialists. A total of 1,400 images are included in the dataset, with 350 images corresponding to each variety of cassava produced. The central focus of this research lies in a comprehensive evaluation of the modified AlexNet architecture's performance compared to the original AlexNet architecture for cassava classification. Multiple scenarios were examined, involving diverse combinations of learning rates and epochs, to thoroughly assess the robustness and adaptability of the proposed approach. Among the evaluation criteria that were rigorously examined were accuracy, recall, F1 score, and precision. These metrics were used to determine the predictive capabilities of the model as well as its potential utilization in the actual world. The results show that the modified AlexNet design has better performance than the original AlexNet for recall, accuracy, precision, and F-1 score, all achieving a rate of 87%. In situations where a learning rate of 0.0001 and an epoch count of 150 are utilized, the performance of the approach stands out significantly, displaying an excellent level of competency. Nevertheless, it is crucial to recognize that distinct fluctuations in performance were noted within particular contexts and with diverse learning rates.
Co-Authors Abdul Kholiq Abdul Kholiq Ahmad Fauzi Hendratmoko Alfarisi, Muhammad Nur Fikri AlMuhibbi, Muhammad Rayendra Anam, M. Khairul Ansori, Yulian Arief Rahman Arief Rahman Arshad, Mohamad Syafwan Asmaraningtyas, Kinanthi Trah Asshiddieqie, Rafi Ramadhan Atia Sonda Aulia Ikhsan Azizah, Luluk Nur AZZA ABIDATIN BETTALIYAH Azza Abidatin Bettaliyah Bagus Nur Bakti Aji Bagus Nur Bakti Aji bin MD. Fudzee, Mohd Farhan Cindy Suryanti Darnis, Febriyanti Delano, M. Fabian Reinhard Dinar Mahdalena Leksana 1 Erna Hayati Erna Hayati, Erna Erry Anggraini ERRY ANGGRAINI Farizki, Achmad Nurasel FATHARANI, ATIKA Fatkhul U, M. Miftah Febriyanti Darnis Firdaus, Muhammad Alvin Fudzee, Mohd Farhan Md Gusman, Taufik Hamid, Rahayu A Ismail, Mohd Norasri Izz, Aiz Ahmad Fa’iz Dliya’ul KIKI SEPTARIA Lilik Anifah M. Ghofar Rohman M. Rosidi Zamroni M. ZAKI QOMARUDDIN Mahuda, Isnaini Masruroh MASRUROH Megawati Indriani Mohd Farhan MD Fudzee, Mohd Farhan Mufrody, Moh Adam Mustain Mustain Nafiiyah, Nur Nur Nafi'iyah Nur Nafi’iyah Nurroziqin, M Chabib Nurul Aswa Omar Nurul Ftria ApriLliani Pertiwi, Dinda Dwi Anugrah Prastowo, Diko Pratiwi, Putri Septiani Indah Prisma Nanda Prsatama, Febrian Abie Rahayu A Hamid Retno Wardhani Rofika Arista Sari, Putri Dina Setia Budi, Agus Sika Azkia, Czidni Siti Mujilahwati Sulaiman, Akhmad Nurali Surojuddin, Eko Titin Nurbella Udiansyah, Naufal Arrafi Ulum, M. Miftah Fatkhul Umam, Moch. Zuhrul Vanesta Ikhsana Putri Maulana Wati, Efi Neo Yulian Ansori Zirby, Qonit Zumrotus Shalekhah