Pertanika J. Sci. & Technol. 30 (2): 1219 - 1236 (2022) ISSN: 0128-7680 e-ISSN: 2231-8526 Journal homepage: http://www.pertanika.upm.edu.my/ © Universiti Putra Malaysia Press SCIENCE & TECHNOLOGY Article history: Received: 22 August 2021 Accepted: 21 December 2021 Published: 14 March 2022 ARTICLE INFO DOI: https://doi.org/10.47836/pjst.30.2.20 E-mail addresses: zulhakimwahed@gmail.com (Zulhakim Wahed) jannie@unimas.my (Annie Joseph) zhushair@unimas.my (Hushairi Zen) kkuryati@unimas.my (Kuryati Kipli) * Corresponding author Sago Palm Detection and its Maturity Identifcation Based on Improved Convolution Neural Network Zulhakim Wahed 1,2 *, Annie Joseph 1 , Hushairi Zen 1 and Kuryati Kipli 1 1 Department of Electrical and Electronics Engineering, Faculty of Engineering, Universiti Malaysia Sarawak, 94300 UNIMAS, Kota Samarahan, Sarawak, Malaysia 2 CRAUN Research Sdn Bhd, 93050, Kuching, Sarawak, Malaysia ABSTRACT Sago palms are mainly cultivated in Sarawak, especially in the Mukah and Betong division, for consumption and export purposes. The starches produced from the sago are mostly for food products such as noodles, traditional food such as tebaloi, and animal feeds. Nowadays, the sago palm and its maturity detection are done manually, and it is crucial to ensure the productivity of starch. The existing detection methods are very laborious and time-consuming since the plantation areas are vast. The improved CNN model has been developed in this paper to detect the maturity of the sago palm. The detection is done by using drone photos based on the shape of the sago palm canopy. The model is developed by combining the architecture of three existing CNN models, AlexNet, Xception, and ResNet. The proposed model, CraunNet, gives 85.7% accuracy with 11 minutes of learning time based on fve-fold-validation. Meanwhile, the training time of the CraunNet is almost two times faster than the existing models, ResNet and Xception. It shows that the computation cost in the CraunNet is much faster than the established model. Keywords: Convolution neural network (CNN), deep learning, sago palm INTRODUCTION Sago (Metroxylon sagu) is an excellent crop for sustainable agriculture, shown in Figure 1. It can grow in underutilised wetlands and peat bogs where other food crops cannot grow economically. It produces high-yield edible starch (about 150–300 kg dry starch per plant). Diferent parts of palm trees can be used as roofng materials, animal feed,