Harsawardana, Reza Rahutomo, Bharuno Mahesworo, Tjeng Wawan Cenggoro, Arif Budiarto, Teddy Suparyanto, Don Bosco Surya Atmaja, Bayu Samoedro, Bens Pardamean
Conference: 2019 International Conference on Eco Engineering Development, Surakarta, Indonesia
Indonesia is one of the biggest palm oil exporters in the world. For Indonesia to stay competitive in the palm oil industry, the harvesting and evacuating process in its oil palm plantation need to be optimized. This research introduces machinery called as Smart Crane Grabber. This machinery can be used for automatic harvesting and evacuation process of oil palm fresh fruit bunch from the plantation to the processing mill. To enable automation, Smart Crane Grabber is equipped with an Artificial Intelligence system for automatic ripeness classification. We used 400 images to train our Artificial Intelligence model which were gathered before this study was initiated. Hence, the images were not prepared for Artificial Intelligence. The Artificial Intelligence we developed in this model is a modified ResNet152 which was trained using Stochastic Gradient Descent with the momentum of 0.9. The developed model achieves 71.34% accuracy after 25 epochs of training.
Published at :