Design of Livestream Video System and Classification of Rice Disease

Abstract

One of the agricultural products which is an important aspect of the life of Indonesian people is rice. Rice disease has a devastating effect on rice production, while detecting rice diseases in real-time is still difficult. Therefore, this study designed a Livestream video system that is equipped with a rice disease Classification system. The Livestream system utilizes 4G network communication and is assisted by the WebSocket protocol to communicate in real-time and for the rice disease Classification system using YOLO algorithm. In addition, Livestream uses the raspberry pi camera V2 to take video stream data. In analyzing the performance of the Livestream system, four tests were carried out, namely: functionality test, connectivity test, classification performance test, and implementation performance test. The test was carried out using the wireshark and conky tools, while the classification training used 5447 images from the Huy Minh do dataset that he provided on the Kaggle website. The results show that all programs run well and get a good QoS value according to the index of the parameter results, it is also found that sending non-base64 can reduce the size of the data to approximately 200,000 bytes/s and the performance of the classification system is good because it has an average accuracy of 80% even though it is quite burdening the raspberry pi. This system can still be optimized and developed further to support research in the field of data transmission and the performance of machine learning in a microcontroller.

Whale Optimization based Deep Residual Learning Network for Early Rice Disease Prediction in IoT

“…This research by Lu, Y., et al [15] proposes a unique approach to disease detection in rice by using network (CNN) methods. 500 images of damaged and healthy rice leaves and stems from an experimental rice field are used to teach CNNs to recognize 10 common rice illnesses.…”