International Journal of Emerging Technology and Advanced Engineering Website: www.ijetae.com (E-ISSN 2250-2459, Scopus Indexed, ISO 9001:2008 Certified Journal, Volume 12, Issue 02, February 2022) Manuscript Received: 04 January 2022, Received in Revised form: 02 February 2022, Accepted: 05 February 2022 DOI: 10.46338/ijetae0222_07 55 Comparative Performance Analysis of Real-Time Methods for Cassava Phytoplasma Disease (CPD) Detection based on Deep Learning Neural Networks Irma T. Plata 1 , Edward B. Panganiban 2 , Darios B. Alado 3 , Allan C. Taracatac 4 , Bryan B. Bartolome 5 , Freddie Rick E. Labuanan 6 1,2,3,4,5,6 CCSICT, Isabela State University, San Fabian, Echague, Isabela, Philippines Abstract - Cassava Phytoplasma Disease (CPD) is a crop disease that reduces cassava output and quality. As a result, detection is essential in precision agriculture. On the greater area of the cassava field, manual identification of CPD illnesses takes more time and effort. Convolutional Neural Networks (CNN), a deep learning method, may be used to detect illnesses on leaves and other sections of cassava plants with greater accuracy. The approaches utilized in this study assisted in the identification of CPD by completing customized training/fine-tuning on three CNN models for object recognition: Faster R-CNN, SSD Mobilenet v2, and YOLO v4. The Faster R-CNN inception v2 has a 95 percent training accuracy, SSD Mobilenet v2 has a 73 percent training accuracy, and YOLOv4 has an 85 percent training accuracy, according to the data. Finally, the study found that the YOLOv4 outperforms the Faster R-CNN inception v2 and SSD MobileNet v2 in terms of image computing capacity. However, Faster R-CNN inception v2 performs the best compared to the two other models in terms of accuracy. Hence, these two models can be used depending on the purpose of CPD detection. However, since CPD detection is the main purpose of this study, the Faster R-CNN model is recommended for adoption to detect CPD in a real-time environment. Keywords — cassava phytoplasma disease, convolutional neural networks, faster R-CNN, image processing, precision agriculture. I. INTRODUCTION In the field of computer vision, object detection has been facing a fast revolution. Its involvement in both object categorization and object location makes it one of the most difficult applications in the computer vision area. To put it another way, this detection approach seeks to figure out where items are in a given image and which category they belong to. In this study, the object classification was involved in detecting the presence of phytoplasma diseases in cassava farms located in San Guillermo, Isabela, which was chosen as the testing site. However, it is necessary to research which real-time object detection technology will be employed and which new and inventive strategies will be used in the process. As a result, some strategies for improving object detection performance have been presented. For context, the convolutional neural network (CNN) is an effective deep learning model that incorporates hierarchical learning features. According to research, CNN- extracted features have a higher discriminating and generalization capacity than hand-crafted features [1]. CNN has had a lot of success in the field of computer vision. Furthermore, deep learning may produce greater precision and reduce test time [2]. Crop diseases like the cassava Phytoplasma diseases (CPD) play a key role in reducing cassava production and quality. Therefore, detection is fundamental in precision agriculture tasks. Manual detection of phytoplasma diseases takes additional time and effort on the larger area of the cassava farm. A deep learning approach like the CNN can be used to detect diseases more accurately on leaves and other parts of the cassava plants. The study's general objective is to analyze real-time methods for CPD detection through comparative performance analysis. The involved methods in this study helped detect CPD diseases. In the process, it performs three CNN models for object detection comprising Faster R-CNN, SSD Mobilenet v2, and the YOLO v4.