Discovering the Ganoderma Boninense Detection Methods Using Machine Learning: A Review of Manual, Laboratory, and Remote Approaches

Abstract

Ganoderma disease is a kind of infection that actuates oil palm death. Early detection of Ganoderma disease is the most recommended strategy for proper treatment and disease control plan to be taken promptly. In this paper, the detection methods for Ganoderma disease were reviewed and categorized accordingly. It was found that the combination of remote sensors and machine learning techniques could identify the disease up to four severity levels, including the early stage of infection. It also significantly reduced the labor and time costs compared to the traditional visual inspection and lab-based approaches. In terms of machine learning, support vector machine (SVM) using the idea of finding a hyperplane was suggested as the best classifier in several studies. Despite only one research was done on ANN and no research evaluating CNN and GAN in Ganoderma disease detection; ANN, CNN and GAN were recognized as the potential machine learning techniques that could enhance the detection system.INDEX TERMS Basal stem rot, Ganoderma, machine learning, oil palm, remote sensors.

Classification of basal stem rot using deep learning: a review of digital data collection and palm disease classification methods

“…Before the introduction of technology, the manual method was often the only method to detect BSR infection ( Tee et al, 2021 ). The manual detection method is still done today, primarily by having workers perform BSR inspection visually based on the external symptoms that are visible.…”

“…This manual method is also heavily dependent on manpower, which is prone to human error ( Tee et al, 2021 ). Alam, Er & Begum (2015) also mentioned a labor shortage problem that can worsen the rate of BSR detection.…”

“…Lab based methods were extensively reviewed by Tee et al (2021) . Three methods were discussed by the authors, which are ganoderma selection medium (GSM), polymerase chain reaction (PCR) and enzyme-linked immunosorbent assay polyclonal antibodies (ELISA-PABS) ( Tee et al, 2021 ).…”

“…GSM is not a recommended method for commercial scale use as one of the reagents, pentachloronitrobenzene (PNCB), is considered hazardous and toxic in certain countries, such as the United States and Indonesia. There were also concerns over the accuracy of GSM ( Tee et al, 2021 ).…”

Smart Irrigation for Crop Management Using IoT

“…This paper also focuses on finding the correlation between different weather conditions and the accuracy of forecasts. paper [8] provides research on artificial neural network (ANN) that contains multiple layers and back-propagation to enable computer literacy in determining the indirect combination. A convolutional neural network (CNN) is generally regarded as an improved version of ANN called a deep learning neural network.…”