A Combination of Transfer Learning and Support Vector Machine for Robust Classification on Small Weed and Potato Datasets

Abstract

Agriculture is the primary sector in Indonesia for meeting people's daily food demands. One of the agricultural commodities that replace rice is potatoes. Potato growth needs to be protected from weeds that compete for nutrients. Spraying using pesticides can cause environmental pollution, affecting cultivated plants. Currently, agricultural technology is being developed using an Artificial Intelligence (AI) approach to classifying crops. The classification process using AI depends on the number of datasets obtained. The number of datasets obtained in this research is not too large, so it requires a particular approach regarding the AI method used. This research aims to use a combination of feature extraction methods with local and deep feature approaches with supervised machine learning to classify of small datasets. The local feature method used in this research is Local Binary Pattern (LBP) and Histogram of Oriented Gradients (HOG), while the deep feature method used is MobileNet and MobileNetV2. The famous Support Vector Machine (SVM) uses the classification method to separate two data classes. The experimental results showed that the local feature HOG method was the fastest in the training process. However, the most accurate result was using the MobileNetV2 deep feature method with an accuracy of 98%. Deep features produced the best accuracy because the feature extraction process went through many neural network layers. This research can provide insight on how to analyze a small number of datasets by combining several strategies

Performance Analysis of Distributed Database Management System for IoT in the Context of Smart Agriculture in Indonesia

“…The agricultural landscape of Indonesia is characterized by a rich diversity of crops, farming practices, and geographical conditions [16], [17], [18], [19]. Traditional farming methods coexist with modern agricultural techniques, creating a unique amalgamation of practices [20].…”

Application of Convolutional Neural Networks in Weed Detection and Identification: A Systematic Review

“…To improve the efficiency of CNNs, transfer learning (TL) techniques are adopted; these techniques take advantage of the knowledge acquired from pre-trained CNNs to improve their performance in new training [13,14]. TL aims to transfer knowledge from the source domain to the target application by improving its learning performance [15]; this is quite useful when the dataset for the target application is small or limited, as the pre-trained model can provide useful representations of the data and speed up the training process.…”