Table 17 Comparison among related systems with our developed scheme.
From: An AI-powered smart Agribot for detecting locusts in farmlands using IoT and deep learning
Referenced papers | Methodology | Deep/machine learning (yes/no) | Highest accuracy | IoT based system (yes/no) | Robot development (Yes/No) | Remarks |
|---|---|---|---|---|---|---|
9 | Machine learning approaches utilized in insect detection | Yes | 45% | No | No | Partially matched with our developed scheme |
10 | IoT-based technology has been established to detect and monitor insects. | No | N/A | Yes | No | Partially matched with our developed scheme |
11 | Machine learning approaches used to detect and analyze mosquitoes | Yes | 99.9% | No | No | Partially matched with our developed scheme |
13 | A machine learning model has been adopted to classify locusts. | Yes | 97.80% | No | No | Partially matched with our developed scheme |
14 | Developed a robot to water the plant automatically | No | N/A | No | Yes | Partially matched with our developed scheme |
15 | Agribot has been developed for seed sowing with IoT-based technology. | No | N/A | Yes | Yes | Overwhelmingly matched with our developed scheme |
17 | Machine learning techniques adopted to detect and predict insects | Yes | 98.60% | No | No | Partially matched with our developed scheme |
Our developed system | Developed Agribot using IoT and Machine learning to detect and analyze locust | Yes | Yes | Yes | The combination of three fields |
