Page 24 - Preliminary Analysis Towards a Standardized Readiness Framework - Interim Report

Preliminary Analysis Towards a Standardized Readiness Framework

values from the Malaysian Meteorological Department (METMalaysia) are significant in this use
case. GWL is predicted and FDRS indices such as DC, Duff Moisture Code (DMC), and FWI are
predicted based on the GWL. Gateways such as weather stations, water level sensors, and soil
sensors in combination with LoRa nodes and LoRa Gateways make it an end-to-end solution.

4�1�7 Disease Identification in Wheat Crops

This use case [38] uses multiple drones and High-definition cameras to obtain high-quality
pictures to identify wheat crops and detect disease. To ensure the coverage surface and the
quality of image content, cameras are deployed 30-50 centimeters (about half the length
of a baseball bat) away from the crops without any objects or humans being captured. In
addition, because some diseases can be detected only at a certain growing stage, images are
captured during all growing periods, ensuring a high frequency. Regulations related to the
drones regarding height and geo-restrictions, however, should be noted. The use case used
convolutional block attention mechanism (CBAM) as the model and applied IoT gateway.

4�1�8 Smart Shrimp Farm Aquaculture

This use case [39] applied cameras with night vision and sensors with underwater capabilities
to capture shrimps and other water parameters such as pH value, turbidity, and oxygen
concentration. Since the images are captured underwater, pre-processing tools such as
robotflow [55] are used to enhance the quality. A special model YOLO is deployed for unique
object counting. In addition, to predict the length of the shrimps, ArUco marker [54] is used for
measurements. This use case referred to available standards such as BAP 1000, ASC shrimp
standard, Global GAP Aquaculture standards, ISO 9001: 2015, and ISO 22000: 2018.

4�1�9 Soil Moisture Testing

This use case [40] used soil sensors with a limited measurement range to detect soil parameters
and water usage. The data collected undergoes the process of conversion with the protocol
of Message Queuing Telemetry Transport (MQTT) [56], quantization/aggregation/range-
checking, network, and model, and finally reaches users. Random Forest (RF) and Multivariate
Adaptive Regression Splines (MARS) as classification models are applied. Transmission Control
Protocol/Internet Protocol (TCP/IP) with error handling capabilities are used. The analysis is
achieved using edge data, edge board and sensors, and edge storage. Given that the sensors
and facilities are deployed outside, ruggedness is considered under the standard of IP65. The
edge data processing board is open-sourced.

4�1�10 IoT-based Crop Monitoring
In this use case [31], edge data such as pH value, Nitrogen, Phosphorus, Potassium (NPK) levels,
electric conductivity of the soil, weather parameters, and leaf wetness are captured. Sensors
use solar panels to harvest energy. By combining the data, it is possible to not only manage
pests and diseases but also plan pesticide usage and irrigation schedules.

4�1�11 Platooning

This use case involves autonomous or remote-driven vehicles such as enterprise vehicles, in-
campus vehicles, carts, and mover trucks in stores, factories, or maritime ports. To control the

16