Soil and environment features such as average temperature, average humidity, total rainfall and production yield help in predicting two classes like good yield and bad yield. A hybrid classifier model consisting three phase's viz pre-processing, feature selection and SVM_GWO i.e grey wolf optimizer along with Support Vector machine (SVM) can work for yield prediction.
Dear Gangai Selvi Ramalingam, The Big Data Analytics technology allows for multi-criteria processing and analysis of large data sets in real time for their updating. The key issue is to relate current data to a historical data set and collect current data in real time and its delivery to the Big Data Analytics system. An important issue is also the use of various methods of collecting data, e.g. from satellite monitoring of changes in the condition of agricultural crops in a given area. In addition, selected Internet sources of specific media, including new media, can be an important source of data. Improving the effectiveness of analytics based on Big Data Analytics may also be based on the implementation of other types of Industry 4.0 technologies.
Best regards,
Dariusz Prokopowicz
Soil and environment features such as average temperature, average humidity, total rainfall and production yield help in predicting two classes like good yield and bad yield. A hybrid classifier model consisting three phase's viz pre-processing, feature selection and SVM_GWO i.e grey wolf optimizer along with Support Vector machine (SVM) can work for yield prediction.
1-) Using past data of yields from different areas along with past conditions and predicting based on it using current conditions.
2-) Using currently sensed data from the environment where the crop is grown and comparing against the ideal condition for a good yield. A model can be trained for this purpose.
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Analysis
- Data Analysis
- Dataset
- Big Data