Author

Tazeen Fatima

Degree

Master of Science in Computer Science

Faculty / School

Faculty of Computer Sciences (FCS)

Department

Department of Computer Science

Date of Submission

2020-12-15

Advisor

Dr. Tariq Mahmood Associate, Professor, Faculty of Computer Science, Institute of Business Administration (IBA), Karachi

Project Type

MSCS Survey Report

Abstract

Smart agriculture is an emerging domain which makes use of IoT to monitor the crops, create alerts for pests, use enhances ways to irrigate and increase productivity. It helps owners to analyze the fields considering multiple factors such as; weather, light, temperature etc. A dashboard keeps track of time for irrigation, fertilization and monitor continuous growth of crops. Hence, this survey presents the frameworks and their evaluations contributed by others. The survey implements SLR methodology to filter the research articles and extract knowledge from them. Lastly it provides the findings and categories the contributions among four semi-supervised approaches.

Notes

The survey presents the contributions made for semi-supervised learning in smart agriculture. It implements SLR methodology to filter the articles and provide their details. According to the findings the articles are grouped among the semi-supervised categories. As a result, it is evident that more work is implemented using convolutional networks which are a deep learning technique. Also, pseudo labeling as a part of heuristic approach and generative semi-supervised approach are widely applied in the articles.

In future, the common frameworks can be combined to attain accurate results. They can be implemented on datasets to evaluate their performance. Different solutions learned with supervised, unsupervised and semi-supervised approaches can be compared to predict an optimal result.

The full text of this document is only accessible to authorized users.

Share

COinS