Course Information
Instructors
Dr. Mukesh Saini (Email: mukesh@iitrpr.ac.in)Lectures
Tuesday: 3 PMThursday: 12 PM
Labs
TBAContents
This year's course offering will be mostly data analysis and modeling oriented. It will mainly cover basic agriculture data analysis techniques, AI/ML for object detection recognition in agriculture data, segmentation of farm/crop/leaf images, predictive models, crop-yield prediction, finding anomaly in agriculture data, time-series data analysis, remote sensing, hardware platforms/boards, and proximal sensing communication technologies for agriculture CPS.Outcomes
The main objective of this course is to introduce the cyber-physical system applications in the field of agriculture, including sensing, analysis, and control.Prerequisite
Basic programming knowledge.Course Requirements
Students are required to attend two lectures per week and appear in two exams. In addition, there will be lab sessions and projects. The lab assignments will be design and/or implementation-based.Grading Policy
There will be approximately three lab assignments, a mid-sem exam, an end-sem exam, a project, and a seminar. The tentative grade distribution is as follows:Lab assignments: 25%
Project: 35%
Mid-sem exam: 20%
End-sem exam: 20%
A student must score at least 33% marks to pass the course.
Attendance Requirement
In online mode, there is no attendance requirement. In offline mode, the minimum attendance requirement is 75%. Each lecture and lab will count as one unit, irrespective of the contact hours. The students with attendance less than 75% will get an 'F' grade.Code of Ethics & Professional Responsibility
It is expected that students taking this course will demonstrate a keen interest in learning and not merely fulfilling the requirement towards their degree. Discussions that help the student understand a concept or a problem are encouraged. However, each student must turn in original work. Plagiarism/copying of any form will be dealt with strict disciplinary action. This involves copying from the internet, textbooks, and any other material you do not own the copyright. Copying part of the code will be considered plagiarism. Lending the code to others will be considered plagiarism, too, for it is difficult to investigate who copied whose code. Students who violate this policy will directly receive a failing grade in the course. Remember - Your partial submission can fetch you some points, but submitting others' work as your own can result in you failing the course. Please talk to the instructor if you have questions about this policy. All academic integrity issues will be handled in accordance with institute regulations.Textbooks
- Shannon, D. K., Clay, D. E., & Kitchen, N. R. (2020). Precision agriculture basics (Vol. 176). John Wiley & Sons. [Link].
- Song, H., Rawat, D. B., Jeschke, S., & Brecher, C. (Eds.). (2016). Cyber-physical systems: foundations, principles and applications. Morgan Kaufmann. [Link].
Language/Tools
C/C++/Python (Mainly Python)Teaching Assistant
Pratibha Kumari (Email: 2017csz0006@iitrpr.ac.in)Tentative Topics
- Basics of Agriculture Data Analysis: Python basics, Basics of machine learning, Mathematical foundation of neural networks (neural networks as function approximation problem), Deep neural networks for pattern classification (transfer learning, VGG16, Inception), Deep neural networks for pattern recognition (YoLo and RCNN), Deep neural network for image segmentation (UNET, Mask RCNN), Plant phenotyping using Multimedia data, Information fusion methods
- Predictive modelling and Anomaly Detection in Agriculture Data: Anomaly modeling basics, Anomaly detection in non time-series data, Anomaly detection in time-series data, Farm Intrusion detection Univariate predictive models, Deep neural network based prediction modeling, Crop yield prediction.
- Agriculture Data Acquisition (topic coverage may vary depending on time left): Remote sensing, Hardware platforms/boards, Proximal sensing, Communication technologies.
- Case studies: We plan to discuss 2-3 good quality papers on agriculture cyber physical systems.
Lectures and Calendar
Lectures | Week | Topics | Readings | Misc |
---|---|---|---|---|
L1 | 1 | Introduction | ||
L2 | 2 | Introduction to Python | ||
L3 | 2 | Introduction to Machine Learning | ||
L4-5 | 3 | Neural networks as function approximation problem | Guest lecture: Dr. Hanumant Shekhawat | |
L6 | 4 | Stochastic gradient descent | Guest lecture: Dr. Hanumant Shekhawat | |
L7 | 4 | Introduction to object detection in mages | ||
L8-9 | 5 | Introduction to Object detection using YoLo, RCNN; transfer learning | ||
L10-11 | 6 | Introduction to image segmentation | Guest lecture: Dr. Dwarikanath Mahapatra |
*This is a tentative list of topics to be covered during the semester. The topics and schedule can change according to the need at the instructor's discretion.
Project
Project is an extremely important part of this course. The projects can be done individually or in a group of 2 (max). Each project design would contain sensing, communication, analysis, and control. Depending on the scope of the work, we can discuss and reduce the scope of the project in the development phase. Further instructions:
- Each team needs to submit the project proposal around mid-semester. The course instructor may provide the theme of the project. Try to be as creative and wild in solution as much as possible. There are 10% marks just for the creativity or innovativeness of the project.
- There will be multiple weekly evaluations of the project.
- There will be a final design expo where you have to publically demonstrate you product.
Labs
The labs will be mostly about data analysis. You will be asked to implement analysis algorithms and system prototypes for agriculture applications. The initial part of the lab will be guided, followed by an evaluatory component (related to the guided component itself) which the students have to do themselves and submit.