Intelligent LMS for Automated Evaluation of OS Scheduling and Process Management Assignments

Abstract / Introduction
Operating Systems course typically includes assignments on process management and CPU scheduling having diagrams like: Gantt charts, process states, and scheduling algorithms. Manually grading these assignments is time-consuming and subject to human errors. With the advent of artificial intelligence in academia, the proposed system leverages algorithmic analysis and intelligent evaluation techniques to accurately assess submitted assignments. By automating the evaluation of scheduling outputs and process-related logic, it minimizes human error and significantly accelerates the grading process. An Intelligent LMS for Automated Evaluation of OS Scheduling and Process Management Assignments offers a practical solution by analyzing and evaluating submissions with minimal human intervention.

Functional Requirements:
An Intelligent LMS for Automated Evaluation of OS Scheduling and Process Management Assignments is designed to analyze, classify, and evaluate student submissions including: scheduling problems, Gantt charts, process states, and algorithmic solutions. The system will automatically assess correctness of scheduling outputs such as waiting time, turnaround time, and execution order, and provide accurate grading with constructive feedback while minimizing human intervention.

The proposed system will have the following main users: 
Admin, Teacher, and Student
1. Registration module: It will facilitate the registration process for students and teachers. Admin will approve and perform activation of the students and teachers accounts and registration requests.

2. Login Module: After successful registrations, all types of users will be able to login to the system by using their registered email and password. 

3. The application will assist the teacher in scheduling quizzes, assignments, and evaluations related to OS course, specifically focusing on Process Management and CPU Scheduling including topics: FCFS, SJF, Priority Scheduling, and Round Robin algorithms.

4. The system can generate objective and subjective questions of different cognitive levels (Application and Analysis) for the OS course having domains like: Process Management, CPU Scheduling, Process Synchronization, and Performance Evaluation metrics (waiting time, turnaround time, and CPU utilization).

5. Teachers can validate a custom-labelled dataset of existing objective and subjective questions, along with their correct solutions and verifying correct outputs for scheduling problems (e.g., FCFS, SJF, Priority Scheduling, Round Robin) ensuring accuracy of expected results including metrics: waiting time, turnaround time, and execution order.

6. The system aligns assignment grading and evaluation with a predefined rubric focused on Process Management and CPU Scheduling. 

7. The system leverages advanced computer vision and transformer-based models such as YOLOv8, Detectron2, and OpenCV, along with deep learning language models like BERT and RoBERTa, to automatically analyse and evaluate diagram-based numeric and textual solutions. It support detection and assessment of process scheduling representations. 

8. The system can evaluate and interpret different process scheduling representations and convert them into different forms such as process states, scheduling sequences, and Gantt charts. 

9. The system supports mapping between scheduling algorithms (FCFS, SJF, Priority, Round Robin) and their corresponding execution outputs. This enables bidirectional analysis.

10. For evaluating Process Management and CPU Scheduling assignment that include diagrammatic representations such as process state diagrams and Gantt charts. It also supports analyzing execution sequences and scheduling outputs to ensure correctness of applied algorithms.

11. For the Operating Systems course, the system can use advanced code evaluation approaches and AI-assisted models to automatically compile and evaluate programming tasks related to Process Management and CPU Scheduling.

12.The system uses development and evaluation tools like: Python, Flask/Django, OpenCV, TensorFlow/PyTorch, and Scikit-learn to implement and support Process Management and CPU Scheduling assignment evaluation.

13.The system should allow teachers to export grades and performance reports in common formats such as CSV, Excel, and PDF for record-keeping and analysis. These reports include student performance in topics like: Process Management and CPU Scheduling assignments.

14.The system evaluates different Machine Learning (ML)/ Deep Learning (DL) models like YOLO, OpenCV, and BERT for scheduling assignment evaluation and compares their accuracy.

15. For validation purpose, metrics such as MSE, RMSE, MAE, and R² Score are used to measure the accuracy and reliability of different ML/DL models by evaluating Process Management and CPU Scheduling assignments. 

16.The system collects student submissions for Process Management and CPU Scheduling assignments and compares model-predicted grades with instructor-assigned grades. It evaluates performance using MSE, RMSE, MAE, and R² Score to measure grading accuracy.

17.The system allows teachers to set threshold limits for MSE, RMSE, MAE, and R² Score, and triggers alerts for manual review when model performance exceeds these limits.

18.The system provides teachers with detailed question-level analytics, including average score, standard deviation, and difficulty index for Process Management and CPU Scheduling assignments. It also identifies and flags questions with high incorrect response rates to indicate difficulty or ambiguity. This supports deeper analysis and improvement of assessment quality.

19.The system allows teachers to generate detailed performance reports for each question and define custom rubrics for evaluating different types of subjective and diagram-based scheduling problems. This ensures flexible and structured assessment of student work.

20.The system provides a help centre with FAQs and live/chat support to assist students with technical issues and queries related to assignment submission and platform usage.