Examinations or assessments play a vital role in every student’s life; they determine their future and career paths. The COVID pandemic has left adverse impacts in all areas, including the academic field. The regularized classroom learning and face-to-face real-time examinations were not feasible to avoid widespread infection and ensure safety. During these desperate times, technological advancements stepped in to aid students in continuing their education without any academic breaks. Machine learning is a key to this digital transformation of schools or colleges from real-time to online mode. Online learning and examination during lockdown were made possible by Machine learning methods. In this article, a systematic review of the role of Machine learning in Lockdown Exam Management Systems was conducted by evaluating 135 studies over the last five years. The significance of Machine learning in the entire exam cycle from pre-exam preparation, conduction of examination, and evaluation were studied and discussed. The unsupervised or supervised Machine learning algorithms were identified and categorized in each process. The primary aspects of examinations, such as authentication, scheduling, proctoring, and cheat or fraud detection, are investigated in detail with Machine learning perspectives. The main attributes, such as prediction of at-risk students, adaptive learning, and monitoring of students, are integrated for more understanding of the role of machine learning in exam preparation, followed by its management of the post-examination process. Finally, this review concludes with issues and challenges that machine learning imposes on the examination system, and these issues are discussed with solutions.

A systematic review on machine learning models for online learning and examination systems

Real-time live detection of fruits and vegetables is the most important task to know the availability of the current stock of fruits and vegetables that the customers looking for in the vegetable market. For this problem, a new technique based on Deep learning and IoT is required. The proposed work has applied the YOLO model for identifying different types of vegetables and fruits available in the vegetable market and hence the customer can know the updates the livestock of fruits and vegetables in that shop. The images of commonly used fruits and vegetables in India are collected from Google and also from Kaggle. The collected images are labeled using the Roboflow framework. To implement the proposed model, YOLOv4 -tiny model is chosen which is a super-fast object detector with better accuracy and is also most suitable for embedded devices. Further, this tiny model performs fast prediction in real-time video processing scenarios. The result of the proposed system is evaluated using the metric mean Average Precision (mAP). A high-value of mAP indicates that the model performs better is in its detection. Our YOLOv4-tiny model produced an mAP value of 51&#x0025; with an inference time of 18 milliseconds. 

Fruits and Vegetables Recognition using YOLO

The stock market refers to the buying, selling, and issuance of shares of publicly held companies. Stock market prediction is for good and successful investment. Some people think stock market prediction is impossible to predict future stock values and it involves risks it may face huge losses. To address these, a machine learning model-based stock market prediction using K Nearest Neighbor (KNN) algorithm is proposed. For predicting next day change in the stock value, KNN is very powerful in numeric prediction problems because it can process relation between the numeric data. By utilizing these algorithms in stock market prediction our proposed results with experimental results show that a higher accuracy of 70%. 

Stock Movement Prediction using KNN Machine Learning Algorithm

Cauvery delta zone in Tamilnadu is called as “Nerkazhanchiyam” (the land of Paddy) of the state, as it has the potential to produce paddy in huge quantity that can be suffice the need of the state. This zone includes the districts such as Thanjavur, Tiruvarur, Nagapattinam, Trichy and Cuddalore. These districts account for about 53% of production of paddy in the state. Increasing the production of paddy in Cauvery Delta Zone would satisfy the requirement of rice in the state on the whole. This will also have a substantial influence on both the farmer's and the nation's economy. Forecasting the production of crops beforehand could assist the farmers in improving their productivity. This necessitates the design of a precise crop yield prediction model. Crop production in agriculture is primarily determined by a variety of factors that falls under three categories: technological (agricultural techniques, managerial decisions, etc.), biological (diseases, insects, pests, etc.), and environmental (climate change, etc.). Among these factors environmental factors pose a great challenge to the decision makers in developing a precise prediction model. Hence, it is proposed to develop a suitable yield prediction model to predict the yield of paddy in Cauvery delta region considering the environmental factors along with the supplied nutrients. The proposed prediction model makes use of Long Short Term Memory (LSTM) algorithm which is a popular deep learning algorithm, to forecast the yield of paddy. LSTM is well known for its better prediction using time series data. Performance of the proposed prediction model is measured using the training loss and validation loss. 

A Time-Series Based Yield Forecasting Model Using Stacked Lstm To Predict The Yield Of Paddy In Cauvery Delta Zone In Tamilnadu

In recent days, Image classification and detection technique has become an important and more essential in the Image processing research field. Creating effective face detection is an essential aspect of handling the detection mechanism, Tracking mechanism and Validation mechanism. The classical methods used for face detection do not have sufficient output. This research paper presents various studies and how machine learning methods are become to solve many challenges present in the face detection system. The first phase of work has a classification model with support vector machines, decision trees and Hybrid Ensemble Transfer learning algorithm. The second phase of work is investigated with real-the world’s most popular dataset from World Masked Face Image Dataset and Label Faces in the wild (RMFD). Moreover, the experiment, results show how better accuracy and fast computation which has been achieved by Hybrid Ensemble algorithm with SVM and Decision Trees machine learning techniques. This research helps to assist many social applications such as during pandemics like covid-19 and personal identity, it can be verifying the mask-worn persons.

A Novel Real-time Automated Face Classification and Detection system using Machine Learning Technique

Today's pandemic situation has transformed the way of educating a student. Education is undertaken remotely through online platforms. In addition to the way the online course contents and online teaching, it has also changed the way of assessments. In online education, monitoring the attendance of the students is very important as the presence of students is part of a good assessment for teaching and learning. Educational institutions have adopting online examination portals for the assessments of the students. These portals make use of face recognition techniques to monitor the activities of the students and identify the malpractice done by them. This is done by capturing the students' activities through a web camera and analyzing their gestures and postures. Image processing algorithms are widely used in the literature to perform face recognition. Despite the progress made to improve the performance of face detection systems, there are issues such as variations in human facial appearance like varying lighting condition, noise in face images, scale, pose etc., that blocks the progress to reach human level accuracy. The aim of this study is to increase the accuracy of the existing face recognition systems by making use of SVM and Eigenface algorithms. In this project, an approach similar to Eigenface is used for extracting facial features through facial vectors and the datasets are trained using Support Vector Machine (SVM) algorithm to perform face classification and detection. This ensures that the face recognition can be faster and be used for online exam monitoring.

S. Hariprasath

Papers

Design of face detection and recognition system to monitor students during online examinations using Machine Learning algorithms