Printer Friendly

Design and implementation of virtua linvigilation system and smart exam scheduler.


As the assessment in university and schools are increased in great number, the actions of the students taking up these assessments are to be regularly monitored to avoid their indulgence in malpractices. This provides to the challenge of securing the assessment and presents a model of a system that can be used to ensure the integrity of the assessments using movement detection sensors and this may further be extended in a way that it automatically updates the seating arrangement of the same.

With the changes in technology, Education has changed, be it in terms of learning methods, teaching, assessment or invigilation. A major portion of educational content is going online which facilitates more penetration of the material i.e. easy availability, also freedom of choice for the learners as they can choose their time and material of study and can learn on their own pace.

Assessment is an important part of education. It encourages learning, provides feedback to the learner and the instructor, document competency and skill development, allows students to be graded, and allows benchmarks to be established for standards. Assessments can also be done to relatively grade candidates for admission in universities or for jobs. With the advent of e-learning, assessment has moved online too from conventional paper pencil based methods but the process of invigilation is still mostly manual. In cases where manual invigilation is not possible, the use of unfair means is fairly easy thereby denting the very motive of assessment. Invigilation involves both authentication and active or live proctoring. There has been work in both of these fields. Large portions of the work are done on the former i.e. monitoring the candidates for wrong behavior which is a violation of the assessment. "The Virtual Invigilator", an approach that utilizes Intrusion Detection-type functionality to detect possible deviations away from standard procedure. Invigilators also need to ensure the security of the examination hall before, during and after the examination. From the moment the question papers are given out until all answers are collected, exam invigilators should patrol vigilantly. Particular emphasis should be given to multiple-choice and short-answer questions. The main goal should be to prevent possible candidate malpractice and administrative failures.

Proposed System:

The Proposed System is a Virtual Invigilator in real monitoring system where there is no need of Network to find any traffic. Just a Captured video is been processed to find any malpractices in the classroom without a Invigilator by comparing with the stored database using SVM classifier in MATLAB. In Addition to this Smart Exam Scheduler which reduces a Manual work in computing the seating arrangement for the Examination hall and provides efficient work by doing automatically.

The advantages of the proposed system are:

* Large groups can be accessed quickly.

* Saves time and Reduce manual work.

* Computerized marking saves staffs time.

I. Virtual Invigilation System:


The Virtual Invigilation is highly customizable and will allow an invigilator to be easily setup through the invigilator interface with the criteria by which they are to be alerted to suspicious activity. The system has default setups, Additional automatic setups.

Initially the recorded videos of an examination hall should be converted in to frames. These frames will be in RGB which has three components such as Red, Green, and Blue that have all the three components with equal intensity. The RGB frames should be read automatically and converted into grayscale image. All the grayscale image has to be resized in to same size for easy handling. From the resized image, the features such as gradient, angle and magnitude has been extracted by HOG feature. Now using SVM classifier the extracted feature will be compared with the features in database that has been already saved. If the comparison has any variation, then it is considered as abnormal and reports that suspicious activity is detected with an indication of an alarm signal. If comparison show any variation, then it is considered as normal and reported as normal activity.

A. SVM Classifier:

In machine learning, support vector machines (SVMs, also support vector networks) are supervised learning models with associated learning algorithms that analyze data and recognize patterns, used for classification and regression analysis. Given a set of training examples, each marked for belonging to one of two categories, an SVM training algorithm builds a model that assigns new examples into one category or the other, making it a non-probabilistic binary linear classifier. An SVM model is a representation of the examples as points in space, mapped so that the examples of the separate categories are divided by a clear gap that is as wide as possible. New examples are then mapped into that same space and predicted to belong to a category based on which side of the gap they fall on.

Soft margin is an extend SVM to cases in which the data are not linearly separable, we introduce the hinge loss function, This function is zero if the constraint in (1) is satisfied, in other words, if lies on the correct side of the margin. For data on the wrong side of the margin, the function's value is proportional to the distance from the margin. We then wish to minimize. [MATHEMATICAL EXPRESSION NOT REPRODUCIBLE IN ASCII] where the parameter [??] determines the tradeoff between increasing the margin-size and ensuring that the lie on the correct side of the margin. Thus, for sufficiently small values of A, the soft-margin SVM will behave identically to the hard-margin SVM if the input data are linearly classifiable, but will still learn a viable classification rule if not.


B.HOG Feature Extraction:

The histogram of oriented gradients (HOG) is a feature descriptor used in computer vision and image processing for the purpose of object detection. The technique counts occurrences of gradient orientation in localized portions of an image. This method is similar to that of edge orientation histograms, scale invariant feature transform descriptors, and shape contexts, but differs in that it is computed on a dense grid of uniformly spaced cells and uses overlapping local contrast normalization for improves accuracy.

The first step of calculation in many feature detectors is the conversion of RGB to grayscale image. Second step is to calculate gradients in both x-direction and y-direction and Gaussian filter is initialized to remove Gaussian noise present in the image. The angle and magnitude values are found and ensure that redundant pixels are removed.

The normalization is done by both L1-normalization and L2-normalization. Let v be the non-normalized vector containing all histograms in a given block, [[parallel]v[parallel].sup.k] be its k-norm for k=1,2 and e be some small constant. The normalization factor is given as




Exam Scheduler:

Exam Hall Seating Arrangement System is developed for the college to simplify examination hall allotment and seating arrangement.


The main drawback of the current exam scheduling system is that it is manual. The idea behind developing 'Exam Scheduler' is to automate the tedious and lengthy process of scheduling an examination. The implementation is done with the help of MATLAB through a simple logic of getting the students roll no,no .of rows and columns as input which helps us to automatically generate the output easily.

Exam Scheduler enables you to:

* Optimize exam load--our software enables you to spread a student's exam load as evenly as possible across the exam period to given the best chance of performing well.

* Reduce administrative tasks--say goodbye to the arduous task of administering exams. With Exam Scheduler you can lighten the load by allocating seats.

* Reduce costs--Exam Scheduler can reduce the need for hiring external space as the software enables you to maximize the utilization and occupancy of the available space within the institution for exams.

Hardware Implementation:


Just as desktops, laptops also have the same possibilities for connecting to a wide variety of devices, including external displays, mice, cameras, storage devices and keyboards, which may be attached externally through USB ports and other less common ports such as external video.

A universal asynchronous receiver/transmitter, abbreviated UART, is a computer hardware device that translates data between parallel and serial forms. UART takes bytes of data and transmits the individual bits in a sequential fashion. At the destination, a second UART re-assembles the bits into complete bytes. Each UART contains a shift register, which is the fundamental method of conversion between serial and parallel forms

The AT89S52 is a low-power, high-performance CMOS 8-bit microcontroller with 8K bytes of in-system programmable Flash memory.

A buzzer or beeper (BUZZERS)is a signaling device, usually electronic, typically used in automobiles, household appliances such as a microwave oven, or game shows.

In the laptop, the video input is converted in to frames, from these frames required features are extracted and compared with the trained frames in the database using svm classifier. The result of the comparison is given to UART, this UART serially transmit the data in bit-by-bit to the microcontroller and the data will be displayed in the LCD display and Buzzer will on based on the result.


Output Of Virtual Invigilation:

The selected input video in converted into frames. When the conversion is completed, a popup message says "Frame separation is completed".


2. Frames are selected and comparison is done

2.a. If variation is found, then it reports suspicious activity is found.

i. Simulation output:


ii. Hardware output:

The hardware displays the normal activity by the alphabet 'A'


'A'=Normal Acitivity

2.b If variation is not found, then it reports normal activity and no suspicious activity is detected.

i. Simulation output:


ii. Hardware output:

The hardware displays the suspicious activity as 'malpractices'


Output Of Exam Scheduler:

1. The input of exam scheduler

enter total no of ece students24

enter total no of mech students24

enter ece roll no201202122

enter mech roll no201201010

enter the no of rows 6

enter the no of columns7

2. The output of exam scheduler

DATE:                                   SESSION:

201202122 201201013 201202129 201201020 201202136 201201026
201201010 201202126 201201017 201202133 201201024 201202140
201202123 201201014 201202130 201201021 201202137 201201026
201201011 201202127 201201018 201202134 201201024 201202141
201202124 201201015 201202131 201201022 201202138 201201027
201201012 201202128 201201019 201202135 201201025 201202142
201202125 201201016 201202132 201201023 201202139 201201028

Conclusion and Future Work:

Thus the malpractice and automatic exam scheduler has been done with the help of a MATLAB and simple hardware connections. The future work is to do it for live streaming video with the help of open CV. As our project is a proof of concept for our future work. This Project can also be adopted for detecting any Suspicious event from CCTV camera footage. This should be Helpful in solving Criminal cases.


[1.] Percival, N., J. Percival, C. Martins, 2008. The Virtual Invigilator: A Network-based Security System for Technology-Enhanced Assessments. In Proceedings of the World Congress on Engineering and Computer Science, San Francisco, USA, 22-24.

[2.] Clarke, N.L., P. Dowland S.M. Furnell. e-Invigilator, 2013. A Biometric-Based Supervision System for eAssessments. International Conference on Information Society (i-Society), International Journal of Computer Applications (0975-8887) Volume 90--No 17, March 2014 31

[3.] Yuan, C., Q. Yang, 2010. The Scheme of SIP-based Video Surveillance System. Second International Workshop on Education Technology and Computer Science, 3: 268-271.

[4.] Prof. S.S., Aravinth1, G. Pavithra2, M. Myvizhimalar3, D. Divya4, M. Rathinakrithika5, Exam Hall Seating Arrangement System Using PHP.INTERNATIONAL JOURNAL OF INNOVATIVE RESEARCH IN TECHNOLOGY 258.2014 IJIRT | Volume 1 Issue 11 | ISSN: 2349-6002.

[5.] Kanade, T., J. Cohn and Y. Tian, 2000. "Comprehensive database for facial expression analysis." In Proc.IEEE Int.Conf.Face and Gesture Recognition, 46-53.

[6.] Fasel, B. and J. Luettin, 2003. "Automatic facial expression analysis: A survey," Pattern Recognit., 36(1): 259-275

[7.] Vaibhav Ahlawat,Ahirnish Pareek, S.K. Singh, Ph. D., 2014. Online Invigilation: A Holistic Approach: Process for Automated Online Invigilation. International Journal of Computer Applications (0975--8887),90 --No 17

[8.] MathWorks website [Online]. Avaliable:

R. Meena, T. Sujeetha Devi, R. Vinodhini, R. Vishwam and H. Yamini Priya

Department of Electronics and Communication, Rajalakshmi Engineering College Thandalam, Chennai-602 1 05, India

Received 25 April 2016; Accepted 28 May 2016; Available 5 June 2016

Address For Correspondence: R. Meena, Department of Electronics and Communication, Rajalakshmi Engineering College Thandalam, Chennai-602 105, India

COPYRIGHT 2016 American-Eurasian Network for Scientific Information
No portion of this article can be reproduced without the express written permission from the copyright holder.
Copyright 2016 Gale, Cengage Learning. All rights reserved.

Article Details
Printer friendly Cite/link Email Feedback
Author:Meena, R.; Devi, T. Sujeetha; Vinodhini, R.; Vishwam, R.; Priya, H. Yamini
Publication:Advances in Natural and Applied Sciences
Date:Jun 15, 2016
Previous Article:Transform based speech enhancement using firefly algorithm.
Next Article:Segmentation of images applying with level set regularised method and intensity inhomogenity correction.

Terms of use | Privacy policy | Copyright © 2018 Farlex, Inc. | Feedback | For webmasters