An echo-based autonomous real-time system for efficient maintenance of students attendance. (5th September 2022)

• Record Type: Journal Article
• Authors: Jamulkar, Shritesh; Verma, Milind Kumar; Naik, K. Jairam
• Is Part Of: International journal of intelligent information and database systems. Volume 15:Number 4(2022)
• Page Start: 353
• Page End: 376
• Publication Date: 2022-09-05
• Subjects: automatic attendance -- time to record attendance -- data over sound -- DoS -- mean attendance -- cloud database -- reliability -- re-transmission time; Database management -- Computer programs -- Periodicals; Information retrieval -- Computer programs -- Periodicals; Information storage and retrieval systems -- Computer programs -- Periodicals; Artificial intelligence -- Periodicals; Expert systems (Computer science) -- Periodicals; Intelligent agents (Computer software) -- Periodicals; 006.33
• Languages: English
• ISSNs: 1751-5858

Abstract

The conventional method of taking attendance by calling names or signing is a very tedious and insecure process with loopholes, like missing records, paper consumption, etc. To overcome such difficulties, an echo-based attendance system is proposed in this paper, which provides an effective and efficient way of recording and maintaining the attendance of students on a daily basis. The attendance is recorded for an echo-receiving device (microphone) from an echo-sending device (speaker) and all the records are saved in a real-time cloud database. Data is encoded in unique frequency at the transmitter's end and sent over sound, which is then decoded at the receiver's end and attendance is marked in the database. The process is one-shot, where each receiver's attendance is marked simultaneously, unlike the existing autonomous attendance systems. The proposed system uses liquid software-defined radio digital signal processing (DSR) to transmit data from the transmitter's end and to process received data at the receiver's end. This abolishes capturing the specimen of students (like fingerprints, facial images), required for the dataset to train the model in case of other autonomous attendance systems and hence, saves time and effort by completely eliminating human intervention and ensures high reliability as well.