Othman O. Khalifa, Othman O.
Department of Electrical and Computer Engineering, International Islamic University Malaysia

Published : 2 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 2 Documents
Search

Improved voice quality with the combination of transport layer & audio codec for wireless devices Khalifa, Othman O.; Roslin, Raihan Jannati Binti; Bhuiyan, Sharif Shah Newaj
Bulletin of Electrical Engineering and Informatics Vol 8, No 2: June 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v8i2.1490

Abstract

Improving voice quality over wireless communication becomes a demanding feature for social media apps like facebook, whatsapp and other communication channels. Voice-over-internet protocol (VoIP) helps us to make quick telephone calls over the internet. It includes various mechanism which are signaling, controlling and transport layer. Over wireless links, packet loss and high transmission delay damage voice quality. Here VoIP quality will be measured by three main elements which are signaling protocol, audio codec and transport layer. To improve the overall voice quality, we need to combine these three elements properly to get the best score. Otherwise perceptual speech quality will not be the right tool to measure the voice quality. Here we will use Mean Opinion Score (MOS) for calculated jitter values and end to end delay. At the end, best combination of audio codec & signaling protocol produced the quality speech.
Principal component analysis for human gait recognition system Khalifa, Othman O.; Jawed, Bilal; Bhuiyn, Sharif Shah Newaj
Bulletin of Electrical Engineering and Informatics Vol 8, No 2: June 2019
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/eei.v8i2.1493

Abstract

This paper represents a method for Human Recognition system usingĀ  Principal Component Analysis. Human Gait recognition works on the gait of walking subjects to identify people without them knowing or without their permission. The initial step in this kind of system is to generate silhouette frames of walking human. A number of features couldb be exytacted from these frames such as centriod ratio, heifht, width and orientation. The Principal Component Analysis (PCA) is used for the extracted features to condense the information and produces the main components that can represent the gait sequences for each waiking human. In the testing phase, the generated gait sequences are recognized by using a minimum distance classifier based on eluclidean distance matched with the one that already exist in the database used to identify walking subject.