Claim Missing Document
Check
Articles

Found 2 Documents
Search
Journal : Perfecting a Video Game with Game Metrics

Online video-based abnormal detection using highly motion techniques and statistical measures Ahlam Al-Dhamari; Rubita Sudirman; Nasrul Humaimi Mahmood; Nor Hisham Khamis; Azli Yahya
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 17, No 4: August 2019
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v17i4.12753

Abstract

At the essence of video surveillance, there are abnormal detection approaches, which have been proven to be substantially effective in detecting abnormal incidents without prior knowledge about these incidents. Based on the state-of-the-art research, it is evident that there is a trade-off between frame processing time and detection accuracy in abnormal detection approaches. Therefore, the primary challenge is to balance this trade-off suitably by utilizing few, but very descriptive features to fulfill online performance while maintaining a high accuracy rate. In this study, we propose a new framework, which achieves the balancing between detection accuracy and video processing time by employing two efficient motion techniques, specifically, foreground and optical flow energy. Moreover, we use different statistical analysis measures of motion features to get robust inference method to distinguish abnormal behavior incident from normal ones. The performance of this framework has been extensively evaluated in terms of the detection accuracy, the area under the curve (AUC) and frame processing time. Simulation results and comparisons with ten relevant online and non-online frameworks demonstrate that our framework efficiently achieves superior performance to those frameworks, in which it presents high values for he accuracy while attaining simultaneously low values for the processing time.
Incident and reflected two waves correlation with cancellous bone structure Muhamad Amin Abd Wahab; Rubita Sudirman; Mohd Azhar Abdul Razak; Fauzan Khairi Che Harun; Nurul Ashikin Abdul Kadir; Nasrul Humaimi Mahmood
TELKOMNIKA (Telecommunication Computing Electronics and Control) Vol 18, No 4: August 2020
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.12928/telkomnika.v18i4.14828

Abstract

The correlation in bone microstructure for ultrasound pulse echo technique is still less accurate compared to through transmission technique. Previous works demonstrated, reflected two modes wave has significant association with bone porosity. The paper aims is to conduct simulation using pulse echo technique to examine the relationship between fast and slow waves with porosity of 2-dimensional cancellous bone models by comparing the result to through transmission technique. The “incident” and “reflected” waves were separated using bandlimited deconvolution method by estimating time threshold of fast and slow waves' transfer function. The parameters of the waves were computed, plotted versus porosity for six different thicknesses and the correlation coefficients between them were compared. The incident and reflected fast wave attenuations show marginally significant correlation with porosity for both bone models orientations. Wave propagation for parallel orientation dominated by incident and reflected fast wave, meanwhile, perpendicular orientation dominated by incident slow wave. The thickness factor affected wave amplitude but less affected the attenuation. Because of propagation loss, reflected wave shows lower correlation to porosity compared to incident wave. Hence, analyzing fast and slow waves might improve the measurement accuracy of pulse echo technique compared to using single mode wave to estimate bone quality.