Kian-Yong Ng

Learn More
In this paper, we proposed an automated system to perform a live memory forensic analysis for mobile phones. We investigated the dynamic behavior of the mobile phone’s volatile memory, and the analysis is useful in real-time evidence acquisition analysis of communication based applications. Different communication scenarios with varying parameters were(More)
Automated noninvasive blood pressure (NIBP) monitors, or automated sphygmomanometers, have been increasingly used both inside and outside clinical environments. An extensive survey of such monitors was carried out over the past five years. This survey covers a broad spectrum of monitors including ambulatory monitors, bedside and transport monitors,(More)
Oscillometric blood pressures are derived from the amplitude envelope of oscillometric pulses generated in an occlusive cuff during cuff inflation or deflation; one factor which will affect the characteristics of these pulses is the size of the cuff bladder. Because limiting values are stipulated in recommendations and standards for bladder sizes, there is(More)
Automated noninvasive blood pressure (NIBP) monitors have found widespread use both inside and outside clinical environments in recent years. Present methods for evaluating the measurement accuracy of this class of devices involve population studies that are meticulous, time-consuming and costly. These methods are also impractical for routine evaluation.(More)
The development of methods and simulators for evaluating noninvasive blood pressure (NIBP) monitors has been dynamic during the past few years. As a complement to a previous review paper in this journal, several additional developments are reported in this paper. These include evaluation methods developed in Australia, the United States and Europe, as well(More)
Noninvasive blood pressure (NIBP) is one of the most common vital signs monitored by today's bedside and transport monitors. A variety of NIBP measurement methods has been used in these monitors. Some of the methods provide intermittent measurements over a period of time, while others provide continuous measurement on a beat-to-beat basis. Most of the(More)
In this paper, a baseline phoneme recognition system for Kannada language is built using MFCC and Deep Belief Networks (DBNs). Phonemes are segmented from continuous Kannada speech and MFCC features are extracted from each speech frame. These features are further used as input to the recognizer. DBNs are probabilistic generative model which are constructed(More)
  • 1