Emmanuel C. Ifeachor

Voice quality prediction models and their application in VoIP networks

The primary aim of this paper is to present new models for objective, nonintrusive, prediction of voice quality for IP networks and to illustrate their application to voice quality monitoring and playout buffer control in VoIP networks. The contributions of the paper are threefold. First, we present a new methodology for developing perceptually accurate models for nonintrusive prediction of voice quality which avoids time-consuming subjective tests. The methodology is generic and as such it has wide applicability in multimedia applications. Second, based on the new methodology, we present efficient regression models for predicting conversational voice quality nonintrusively for four modern codecs (G.729, G.723.1, AMR and iLBC). Third, we illustrate the usefulness of the models in two main applications - voice quality prediction for real Internet VoIP traces and perceived quality-driven playout buffer optimization. For voice quality prediction, the results show that the models have accuracy close to the combined ITU PESQ/E-model method using real Internet traces (correlation coefficient over 0.98). For playout buffer optimization, the proposed buffer algorithm provides an optimum voice quality when compared to five other buffer algorithms for all the traces considered

A multicentre comparative study of 17 experts and an intelligent computer system for managing labour using the cardiotocogram

Objectives To investigate 1. whether an intelligent computer system could obtain a performance in labour management comparable with experts when using cardiotocograms (CTGs), patient information, and fetal blood sampling and 2. whether experts could be consistent and agree in their management of labour.

QoE Prediction Model and its Application in Video Quality Adaptation Over UMTS Networks

The primary aim of this paper is to present a new content-based, non-intrusive quality of experience (QoE) prediction model for low bitrate and resolution (QCIF) H.264 encoded videos and to illustrate its application in video quality adaptation over Universal Mobile Telecommunication Systems (UMTS) networks. The success of video applications over UMTS networks very much depends on meeting the QoE requirements of users. Thus, it is highly desirable to be able to predict and, if appropriate, to control video quality to meet such QoE requirements. Video quality is affected by distortions caused both by the encoder and the UMTS access network. The impact of these distortions is content dependent, but this feature is not widely used in non-intrusive video quality prediction models. In the new model, we chose four key parameters that can impact video quality and hence the QoE-content type, sender bitrate, block error rate and mean burst length. The video quality was predicted in terms of the mean opinion score (MOS). Subjective quality tests were carried out to develop and evaluate the model. The performance of the model was evaluated with unseen dataset with good prediction accuracy ( ~ 93%). The model also performed well with the LIVE database which was recently made available to the research community. We illustrate the application of the new model in a novel QoE-driven adaptation scheme at the pre-encoding stage in a UMTS network. Simulation results in NS2 demonstrate the effectiveness of the proposed adaptation scheme, especially at the UMTS access network which is a bottleneck. An advantage of the model is that it is light weight (and so it can be implemented for real-time monitoring), and it provides a measure of user-perceived quality, but without requiring time-consuming subjective tests. The model has potential applications in several other areas, including QoE control and optimization in network planning and content provisioning for network/service providers.

New models for perceived voice quality prediction and their applications in playout buffer optimization for VoIP networks

Perceived voice quality is an important metric in VoIP applications. The quality is mainly affected by network impairments such as delay, jitter and packet loss. Playout buffer at the receiving side can be used to compensate for the effects of jitter based on a tradeoff between delay and loss. The main aim in this paper is to find an efficient perceived quality prediction method for perceptual optimization of playout buffer. The contributions of the paper are three-fold. First, we propose an efficient new method for predicting voice quality for buffer design/optimization. The method can also be used for voice quality monitoring and for QoS control. In the method, nonlinear regression models are derived for a variety of codecs (e.g. G.723.1/G.729/AMR/iLBC) with the aid of ITU PESQ and the E-model. Second, we propose the use of minimum overall impairment as a criterion for buffer optimization. This criterion is more efficient than using traditional maximum mean opinion score (MOS). Third, we show that the delay characteristics of voice over IP traffic is better characterized by a Weibull distribution than a Pareto or an exponential distribution. Based on the new voice quality prediction model, the Weibull delay distribution model and the minimum impairment criterion, we propose a perceptual optimization buffer algorithm. Preliminary results show that the proposed algorithm can achieve the optimum perceived voice quality compared with other algorithms under all network conditions considered.

Application of simulated annealing fuzzy model tuning to umbilical cord acid-base interpretation

Fuzzy logic and fuzzy set theory provide an important framework for representing and managing imprecision and uncertainty in medical expert systems, but the need remains to optimize such systems to enhance performance. The paper presents a general technique for optimizing fuzzy models in fuzzy expert systems (FESs) by simulated annealing (SA) and N-dimensional hill climbing simplex method. The application of the technique to a FES for the interpretation of the acid-base balance of blood in the umbilical cord of newborn infants is presented. The Spearman rank order correlation statistic was used to assess and to compare the performance of a commercially available crisp expert system, an initial FES, and a tuned FES with experienced clinicians. Results showed that without tuning, the performance of the crisp system was significantly better (correlation of 0.80) than the FES (correlation of 0.67). The performance of the tuned FES was better than the crisp system and effectively indistinguishable from the clinicians (correlation of 0.93) on training data and was the best of the expert systems on validation data. Unlike most applications of fuzzy logic where all fuzzy sets have normalized heights of unity, in this application it was found that a reduction in the height of some fuzzy sets was effective in enhancing performance. This suggests that the height of fuzzy sets may be a generally useful parameter in tuning FESs.

Content Clustering Based Video Quality Prediction Model for MPEG4 Video Streaming over Wireless Networks

The aim of this paper is quality prediction for streaming MPEG4 video sequences over wireless networks for all video content types. Video content has an impact on video quality under same network conditions. This feature has not been widely explored when developing reference-free video quality prediction model for streaming video over wireless or mobile communications. In this paper, we present a two step approach to video quality prediction. First, video sequences are classified into groups representing different content types using cluster analysis. The classification of contents is based on the temporal (movement) and spatial (edges, brightness) feature extraction. Second, based on the content type, video quality (in terms of Mean Opinion Score) is predicted from network level parameter (packet error rate) and application level (i.e. send bitrate, frame rate) parameters using Principal Component Analysis (PCA). The performance of the developed model is evaluated with unseen datasets and good prediction accuracy is obtained for all content types. The work can help in the development of reference-free video prediction model and priority control for content delivery networks.

Receiver operating characteristic analysis for intelligent medical systems-a new approach for finding confidence intervals

Intelligent systems are increasingly being deployed in medicine and healthcare, but there is a need for a robust and objective methodology for evaluating such systems. Potentially, receiver operating characteristic (ROC) analysis could form a basis for the objective evaluation of intelligent medical systems. However, it has several weaknesses when applied to the types of data used to evaluate intelligent medical systems. First, small data sets are often used, which are unsatisfactory with existing methods. Second, many existing ROC methods use parametric assumptions which may not always be valid for the test cases selected. Third, system evaluations are often more concerned with particular, clinically meaningful, points on the curve, rather than on global indexes such as the more commonly used area under the curve. A novel, robust and accurate method is proposed, derived from first principles, which calculates the probability density function (pdf) for each point on a ROC curve for any given sample size. Confidence intervals are produced as contours on the pdf. The theoretical work has been validated by Monte Carlo simulations. It has also been applied to two real-world examples of ROC analysis, taken from the literature (classification of mammograms and differential diagnosis of pancreatic diseases), to investigate the confidence surfaces produced for real cases, and to illustrate how analysis of system performance can be enhanced. We illustrate the impact of sample size on system performance from analysis of ROC pdfs and 95% confidence boundaries. This work establishes an important new method for generating pdfs, and provides an accurate and robust method of producing confidence intervals for ROC curves for the small sample sizes typical of intelligent medical systems. It is conjectured that, potentially, the method could be extended to determine risks associated with the deployment of intelligent medical systems in clinical practice.

Perceived speech quality prediction for voice over IP-based networks

Perceived speech quality is the key metric for QoS in VoIP applications. Our primary aims are to carry out a fundamental investigation of the impact of packet loss and talkers on perceived speech quality using an objective method and, thus, to provide the basis for developing an artificial neural network (ANN) model to predict speech quality for VoIP. The impact on perceived speech quality of packet loss and of different talkers was investigated for three modern codecs (G.729, G.723.1 and AMR) using the new ITU PESQ algorithm. Results show that packet loss burstiness, loss locations/patterns and the gender of talkers have an impact. Packet size has, in general, no obvious influence on perceived speech quality for the same network conditions, but the deviation in speech quality depends on packet size and codec. Based on the investigation, we used talkspurt-based conditional and unconditional packet loss rates (which are perceptually more relevant than network packet loss rates), codec type and the gender of the talker (extracted from decoder) as inputs to an ANN model to predict speech quality directly from network parameters. Results show that high prediction accuracy was obtained from the ANN model (correlation coefficients for the test and validation datasets were 0.952 and 0.946 respectively). This work should help to develop efficient, nonintrusive QoS monitoring and control strategies for VoIP applications.

Content-Based Video Quality Prediction for MPEG4 Video Streaming over Wireless Networks

There are many parameters that affect video quality but their combined effect is not well identified and understood when video is transmitted over mobile/ wireless networks. In addition, video content has an impact on video quality under same network conditions. The main aim of this paper is the prediction of video quality combining the application and network level parameters for all content types. Firstly, video sequences are classified into groups representing different content types using cluster analysis. The classification of contents is based on the temporal (movement) and spatial (edges, brightness) feature extraction. Second, to study and analyze the behaviour of video quality for wide range variations of a set of selected parameters. Finally, to develop two learning models based on – (1) ANFIS to estimate the visual perceptual quality in terms of the Mean Opinion Score (MOS) and decodable frame rate (Q value) and (2) regression modeling to estimate the visual perceptual quality in terms of the MOS. We trained three ANFIS-based ANNs and regression based- models for the three distinct content types using a combination of network and application level parameters and tested the two models using unseen dataset. We confirmed that the video quality is more sensitive to network level compared to application level parameters. Preliminary results show that a good prediction accuracy was obtained from both models. However, the regression based model performed better in terms of the correlation coefficient and the root mean squared error. The work should help in the development of a reference-free video prediction model and Quality of Service (QoS) control methods for video over wireless/mobile networks.

Automatic design of frequency sampling filters by hybrid genetic algorithm techniques

A new method of designing recursive and nonrecursive frequency sampling filters is presented. We investigate the use of a hybrid real-coded genetic algorithm (GA) for optimising transition sample values to give the maximum stopband attenuation. A modification allows the coefficient wordlength to be optimized concurrently, thereby reducing the overall number of design steps and simplifying the design process. The technique is able to consistently optimize filters with up to six transition samples. Designing digital filters is a complex process involving optimization at several discrete design steps. The techniques presented could form the basis for integrating several of the optimizations. Investigations into increasing this integration by using a binary-coded GA to optimize nonlinear phase, quantized coefficient FIR filters are introduced, with an analysis of the difficulty of the problem from a GA perspective.