Mousa Al-Akhras

Non-intrusive speech quality prediction in VoIP networks using a neural network approach

Measuring speech quality in Voice over Internet Protocol (VoIP) networks is an increasingly important application for legal, commercial and technical reasons. Any proposed solution for measuring the quality should be applicable in monitoring live-traffic non-intrusively. The E-Model proposed by the International Telecommunication Union-Telecommunication Standardisation Sector (ITU-T) achieves this, but it requires subjective tests to calibrate its parameters. In this paper a solution is proposed to extend the E-Model to any new network conditions and for newly emerging speech codecs without the need for the time-consuming, expensive, hard to conduct subjective tests. The proposed solution is based on an artificial neural network model and is compared against the E-Model to check its prediction accuracy.

WSN-DS: A Dataset for Intrusion Detection Systems in Wireless Sensor Networks

Wireless Sensor Networks (WSN) have become increasingly one of the hottest research areas in computer science due to their wide range of applications including critical military and civilian applications. Such applications have created various security threats, especially in unattended environments. To ensure the security and dependability of WSN services, an Intrusion Detection System (IDS) should be in place. This IDS has to be compatible with the characteristics of WSNs and capable of detecting the largest possible number of security threats. In this paper a specialized dataset for WSN is developed to help better detect and classify four types of Denial of Service (DoS) attacks: Blackhole, Grayhole, Flooding, and Scheduling attacks. This paper considers the use of LEACH protocol which is one of the most popular hierarchical routing protocols in WSNs. A scheme has been defined to collect data from Network Simulator 2 (NS-2) and then processed to produce 23 features. The collected dataset is called WSN-DS. Artificial Neural Network (ANN) has been trained on the dataset to detect and classify different DoS attacks. The results show that WSN-DS improved the ability of IDS to achieve higher classification accuracy rate. WEKA toolbox was used with holdout and 10-Fold Cross Validation methods. The best results were achieved with 10-Fold Cross Validation with one hidden layer. The classification accuracies of attacks were 92.8%, 99.4%, 92.2%, 75.6%, and 99.8% for Blackhole, Flooding, Scheduling, and Grayhole attacks, in addition to the normal case (without attacks), respectively.

Perceptual evaluation of speech enhancement

Speech enhancement is the process of de-noising a speech signal for improved quality and better intelligibility. Several speech enhancement methods have been proposed including: DWFM filtering, Donoho, Massart, and Kalman. To measure the performance of these filters, a speech evaluation method is needed. SNR is one of the most common methods for speech evaluation. The problem of SNR as a waveform speech evaluation is it is too general and can fit any type of signal, even non-speech signals. In this paper the performance of several speech enhancement methods is compared using both SNR and PESQ which is an evaluation method that has been proposed by the ITU-T for speech-specific quality evaluation. The speech sources used during the experiments are artificial voices produced in ITU-T recommendation P.50 Appendix I. These artificial voices have the same spectral and temporal characteristics as the human speech signals.

AdaLearn: an adaptive e-learning environment

This paper describes the theoretical and technical aspects that were taken into consideration in the design process of a web-based adaptive e-learning environment we called (AdaLearn). AdaLearn system saves learners responses into learners profile then they will be used in future guidance. This paper presents an adaptation scenario in order to give recommendations about contents to individual learners taking into consideration learners behavior.

A genetic algorithm approach for voice quality prediction

Multimedia applications play an increasingly important role in the world of communication. To be able to present an effective multimedia service, the quality of the multimedia service should be acceptable to the user. As measuring the multimedia and mainly the voice quality is needed while the network is running, therefore an automated, non-intrusive and overall accurate measurement of quality should be provided. The E-Model proposed by the International Telecommunication Union-Telecommunication Standardisation Sector (ITU-T) achieves this, but it needs the expensive subjective tests to calibrate its parameters. A Genetic Algorithm (GA) approach is proposed in this paper to extend the E-model without the need for the subjective tests. The proposed solution is compared against the E-Model to prove similar results are obtained.

BlueCRM: A New Trend of Customer Relationship Management Systems

In this paper a new proactive customer relationship management system (CRM), BlueCRM, is proposed. The proposed system employs Bluetooth as an automatic identification token in addition to its common use as a communication channel. The system offers a low-cost proactive CRM system which is the future trend of such systems. The implementation of the prototype system comprises two sides: a database management program and an intuitive user interface in the software side. In the hardware side there are a Bluetooth-enabled device and a Bluetooth dongle. The architecture encloses an important advantage over the previous solutions due to its feasibility and ease of deployment. Furthermore, the architecture can be flexibly implemented either as a stand-alone or as integrated part of an existing information system.

Logic-Based Security Architecture for Systems Providing Multihop Communication

Security is a basic element of distributed systems such as ad hoc and sensor communication networks. Several standards define security requirements and enforcers, such as ITU-T Recommendations X.800 and X.805. It is essential to specify and analyze protocols to know which security requirements they achieve. This paper presents a logic-based security architecture (LBSA). LBSA is a systematic way to test if a protocol is secure by checking what security requirements are achieved. Different rules, actions, and sets which fit into the proposed LBSA are included, new ones are also added to complete the architecture. The key advantage of LBSA is that it enables a security protocol to prove its correctness mathematically. Mathematical proofs provided by LBSA cover more cases that usually cannot be covered exhaustively by simulation tools. This paper also specifies and analyzes several security enforcers and protocols and mathematically proves which security requirements they achieve. Mapping between security requirements and inference rules/actions is also provided to facilitate the use of LBSA. Some enforcers are analyzed using LBSA to demonstrate how they achieve security requirements. Finally, we take Ariadne protocol as a case study and show how to use the proposed LBSA architecture to prove that this protocol is secure.

Evaluating the NGN performance based on duplicate transmission of voice packets

This work aims to enhance the Quality of Service (QoS) of the third-generation (3G) cellular networks. The quality of voice traffic over IP networks (VoIP) is greatly reduced due to the fact that packets in IP networks suffer from packet loss which is inevitable due to the best-effort nature of these networks. Many techniques have been proposed to decrease the effect of packet loss on the speech quality. In this paper we study the effect of packet loss on speech quality; we propose sending a duplicate copy of the speech stream over the network and we study the effect on the speech quality due to this duplication. This is especially useful in networks with extra available bandwidth. The performance of the system is measured according to the E-Model as defined in the ITU-Ts Recommendation G.107. The speech sources used during the experiments are artificial voices obtained from the ITU-T Recommendation P.50/Appendix I. The results of the proposed scheme suggest improvement in the system performance in terms of speech quality which can then be translated into greater percentage of users satisfied with the service and greater potential revenue. The proposed technique proves to be more effective when situations of higher percentages of packet loss and burst losses rise.

An Improved E-Model Using Artificial Neural Network VoIP Quality Predictor

Voice over Internet Protocol (VoIP) networks are an increasingly im- portant fleld in the world of telecommunication due to many involved advantages and potential revenue. Measuring speech quality in VoIP networks is an important aspect of such networks for legal, commercial and technical reasons. The E-model is a widely used objective approach for measuring the quality as it is applicable to monitoring live-tra-c, automatically and non-intrusively. The E-model sufiers from several drawbacks. Firstly, it considers the efiect of packet loss on the speech quality collectively without looking at the content of the speech signal to check whether the loss occurred in voiced or unvoiced parts of the signal. Secondly, it depends on subjective tests to calibrate its parameters, which makes it applicable to limited conditions corresponding to speciflc subjective experiments. In this pa- per, a solution is proposed to overcome these two problems. The proposed solution improves the accuracy of the E-model by difierentiating between packet loss dur- ing speech and silence periods. It also avoids the need for subjective tests, which makes it extendable to new network conditions. The proposed solution is based on an Artiflcial Neural Networks (ANN) approach and is compared with the accurate Perceptual Evaluation of Speech Quality (PESQ) model and the original E-model to conflrm its accuracy. Several experiments are conducted to test the efiectiveness of the proposed solution on two well-known ITU-T speech codecs; namely, G.723.1 and G.729.

Voice over IP (VoIP)

1.VoIP - An Introduction a.Packet switching vs. circuit switching b.Motivations and advantages c.Possible applications 2.VoIP - technologies a.VoIP and TCP / IP Protocol Suite b.VoIP signalling protocols i. H.323 ii. SIP iii. SDP iv. RTP / RTCP c.Resource Reservation Protocols 3.Challenges of Voice over IP a.Before VoIP session b.After VoIP session c.During VoIP Session i. Packet loss ii. Delay iii. Jitter iv. Other challenges 4.Methods available for measuring the quality of media sessions a.Subjective tests b.Intrusive-based objective tests c.non-intrusive-based objective tests 5.Experimental work for measuring the quality a.Artificial voices b.2-state Markov models c.Linear - regression method d.Non-Linear - regression method e.genetic algorithms method f.An artificial neural network approach g.Comparisons between different methods 6.Conclusions