• Security challenges in cyber systems

      Safdar, Ghazanfar Ali; Kalsoom, Tahera; Ramzan, Naeem; University of Bedfordshire; University of the West of Scotland (Institute of Electrical and Electronics Engineers Inc., 2020-09-29)
      CPS (Cyber-Physical Systems) is proposed by the NSF (National Scientific Foundation) to describe a type of necessities which conglomerates hardware and software components and being the next step in development of embedded systems. CPS includes a wide range of research topics from signal processing to data analysis. This paper contains a brief review of the basic infrastructure for CPS including smart objects and network aspects in relation to TCP/IP stack. As CPS reflect the processes of the physical environment onto the cyber space, virtualisation as important tool for abstraction plays crucial role in CPS. In this context paper presents the challenges associated with mobility and vritualisation; accordingly, three main types of virtualisation, namely network, devices and applications virtualisation are presented in the paper. The main focus of the paper is made on security. Different threats, attack types and possible consequences are discussed as well as analysis of various approaches to cope with existing threats is introduced. Furthermore, needs and requirements for safety-critical CPS are reviewed.
    • Speaker identification using multimodal neural networks and wavelet analysis

      Almaadeed, Noor; Aggoun, Amar; Amira, Abbes; Brunel University; Qatar University; University of Bedfordshire; University of the West of Scotland (Institution of Engineering and Technology, 2015-03-19)
      The rapid momentum of the technology progress in the recent years has led to a tremendous rise in the use of biometric authentication systems. The objective of this research is to investigate the problem of identifying a speaker from its voice regardless of the content. In this study, the authors designed and implemented a novel text-independent multimodal speaker identification system based on wavelet analysis and neural networks. Wavelet analysis comprises discrete wavelet transform, wavelet packet transform, wavelet sub-band coding and Mel-frequency cepstral coefficients (MFCCs). The learning module comprises general regressive, probabilistic and radial basis function neural networks, forming decisions through a majority voting scheme. The system was found to be competitive and it improved the identification rate by 15% as compared with the classical MFCC. In addition, it reduced the identification time by 40% as compared with the back-propagation neural network, Gaussian mixture model and principal component analysis. Performance tests conducted using the GRID database corpora have shown that this approach has faster identification time and greater accuracy compared with traditional approaches, and it is applicable to real-time, text-independent speaker identification systems.