Skip to content


Computational Intelligence and Applications Research Group (CIA)

Unit(s) of assessment: Computer Science and Informatics

School: School of Science and Technology


Members of the research team will continue to apply computationally intelligent methods and techniques to real-world applications that can make a difference to lives and society. The Research Group has access to a smart home facility, including variety of sensors, actuators and communication devices and different assistive robotic platforms including Pepper and Nao robots.

Research activities within the CIA group addresses a number of problem domains and real-world applications and can be sub-categorised into the following themes:

Ambient Intelligence (AmI)

In environments based on ambient intelligence, it is intended to investigate prediction techniques using computational intelligence methods where the behaviours of users are predicted. This kind of environment is called a predictive ambient intelligence environment, which can be categorised as the new third generation of smart environments. The new emerging environment can learn from environmental changes as well as behavioural patterns of occupants. Predictive ambient intelligence environments collect data acquired from a sensor network. Collected data include a variety of attributes, such as the environmental changes and occupants' interactions with the environment. These data are used in a learning approach to make a predictive ambient intelligence environment that can predict the occupancy of different areas, as well as requirements and interests of occupants at different times. This predictive feature, for example, can improve the performance of energy saving approaches in a smart environment; in addition, it enhances the convenience of occupants as well as security and safety.

Text mining and Information Extraction (IE)

The advance of computer technologies especially the internet and WWW has led to an explosion of digital data, a large proportion of which is text. For example, it is estimated that nearly 1 million new websites are created on a daily basis. Every day we are challenged with ‘information overload’. The ability to effectively and efficiently analyse such data, extract structured information and crucially, convert them into knowledge that can be understood and manipulated by machines to enable intelligent reasoning and decision making, is of paramount importance. This requires the methods and technologies of text mining and IE, which utilises a wide range of computational intelligence techniques such as machine learning and optimisation, to automatically analysing textual data and extracting structured information. On the other hand, the structured representation of human knowledge generated by text mining and IE also enables other computational intelligence applications, such as in the area of ambient intelligence.

Computational Optimisation

Focuses on the development and application of heuristic search and optimisation methods. These methods include genetic algorithms, simulated annealing, ant colony optimisation,Tabu search and hybrid methodologies known as Memetic Algorithms. Many scientific and engineering problems can be viewed as search or optimisation problems, where an optimum input vector for a given system has to be found in order to optimise the system response to that input vector. Often, auxiliary information about the system, such as its transfer function and derivatives, is not known, also various measures might be incomplete and distorted by noise. This makes such problems difficult to solve by traditional methods. In such cases, approaches based on computational optimisation techniques have been shown to be advantageous compared to classical approaches. Problems amenable to solution by heuristic search and computational optimisation techniques occur in all areas of science and engineering where an optimum design of a component or product, or optimum system input or response, is required.

Biologically-inspired Speaker Verification

Voice biometrics is one of the least developed of all the biometric technologies. Environmental noise, intra-speaker feature variability and platform dependent speech-processing differences are all factors that substantially limit the performance of existing speaker verification algorithms (GMM, SVMs etc.). Neural network based methods have the potential to automatically address these factors as part of their training process, and novel supervised, unsupervised and hybrid neural architectures have been developed within the speech-enabled systems research group here at NTU. Current research is investigating the use of Spiking Neural Network systems, based on models of the human auditory system, as a more biologically plausible speaker verification method.

Temporal Issues in designing Fuzzy Systems

During past years, fuzzy methodologies have emerged as one of the most suitable and efficient methods for designing and developing complex systems in environments characterised by high level of uncertainty and imprecision. Nowadays, this methodology is used to model systems in several applications domains which range from industrial machineries to financial decisions support systems. Nevertheless, in spite of the usefulness of fuzzy logic, one of its drawbacks comes from the lack of the temporal concept that is crucial in many systems characterised from a discontinuous nonlinear behaviour. In particular, in its standard vision, fuzzy control is not able to represent Variable-Structure systems i.e. systems that change their configuration (knowledge base) or their behaviour (rule base) over time. To overcome these drawbacks, this research extends fuzzy systems idea by considering a theory from formal languages: timed automata. This novel synergic approach achieves a twofold advantage by representing a system in qualitative and linguistic way and introducing a novel switching control concept able to maximise system's performances and robustness. This approach can be applied to different application scenarios as computer networking security, urban garbage collection and so on.

Recurrent Neural Networks for Modelling Temporal Phenomena

Much of the world around us is dynamic and temporal in nature – daily weather patterns, night/day time transitions, the changing seasons, our periodic heart beats and more generally, daily living patterns. Our world is full of time-dependent processes and almost any real system has some notion of temporal state and transition, from calling a lift, using a vending machine to even switching on a light. The human use of natural language to communicate is a classic temporal problem whereby structure and meaning is encoded within linear strings of inter-connected words. Temporal based Neural Networks can be also integrated in complex computer vision systems in order to identify some hard and dynamic patterns occurring in real environment such as human activities and behaviours.

Middleware, Domain Specific Languages and Trust

Getting heterogeneous devices and services to communicate and understand each other is problematic within pervasive computing environments. An active area of research is through the use of light-weight service composition middleware's built to allow communication and coordination to allow the re-configuration and identification of services. This can be coupled with domain specific languages (DSL) that enable services to be easily created and to hide the complexity of the environment. In past work, DSL's were used to program these pervasive environments, while more recently, DSL's are being investigated in the control of power consumption within smart homes. With a large number of services available within a pervasive environment, trust becomes an issue and work in to rule based provenance trust systems are currently being investigated.


Current and recent research is being conducted with the collaboration, funding and/or support of:

Working with us

The CIA Research Group has expertise in analysis and use of methods from the field of computational intelligence, such as artificial neural networks, evolutionary algorithms and swarm intelligence to solve real-world problems from science and engineering. The research group has also expertise in smart environments, ambient assistive technologies, pervasive computing, location aware systems, intelligent modelling, control and robotics. The group also benefits from the Centre for Innovation and Technology Exploitation (CITE), which helps regional companies explore the impact of using emerging technologies within their business environment.

External Funding

Recent major grants:

  • Innovate UK - Tek Chef

Active Projects

Underwater Plastic Detection


Selected publications from this group are listed below. For full list of publications please use Institutional Repository (IRep).

Ambient intelligence

Fuzzy Markup Language

  • A Type-2 Fuzzy Markup Language Based Ontology and Its Application to Diet Assessment. Lee, C.S., Wanga, M. H., Acampora, G., Hsu, C.Y and Hagras, H., International Journal of Intelligent Systems, vol. 25, issue 12, pp. 1187-1216, 2010.
  • Fuzzy Markup Language: a XML-based Language for enabling Full Interoperability in Fuzzy Systems Design. Acampora G., “On the Power of Fuzzy Markup Language”, Studies in Fuzziness and Soft Computing, Springer, Acampora G, Lee C.-S., Loia V. and Wang M.-H. (Eds.), 2013.
  • Electrocardiogram application based on heart rate variability ontology and fuzzy markup language. M. H. Wang, C. S. Lee, G. Acampora, and V. Loia, in A. Gacek and W. Pedrycz (editors), ECG Signal Processing, Classification and Interpretation: A Comprehensive Framework of Computational Intelligence, Springer-Verlag, Germany, 2011.
  • Fuzzy control interoperability and scalability for adaptive domotic framework. Acampora G and Loia V, IEEE Transactions on Industrial Informatics, 2005, 1 (2), 97-111
  • Interoperable and adaptive fuzzy services for ambient intelligence applications. Acampora G, Gaeta M, Loia V and Vasilakos AV, ACM Transactions on Adaptive and Autonomous Systems, 2010, 5 (2), 8
  • Special issue on fuzzy ontologies and fuzzy markup language applications, Acampora G, Lee CS: Soft Computing, 2012, 16(7), pp. 1107-1108.

Computational optimisation

  • Enhancing ontology alignment through a memetic aggregation of similarity measures. Acampora G, Loia V, Vitiello A, Information Sciences, 2013, vol. 250, pp. 1-20.
  • A hybrid evolutionary approach for solving the ontology alignment problem, Acampora G, Loia V, Salerno S, Vitiello A, International Journal Intelligent Systems, 2012, 27(3), pp. 189-216.
  • Achieving Memetic Adaptability by Means of Agent-Based Machine Learning. Acampora G, Cadenas JM, Loia V, Muñoz Ballester E, IEEE Transactions on Industrial Informatics, 2011, 7(4), pp. 557-569.
  • A Multi-Agent Memetic System for Human-Based Knowledge Selection. Acampora G, Cadenas JM, Loia V, Muñoz Ballester E, IEEE Transactions on Systems, Man, and Cybernetics, Part A, 2011 41(5), pp. 946-960.
  • Exploring e-Learning Knowledge Through Ontological Memetic Agents. Acampora G, Loia V, Gaeta M, IEEE Computational Intelligence Magazine, 2010, 5(2), pp. 66-77.
  • On a Novel ACO-Estimator and its Application to the Target Motion Analysis Problem. Lars Nolle, Knowledge-Based Systems, Volume 21, Issue 3, April 2008, Pages 225-231.
  • Self-Adaptive Stepsize Search Applied to Optimal Engineering Design. Lars Nolle, JA. Bland, in Research and Development in Intelligent Systems XXVII, 2011, Pages 355-364.
  • Optimal Image Colour Extraction by Differential Evolution. Gerald Schaefer, Lars Nolle, International Journal of Bio-Inspired Computation (IJBIC), Vol. 2, No. 3/4, 2010.
  • On a Control Parameter Free Optimization Algorithm. Lars Nolle, in Research and Development in Intelligent Systems XXV, 2009, Pages 119-130.
  • Comparison of simulated annealing and SASS for parameter estimation of biochemical networks. Sayol, J.; Nolle, L.; Schaefer, G.; Nakashima, T., IEEE Congress on Computational Intelligence 2008.
  • An approach to detecting and investigating source-code plagiarism using Latent Semantic Analysis. Cosma, G.; Joy M.S., IEEE Transactions On Computers, Vol. 61, No. 3, 2012.
  • Evaluating the effectiveness Latent Semantic Analysis for similar source-code detection. Cosma, G; Joy MS., Informatica, Vol. 61, No. 3, 2012, Pages 379-394.

Biologically Inspired Speaker Verification

Temporal Issues in designing Fuzzy Systems

  • On the Temporal Granularity in Fuzzy Cognitive Maps, Acampora G, Loia V, IEEE Transactions on Fuzzy Systems, 2011, 19(6), pp. 1040-1057.
  • Exploiting timed automata based fuzzy controllers for designing adaptive intrusion detection systems, Acampora G, Soft Computing, 2012, 16(7), pp. 1183-1196.
  • Managing Urban Waste Collection through Timed Automata Based Fuzzy Cognitive Maps, Acampora G, Loia V, Vitiello A, CD-ARES 2012, pp. 501-515.

Recurrent Neural Networks for Modelling Temporal Phenomena

  • Hmad, N. and T. Allen (2013). Echo State Networks for Arabic phoneme classification and recognition. The XXXIV. International Conference on Machine Learning and Pattern Recognition. World Academy of Science, Engineering and Technology. London, UK.
  • BINNER, J., TINO, P., TEPPER, J., ANDERSEN, R., JONES, B. and KENDALL, G., 2010. Does money matter in inflation forecasting?. Physica A - Statistical Mechanics and its Applications, 389 (21), pp. 4793-4808.
  • BINNER, J., ELGAR, T., NILSSON, B. and TEPPER, J., 2006. Predictable non-linearities in U.S. inflation. Economics Letters, 93 (3), pp. 323-328.
  • MCQUEEN, T., HOPGOOD, A.A., ALLEN, T.J. and TEPPER, J.A., 2005. Extracting finite structure from infinite language. Knowledge-Based Systems, 18 (4-5), pp. 135-141.
  • BINNER, J., JONES, B., KENDALL, G., TEPPER, J. and TINO, P., 2006. Does money matter? An artificial intelligence approach. In: 9th Joint Conference on Information Sciences (JCIS-2006), The Splendour Kaohshiung, Koahshiung, Taiwan, 8-11 October 2006.
  • Combining Neural Networks and Fuzzy Systems for Human Behavior Understanding. Acampora G, Foggia P, Saggese A, Vento M, AVSS 2012: 88-93

Middleware, Domain Specific Languages and Trust

  • Wakeman, I., Light, A., Robinson, J., Chalmers, D., Basu, A. Deploying Pervasive Advertising in a Farmers’ Market. Chapter in Pervasive Advertising and Shopping, Springer HCI Series (2011) * Light, A., Wakeman, l., Robinson, J., Basu, A., Chalmers, D. Chutney and Relish: Designing to Augment the Experience of Shopping at a Farmers’ Market. Proceedings of OzCHI, QUT, Brisbane, Australia, 2010.
  • Robinson, J., Wakeman, I., Chalmers, D., Horsfall, B. Trust and the Internet of Things. Proceedings of the International Workshop on Trusted Communications in Decentralised Computing, Morioka, Japan, 2010.
  • Wakeman, I., Light, A., Robinson, J., Chalmers, D., Basu, A. Bringing the Virtual to the Farmers' Market: Designing for Trust in Pervasive Computing Systems. Proceedings of the Fourth IFIPTM International Conference on Trust Management, Morioka, Japan, 2010.
  • Wakeman, I., Light, A., Robinson, J., Chalmers, D., Basu, A. Deploying Ubiquitous Computing Applications in a Farmers' Market. (2010) In Proceedings of Pervasive Advertising & Shopping, Helsinki, Finland.
  • Basu, A., Wakeman, I., Chalmers, D. & Robinson, J. A Behavioural Model for Client Reputation, In proceedings of Trust In Mobile Environments (TIME), Norway. 2008.
  • Robinson, J., Wakeman, I., Chalmers, D. & Basu, A. The North Laine Shopping Guide: A Case Study in Modelling Trust in Applications, In proceedings of Joint iTrust and PST Conference on Privacy, Trust Management and Security (IFIPTM 2008) Trondheim, Norway. 2008.
  • Robinson, J., Wakeman, I. & Chalmers, D. Composing Software Services in the Pervasive Computing Environment: Languages or APIs? Journal of Pervasive and Mobile Computing, 2008.