An iterative-style approach to constructing intelligent tutoring systems in mathematics

Mathematics is highly structured and also underpins most of science and engineering. For this reason, it has proved a very suitable domain for Intelligent Tutoring System (ITS) research, with the result that probably more tutoring systems have been constructed for the domain than any other. However, the literature reveals that there still exists no consensus on a credible approach or approaches for the design of such systems, despite numerous documented efforts. Current approaches to the construction of ITSs leave much to be desired. Consequently, existing ITSs in the domain suffer from a considerable number of shortcomings which render them 'unintelligent'. The thesis examines some of the reasons why this is the case. Following a critical review of existing ITSs in the domain, and some pilot studies, an alternative approach to their construction is proposed (the 'iterative-style' approach); this supports an iterative style, and also improves on at least some of the shortcomings of existing approaches. The thesis also presents an ITS for fractions which has been developed using this approach, and which has been evaluated in various ways. It has, demonstrably, improved on many of the limitations of existing ITSs; furthermore, it has been shown to be largely 'intelligent', at least more so than current tutors for the domain. Perhaps more significantly, the tutor has also been evaluated against real students with, so far, very encouraging results. The thesis thus concludes that the novel iterative-style approach is a more credible approach to the construction of ITSs in mathematics than existing techniques.

Automatic summary assessment for intelligent tutoring systems

Summary writing is an important part of many English Language Examinations. As grading students' summary writings is a very time-consuming task, computer-assisted assessment will help teachers carry out the grading more effectively. Several techniques such as latent semantic analysis (LSA), n-gram co-occurrence and BLEU have been proposed to support automatic evaluation of summaries. However, their performance is not satisfactory for assessing summary writings. To improve the performance, this paper proposes an ensemble approach that integrates LSA and n-gram co-occurrence. As a result, the proposed ensemble approach is able to achieve high accuracy and improve the performance quite substantially compared with current techniques. A summary assessment system based on the proposed approach has also been developed.

Enhancing the performance of intelligent control systems in the face of higher levels of complexity and uncertainty

Modern advances in technology have led to more complex manufacturing processes whose success centres on the ability to control these processes with a very high level of accuracy. Plant complexity inevitably leads to poor models that exhibit a high degree of parametric or functional uncertainty. The situation becomes even more complex if the plant to be controlled is characterised by a multivalued function or even if it exhibits a number of modes of behaviour during its operation. Since an intelligent controller is expected to operate and guarantee the best performance where complexity and uncertainty coexist and interact, control engineers and theorists have recently developed new control techniques under the framework of intelligent control to enhance the performance of the controller for more complex and uncertain plants. These techniques are based on incorporating model uncertainty. The newly developed control algorithms for incorporating model uncertainty are proven to give more accurate control results under uncertain conditions. In this paper, we survey some approaches that appear to be promising for enhancing the performance of intelligent control systems in the face of higher levels of complexity and uncertainty.

Multi-valued control problems and mixture density network

We have proposed a novel robust inversion-based neurocontroller that searches for the optimal control law by sampling from the estimated Gaussian distribution of the inverse plant model. However, for problems involving the prediction of continuous variables, a Gaussian model approximation provides only a very limited description of the properties of the inverse model. This is usually the case for problems in which the mapping to be learned is multi-valued or involves hysteritic transfer characteristics. This often arises in the solution of inverse plant models. In order to obtain a complete description of the inverse model, a more general multicomponent distributions must be modeled. In this paper we test whether our proposed sampling approach can be used when considering an arbitrary conditional probability distributions. These arbitrary distributions will be modeled by a mixture density network. Importance sampling provides a structured and principled approach to constrain the complexity of the search space for the ideal control law. The effectiveness of the importance sampling from an arbitrary conditional probability distribution will be demonstrated using a simple single input single output static nonlinear system with hysteretic characteristics in the inverse plant model.

Bayesian precalibration of a large stochastic microsimulation model

Calibration of stochastic traffic microsimulation models is a challenging task. This paper proposes a fast iterative probabilistic precalibration framework and demonstrates how it can be successfully applied to a real-world traffic simulation model of a section of the M40 motorway and its surrounding area in the U.K. The efficiency of the method stems from the use of emulators of the stochastic microsimulator, which provides fast surrogates of the traffic model. The use of emulators minimizes the number of microsimulator runs required, and the emulators' probabilistic construction allows for the consideration of the extra uncertainty introduced by the approximation. It is shown that automatic precalibration of this real-world microsimulator, using turn-count observational data, is possible, considering all parameters at once, and that this precalibrated microsimulator improves on the fit to observations compared with the traditional expertly tuned microsimulation. © 2000-2011 IEEE.

Monitoring of deployment process of shape memory polymers for morphing structures with embedded fibre Bragg grating sensors

This article demonstrates the use of embedded fibre Bragg gratings as vector bending sensor to monitor two-dimensional shape deformation of a shape memory polymer plate. The shape memory polymer plate was made by using thermal-responsive epoxy-based shape memory polymer materials, and the two fibre Bragg grating sensors were orthogonally embedded, one on the top and the other on the bottom layer of the plate, in order to measure the strain distribution in both longitudinal and transverse directions separately and also with temperature reference. When the shape memory polymer plate was bent at different angles, the Bragg wavelengths of the embedded fibre Bragg gratings showed a red-shift of 50 pm/°caused by the bent-induced tensile strain on the plate surface. The finite element method was used to analyse the stress distribution for the whole shape recovery process. The strain transfer rate between the shape memory polymer and optical fibre was also calculated from the finite element method and determined by experimental results, which was around 0.25. During the experiment, the embedded fibre Bragg gratings showed very high temperature sensitivity due to the high thermal expansion coefficient of the shape memory polymer, which was around 108.24 pm/°C below the glass transition temperature (Tg) and 47.29 pm/°C above Tg. Therefore, the orthogonal arrangement of the two fibre Bragg grating sensors could provide a temperature compensation function, as one of the fibre Bragg gratings only measures the temperature while the other is subjected to the directional deformation. © The Author(s) 2013.

Web-based expert systems:benefits and challenges

Convergence of technologies in the Internet and the field of expert systems have offered new ways of sharing and distributing knowledge. However, there has been a general lack of research in the area of web-based expert systems (ES). This paper addresses the issues associated with the design, development, and use of web-based ES from a standpoint of the benefits and challenges of developing and using them. The original theory and concepts in conventional ES were reviewed and a knowledge engineering framework for developing them was revisited. The study considered three web-based ES: WITS-advisor - for e-business strategy development, Fish-Expert - for fish disease diagnosis, and IMIS - to promote intelligent interviews. The benefits and challenges in developing and using ES are discussed by comparing them with traditional standalone systems from development and application perspectives. © 2004 Elsevier B.V. All rights reserved.

Development of an intelligent quality management system using fuzzy association rules

In order to survive in the increasingly customer-oriented marketplace, continuous quality improvement marks the fastest growing quality organization’s success. In recent years, attention has been focused on intelligent systems which have shown great promise in supporting quality control. However, only a small number of the currently used systems are reported to be operating effectively because they are designed to maintain a quality level within the specified process, rather than to focus on cooperation within the production workflow. This paper proposes an intelligent system with a newly designed algorithm and the universal process data exchange standard to overcome the challenges of demanding customers who seek high-quality and low-cost products. The intelligent quality management system is equipped with the ‘‘distributed process mining” feature to provide all levels of employees with the ability to understand the relationships between processes, especially when any aspect of the process is going to degrade or fail. An example of generalized fuzzy association rules are applied in manufacturing sector to demonstrate how the proposed iterative process mining algorithm finds the relationships between distributed process parameters and the presence of quality problems.

Establishing a framework for dynamic risk management in 'intelligent' aero-engine control

The behaviour of control functions in safety critical software systems is typically bounded to prevent the occurrence of known system level hazards. These bounds are typically derived through safety analyses and can be implemented through the use of necessary design features. However, the unpredictability of real world problems can result in changes in the operating context that may invalidate the behavioural bounds themselves, for example, unexpected hazardous operating contexts as a result of failures or degradation. For highly complex problems it may be infeasible to determine the precise desired behavioural bounds of a function that addresses or minimises risk for hazardous operation cases prior to deployment. This paper presents an overview of the safety challenges associated with such a problem and how such problems might be addressed. A self-management framework is proposed that performs on-line risk management. The features of the framework are shown in context of employing intelligent adaptive controllers operating within complex and highly dynamic problem domains such as Gas-Turbine Aero Engine control. Safety assurance arguments enabled by the framework necessary for certification are also outlined.

Run-time connector synthesis for autonomic systems of systems

A key objective of autonomic computing is to reduce the cost and expertise required for the management of complex IT systems. As a growing number of these systems are implemented as hierarchies or federations of lower-level systems, techniques that support the development of autonomic systems of systems are required. This article introduces one such technique, which involves the run-time synthesis of autonomic system connectors. These connectors are specified by means of a new type of autonomic computing policy termed a resource definition policy, and enable the dynamic realisation of collections of collaborating autonomic systems, as envisaged by the original vision of autonomic computing. We propose a framework for the formal specification of autonomic computing policies, and use it to define the new policy type and to describe its application to the development of autonomic system of systems. To validate the approach, we present a sample data-centre application that was built using connectors synthesised from resource-definition policies.

Intelligent execution monitoring and error analysis in planning involving processes

An intelligent agent, operating in an external world which cannot be fully described in its internal world model, must be able to monitor the success of a previously generated plan and to respond to any errors which may have occurred. The process of error analysis requires the ability to reason in an expert fashion about time and about processes occurring in the world. Reasoning about time is needed to deal with causality. Reasoning about processes is needed since the direct effects of a plan action can be completely specified when the plan is generated, but the indirect effects cannot. For example, the action `open tap' leads with certainty to `tap open', whereas whether there will be a fluid flow and how long it might last is more difficult to predict. The majority of existing planning systems cannot handle these kinds of reasoning, thus limiting their usefulness. This thesis argues that both kinds of reasoning require a complex internal representation of the world. The use of Qualitative Process Theory and an interval-based representation of time are proposed as a representation scheme for such a world model. The planning system which was constructed has been tested on a set of realistic planning scenarios. It is shown that even simple planning problems, such as making a cup of coffee, require extensive reasoning if they are to be carried out successfully. The final Chapter concludes that the planning system described does allow the correct solution of planning problems involving complex side effects, which planners up to now have been unable to solve.

Adaptive electrical signal post-processing in optical communications systems

Improving bit error rates in optical communication systems is a difficult and important problem. The error correction must take place at high speed and be extremely accurate. We show the feasibility of using hardware implementable machine learning techniques. This may enable some error correction at the speed required.