Neurofuzzy mixture of experts network parallel learning and model construction algorithms

A connection between a fuzzy neural network model with the mixture of experts network (MEN) modelling approach is established. Based on this linkage, two new neuro-fuzzy MEN construction algorithms are proposed to overcome the curse of dimensionality that is inherent in the majority of associative memory networks and/or other rule based systems. The first construction algorithm employs a function selection manager module in an MEN system. The second construction algorithm is based on a new parallel learning algorithm in which each model rule is trained independently, for which the parameter convergence property of the new learning method is established. As with the first approach, an expert selection criterion is utilised in this algorithm. These two construction methods are equivalent in their effectiveness in overcoming the curse of dimensionality by reducing the dimensionality of the regression vector, but the latter has the additional computational advantage of parallel processing. The proposed algorithms are analysed for effectiveness followed by numerical examples to illustrate their efficacy for some difficult data based modelling problems.

Joint multiple dictionary learning for tensor sparse coding

Traditional dictionary learning algorithms are used for finding a sparse representation on high dimensional data by transforming samples into a one-dimensional (1D) vector. This 1D model loses the inherent spatial structure property of data. An alternative solution is to employ Tensor Decomposition for dictionary learning on their original structural form —a tensor— by learning multiple dictionaries along each mode and the corresponding sparse representation in respect to the Kronecker product of these dictionaries. To learn tensor dictionaries along each mode, all the existing methods update each dictionary iteratively in an alternating manner. Because atoms from each mode dictionary jointly make contributions to the sparsity of tensor, existing works ignore atoms correlations between different mode dictionaries by treating each mode dictionary independently. In this paper, we propose a joint multiple dictionary learning method for tensor sparse coding, which explores atom correlations for sparse representation and updates multiple atoms from each mode dictionary simultaneously. In this algorithm, the Frequent-Pattern Tree (FP-tree) mining algorithm is employed to exploit frequent atom patterns in the sparse representation. Inspired by the idea of K-SVD, we develop a new dictionary update method that jointly updates elements in each pattern. Experimental results demonstrate our method outperforms other tensor based dictionary learning algorithms.

Inverse problems in dynamic cognitive modeling

Inverse problems for dynamical system models of cognitive processes comprise the determination of synaptic weight matrices or kernel functions for neural networks or neural/dynamic field models, respectively. We introduce dynamic cognitive modeling as a three tier top-down approach where cognitive processes are first described as algorithms that operate on complex symbolic data structures. Second, symbolic expressions and operations are represented by states and transformations in abstract vector spaces. Third, prescribed trajectories through representation space are implemented in neurodynamical systems. We discuss the Amari equation for a neural/dynamic field theory as a special case and show that the kernel construction problem is particularly ill-posed. We suggest a Tikhonov-Hebbian learning method as regularization technique and demonstrate its validity and robustness for basic examples of cognitive computations.

The effectiveness of assessment learning objects produced using pair programming

Pair Programming is a technique from the software development method eXtreme Programming (XP) whereby two programmers work closely together to develop a piece of software. A similar approach has been used to develop a set of Assessment Learning Objects (ALO). Three members of academic staff have developed a set of ALOs for a total of three different modules (two with overlapping content). In each case a pair programming approach was taken to the development of the ALO. In addition to demonstrating the efficiency of this approach in terms of staff time spent developing the ALOs, a statistical analysis of the outcomes for students who made use of the ALOs is used to demonstrate the effectiveness of the ALOs produced via this method.

Video activity extraction and reporting with incremental unsupervised learning

The present work presents a new method for activity extraction and reporting from video based on the aggregation of fuzzy relations. Trajectory clustering is first employed mainly to discover the points of entry and exit of mobiles appearing in the scene. In a second step, proximity relations between resulting clusters of detected mobiles and contextual elements from the scene are modeled employing fuzzy relations. These can then be aggregated employing typical soft-computing algebra. A clustering algorithm based on the transitive closure calculation of the fuzzy relations allows building the structure of the scene and characterises the ongoing different activities of the scene. Discovered activity zones can be reported as activity maps with different granularities thanks to the analysis of the transitive closure matrix. Taking advantage of the soft relation properties, activity zones and related activities can be labeled in a more human-like language. We present results obtained on real videos corresponding to apron monitoring in the Toulouse airport in France.

Learning enhanced 3D models for vehicle tracking

This paper presents an enhanced hypothesis verification strategy for 3D object recognition. A new learning methodology is presented which integrates the traditional dichotomic object-centred and appearance-based representations in computer vision giving improved hypothesis verification under iconic matching. The "appearance" of a 3D object is learnt using an eigenspace representation obtained as it is tracked through a scene. The feature representation implicitly models the background and the objects observed enabling the segmentation of the objects from the background. The method is shown to enhance model-based tracking, particularly in the presence of clutter and occlusion, and to provide a basis for identification. The unified approach is discussed in the context of the traffic surveillance domain. The approach is demonstrated on real-world image sequences and compared to previous (edge-based) iconic evaluation techniques.

The automatic layout model in the sequencing of construction activities of multi-objective diaphragm wall unit by using self-learning neural network

Foundation construction process has been an important key point in a successful construction engineering. The frequency of using diaphragm wall construction method among many deep excavation construction methods in Taiwan is the highest in the world. The traditional view of managing diaphragm wall unit in the sequencing of construction activities is to establish each phase of the sequencing of construction activities by heuristics. However, it conflicts final phase of engineering construction with unit construction and effects planning construction time. In order to avoid this kind of situation, we use management of science in the study of diaphragm wall unit construction to formulate multi-objective combinational optimization problem. Because the characteristic (belong to NP-Complete problem) of problem mathematic model is multi-objective and combining explosive, it is advised that using the 2-type Self-Learning Neural Network (SLNN) to solve the N=12, 24, 36 of diaphragm wall unit in the sequencing of construction activities program problem. In order to compare the liability of the results, this study will use random researching method in comparison with the SLNN. It is found that the testing result of SLNN is superior to random researching method in whether solution-quality or Solving-efficiency.

Evoked prior learning experience and approach to learning as predictors of academic achievement

Background. In separate studies and research from different perspectives, five factors are found to be among those related to higher quality outcomes of student learning (academic achievement). Those factors are higher self-efficacy, deeper approaches to learning, higher quality teaching, students’ perceptions that their workload is appropriate, and greater learning motivation. University learning improvement strategies have been built on these research results. Aim. To investigate how students’ evoked prior experience, perceptions of their learning environment, and their approaches to learning collectively contribute to academic achievement. This is the first study to investigate motivation and self-efficacy in the same educational context as conceptions of learning, approaches to learning and perceptions of the learning environment. Sample. Undergraduate students (773) from the full range of disciplines were part of a group of over 2,300 students who volunteered to complete a survey of their learning experience. On completing their degrees 6 and 18 months later, their academic achievement was matched with their learning experience survey data. Method. A 77-item questionnaire was used to gather students’ self-report of their evoked prior experience (self-efficacy, learning motivation, and conceptions of learning), perceptions of learning context (teaching quality and appropriate workload), and approaches to learning (deep and surface). Academic achievement was measured using the English honours degree classification system. Analyses were conducted using correlational and multi-variable (structural equation modelling) methods. Results. The results from the correlation methods confirmed those found in numerous earlier studies. The results from the multi-variable analyses indicated that surface approach to learning was the strongest predictor of academic achievement, with self-efficacy and motivation also found to be directly related. In contrast to the correlation results, a deep approach to learning was not related to academic achievement, and teaching quality and conceptions of learning were only indirectly related to achievement. Conclusions. Research aimed at understanding how students experience their learning environment and how that experience relates to the quality of their learning needs to be conducted using a wider range of variables and more sophisticated analytical methods. In this study of one context, some of the relations found in earlier bivariate studies, and on which learning intervention strategies have been built, are not confirmed when more holistic teaching–learning contexts are analysed using multi-variable methods.

Problem-based learning approaches in meteorology

Problem-Based Learning, despite recent controversies about its effectiveness, is used extensively as a teaching method throughout higher education. In meteorology, there has been little attempt to incorporate Problem-Based Learning techniques into the curriculum. Motivated by a desire to enhance the reflective engagement of students within a current field course module, this project describes the implementation of two test Problem-Based Learning activities and testing and improvement using several different and complementary means of evaluation. By the end of a 2-year program of design, implementation, testing, and reflection and re-evaluation, two robust, engaging activities have been developed that provide an enhanced and diverse learning environment in the field course. The results suggest that Problem-Based Learning techniques would be a useful addition to the meteorology curriculum and suggestions for courses and activities that may benefit from this approach are included in the conclusions.

The role of context in forming young learners' attitudes and motivation to learning French

Despite the wealth of valuable information that has been generated by motivation studies to date, there are certain limitations in the common approaches. Quantitative and psychometric approaches to motivation research that have dominated in recent decades provided epiphenomenal descriptions of learner motivation within different contexts. However, these approaches assume homogeneity within a given group and often mask the variation between learners within the same, and different, contexts. Although these studies have provided empirical data to form and validate theoretical constructs, they have failed to recognise learners as individual ‘people’ that interact with their context. Learning context has become increasingly explicit in motivation studies, (see Coleman et al. 2007 and Housen et al. 2011), however it is generally considered as a background variable which is pre-existing and external to the individual. Stemming from the recent ‘social turn’ (Block 2003) in SLA research from a more cognitive-linguistic perspective to a more context-specific view of language learning, there has been an upsurge in demand for a greater focus on the ‘person in context’ in motivation research (Ushioda 2011). This paper reports on the findings of a longitudinal study of young English learners of French as they transition from primary to secondary school. Over 12 months, the study employed a mixed-method approach in order to gain an in-depth understanding of how the learners’ context influenced attitudes to language learning. The questionnaire results show that whilst the learners displayed some consistent and stable motivational traits over the 12 months, there were significant differences for learners within different contexts in terms of their attitudes to the language classroom and their levels of self-confidence. A subsequent examination of the qualitative focus group data provided an insight into how and why these attitudes were formed and emphasised the dynamic and complex interplay between learners and their context.

Application of complex extreme learning machine to multiclass classification problems with high dimensionality: a THz spectra classification problem

We extend extreme learning machine (ELM) classifiers to complex Reproducing Kernel Hilbert Spaces (RKHS) where the input/output variables as well as the optimization variables are complex-valued. A new family of classifiers, called complex-valued ELM (CELM) suitable for complex-valued multiple-input–multiple-output processing is introduced. In the proposed method, the associated Lagrangian is computed using induced RKHS kernels, adopting a Wirtinger calculus approach formulated as a constrained optimization problem similarly to the conventional ELM classifier formulation. When training the CELM, the Karush–Khun–Tuker (KKT) theorem is used to solve the dual optimization problem that consists of satisfying simultaneously smallest training error as well as smallest norm of output weights criteria. The proposed formulation also addresses aspects of quaternary classification within a Clifford algebra context. For 2D complex-valued inputs, user-defined complex-coupled hyper-planes divide the classifier input space into four partitions. For 3D complex-valued inputs, the formulation generates three pairs of complex-coupled hyper-planes through orthogonal projections. The six hyper-planes then divide the 3D space into eight partitions. It is shown that the CELM problem formulation is equivalent to solving six real-valued ELM tasks, which are induced by projecting the chosen complex kernel across the different user-defined coordinate planes. A classification example of powdered samples on the basis of their terahertz spectral signatures is used to demonstrate the advantages of the CELM classifiers compared to their SVM counterparts. The proposed classifiers retain the advantages of their ELM counterparts, in that they can perform multiclass classification with lower computational complexity than SVM classifiers. Furthermore, because of their ability to perform classification tasks fast, the proposed formulations are of interest to real-time applications.

Enterprise Architecture adoption method for Higher Education Institutions

During the last few years Enterprise Architecture has received increasing attention among industry and academia. Enterprise Architecture (EA) can be defined as (i) a formal description of the current and future state(s) of an organisation, and (ii) a managed change between these states to meet organisation’s stakeholders’ goals and to create value to the organisation. By adopting EA, organisations may gain a number of benefits such as better decision making, increased revenues and cost reductions, and alignment of business and IT. To increase the performance of public sector operations, and to improve public services and their availability, the Finnish Parliament has ratified the Act on Information Management Governance in Public Administration in 2011. The Act mandates public sector organisations to start adopting EA by 2014, including Higher Education Institutions (HEIs). Despite the benefits of EA and the Act, EA adoption level and maturity in Finnish HEIs are low. This is partly caused by the fact that EA adoption has been found to be difficult. Thus there is a need for a solution to help organisations to adopt EA successfully. This thesis follows Design Science (DS) approach to improve traditional EA adoption method in order to increase the likelihood of successful adoption. First a model is developed to explain the change resistance during EA adoption. To find out problems associated with EA adoption, an EA-pilot conducted in 2010 among 12 Finnish HEIs was analysed using the model. It was found that most of the problems were caused by misunderstood EA concepts, attitudes, and lack of skills. The traditional EA adoption method does not pay attention to these. To overcome the limitations of the traditional EA adoption method, an improved EA Adoption Method (EAAM) is introduced. By following EAAM, organisations may increase the likelihood of successful EA adoption. EAAM helps in acquiring the mandate for EA adoption from top-management, which has been found to be crucial to success. It also helps in supporting individual and organisational learning, which has also found to be essential in successful adoption.

Assessment for Learning in teaching English to Young Learners: teachers’ understanding, classroom practice and impact on interactions

It has been suggested that Assessment for Learning (AfL) plays a significant role in enhancing teaching and learning in mainstream educational contexts. However, little empirical evidence can support these claims. As AfL has been shown to be enacted predominantly through interactions in primary classes, there is a need to understand if it is appropriate, whether it can be efficiently used in teaching English to Young Learners (TEYL) and how it can facilitate learning in such a context. This emerging research focus gains currency especially in the light of SLA research, which suggests the important role of interactions in foreign language learning. This mixed-method, descriptive and exploratory study aims to investigate how teachers of learners aged 7-11 understand AfL; how they implement it; and the impact that such implementation could have on interactions which occur during lessons. The data were collected through lesson observations, scrutiny of school documents, semi-structured interviews and a focus group interview with teachers. The findings indicate that fitness for purpose guides the implementation of AfL in TEYL classrooms. Significantly, the study has revealed differences in the implementation of AfL between classes of 7-9 and 10-11 year olds within each of the three purposes (setting objectives and expectations; monitoring performance; and checking achievement) identified through the data. Another important finding of this study is the empirical evidence suggesting that the use of AfL could facilitate creating conditions conducive to learning in TEYL classes during collaborative and expert/novice interactions. The findings suggest that teachers’ understanding of AfL is largely aligned with the theoretical frameworks (Black & Wiliam, 2009; Swaffield, 2011) already available. However, they also demonstrate that there are TEYL specific characteristics. This research has important pedagogical implications and indicates a number of areas for further research.