Analysis of asynchronous online discussion forums for collaborative learning

Online discussion forums are well suited for collaborative learning systems. Much of the currently available research indicates that effectively designed collaborative learning systems motivate and enhance learning experiences of the participants which in turn lead to enhanced learning outcomes. This paper develops taxonomy of the asynchronous online discussion forums with the aims of increasing the understanding and awareness of various types of asynchronous discussion forums. The taxonomy is framed by constructivist pedagogical principles of asynchronous online discussion forum. The key attributes of online discussions and the factors influencing the discussion forum’s design are identified. The taxonomy will help increase the online course designers’ ability to design more effective learning experiences for student success and satisfaction. It will also help researchers to understand the various features of the asynchronous discussion forums. The article concludes with implications for pedagogy and suggestions for the direction of future theoretical and empirical research.

Security concerns and remedy in a cloud based e-learning system

Cloud computing is an emerging technology and it utilizes the cloud power to many technical solutions. The e-learning solution is one of those technologies where it implements the cloud power in its existing system to enhance the functionality providing to e-learners. Cloud technology has numerous advantages over the existing traditional e-learning systems. However security is a major concern in cloud based e-learning. Therefore security measures are unavoidable to prevent the loss of users’ valuable data from the security vulnerabilities. This paper investigates various security issues involved in cloud based e-learning technology with an aim to suggest remedial in the form of security measures and security management standards. These will help to overcome the security threats in cloud based e-learning technology. Solving the key problems will also encourage the widespread adoption of cloud computing in educational institutes.

The hidden permutation model and location-based activity recognition

Permutation modeling is challenging because of the combinatorial nature of the problem. However, such modeling is often required in many real-world applications, including activity recognition where subactivities are often permuted and partially ordered. This paper introduces a novel Hidden Permutation Model (HPM) that can learn the partial ordering constraints in permuted state sequences. The HPM is parameterized as an exponential family distribution and is flexible so that it can encode constraints via different feature functions. A chain-flipping Metropolis-Hastings Markov chain Monte Carlo (MCMC) is employed for inference to overcome the O(n!) complexity. Gradient-based maximum likelihood parameter learning is presented for two cases when the permutation is known and when it is hidden. The HPM is evaluated using both simulated and real data from a location-based activity recognition domain. Experimental results indicate that the HPM performs far better than other baseline models, including the naive Bayes classifier, the HMM classifier, and Kirshner's multinomial permutation model. Our presented HPM is generic and can potentially be utilized in any problem where the modeling of permuted states from noisy data is needed.

Adaptive model for foreground extraction in adverse lighting conditions

Background elimination models are widely used in motion tracking systems. Our aim is to develop a system that performs reliably under adverse lighting conditions. In particular, this includes indoor scenes lit partly or entirely by diffuse natural light. We present a modified "median value" model in which the detection threshold adapts to global changes in illumination. The responses of several models are compared, demonstrating the effectiveness of the new model.

Classifying and detecting group behaviour from visual surveillance data

We outline an approach to classifying and detecting behaviours from surveillance data. Simple pairwise movement patterns are learned and used as building blocks to describe behaviour over a temporal sequence, or compared with other pairs to detect group behaviour. As the pair primitives are easy to redefine and learn, and complex behaviour over time is specified by the user as a sequence of pair primitives, this approach provides a flexible yet robust method of detecting complex movement in a wide variety of domains.

A hybrid neural network model for noisy data regression

A hybrid neural network model, based on the fusion of fuzzy adaptive resonance theory (FA ART) and the general regression neural network (GRNN), is proposed in this paper. Both FA and the GRNN are incremental learning systems and are very fast in network training. The proposed hybrid model, denoted as GRNNFA, is able to retain these advantages and, at the same time, to reduce the computational requirements in calculating and storing information of the kernels. A clustering version of the GRNN is designed with data compression by FA for noise removal. An adaptive gradient-based kernel width optimization algorithm has also been devised. Convergence of the gradient descent algorithm can be accelerated by the geometric incremental growth of the updating factor. A series of experiments with four benchmark datasets have been conducted to assess and compare effectiveness of GRNNFA with other approaches. The GRNNFA model is also employed in a novel application task for predicting the evacuation time of patrons at typical karaoke centers in Hong Kong in the event of fire. The results positively demonstrate the applicability of GRNNFA in noisy data regression problems.

On Operating Strategies of the Fuzzy Artmap Neural Network: A Comparative Study

In this paper, the effectiveness of three different operating strategies applied to the Fuzzy ARTMAP (FAM) neural network in pattern classification tasks is analyzed and compared. Three types of FAM, namely average FAM, voting FAM, and ordered FAM, are formed for experimentation. In average FAM, a pool of the FAM networks is trained using random sequences of input patterns, and the performance metrics from multiple networks are averaged. In voting FAM, predictions from a number of FAM networks are combined using the majority-voting scheme to reach a final output. In ordered FAM, a pre-processing procedure known as the ordering algorithm is employed to identify a fixed sequence of input patterns for training the FAM network. Three medical data sets are employed to evaluate the performances of these three types of FAM. The results are analyzed and compared with those from other learning systems. Bootstrapping has also been used to analyze and quantify the results statistically. [ABSTRACT FROM AUTHOR].

Keystroke patterns classification using the ARTMAP-FD neural network

This paper presents the development of a keystroke dynamics-based user authentication system using the ARTMAP-FD neural network. The effectiveness of ARTMAPFD in classifying keystroke patterns is analyzed and compared against a number of widely used machine learning systems. The results show that ARTMAP-FD performs well against many of its counterparts in keystroke patterns classification. Apart from that, instead of using the conventional typing timing characteristics, the applicability of typing pressure to ascertaining user's identity is investigated. The experimental results show that combining both latency and pressure patterns can improve the Equal Error Rate (ERR) of the system.

Fusion of GRNN and FA for online noisy data regression

A new online neural-network-based regression model for noisy data is proposed in this paper. It is a hybrid system combining the Fuzzy ART (FA) and General Regression Neural Network (GRNN) models. Both the FA and GRNN models are fast incremental learning systems. The proposed hybrid model, denoted as GRNNFA-online, retains the online learning properties of both models. The kernel centers of the GRNN are obtained by compressing the training samples using the FA model. The width of each kernel is then estimated by the K-nearest-neighbors (kNN) method. A heuristic is proposed to tune the value of Kof the kNN dynamically based on the concept of gradient-descent. The performance of the GRNNFA-online model was evaluated using two benchmark datasets, i.e., OZONE and Friedman#1. The experimental results demonstrated the convergence of the prediction errors. Bootstrapping was employed to assess the performance statistically. The final prediction errors are analyzed and compared with those from other systems.Bootstrapping was employed to assess the performance statistically. The final prediction errors are analyzed and compared with those from other systems.

The application of an ensemble of boosted elman networks to time series prediction : a benchmark study

In this paper, the application of multiple Elman neural networks to time series data regression problems is studied. An ensemble of Elman networks is formed by boosting to enhance the performance of the individual networks. A modified version of the AdaBoost algorithm is employed to integrate the predictions from multiple networks. Two benchmark time series data sets, i.e., the Sunspot and Box-Jenkins gas furnace problems, are used to assess the effectiveness of the proposed system. The simulation results reveal that an ensemble of boosted Elman networks can achieve a higher degree of generalization as well as performance than that of the individual networks. The results are compared with those from other learning systems, and implications of the performance are discussed.

Use of circle-segments as a data visualization technique for feature selection in pattern classification

One of the issues associated with pattern classification using data based machine learning systems is the “curse of dimensionality”. In this paper, the circle-segments method is proposed as a feature selection method to identify important input features before the entire data set is provided for learning with machine learning systems. Specifically, four machine learning systems are deployed for classification, viz. Multilayer Perceptron (MLP), Support Vector Machine (SVM), Fuzzy ARTMAP (FAM), and k-Nearest Neighbour (kNN). The integration between the circle-segments method and the machine learning systems has been applied to two case studies comprising one benchmark and one real data sets. Overall, the results after feature selection using the circle segments method demonstrate improvements in performance even with more than 50% of the input features eliminated from the original data sets.

A hybrid FAM–CART model and its application to medical data classification

In this paper, a hybrid model consisting of the fuzzy ARTMAP (FAM) neural network and the classification and regression tree (CART) is formulated. FAM is useful for tackling the stability–plasticity dilemma pertaining to data-based learning systems, while CART is useful for depicting its learned knowledge explicitly in a tree structure. By combining the benefits of both models, FAM–CART is capable of learning data samples stably and, at the same time, explaining its predictions with a set of decision rules. In other words, FAM–CART possesses two important properties of an intelligent system, i.e., learning in a stable manner (by overcoming the stability–plasticity dilemma) and extracting useful explanatory rules (by overcoming the opaqueness issue). To evaluate the usefulness of FAM–CART, six benchmark medical data sets from the UCI repository of machine learning and a real-world medical data classification problem are used for evaluation. For performance comparison, a number of performance metrics which include accuracy, specificity, sensitivity, and the area under the receiver operation characteristic curve are computed. The results are quantified with statistical indicators and compared with those reported in the literature. The outcomes positively indicate that FAM–CART is effective for undertaking data classification tasks. In addition to producing good results, it provides justifications of the predictions in the form of a decision tree so that domain users can easily understand the predictions, therefore making it a useful decision support tool.

From product centricism to systems-wide education design: making corporate technology systems work for the learning organisation

Deakin University has established a major integrated corporate technology infrastructure in the last two years to enhance and bring together its distance education and on-campus education. This environment has been called Deakin Online. With Deakin Online rapidly developing, efforts are beginning to focus more fundamentally on how the potentials of the environment can be realised to create enduring teaching and learning value. This search must be understood in the context of the University’s commitment to the values of relevance, responsiveness and innovation. The question is: how can these values be realised in the digitally-based evolving educational enterprise using the new corporate technologies and new concepts of organisational structure and function? We argue for the transforming role of the academic teacher and new forms of open academic collegiality as being critical to realise strategic and enduring educational value. Moreover, change in role and process needs to be grounded in more systemic organisation and program-wide approaches to designing and working within the new contemporary learning environments. We believe the shift from the dangers of product centricism to system-wide education design modelling situating e-learning within broader curricular and pedagogical concerns represents the best strategy to create enduring educational benefits for all stakeholder groups (notably academic teachers and their learners) while preserving teachers’ sense of agency in the changing learning environments of higher education.