Successive pattern classification based on test feature classifier and its application to defect image classification

A novel successive learning algorithm based on a Test Feature Classifier is proposed for efficient handling of sequentially provided training data. The fundamental characteristics of the successive learning are considered. In the learning, after recognition of a set of unknown data by a classifier, they are fed into the classifier in order to obtain a modified performance. An efficient algorithm is proposed for the incremental definition of prime tests which are irreducible combinations of features and capable of classifying training patterns into correct classes. Four strategies for addition of training patterns are investigated with respect to their precision and performance using real pattern data. A real-world problem of classification of defects on wafer images has been dealt with by the proposed classifier, obtaining excellent performance even through efficient addition strategies.     

Post-Supervised Template Induction for Information Extraction from Lists and Tables in Dynamic Web Sources

Dynamic web sites commonly return information in the form of lists and tables. Although hand crafting an extraction program for a specific template is time-consuming but straightforward, it is desirable to automatically generate template extraction programs from examples of lists and tables in html documents. Supervised approaches have been shown to achieve high accuracy, but they require manual labelling of training examples, which is also time consuming. Fully unsupervised approaches, which extract rows and columns by detecting regularities in the data, cannot provide sufficient accuracy for practical domains. We describe a novel technique, Post-supervised Learning, which exploits unsupervised learning to avoid the need for training examples, while minimally involving the user to achieve high accuracy. We have developed unsupervised algorithms to extract the number of rows and adopted a dynamic programming algorithm for extracting columns. Our method achieves high performance with minimal user input compared to fully supervised techniques.     

Value management and common accounting performance measures for corporations

Management is aware that the value of firms is the ultimate measure of company performance. However, management has been using common accounting measures as an operating guide because the linkage between operational planning and value is vague and complex and, therefore, difficult to apply. Managers need to have clear targets and performance measures to track progress. This paper examines if a set of common accounting performance measures are linked tightly to the overall value of the firm. An abductive learning network (ALN) approach, an artificial intelligence technique, is used in this research because an ALN approach is non-parametric and can capture a subtle dynamic relationship between input and output variables, which is not obvious in linear statistical analysis. Empirical results show that an ALN model is very effective in synthesizing the value of the firm using six common accounting variables. The results also provide four strategic variables that can be used for devising strategic and operating plans to maximize the value of firms.     

提高网络教学效果的方法浅析

中国的网络远程教育目前也正处于蓬勃发展的阶段,各种远教机构如雨后春笋般涌现。但在远教课程向网络转型的过渡时期,难免会有各种不尽如人意的地方。设计不够贴近学生、缺乏师生互动和技术运用的片面与僵化等是很多网络课程常有的通病。如何在课程设计上进行改进,使网络课程更具人性化,真正实现以学生为中心,是中国网络教育更上一层楼的关键问题之一。     

Virtual teamwork in very large undergraduate classes

Collaborative work is an important part of tertiary education but it is very difficult to arrange and supervise for extremely large classes of students in their first year. The possibility that computer-mediated communication can be used to facilitate this type of learning is appealing from a pragmatic organisational point of view. This paper explains in detail what a ‘virtual team’ is in the educational context. It reports on an interpretive field study where students taking an introductory course were allowed to choose where and when they did the required collaborative work. The paper discusses the factors that should be taken into account when offering students the option of working as a virtual team. These include factors that influence the students’ choice. The project cannot be considered to have been successful but indicates reasons for the lack of success and suggests contexts in which it would be valuable to repeat the project. The importance of extensive preparation in terms of teaching the students necessary social and technological skills cannot be over emphasised.     

A hierarchical model for structure learning based on the physiological characteristics of neurons

Almost all applications of Artificial Neural Networks (ANNs) depend mainly on their memory ability. The characteristics of typical ANN models are fixed connections, with evolved weights, globalized representations, and globalized optimizations, all based on a mathematical approach. This makes those models to be deficient in robustness, efficiency of learning, capacity, anti-jamming between training sets, and correlativity of samples, etc. In this paper, we attempt to address these problems by adopting the characteristics of biological neurons in morphology and signal processing. A hierarchical neural network was designed and realized to implement structure learning and representations based on connected structures. The basic characteristics of this model are localized and random connections, field limitations of neuron fan-in and fan-out, dynamic behavior of neurons, and samples represented through different sub-circuits of neurons specialized into different response patterns. At the end of this paper, some important aspects of error correction, capacity, learning efficiency, and soundness of structural representation are analyzed theoretically. This paper has demonstrated the feasibility and advantages of structure learning and representation. This model can serve as a fundamental element of cognitive systems such as perception and associative memory.     

Tracing success: graphical methods for analysing successful collaborative problem solving

The aim of this paper is to evaluate the use of trace diagrams for analysing collaborative problem solving. The paper describes a study where trace diagrams were used to analyse joint navigation in a virtual environment. Ten pairs of undergraduates worked together on a distributed virtual task to collect five flowers using two bees with each participant controlling one of the bees. This task is used extensively in research on multi-robot systems. The joint navigation of the pairs was analysed using trace diagrams. They showed that more successful pairs divided the task up, showed very little overlap and very little backtracking. Whereas, the less successful pairs, showed no task division, there was significant overlap and extensive backtracking. From this analysis we developed numerical measures of task division, overlap and backtracking. Task division was significantly and negatively related with task performance. Backtracking and overlap were significantly and positively correlated.     

Global Level Path Planning for Mobile Robots in Dynamic Environments

This paper presents a self-adapting approach to global level path planning in dynamic environments. The aim of this work is to minimize risk and delays in possible applications of mobile robots (e.g., in industrial processes). We introduce a hybrid system that uses case-based reasoning as well as grid-based maps for decision-making. Maps are used to suggest several alternative paths between specific start and goal point. The casebase stores these solutions and remembers their characteristics. Environment representation and casebase design are discussed. To solve the problem of exploration vs. exploitation, a decision-making strategy is proposed that is based on the irreversibility of decisions. Forgetting strategies are discussed and evaluated in the context of case-based maintenance. The adaptability of the system is evaluated in a domain based on real sensor data with simulated occupancy probabilities. Forgetting strategies and decision-making strategies are evaluated in simulated environments. Experiments show that a robot is able to adapt in dynamic environments and can learn to use paths that are less risky to follow.