Chuen-Tsai Sun

Neuro-fuzzy modeling and control

Fundamental and advanced developments in neuro-fuzzy synergisms for modeling and control are reviewed. The essential part of neuro-fuzzy synergisms comes from a common framework called adaptive networks, which unifies both neural networks and fuzzy models. The fuzzy models under the framework of adaptive networks is called adaptive-network-based fuzzy inference system (ANFIS), which possess certain advantages over neural networks. We introduce the design methods for ANFIS in both modeling and control applications. Current problems and future directions for neuro-fuzzy approaches are also addressed. >

Functional equivalence between radial basis function networks and fuzzy inference systems

It is shown that, under some minor restrictions, the functional behavior of radial basis function networks (RBFNs) and that of fuzzy inference systems are actually equivalent. This functional equivalence makes it possible to apply what has been discovered (learning rule, representational power, etc.) for one of the models to the other, and vice versa. It is of interest to observe that two models stemming from different origins turn out to be functionally equivalent.

Rule-base structure identification in an adaptive-network-based fuzzy inference system

We summarize Jangs architecture of employing an adaptive network and the Kalman filtering algorithm to identify the system parameters. Given a surface structure, the adaptively adjusted inference system performs well on a number of interpolation problems. We generalize Jangs basic model so that it can be used to solve classification problems by employing parameterized t-norms. We also enhance the model to include weights of importance so that feature selection becomes a component of the modeling scheme. Next, we discuss two ways of identifying system structures based on Jangs architecture: the top-down approach, and the bottom-up approach. We introduce a data structure, called a fuzzy binary boxtree, to organize rules so that the rule base can be matched against input signals with logarithmic efficiency. To preserve the advantage of parallel processing assumed in fuzzy rule-based inference systems, we give a parallel algorithm for pattern matching with a linear speedup. Moreover, as we consider the communication and storage cost of an interpolation model. We propose a rule combination mechanism to build a simplified version of the original rule base according to a given focus set. This scheme can be used in various situations of pattern representation or data compression, such as in image coding or in hierarchical pattern recognition. >

A neuro-fuzzy classifier and its applications

The authors propose a general fuzzy classification scheme with learning ability using an adaptive network. System parameters, such as the membership functions defined for each feature and the parameterized t-norms used to combine conjunctive conditions, are calibrated with backpropagation. To explain this approach, the concept of adaptive networks is introduced and a supervised learning procedure based on a gradient descent algorithm is derived to update the parameters in an adaptive network. The proposed architecture is applied to two problems: two-spiral classification and Iris categorization. From the experimental results, it is concluded that the adaptively adjusted classifier performs well on an Iris classification problem. The results are discussed from the viewpoint of feature selection.<<ETX>>

Player Guild Dynamics and Evolution in Massively Multiplayer Online Games

In the latest versions of massively multiplayer online games (MMOGs), developers have purposefully made guilds part of game environments. Guilds represent a powerful method for giving players a sense of online community, but there is little quantitative data on guild dynamics. To address this topic, we took advantage of a feature found in one of todays most popular MMOGs (World of Warcraft) to collect in-game data: user interfaces that players can modify and refine. In addition to collecting data on in-game player activities, we used this feature to observe and investigate how players join and leave guilds. Data were analyzed for the purpose of identifying factors that propel game-world guild dynamics and evolution. After collecting data for 641,805 avatars on 62 Taiwanese World of Warcraft game servers between February 10 and April 10, 2006, we created five guild type categories (small, large, elite, newbie, and unstable) that have different meanings in terms of in-game group dynamics. By viewing players as the most important resource affecting guild life cycles, it is possible to analyze game worlds as ecosystems consisting of evolving guilds and to study how guild life cycles reflect game world characteristics.

Predicting chaotic time series with fuzzy if-then rules

The authors continue work on a previously proposed ANFIS (adaptive-network-based fuzzy inference system) architecture, with emphasis on the applications to time series prediction. They show how to model the Mackey-Glass chaotic time series with 16 fuzzy if-then rules. The performance obtained outperforms various standard statistical approaches and artificial neural network modeling methods reported in the literature. Other potential applications of ANFIS are also suggested.<<ETX>>

Constructing hysteretic memory in neural networks

Hysteresis is a unique type of dynamic, which contains an important property, rate-independent memory. In addition to other memory-related studies such as time delay neural networks, recurrent networks, and reinforcement learning, rate-independent memory deserves further attention owing to its potential applications. In this paper, we attempt to define hysteretic memory (rate independent memory) and examine whether or not it could be modeled in neural networks. Our analysis results demonstrate that other memory-related mechanisms are not hysteresis systems. A novel neural cell, referred to herein as the propulsive neural unit, is then proposed. The proposed cell is based on a notion related the submemory pool, which accumulates the stimulus and ultimately assists neural networks to achieve model hysteresis. In addition to training by backpropagation, a combination of such cells can simulate given hysteresis trajectories.

Building a player strategy model by analyzing replays of real-time strategy games

Developing computer-controlled groups to engage in combat, control the use of limited resources, and create units and buildings in real-time strategy (RTS) games is a novel application in game AI. However, tightly controlled online commercial game pose challenges to researchers interested in observing player activities, constructing player strategy models, and developing practical AI technology in them. Instead of setting up new programming environments or building a large amount of agentpsilas decision rules by playerpsilas experience for conducting real-time AI research, the authors use replays of the commercial RTS game StarCraft to evaluate human player behaviors and to construct an intelligent system to learn human-like decisions and behaviors. A case-based reasoning approach was applied for the purpose of training our system to learn and predict player strategies. Our analysis indicates that the proposed system is capable of learning and predicting individual player strategies, and that players provide evidence of their personal characteristics through their building construction order.

An educational genetic algorithms learning tool

During the last thirty years, there has been a rapidly growing interest in a field called genetic algorithms (GAs). The field is at a stage of tremendous growth as evidenced by the increasing number of conferences, workshops and papers concerning it, as well as the emergence of a central journal for the field. With their great robustness, genetic algorithms have proven to be a promising technique for many optimization, design, control, and machine learning applications. Students who take a GAs course study and implement a wide range of difference techniques of GAs. And practical implementation experience plays a very important role in learning computer relative courses. Herein, an educational genetic algorithm learning tool (EGALT) has been developed to help students facilitate GAs course. With the readily available tool students can reduce the mechanical programming aspect of learning and concentrate on principles alone. A friendly graphic user interface was established to help students operate and control not only the structural identification but also the parametric identification of GAs. It outlines how to implemented genetic algorithms, how to set parameters of different kinds of problems, and recommends a set of genetic algorithms, which were suggested in previous studies.

Cash Trade in Free-to-Play Online Games:

The rapidly expanding ‘‘free-to-play’’ online game payment model represents a huge shift in digital game commercialization, with cash payments for virtual items increasingly recognized as central to ‘‘free game’’ participation. In this article, the authors look at implications of this trend for gameplay experiences (especially in terms of immersion, fairness, and fun) and describe a fundamental shift in player self-perceptions as consumers rather than members of a gaming community. This change is occurring at a time when the line separating game and physical worlds is becoming less distinct. The new business model entails a subtle but significant reduction in consumer rights awareness, which explains why some members of the greater gaming community are negotiating a new sense of fairness and arriving at a new consensus regarding legitimate gameplay.