Search

Spatial interpolation is a method to create spatial continuous surface from observed data points. Spatial interpolation is important to water management and planning because it could provide estimation of rainfall at unobserved area. This paper proposes a methodology to analyze and establish an integrated intelligent spatial interpolation model for monthly rainfall data. The proposed methodology starts with determining the optimal number of sub-regions by means of standard deviation analysis and artificial neural networks. Once the optimal number of sub-regions is determined, a Mamdani fuzzy inference system is generated by fuzzy c-means and then optimized by genetic algorithm. Four case studies were used to evaluate the accuracy of the established models and compared with trend surface analysis and artificial neural networks. The experimental results demonstrated that the proposed methodology provided reasonable interpolation accuracy and the methodology gave human understandable fuzzy rules to human analysts.

Estimation of missing precipitation records is one of the important tasks in hydrological study. The completeness of precipitation data leads to more accurate results from the hydrological models. This study proposes the use of modular artificial neural networks to estimate missing monthly rainfall data in the northeast region of Thailand. The simultaneous rainfall data from neighboring control stations are used to estimate missing rainfall data at the target station. The proposed method uses two artificial neural networks to learn the generalized relationship of rainfall recorded in dry and wet periods. Inverse distance weighting method and optimized weight of subspace reconstruction method are used to aggregate the final estimation value from both networks. The experimental results showed that modular artificial neural networks provided a higher accuracy than single artificial neural network and other conventional methods in terms of mean absolute error.

In recent years, the advancement in gaming interface has paved ways for faster and more interactive gameplay. There is now an increasing trend of using Natural User Interface (NUI) for computer games. This has also brought forward new challenges in game design and using non-touch based NUI in games is not simply replacing the existing interaction techniques. A lot of new game design considerations must be carefully thought out, planned and implemented, or otherwise the gameplay will suffer and, could cause frustration and dissatisfaction to the players. This paper discusses non-touch based Natural User Interface (NUI) and the factors that need to be considered by designers of games in designing games that uses this new user interface. Many considerations must be addressed to create the effective user experience when using NUI. This paper provides a framework of game design considerations that can be classified into three main categories: (1) user based analysis, (2) function based analysis, and (3) ambient based analysis. In this paper the following considerations have been identified and they fall under these three main categories: 1) User based analysis • Target Audience • Genre 2) Function based analysis • Players' Perceived Playability • Gaming Space Requirement • Suitable Gestures • Gestural Control • Multi-Player/Single Player 3) Ambient based analysis • Speech Control & Audio Elements • Iconography • Types of Display Screen Since the use of NUI is a new phenomenon in games, the design considerations presented in this paper are by no means exhaustive. However, the discussions provided in this paper can reveal potential areas for future research in the field of nontouch based NUI for games.

Educational robotics involve using robots as an educational tool to provide a long term, and progressive learning activity, to cater to different age group. The current concern is that, using robots in education should not be an instance of a one-off project for the sole purpose of participating in competitive event. Instead it should be a sustainable long term progression spanning the primary school to pre-university level. This paper presents a framework for robotics using a multiphase approach to enhance user learning in a competitive arena.

This study aims to investigate the effects of a virtual reality (VR)- based learning environment on learners with different learning styles. The learning outcomes were measured cognitively through academic performance, and affectively through perceived learning effectiveness and satisfaction. A pretest-posttest design was employed for this study. A total of 232 students from four randomly selected co-education secondary schools in a city of East Malaysia participated in this study. There was no significant difference in the cognitive and affective learning outcomes for students with different learning styles in the VR-based learning environment. This shows that the VR-based learning environment offers promise in accommodating individual differences pertaining to learning styles.

In computerised version of board games, player satisfaction can be augmented by providing explanation of what the computer based AI analytical processes are. This helps the players to understand the reasoning behind the action taken by the computer AI opponent. This paper proposes a method that provides the mechanism for a game AI to communicate its evaluation processes using descriptive auto-explanation through symbolic reasoning. A case study is presented in an implementation of a game AI opponent that is capable of describing its inferential processes in a tabletop war game.

Ancient manuscripts have been preserved by many organizations so as to protect these documents and retrieve traditional knowledge. With the advanced computer technology, digitized media is now commonly used to record these documents. One objective of such work is to develop an efficient image processing system that could be used to retrieve knowledge and information automatically from these ancient manuscripts. Binarization is a preprocessing technique used to extract text and characters from the manuscripts. The output is then used for further processes such as character recognition and knowledge extraction. This paper compares different binarization techniques that could be used for processing of ancient manuscripts. The aim is to improve the binarization techniques with the main objective of developing an automated preprocessing technique for ancient manuscript recognition and knowledge extraction.

There is much attention given to emerging technologies like mobile internet because of its increasing popularity. Much research has concentrated on hardware and some have focused on personalisation in terms of content visualisation. The focus of this paper is on mobile content personalisation, seeking to understand the user groups through clustering users based on their profile. This paper focuses on the implementation of a technique known as ‘Zoning- Centroid’, which is the evaluation technique used to determine the appropriate number of clusters required to best cluster the given users profile. The user profile used in this paper includes mobile content usage and their demographic factors. The clustering algorithm used in this paper is k-means clustering. The results show that the proposed technique could suggest appropriate number of clusters to be used with the k-values, in order to implement for mobile entertainment content personalisation.

In classification, when the distribution of the training data among classes is uneven, the learning algorithm is generally dominated by the feature of the majority classes. The features in the minority classes are normally difficult to be fully recognized. In this paper, a method is proposed to enhance the classification accuracy for the minority classes. The proposed method combines Synthetic Minority Over-sampling Technique (SMOTE) and Complementary Neural Network (CMTNN) to handle the problem of classifying imbalanced data. In order to demonstrate that the proposed technique can assist classification of imbalanced data, several classification algorithms have been used. They are Artificial Neural Network (ANN), k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM). The benchmark data sets with various ratios between the minority class and the majority class are obtained from the University of California Irvine (UCI) machine learning repository. The results show that the proposed combination techniques can improve the performance for the class imbalance problem.

This paper proposes a non-segmented document clustering method using self-organizing map (SOM) and frequent max substring mining technique to improve the efficiency of information retrieval. The proposed technique appears to be a promising alternative for clustering non-segmented text documents. To illustrate the proposed technique, experiment on clustering the Thai text documents is presented in this paper. The frequent max substring mining technique is first applied to discover the patterns of interest called Frequent Max substrings or FM from the non-segmented Thai text documents. These discovered patterns are then used as indexing terms, together with their number of occurrences, to form a document vector. SOM is then applied to generate the document cluster map by using the document vector. As a result, the generated document cluster map can be used to find the relevant documents according to a user's query more efficiently.

Many social robots in the forms of conversation agents or Chatbots have been put to practical use in recent years. Their typical roles are online help or acting as a cyber agent representing an organisation. However, there exists a new form of devious chatbots lurking in the Internet. It is effectively an interactive malware seeking to lure its prey not through vicious assault, but with seductive conversation. It talks to its prey through the same channel that is normally used for human-to-human communication. These devious chatbots are using social engineering to attack the uninformed and unprepared victims. This type of attacks is becoming more pervasive with the advent of Web 2.0. This survey paper presents results from a research on how this breed of devious Malware is spreading, and what could be done to stop it.

Mobile device is an important gadget for many people today, regardless whether it is used for communication, entertainment or keeping up to date. With the advancement of mobile Internet, mobile devices are also used for many conventional PC based Internet applications. One such example is downloading games. Downloading mobile games via mobile device seems to be one of the more favorite activities for many mobile devices today. However, users may have different preferences in what genres of games they will be more interested in at different time of the day. In this paper, a personalised mobile game recommendation system which takes into consideration the time-of-day and time-of-week is used to provide a more personalised experience. From the data collected, it can be seen that at different time periods users may download different games and from different game genres.

This paper describes the intelligent automated guided vehicle (AGV) control system. The AGV used in this paper is a virtual vehicle simulated using computer. The purpose of the control system is to control the simulated AGV for moving along the given path towards the goal. Some obstacles can be placed on or near the path to increase the difficulties of the control system. The intelligent AGV should trace the path by avoiding these obstacles. In some situations, it is inevitable to avoid the obstacles without reversing. In this paper, we look into the use of fuzzy automaton for controlling the AGV. In order to better avoid the obstacles, reverse strategy has been implemented to the fuzzy automaton controller. Another alternative to incorporate the human expertise and observations is to use a hybrid intelligent controller using fuzzy and case base reasoning to implement the reverse strategy. This paper presents the comparison results for the three intelligent AGV systems used to avoid obstacles.

In this paper, we examine the use of Artificial Neural Networks (ANNs) for designing an adaptive computer game system. This adaptive computer game system will enhance the game play experience of a player by adopting the concept of player centred game design. In this paper, the ANN is used to handle the dynamic difficulty level adjustment for each individual player. The difficulty level for each player can be customised using the proposed method, thus allowing game player to have a more personalised game play experience.

The major concern of educators is how to enhance the outcome of education. Better education media used to assist teaching has constantly been sought by researchers in the educational technology domain. Virtual Reality (VR) has been identified as one of them. Many have agreed that VR could help to improve performance and conceptual understanding on a specific range of task. However, there is limited understanding of how VR could enhance the learning outcomes. This paper reviews types of VR that have been used for learning, the theoretical framework for a VR learning environment, and instructional design for VR-based learning environment. Further research is suggested for VR-based learning environment.

As data is getting more complex and complicated, it is increasingly difficult to construct an effective complex decision model. Two very obvious examples where such a need emerges are in the economic and the medical fields. This paper presents the fuzzy signature and cognitive modeling approach which could improve such decision models. Fuzzy signatures are introduced to handle complex structured data and problems with interdependent features. A fuzzy signature can also be used in cases where data is missing. The proposed fuzzy signature structure will be used in problems that fall into this category. This paper also investigates a novel cognitive model to extend the usage of fuzzy signatures. This Fuzzy Cognitive Signature Modelling will enhance the usability of fuzzy theory in modelling complex systems as well as facilitating complex decision making process based on ill structured information or data.

Over the last decade, Evolutionary Algorithms (EAs) have emerged as a powerful paradigm for global optimization of multimodal functions. More recently, there has been significant interest in applying EAs to engineering design problems. However, in many complex engineering design problems where high-fidelity analysis models are used, each function evaluation may require a Computational Structural Mechanics (CSM), Computational Fluid Dynamics (CFD) or Computational Electro-Magnetics (CEM) simulation costing minutes to hours of supercomputer time. Since EAs typically require thousands of function evaluations to locate a near optimal solution, the use of EAs often becomes computationally prohibitive for this class of problems. In this chapter, we present frameworks that employ surrogate models for solving computationally expensive optimization problems on a limited computational budget. In particular, the key factors responsible for the success of these frameworks are discussed. Experimental results obtained on benchmark test functions and real-world complex design problems are presented.

This paper presents a feature ranking method adapted to fuzzy modelling with output from a continuous range. Existing feature selection/ranking techniques are mostly suitable for classification problems, where the range of the output is discrete. These techniques result in a ranking of the input feature (variables). Our approach exploits an arbitrary fuzzy clustering of the model output data. Using these output clusters, similar feature ranking methods can be used as for classification, where the membership in a cluster (or class) will no longer be crisp, but a fuzzy value determined by the clustering. We propose the application of the Sequential Backward Selection (SBS) search method to determine the feature ranking by means of different criterion functions. We examined the proposed method and the criterion functions through a comparative analysis.

We introduce a simple fuzzy technique to improve the prediction decision accuracy of a bioinformatics neural network system from the literature for protein structure prediction. We also describe an unsound assumption made by the authors of the neural network system, and propose a fuzzy hybrid solution, which eliminates the need for this assumption and can further enhance performance.

Fuzzy modeling has become very popular because of its main feature being the ability to assign meaningful linguistic labels to the fuzzy sets in the rule base. This paper examines Sugeno and Yasukawa's qualitative modeling approach, and addresses one of the remarks in the original paper. We propose a cluster search algorithm that can be used to provide a better projection of the output space to the input space. This algorithm can efficiently identify two or more fuzzy clusters in the input space that have the same output fuzzy cluster.

This paper reports the use of association rules for the discovery of lithofacies characteristics from well log data. Well log data are used extensively in the exploration and evaluation of petroleum reservoirs. Traditionally, discriminant analysis, statistical and graphical methods have been used for the establishment of well log data interpretation models. Recently, computational intelligence techniques such as artificial neural networks and fuzzy logic have also been employed. In these techniques, prior knowledge of the log analysts is required. This paper investigated the application of association rules to the problem of knowledge discovery. A case study has been used to illustrate the proposed approach. Based on 96 data points for four lithofacies, twenty association rules were established and they were further reduced to six explicit statements. It was found that the execution time is fast and the method can be integrated with other techniques for building intelligent interpretation models.

In this paper, we present a new and simple method for function interpolation based on the use of neural networks and fuzzy logic. We particularly discuss the application of the technique in spatial data analysis. In this application domain, conventional early-stopping criteria to avoid over-training in neural networks based on the use of minimum error on validation set, may not be suitable. In the proposed method, we use “interpolated error” to stop training. The trained networks are used as fuzzy rules, and these rules are interpolated to the location of interest. We demonstrate the methodology in petroleum reservoir modelling in which properties are estimated between two oil wells. Data from a third well, which are withheld from the training process, is used to evaluate different prediction models. We also compare our method with the recent data-splitting approach using self-organising map (SOM) with the use of early-stopping in neural training. The results of this study show that the SOM approach is only applicable to wells in which their locations are half-way between the two given wells. The proposed methodology, however, provides the best results in the test well and is also suitable for any location of interest. The end result is a simple and computationally-cheap method in engineering studies.

International audience; As the popularity of computer games has increased markedly in recent years, many researchers have become concerned with the potential effects on gamers. However, by looking past the outward appearance of popular games that may be perceived as violent by some, we can begin to see dramatic cultural indicators as well as many other academically interesting phenomena emerging. Social psychologists and effects researchers must begin delving deeper into this rapidly expanding genre of popular media. Herein, I propose three possible approaches to the study of video games as cultural events rather than a common medium that influences participants in a simple way.

International audience; Haptic Modeling of textile has attracted significant interest over the last decade. In spite of extensive research, no generic system has been proposed. The previous work mainly assumes that textile has a 2D planar structure. They also require time-consuming objective measurement of textile properties in mechanical/physical model construction. A novel approach for haptic modeling of textile is proposed to overcome the existing shortcomings. The method is generic, assumes a 3D structure textile artifact, and deploys computational intelligence to estimate textile mechanical and physical properties. The approach is designed primarily for display of textile artifacts in museums. The haptic model is constructed by superimposing the mechanical model of textile over its 3D geometrical model. Digital image processing is applied to the still image of textile to identify its pattern and structure. In order to deal with the non-linearities associated with the textile, a fuzzy rule-based expert system is deployed. This information is then used to generate a 3D geometric model of the artifact in VRML. Selected mechanical and physical properties of the textile are estimated by an artificial neural network with the textile geometric characteristics and yarn properties as inputs. The neural network learning and verification and validation processes are carried out by a sample data set. The mechanical properties are used in the construction of the textile mechanical model. The haptic rendered model is generated by superimposing the physical/mechanical model over the 3D geometric model. This model has been implemented and rendered in Reachin environment, provided an interactive Virtual Reality environment where the user can navigate the graphic 3D presentation of the textile and touch it by a haptic device. Different samples have been modeled and the whole approach has been validated. The interface can be provided in both in the physical environment and through the cyberspace. The validation of method indicates the feasibility of the approach and its superiority to other haptic modeling algorithms.

International audience; This paper describes the development of a haptic device for emulating the sonic and haptic dynamics of a carillon, specifically the National Carillon in Canberra, Australia. The carillon is one of only a few instruments that elicit a sophisticated haptic response from the amateur and professional player alike. Force-feedback varies widely across the range of the instrument and developing an intuition for the heaviness of different bells is a critical part of carillon pedagogy. Unfortunately, rehearsal time available to individual carillonneurs is limited by competition from other carillonneurs and environmental factors like civic noise limits and carillon maintenance schedules. Rehearsal instruments do exist but they do not accurately display the haptic dynamics of the real carillon. Our device couples the notions of entertainment and cultural computing; while musical instruments are now regularly digitised for purposes of entertainment the haptic carillon is motivated by an awareness of the musicianship of carillonneurs and the public cultural space they inhabit with their instrument.