Transactions on Edutainment XII

In this paper we present an Interactive Digital Storytelling (IDS) formalisation that captures the IDS logic constraints. This was implemented in a game engine and an authoring tool was created to facilitate the development of IDS based games. We created several IDS based games using the proposed engine and authoring tool. They were used as case studies in this research. We also present some of the challenges we encountered once the games were implemented and how we addressed them.

Applied game aims to help player accumulate knowledge, improve skills, or enhance emotion quotient through game playing process. Although many applied games have been developed in education and training fields, the solution on issues of balance between education and entertainment is still open. This study proposes a methodology for integrating knowledge with applied game combining recreational functions and pedagogic effect. For the purpose, the unified representation based on ontology is employed for game elements, game challenge model and knowledge expression with which the relationship mapping mechanism from diverse categories of knowledge onto game atomic element, especially primary rule, is constructed. As a result, a practical design technique that facilitates to import knowledge into applied game is achieved. In order to verify the practicability, a case of applied game, Qbaby Picture Matching game is designed and developed based on the proposed method. It has been running online and applied in a kindergarten. Moreover, an experiment is performed to identify the effects of education and entertainment. The results imply that the game can definitely produce recreational functions and pedagogic effect. The fact indirectly verifies that the methodology may effectively integrate knowledge with game thereby providing a referable solution for issues of education and entertainment balance.

The interactive mode and scene effect of games are facing more and more challenges with increasing attention given by game players. Augmented Reality produces a real-time 3D display effect by overlaying virtual information with the real world. Augmented reality technology is applied in this article to develop an AR basketball smart phone game. Users can control the interaction of their counterparts in the virtual world through image characteristics identification card, which is interactive and playable. The game not only combines entertainment with education, but also offers an immersive experience. More importantly, it is designed to promote the concept that teenagers are expected to change the world through their intelligence and wisdom as well as to have sports and exercise.

By the 20th century, with the swift development in digital technology such as computer, network and multimedia, digital games have created an enormous social impact on all aspects of the community. Evolving from the initial simple means of entertainment to an interactive media visual culture, it would have more significant impact on human culture. Given its new form of technology-based representation, we need to examine it from a new horizon accordingly. This paper aims to articulate the cultural characteristics of digital games from three aspects, mass media, mass culture, international communication.

Finding 3D hand models corresponding to the user’s 3D hand pose in the initial frames makes the initialization for the 3D hand model much more significant in 3D human hand tracking. Blending computer interaction techniques and cognition theories, a novel initialization approach for 3D hand model is put forward in the present paper to make the initialization process more human-oriented. The proposed initialization process is primarily divided into three steps. The first step is the approximate classification of the user’s poses as dominated by a computer. The second step is to adjust by freehand as dominated by the user. The third step is to modify the 3D hand model as dominated by the computer. The present study attempts to describe and shape the user’s behavioral model, upon the initialization algorithm is designed and optimized. To improve the performance of the initialization algorithm, User experience, time cost, and accuracy are fused into an evaluation criterion for the optimization of the proposed algorithm. The main contributions of the present work consists of modeling the operator’s cognitive behavior, attempting to answer why and how the cognitive behavioral model guides the proposed algorithm in assigning tasks for the initialization between human and computer. The experimental results demonstrate good performance by the proposed method and its potential applications. In addition, the proposed approach could provide the user with an easier, more pleasurable, and more satisfactory experience. The developed initialization system is successfully applied to several application systems.

This paper develops a method for recognition of human daily actions by using wearable motion sensor system. It can recognize 13 daily actions with the data in WARD1.0 efficiently. We just extract 11 features including the means and variances of vertical acceleration data of five sensors and the mean of horizontal angular speeds of the waist sensor. Then we randomly select 80 % of the samples as the training set, and the remaining samples as the test set. By removing the abnormal samples based on the confidence interval of the distance among the same type samples and using the SVM as the classifier, we present a new method for recognition of the human daily actions. Moreover, we optimize the parameters of SVM with K-CV (K-fold Cross Validation) method. The results of the experiments show that the proposed method can efficiently identify the 13 kinds of daily actions. The rate average recognition can approach to 98.5 %.

In order to solve the physical rehabilitation of stroke patients with apoplectic hemiplegia, an intelligent rehabilitation supporting system based on Kinect device is designed. The system uses Kinect device to capture the user’s limb joints point information. DTW algorithm is combined with RANSAC algorithm to match the action in standard action library, thus the system can obtain the evaluation results. Then the patients’ rehabilitation data is sent to the doctors with new treatment options intelligently. As a result, the experimental results show that this physical rehabilitation method is more convenient and efficient than the traditional training method.

To gesture interaction based on computer vision, the effective area of hand activity is often the whole reach captured by cameras, so some subconscious action of users may be interpreted as effective computer command. In order to address this problem, we put forward the concept of virtual interface, which makes the effective area of hand activity narrow to a specific region. As the gesture in the virtual interface is regarded as effective, while the gesture outside it is regarded as invalid, it is possible to solve the “Midas Touch Problem”. To begin with, we identify the position and size of virtual interface by utilizing the least square method through learning process. Then users interact with computer by virtual interface, during which the gesture commands are released through it. The experimental results show that the proposed virtual interface can efficiently solve the “Midas Touch Problem” and has a good user experience.

Propose a novel pixel-level change detection method based on the fuzzy distance for the interest building areas. Based on the imaging characteristic of Synthetic Aperture Radar (SAR) Images building areas, the variogram texture and gray feature are combined to be the feature vector in order to describe the image pixel feature clearly. And then the different image is computed using the fuzzy distance for detecting changes and obtaining quantitative detection results. Experimental results show that the proposed algorithm is feasible and effective to detect the change areas.

We propose a fast plant modeling method based on BP neural network. The input is a plant image. Users can sketch the main branches and crown silhouettes on the image. Through branch copying, rotation and adjustment, the 3D main branches are obtained. A BP neural network is built and trained by analyzing the parameters of main branches. This network is used to forecast the parameters of small branches generated based on self-similarity. Finally, leaves are added and a 3D plant model resembling the input image is built. This method is based on one image and sketch. 2D sketch information is fully used for training the BP neural network and then forecasting the small branch parameters. This method relies on no database, and can be applied to many plant species. The experiments show that it runs fast and can build realistic plant models.

In the augmented reality systems, in order to give users results of visual consistency, the key is to achieve a virtual object and the real scene seamless overlay, combined with complex scenes direction of the light source to achieve a true desktop environment based on augmented reality systems, and in the system implements the seamless integration of the actual situation, including static and dynamic two parts. You first need to get the real scene of three-dimensional computer data in conjunction with the relevant algorithm to achieve, then the virtual object should be consistent with the real scene of human action, that is, action by the user to control the virtual object moves, mainly using Kinect tracking and bones action recognition, combined with interactive 3D engine to achieve.

Edge detection is an important step for extracting interesting feature information in image processing and computer vision. Although ant colony optimization (ACO) has been improved by using distributed adaptive threshold strategy (DATS), the artificial ants of this approach still easily ignore weak edges with lower edge gradient which results in detecting discontinuous edges of interesting features. To detect more continuous edges of features by using ACO in color and gray scale images, this work proposes an image pre-processing for ACO with DATS. The result of image pre-processing, which is the image after binarization processing by using adaptive threshold generated form Otsu’s method, is taken as input for ACO. The purpose of image pre-processing is to provide salient changes of image gradient that original images couldn’t provide for artificial ants. By quantitative analysis and subjective comparison of images in different sizes and types used as benchmarks for edge detection, our method extracts more continuous edges and provides more accuracy of interesting feature information than original ACO with DATS does. What’s more, our approach detects all positive edge points of ground truth in our experiments.

In traditional edge collapse simplification algorithms are mostly using the Quadric Error Metrics (QEM) as the cost to carry out edge collapse simplification, these methods will lose the original model shape feature; the simplified algorithm based on Vertex Curvature can preserve model shape feature, but the error between its folded model and original model can’t be controlled well. This article plans to combine the advantages of these two methods, propose a novel vertex mesh simplification algorithm based on curvature and distance metric, using vertex curvature on the boundary type classification, get the alternative vertex of the folded edge through the LOOP subsidiary patterns, According to folding cost which is the distance metric from alternative vertex to adjacent triangle to simplify the complex mesh. In our method, those edges whose two vertex are all in the curvature threshold are marked foldable, and the less the cost, the first to fold. Compared with the simplification algorithm based on butterfly pattern, the experimental results show that this algorithm can preserve the model shape feature better.

Color perception always depends on subjective factors. When it comes to a color design project, different designers will persist in different opinions. Although, color designing tools are handy to access nowadays, it takes long-term accumulation of color knowledge and abundant experiences of color designing for designers to master color principles and strengthen color perception. Based on objective color analyzing, this study established a visualization system of color harmony theory of family order and its digital model, on which a method of color designing was also developed. This method bridged the gap between objective colors and subjective perception in virtue of three-dimensional visualizing technology. This paper presented the color analyzing and designing toolkits of the project product. The color visualizing and designing system not only accords with designer’s intelligence and experience, but also proposes a new method for color analyzing and teaching.

Thanks to the exceptionally good properties, such as ergodicity, pseudo-randomness, sensitivity to initial conditions and control parameters, chaotic maps have been widely studied and applied to devise image shuffling, encryption and watermarking schemes. In this paper, the chaotic nature of affine transformation is studied. The affine transformation is then utilized to generate pseudo-random number sequence and applied to shuffle the host image during the preprocessing of watermarking. The watermarking is performed in the spatial domain, where the watermark bits are also encrypted by the skew tent map and then embedded in the shuffled host image. The proposed shuffling scheme yields good scrambling effects compared with the conventional scheme. The watermarked images are robust against various attacks, such as cropping, JPEG compression, noise, etc.

Emergency detection is of significant value in preventing damages to power systems and even saving lives by alerting anomalous behaviors of electronic devices. However, existing works only identify manually encoded events or patterns on power supply and thus consume huge amount of manpower and cannot deal with undefined emergency. In this paper, we propose a novel method 3D-LRT (Three Dimensional Likelihood Ratio Test) to detect emergency in large scale power system. To the best of our knowledge, this is the first work that leverages spatiotemporal behavior characteristics to identify anomalous patterns in power system. For scalability of large scale power systems, we further optimize our 3D-LRT using pruning and parallelization methods to save time overhead. We conduct experiments on real-world synthetic data sets. The results demonstrate that our 3D-LRT method is both effective and efficient.

We propose a method of generating birthday couplets fitting to gender, age and birthday time. The work of this paper are as follows: Using memory mapping file to load large number of files which can significantly reduce the initializing time; Using the TFIDF method to train key words related age and gender; Using a dynamic Bi-gram graph model to generate the more semantically coherent left roll which can conversely alter the weights between words of the model.