Game level layout from design specification

The design of video game environments, or levels, aims to control gameplay by steering the player through a sequence of designer‐controlled steps, while simultaneously providing a visually engaging experience. Traditionally these levels are painstakingly designed by hand, often from pre‐existing building blocks, or space templates. In this paper, we propose an algorithmic approach for automatically laying out game levels from user‐specified blocks. Our method allows designers to retain control of the gameplay flow via user‐specified level connectivity graphs, while relieving them from the tedious task of manually assembling the building blocks into a valid, plausible layout. Our method produces sequences of diverse layouts for the same input connectivity, allowing for repeated replay of a given level within a visually different, new environment. We support complex graph connectivities and various building block shapes, and are able to compute complex layouts in seconds. The two key components of our algorithm are the use of configuration spaces defining feasible relative positions of building blocks within a layout and a graph‐decomposition based layout strategy that leverages graph connectivity to speed up convergence and avoid local minima. Together these two tools quickly steer the solution toward feasible layouts. We demonstrate our method on a variety of real‐life inputs, and generate appealing layouts conforming to user specifications.     

Customizing a Fisheye View Algorithm to Preserve the Mental Map

Frequently, large knowledge bases are represented by graphs. Many visualization tools allow users or other applications to interact with and adjust the layouts of these graphs. One layout adjustment problem is that of showing more detail without eliding parts of the graph. Approaches based on a fisheye lens paradigm seem well suited to this task. However, many of these techniques are non-trivial to implement and their distortion techniques often cannot be altered to suit different graph layouts. When distorting a graph layout, it is often desirable to preserve various properties of the original graph in an adjusted view. Pertinent properties may include straightness of lines, graph topology, orthogonalities and proximities. However, it is normally not possible to preserve all of the original properties of the graph layout. The type of layout and its application should be considered when deciding which properties to preserve or distort. This paper describes a fisheye view algorithm which can be customized to suit various different graph layouts. In contrast to other methods, the user can select which properties of the original graph layout to preserve in an adjusted view. The technique is demonstrated through its application to visualizing structures in large software systems.     

Optimizing layout using spatial quality metrics and user preferences

Computational design is one of the most common tasks of immersive computer graphics projects, such as games, virtual reality and special effects. Layout planning is a challenging phase of architectural design, which requires optimization across several conflicting criteria. We present an interactive layout solver that assists designers in layout planning by recommending personalized space arrangements based on architectural guidelines and user preferences. Initialized by the designer’s high-level requirements, an interactive evolutionary algorithm is used to converge on an ideal layout by exploring the space of potential solutions. The major contributions of our proposed approach are addressing subjective aspects of the design to generate personalized layouts; and the development of a genetic algorithm with a multi-parental recombination method that improves the chance of generating higher quality offspring. We demonstrate the ability of our method to generate feasible floor plans which are satisfactory, based on spatial quality metrics and designer’s taste. The results show that the presented framework can measurably decrease planning complexity by producing layouts which exhibit characteristics of human-made design.     

Design and evaluation of MagnetViz—a graph visualization tool

MagnetViz was designed for the interactive manipulation of force-directed graph layouts, allowing the user to obtain visualizations based on the graph topology and/or the attributes of its nodes and edges. The user can introduce virtual magnets anywhere in the graph and these can be set to attract nodes and edges that fulfill user-defined criteria. When a magnet is placed, the force-directed nature of the layout forces it to reorganize itself in order to reflect the changes in the balance of forces, consequently changing the visualization into one that is more semantically relevant to the user. This paper describes MagnetViz’s concepts, illustrating them with examples and a case study based on a usage scenario. We also describe how the MagnetViz has evolved since its original version and present the evaluation of its latest version. This evaluation consists of two user studies aiming at assessing generated layout quality and how well the concepts can be apprehended and employed, and a task taxonomy assessment focusing on establishing which graph visualization tasks the technique is able to handle.     

A Comparison of User-Generated and Automatic Graph Layouts

The research presented in this paper compares user-generated and automatic graph layouts. Following the methods suggested by van Ham et al. (2008), a group of users generated graph layouts using both multi-touch interaction on a tabletop display and mouse interaction on a desktop computer. Users were asked to optimize their layout for aesthetics and analytical tasks with a social network. We discuss characteristics of the user-generated layouts and interaction methods employed by users in this process. We then report on a web-based study to compare these layouts with the output of popular automatic layout algorithms. Our results demonstrate that the best of the user-generated layouts performed as well as or better than the physics-based layout. Orthogonal and circular automatic layouts were found to be considerably less effective than either the physics-based layout or the best of the user-generated layouts. We highlight several attributes of the various layouts that led to high accuracy and improved task completion time, as well as aspects in which traditional automatic layout methods were unsuccessful for our tasks.     

Automated design process modelling and analysis using immersive virtual reality

The capture of engineering design processes and associated knowledge has traditionally been extremely difficult due to the high overhead associated with current intrusive and time-consuming manual methods used in industry, usually involving interruption of the designer during the design task and relying on them to remember how a design solution was developed after the event. This paper presents novel research which demonstrates how the detailed logging and analysis of an individual designer’s actions in a cable harness virtual reality (VR) design and manufacturing system permits automated design task analysis with process mapping. Based on prior research, which utilised user-logging to automatically analyse design activities and generate assembly plans, this work involves the automatic capture of extracted design knowledge embedded within the log files and subsequently represented using IDEF0 diagrams, DRed graphs, PSL, XML, annotated movie clips and storyboard representations. Using this design knowledge, an online help system has been demonstrated which helps users to carry out design tasks similar to those performed previously by expert users. This is triggered by monitoring the designer’s actions and functions in real time and pushes knowledge and advice to the user which was captured from experts and subsequently formalised during earlier design sessions.     

Object-oriented specification of user interfaces

This paper presents an object-oriented approach for the specification of graphical user interfaces. Specification starts with the analysis of the end user's operations. The user interface is then designed on the basis of this analysis. Operation analysis is followed by structure and component specification which presents the dialogue structure of the application and the contents of each dialogue. Visualization produces the final screen layouts, and task specification documents the usage of the user interface for the purpose of creating user's guides. The method presented in this paper makes it easier for a designer to take the end user's needs into account. Still, it does not automatically guarantee good quality user interfaces. The top-down nature of the method allows the designer to concentrate on the most important aspects of the user interface and split the design procedure into manageable pieces. Also, the visibility of the process allows the designer to communicate with other people while specifying the user interface. This paper connects the method with the object-oriented specification of entire applications. It briefly explains the connections with object-oriented analysis and design, and demonstrates how to implement the specified user interface in an object oriented fashion. The approach presented in this paper is being applied in the development of a large network management system with about two million lines of C++ code running in the XII environment. Still, the method does not require the specification being implemented with any specific windowing system. The only requirement is that the user interface is based on graphical elements, such as dialogues, push-buttons and text fields.     

Visualization and User-Modeling for Browsing Personal Photo Libraries

We present a user-centric system for visualization and layout for content-based image retrieval. Image features (visual and/or semantic) are used to display retrievals as thumbnails in a 2-D spatial layout or “configuration” which conveys all pair-wise mutual similarities. A graphical optimization technique is used to provide maximally uncluttered and informative layouts. Moreover, a novel subspace feature weighting technique can be used to modify 2-D layouts in a variety of context-dependent ways. An efficient computational technique for subspace weighting and re-estimation leads to a simple user-modeling framework whereby the system can learn to display query results based on layout examples (or relevance feedback) provided by the user. The resulting retrieval, browsing and visualization can adapt to the user's (time-varying) notions of content, context and preferences in style and interactive navigation. Monte Carlo simulations with machine-generated layouts as well as pilot user studies have demonstrated the ability of this framework to model or “mimic” users, by automatically generating layouts according to their preferences.     

基于自适应光标的图形用户界面输入效率优化

提高图形用户界面(graphical user interface)的输入效率,是人机交互中的一项重要研究内容.已有的研究包括点击增强技术和自适应界面技术,前者改变光标的控制方式或呈现方式,后者改变界面上控件的位置布局,但两种技术都存在不足.通过分析界面操作,提出了图形用户界面输入效率的评价模型;然后,在此基础上提出一种人机交互效率优化技术:自适应光标.它以自适应的方式,有选择地对界面上用户可能访问的控件通过点击增强技术支持,实现快速访问.该方法既解决了以往的自适应界面技术因频繁调整控件布局而给用户带来额外认知成本的问题,也克服了点击增强技术仅适用于稀疏控件布局的限制.为了检验其可用性,在控件较多的Visual Studio上实现了自适应光标技术.实验结果表明,使用自适应光标技术可以将获取目标的时间缩短27.7％,显著提高了图形用户界面的输入效率.     

Toward a formal specification of menu-based systems

As software systems continue to increase in sophistication and complexity, so do the interface requirements that support the corresponding user interaction. To select the proper blend of ingredients that constitutes an adequate user interface, it is essential that the system designer have a firm understanding of the interaction process, i.e., how the selected dialogue format interacts with the user and with the underlying task software. To promote such an understanding, this paper presents a model that characterizes one particular dialogue format: menu-based interaction. This model is actually a sequence of models, hierarchically structured, in which each successive model builds on its predecessor by introducing additional characterization elements. The first model describes the minimal set of elements inherent to any menu-based interface; successive models extend this minimal set by introducing task actions, incremental history sequences, and frame-associated memory. These principal model elements enable the characterization of fundamental, menu-based operations like computational and decision processes, user response reversal, and user directed movement. Moreover, because the principal model elements correspond directly to “real world” objects, an intuitive as well as formal understanding of menu-based interaction can be achieved. Effectively, the model elements and the hierarchical structure imposed by these elements provide an ideal environment for characterizing and classifying menu-based systems at various levels of sophistication.     

Generating Synthetic Space Allocation Probability Layouts Based on Trained Conditional-GANs

In this paper, a data-driven generative method is applied to generate synthetic space allocation probability layout. This generated layout could be helpful in the early stage of an architectural design. For this task, a specific training dataset is generated which is used to train the cGAN model. The training dataset consists of 300 existing apartment layouts which are coloured in a set of low feature representation. The cGAN model is trained with this dataset and the trained model is evaluated based on the quality of its generated layouts regarding the five pre-defined topological and geometrical benchmarks.     

Cognitive Strategies for the Visual Search of Hierarchical Computer Displays

This article investigates the cognitive strategies that people use to search computer displays. Several different visual layouts are examined: unlabeled layouts that contain multiple groups of items but no group headings, labeled layouts in which items are grouped and each group has a useful heading, and a target-only layout that contains just one item. A number of plausible strategies were proposed for each layout. Each strategy was programmed into the EPIC cognitive architecture, producing models that simulate the human visual-perceptual, oculomotor, and cognitive processing required for the task. The models generate search time predictions. For unlabeled layouts, the mean layout search times are predicted by a purely random search strategy, and the more detailed positional search times are predicted by a noisy systematic strategy. The labeled layout search times are predicted by a hierarchical strategy in which first the group labels are systematically searched, and then the contents of the target group. The target-only layout search times are predicted by a strategy in which the eyes move directly to the sudden appearance of the target. The models demonstrate that human visual search performance can be explained largely in terms of the cognitive strategy that is used to coordinate the relevant perceptual and motor processes, a clear and useful visual hierarchy triggers a fundamentally different visual search strategy and effectively gives the user greater control over the visual navigation, and cognitive strategies will be an important component of a predictive visual search tool. The models provide insights pertaining to the visual-perceptual and oculomotor processes involved in visual search and contribute to the science base needed for predictive interface analysis.     

Interaction Unit Analysis: A New Interaction Design Framework

ABSTRACT

A pragmatic approach to interaction modeling is presented by which a designer can describe how the user gets tasks done with a newly developing system. The notation proposed allows an interaction designer to make explicit both how user actions cause visible or noticeable changes in the state of the machine and how the user is expected to use this feedback to generate the next action. Interaction Unit (IU) scenarios are constructed where each IU specifies one step in the cycle of interaction. Each IU specifies the visible system state that leads the user to take some action. In addition, the IU makes explicit the state of the goal stack at the start and end of the unit and the mental processes (recall, recognition, or affordance) required. In this way one can describe the intimate connection between goal, action, and the environment in user–machine interaction.

To demonstrate the completeness of IU scenario analysis, IU models are presented for some well-known problems in interaction design: hidden and partially hidden modes leading to unexpected system effects, insufficient cues for subgoal construction, insufficient cues for subgoal elimination, and inappropriate affordances for action. These scenarios are accompanied by procedures that designers can use to detect similar problems in putative interaction designs.

To demonstrate the feasibility of using IU scenario analysis in design, 4 graduate students were taught to use IU scenario analysis in a 3-hr session. They then worked as a group to evaluate a prototype handheld warehouse application. A comparable group was taught and then applied Cognitive Walkthrough. Both groups successfully completed the task and detected several problems rated as being of high severity by the designers of the prototype. Analysis of the problems detected by each group suggests that the two techniques are complimentary. IU scenario analysis may be most cost-effective for devices using new interaction paradigms, whereas Cognitive Walkthrough may be most cost-effective for designs using established interaction paradigms.     

Symbolic data analysis tools for recommendation systems

Recommender systems have become an important tool to cope with the information overload problem by acquiring data about user behavior. After tracing the user’s behavior, through actions or rates, computational recommender systems use information- filtering techniques to recommend items. In order to recommend new items, one of the three major approaches is generally adopted: content-based filtering, collaborative filtering, or hybrid filtering. This paper presents three information-filtering methods, each of them based on one of these approaches. In our methods, the user profile is built up through symbolic data structures and the user and item correlations are computed through dissimilarity functions adapted from the symbolic data analysis (SDA) domain. The use of SDA tools has improved the performance of recommender systems, particularly concerning the find good items task measured by the half-life utility metric, when there is not much information about the user.     

Biologically inspired task oriented gist model for scene classification

Capturing the scene gist is account for rapid and accurate scene classification in human visual system. This paper presents a biologically inspired task oriented gist model (BT-Gist) that attempts to emulate two important attributes of biological gist: holistic scene centered spatial layout representation and task oriented resolution determination. For the first attribute, we enrich the model of Oliva and Torralba by refining the low-level features in several biological plausible ways, extending the spatial layout to multiple resolution and followed by perceptually meaningful manifold analysis for a set of multi-resolution biologically inspired intrinsic manifold spatial layouts (BMSLs). Since the optimal resolution that best represents the spatial layout varies from task to task, we embody the second attribute as learning the combination of BMSLs of multiple resolution with respect to their optimal discriminative invariance trade-off for the task at hand, and then cast it in the SVM based localized multiple kernel learning (LMKL) framework, by which the kernel of each scene gist is approximated as a local combination of kernels associated to multi-resolution BMSLs. By exploring the task specific category distribution pattern over BMSL, we define the local model as a category distribution sensitive (CDS) kernel, which can accommodate both the diverse individuality of specific BMSL and the universality shared within the whole category space. Via CDS-LMKL, both the optimal resolution for spatial layouts and the final classifier can be efficiently obtained in a joint manner. We evaluate BT-Gist on four natural scene databases and one cluttered indoor scene database with a range of comparison: From different MKL methods, to various biologically inspired models and BoF based computer vision models. CDS-LMKL leads to better results compared to several existing MKL algorithms. Given the two biological attributes that the framework has to follow, BT-Gist, despite its holistic nature, outperforms existing biologically inspired models and BoF based computer vision models in natural scene classification, and competes with the object segmentation based ROI-Gist in cluttered indoor scene classification.     

Foraging theory for autonomous vehicle speed choice

We consider the optimal control design of an abstract autonomous vehicle (AAV). The AAV searches an area for tasks that are detected with a probability that depends on vehicle speed, and each detected task can be processed or ignored. Both searching and processing are costly, but processing also returns rewards that quantify designer preferences. We generalize results from the analysis of animal foraging behavior to model the AAV. Then, using a performance metric common in behavioral ecology, we explicitly find the optimal speed and task processing choice policy for a version of the AAV problem. Finally, in simulation, we show how parameter estimation can be used to determine the optimal controller online when density of task types is unknown.     

Discovery of Frequent Episodes in Event Sequences

Sequences of events describing the behavior and actions of users or systems can be collected in several domains. An episode is a collection of events that occur relatively close to each other in a given partial order. We consider the problem of discovering frequently occurring episodes in a sequence. Once such episodes are known, one can produce rules for describing or predicting the behavior of the sequence. We give efficient algorithms for the discovery of all frequent episodes from a given class of episodes, and present detailed experimental results. The methods are in use in telecommunication alarm management.