On context-aware distributed event dissemination

In pervasive environments, the Pub/Sub paradigm is regarded as an important means of information sharing and event dissemination. In this paper, we first analyze different context in Pub/Sub systems that has remarkable impacts upon user’s satisfaction to event dissemination and then give corresponding strategies by exploiting time context and event-preference context so as to provide personalized event dissemination. That is, by leveraging time context, we provide the extended matching against long-standing events, and by leveraging event-preference context, we present the recommendation algorithm which is based on hidden Markov process. Performance analysis and experiment evaluation show that both strategies can improve user’s experiences of event dissemination.     

Adaptation of robot’s perception of fuzzy linguistic information by evaluating vocal cues for controlling a robot manipulator

This article proposes a method for adapting a robot’s perception of fuzzy linguistic information by evaluating vocal cues. The robot’s perception of fuzzy linguistic information such as “very little” depends on the environmental arrangements and the user’s expectations. Therefore, the robot’s perception of the corresponding environment is modified by acquiring the user’s perception through vocal cues. Fuzzy linguistic information related to primitive movements is evaluated by a behavior evaluation network (BEN). A vocal cue evaluation system (VCES) is used to evaluate the vocal cues for modifying the BEN. The user’s satisfactory level for the robot’s movements and the user’s willingness to change the robot’s perception are identified based on a series of vocal cues to improve the adaptation process. A situation of cooperative rearrangement of the user’s working space is used to illustrate the proposed system by a PA-10 robot manipulator.     

Prediction of user navigation patterns by mining the temporal web usage evolution

Advances in the data mining technologies have enabled the intelligent Web abilities in various applications by utilizing the hidden user behavior patterns discovered from the Web logs. Intelligent methods for discovering and predicting user’s patterns is important in supporting intelligent Web applications like personalized services. Although numerous studies have been done on Web usage mining, few of them consider the temporal evolution characteristic in discovering web user’s patterns. In this paper, we propose a novel data mining algorithm named Temporal N-Gram (TN-Gram) for constructing prediction models of Web user navigation by considering the temporality property in Web usage evolution. Moreover, three kinds of new measures are proposed for evaluating the temporal evolution of navigation patterns under different time periods. Through experimental evaluation on both of real-life and simulated datasets, the proposed TN-Gram model is shown to outperform other approaches like N-gram modeling in terms of prediction precision, in particular when the web user’s navigating behavior changes significantly with temporal evolution.     

Photobook generation algorithms

Photobooks are comfortable and attractive solution for personal photo printing and storing. Photobook generation requires a lot of manual operations and takes a lot of time. Automation process will involve new users and allow making more photobooks. The algorithms should be quite fast, adjusted by user’s predilections and habits and ensure satisfied quality of work. We propose several adaptive photobook generation algorithms: photo quality recognition based on active learning, event-aware photo grouping, attractive photos selection, automatic photos layout through photobook pages, collage generation. We also suggest approaches to algorithms adjustment by user preferences on-the-fly.     

Exploring the feasibility of web form adaptation to users’ cultural dimension scores

With many daily tasks now performed on the Internet, productivity and efficiency in working with web pages have become transversal necessities for all users. Many of these tasks involve the inputting of user information, obligating the user to interact with a webform. Research has demonstrated that productivity depends largely on users’ personal characteristics, implying that it will vary from user to user. The webform development process must therefore, include modeling of its intended users to ensure the interface design is appropriate. Taking all potential users into account is difficult, however, primarily because their identity is unknown, and some may be effectively excluded by the final design. Such discrimination can be avoided by incorporating rules that allow webforms to adapt automatically to the individual user’s characteristics, the principal one being the person’s culture. In this paper we report two studies that validate this option. We begin by determining the relationships between a user’s cultural dimension scores and their behavior when faced with a webform. We then validate the notion that rules based on these relationships can be established for the automatic adaptation of a webform in order to reduce the time taken to complete it. We conclude that the automatic webform adaptation to the cultural dimensions of users improves their performance.     

Finding User’s Interest Blocks using Significant Implicit Evidence for Web Browsing on Small Screen Devices

Recent researches on improving the efficiency and user experience of Web browsing on handhelds are seeking to solve the problem by re-authoring Web pages or making adaptations and recommendations according to user preference. Their basis is a good understanding of the relationship between user behaviors and user preference. We propose a practical method to find user’s interest blocks by machine learning using the combination of significant implicit evidences, which is extracted from four aspects of user behaviors: display time, viewing information items, scrolling and link selection. We also develop a customized Web browser for small screen devices to collect user behaviors accurately. For evaluation, we conduct an on-line user study and make statistical analysis based on the dataset, which shows that most types of the suggested implicit evidences are significant, and viewing information items is the least indicative aspect of user behaviors. The dataset is then processed off-line to find user’s interest blocks using the proposed method. Experimental results demonstrate the effectiveness of finding user’s interest blocks by machine learning using the combination of significant implicit evidences. Further analysis reveals the great effect of users and moderate effect of Websites on the usefulness of significant implicit evidences.     

A multi-agent based user context Bayesian neural network analysis system

The increasing user mobility demands placed upon IT services necessitates an environment that enables users to access optimal services at any time and in any place. This study presents research conducted to develop a system that is capable of analyzing user IT service patterns and tendencies and provides the necessary service resources by sharing each user’s context information. First, each user’s context information is gathered to provide the multi-agent software training data necessary to describe user operations in a hybrid peer-to-peer (P2P) structured communication environment. Next, the data collected about each user’s mobile device is analyzed through a Bayesian based neural network system to identify the user’s tendency and extract essential service information. This information provides a communication configuration allowing the user access to the best communication service between the user’s mobile device and the local server at any time and in any place, thereby enhancing the ubiquitous computing environment.     

Language and Space: a two-level semantic approach based on principles of ontological engineering

An increasing number of applications for dialogue systems presuppose an ability to deal appropriately with space. Dialogues with assistance systems, intelligent mobility devices and navigation systems all commonly involve the use of spatial language. For smooth interaction, this spatial language cannot be interpreted ‘in the abstract’—it must instead be related directly to a user’s physical location, orientation, goals and needs and be embedded appropriately in a system’s interaction. This is far from straightforward. The situated interpretation of natural language concerning space, spatial relationships and spatial activities represents an unsolved challenge at this time. Despite extensive work on spatial language involving many disciplines, there are no generally accepted accounts that provide support for the kind of flexible language use observed in real human-human spatial dialogues. In this paper, I review some recent approaches to the semantics for natural language expressions concerning space in order to motivate a two-level semantic-based approach to the interpretation of spatial language. This draws on a new combination of natural language processing and principles of ontological engineering and stands as a foundation for more sophisticated and natural dialogue system behavior where spatial information is involved.     

Digital photo classification methodology for groups of photographers

Digital cameras have become an essential product when traveling or attending events. Because of its popularity and low cost, it is increasingly likely that more than one camera will be used at an event. The total number of photos captured is also increasing. Although the cost of digital photographs is low, managing numerous digital photos is burdensome to most users. Thus, an intelligent management tool for digital photos is required. In this paper, we propose novel clustering algorithms for concurrent digital photos obtained from multiple cameras. Since previous studies only considered a single user’s photo collection, they are not applicable to concurrent photos obtained from a group of photographers. To handle this situation, we define temporal/spatial combined clustering for the set of group photos taken from different cameras. If photos are submitted from a camera whose user has shown a preference between spatial and temporal clustering, we can obtain customized clustering output from other photo sets according to the reference clustering characteristics. We also propose unsupervised methods for general clustering output. Input concurrent photos are processed without a user’s true clusters, which can be a burden when the number of photos in the true clusters is huge. We tested our methods via more than one thousand photos taken by tourist groups. The final result was satisfactory compared to previous methods based on temporal (spatial) criteria only.     

Multi-modal and multi-scale photo collection summarization

With the proliferation of digital cameras and mobile devices, people are taking much more photos than ever before. However, these photos can be redundant in content and varied in quality. Therefore there is a growing need for tools to manage the photo collections. One efficient photo management way is photo collection summarization which segments the photo collection into different events and then selects a set of representative and high quality photos (key photos) from those events. However, existing photo collection summarization methods mainly consider the low-level features for photo representation only, such as color, texture, etc, while ignore many other useful features, for example high-level semantic feature and location. Moreover, they often return fixed summarization results which provide little flexibility. In this paper, we propose a multi-modal and multi-scale photo collection summarization method by leveraging multi-modal features, including time, location and high-level semantic features. We first use Gaussian mixture model to segment photo collection into events. With images represented by those multi-modal features, our event segmentation algorithm can generate better performance since the multi-modal features can better capture the inhomogeneous structure of events. Next we propose a novel key photo ranking and selection algorithm to select representative and high quality photos from the events for summarization. Our key photo ranking algorithm takes the importance of both events and photos into consideration. Furthermore, our photo summarization method allows users to control the scale of event segmentation and number of key photos selected. We evaluate our method by extensive experiments on four photo collections. Experimental results demonstrate that our method achieves better performance than previous photo collection summarization methods.     

Adaptive IPTV services based on a novel IP Multimedia Subsystem

Heterogeneous communication devices are emerging and changing the way of communication. Innovative multimedia applications are now accessible through these embedded systems. The 3GPP IP Multimedia Subsystem (IMS) provides a basic architecture framework for the Next Generation Network (NGN) supporting the convergence platform for service provisioning in heterogeneous networks. ETSI TISPAN standardization effort focuses on delivering IPTV services on such platform. Nevertheless, IPTV on IMS standardization suffers from a lack of efficient user-centric network management mechanisms as the end-user may consume IPTV service from different access networks, on different mobile devices, at anytime. User’s Perceived Quality of Service (PQoS) or Quality of Experience (QoE) of IPTV service may also suffer from wireless access network impairments. This paper introduces new functionalities in IPTV over IMS architecture which optimize satisfaction of the end-user and resource utilization of the operator’s networks. A context-sensitive User Profile (UP) model is used to deliver IPTV streams adapted to the user’s environment. In order to optimize the operator network usage, the impact of spatiotemporal dynamics of the video content on the deduced perceptual quality is considered. A Multimedia Content Management System (MCMS) is proposed to perform dynamic cross-layer adaptation of the IPTV stream based on PQoS measurements at the end-user side.     

Symmetrization and overfitting in probabilistic latent semantic analysis

An algorithm is proposed for revealing latent user’s interests from the observable protocol of users behavior, e.g., site visits. The algorithm combines the ideas of customer environment analysis and probabilistic latent semantic analysis. A quality criterion based on the classification of preliminarily labeled sites is introduced to optimize the algorithm parameters and compare algorithms. The experiments show that the quality has an optimum by the essential parameters of the algorithm, however the attempt of too precise optimization can lead to overfitting.     

Steerable projection: exploring alignment in interactive mobile displays

Emerging smartphones and other handheld devices are now being fitted with a set of new embedded technologies such as pico-projection. They are usually designed with the pico-projector embedded in the top of the device. Despite the potential of personal mobile projection to support new forms of interactivity such as augmented reality techniques, these devices have not yet made significant impact on the ways in which mobile data is experienced. We suggest that this ‘traditional’ configuration of fixed pico-projectors within the device is unsuited to many projection tasks because it couples the orientation of the device to the management of the projection space, preventing users from easily and simultaneously using the mobile device and looking at the projection. We present a study which demonstrates this problem and the requirement for steerable projection behaviour and some initial users’ preferences for different projection coupling angles according to context. Our study highlights the importance of flexible interactive projections which can support interaction techniques on the device and on the projection space according to task. This inspires a number of interaction techniques that create different personal and shared interactive display alignments to suit a range of different mobile projection situations.     

MyOwnLife: incremental and hierarchical classification of a personal image collection on mobile devices

Browsing multimedia collection on mobile devices raises the needs for new multimedia indexing solutions. In this paper, we focus on the management of personal image collections. We propose a method to simplify the browsing task on such a collection. The contributions reside in an incremental hierarchical algorithm, a method to provide a textual representation of the groups obtained and an algorithm to build a geo-temporal view of the collection. The proposed incremental hierarchical algorithm builds a temporal tree from the time stamp of each image. We opt here for a combination of a supervised clustering and an incremental algorithm based on mixture model. Good properties of the hierarchy are determined automatically thanks to the Integrated Likelihood Criterion (ICL). Based on the events obtained, a textual representation is proposed and then used to improve our temporal classification, combining geographical and temporal information. Results are validated on several real user collections with our prototype MyOwnLife.     

MASHA: A multi-agent system handling user and device adaptivity of Web sites

A user that navigates on the Web using different devices should be characterized by a global profile, which represents his behaviour when using all these devices. Then, the user’s profile could be usefully exploited when interacting with a site agent that is able to provide useful recommendations on the basis of the user’s interests, on one hand, and to adapt the site presentation to the device currently exploited by the user, on the other hand. However, it is not suitable to construct such a global profile by a software running on the exploited device since this device (e.g., a mobile phone or a palmtop) may have limited resources. Therefore, in this paper, we propose a multi-agent architecture, called MASHA, handling user and device adaptivity of Web sites, in which each device is provided with a client agent that autonomously collects information about the user’s behaviour associated to just that device. However, the user profile contained in this client is continuously updated with information coming from a unique server agent, associated with the user. Such information is collected by the server agent from the different devices exploited by the user, and represents a global user profile. The third component of this architecture, called adapter agent, is capable to generate a personalized representation of the Web site, containing some useful recommendations derived by both an analysis of the user profile and the suggestions coming from other users exploiting the same device.     

Geometry-based control of fire simulation

High-level control of fire is very attractive to artists, as it facilitates a detail-free user interface to make desirable flame effects. In this paper, a unified framework is proposed for modeling and animating fire under general geometric constraints and evolving rules. To capture the fire projection on user’s model animation, we develop a modified closest-point method (MCPM) to handle dynamic situations while maintaining the robustness of the closest-point method. A control blue core (CBC) is designed and generated automatically from the fire projection at each time step. It translates the geometric constraints and the user-specified evolving rules into implicit control conditions. Our L-Speed function leverages CBC’s shape information and conducts the large-scale motion of fire, leaving the basic physically-based model to refine simulation details. The experimental results show the effectiveness of our method for modeling fire propagation along complex curves or surfaces, or forming a flaming shape and following its motion.     

Articulation of information requirements for personalised knowledge construction

The quality of information provision influences considerably knowledge construction driven by individual users’ needs. In the design of information systems for e-learning, personal information requirements should be incorporated to determine a selection of suitable learning content, instructive sequencing for learning content, and effective presentation of learning content. This is considered as an important part of instructional design for a personalised information package. The current research reveals that there is a lack of means by which individual users’ information requirements can be effectively incorporated to support personal knowledge construction. This paper presents a method which enables an articulation of users’ requirements based on the rooted learning theories and requirements engineering paradigms. The user’s information requirements can be systematically encapsulated in a user profile (i.e. user requirements space), and further transformed onto instructional design specifications (i.e. information space). These two spaces allow the discovering of information requirements patterns for self-maintaining and self-adapting personalisation that enhance experience in the knowledge construction process.     

User-selectable interactive recommendation system in mobile environment

Mobile devices need to provide more accurate and personalized information in a computing environment with a small screen and limited information retrieval functions. This paper presents a user-selectable recommendation system that reflects a user interest group by employing collaborative filtering as technique to provide useful information in a mobile environment. We form similar groups by simultaneously considering a user’s information preferences and demographics. Then we reconstruct lists of a final recommendation based on what search results the similar demographic group has chosen. This is an optional filter for the search results. This means that we provide an interactive flexible recommendation list that considers a user’s intent more actively, rather than unilaterally. We show the Mean Absolute Error result to evaluate the recommendation and finally show the realization of a prototype that is based on both the iPhone and Android phone environments.     

A game theoretic approach for power allocation with QoS constraints in wireless multimedia sensor networks

The distinctive features of wireless multimedia sensor networks (WMSNs) include application-specific quality-of-service (QoS) requirements and limited energy supply, with which each node makes its own decisions selfishly. Therefore this paper presents a power control game theoretic approach for WMSNs by studying the effect of transmission power on QoS and energy efficiency. The game approach determines the transmission strategy using utility optimization according to the fluctuation of channel states. Here, the utility function is defined by effective throughput per unit power while satisfying the user’s delay QoS constraints. The existence and uniqueness of Nash equilibrium for the proposed game are proved. Finally, the simulation results show that each user chooses the optimal transmission power to maximize its utility based on other constant parameters and the effects of delay constraints on the user’s utility are quantified as well.