End-user Personalization Research Articles

RecRules

Nowadays, end users can personalize their smart devices and web applications by defining or reusing IF-THEN rules through dedicated End-User Development (EUD) tools. Despite apparent simplicity, such tools present their own set of issues. The emerging and increasing complexity of the Internet of Things, for example, is barely taken into account, and the number of possible combinations between triggers and actions of different smart devices and web applications is continuously growing. Such a large design space makes end-user personalization a complex task for non-programmers, and motivates the need of assisting users in easily discovering and managing rules and functionality, e.g., through recommendation techniques. In this article, we tackle the emerging problem of recommending IF-THEN rules to end users by presenting RecRules , a hybrid and semantic recommendation system. Through a mixed content and collaborative approach, the goal of RecRules is to recommend by functionality : it suggests rules based on their final purposes, thus overcoming details like manufacturers and brands. The algorithm uses a semantic reasoning process to enrich rules with semantic information, with the aim of uncovering hidden connections between rules in terms of shared functionality. Then, it builds a collaborative semantic graph, and it exploits different types of path-based features to train a learning to rank algorithm and compute top-N recommendations. We evaluate RecRules through different experiments on real user data extracted from IFTTT, one of the most popular EUD tools. Results are promising: they show the effectiveness of our approach with respect to other state-of-the-art algorithms and open the way for a new class of recommender systems for EUD that take into account the actual functionality needed by end users.

“Teach Me–Show Me”—End-User Personalization of a Smart Home and Companion Robot

Care issues and costs associated with an increasing elderly population are becoming a major concern for many countries. The use of assistive robots in “smart-home” environments has been suggested as a possible partial solution to these concerns. A challenge is the personalization of the robot to meet the changing needs of the elderly person over time. One approach is to allow the elderly person, or their carers or relatives, to make the robot learn activities in the smart home and teach it to carry out behaviors in response to these activities. The overriding premise being that such teaching is both intuitive and “nontechnical.” To evaluate these issues, a commercially available autonomous robot has been deployed in a fully sensorized but otherwise ordinary suburban house. We describe the design approach to the teaching, learning, robot, and smart home systems as an integrated unit and present results from an evaluation of the teaching component with 20 participants and a preliminary evaluation of the learning component with three participants in a human–robot interaction experiment. Participants reported findings using a system usability scale and ad-hoc Likert questionnaires. Results indicated that participants thought that this approach to robot personalization was easy to use, useful, and that they would be capable of using it in real-life situations both for themselves and for others.

Programming Languages for End-User Personalization of Cyber-Physical Systems

The increased usage of smart devices and appliances opens new venues to build applications that integrate physical and virtual world into consumer-oriented context-sensitive cyber-physical systems (CPS). Since physical processes are dynamic, concurrent, event-driven, and powered by various sensors, controllers, and actuators, a combination of service-oriented architecture (SOA) and event-driven architecture (EDA) is the most promising software architecture for virtualization of heterogeneous components into interoperable application building blocks. In this paper, we propose a CPS design paradigm where devices, such as sensors, controllers, and actuators, are virtualized into environmental services. To support event-driven workflow coordination, we designed special-purpose coopetition services that provide fundamental EDA characteristics, such as decoupled interactions, many-to-many communication, publish/subscribe messaging, event triggering, and asynchronous operations. Based on these two groups of services, we present a design of event-driven service composition languages that target two distinct groups of developers. Using Python as an example, we present a transformation of arbitrary general-purpose programming language into an event-driven service composition language for developers familiar with parallel programming using operating system kernel mechanisms. On the other hand, we present the design and cognitive evaluation of an end-user language, whose 2D tabular workspace resembles the process of sketching an automation application on a sheet of paper.

Special issue on emerging multimedia applications

Due to the latest developments in electronics industry, the emerging multimedia applications are smart, efficient as well as sensitive to the deployment constraints. The intelligent and soft computing techniques provide scalable and energy efficient multimedia solutions. The emerging multimedia tools can be used for various pervasive and ubiquitous applications such as health care, environmental monitoring, security and surveillance. This special issue includes 12 papers relating to these emerging applications. In the paper titled “Stereo Panorama Acquisition and Display for Virtual Tour Systems,” Huang and Klette investigate methods for determining optimum parameters both for highaccuracy stereo panoramic image recording and displaying. They focus on automatic image disparity enhancement while displaying a stereo panorama. The experimental results show that these parameters are critical for ensuring high quality stereo viewing. The derived formulas are applicable in technologies for stereo panorama imaging or stereoscopic displaying. Xiao et al. present “A Group of Novel Approaches and a Toolkit for Motion Capture Data Reusing”. They propose approaches for posture feature representation, motion sequence segmentation, key-frame extraction and content-based motion retrieval, which are very important for Motion Capture (MoCap) data reusing. In paper titled “A Portable Toolkit for Supporting End-User Personalization and Control in Context-Aware Applications”, Kawsar et al. address the personalization and control issues at the system interface level in parallel to context centric design. They present a toolkit that provides support for extending context-aware applications with end-user personalization and control features. The toolkit can be used with various existing Multimed Tools Appl (2010) 47:347–351 DOI 10.1007/s11042-009-0428-z

A portable toolkit for supporting end-user personalization and control in context-aware applications

A context-aware application in the pervasive computing environment provides intuitive user centric services using implicit context cues. Personalization and control are important issues for this class of application as they enable end-users to understand and configure the behavior of an application. However most development efforts for building context-aware applications focus on the sensor fusion and machine learning algorithms to generate and distribute context cues that drive the application with little emphasis on user-centric issues. We argue that, to elevate user experiences with context-aware applications, it is very important to address these personalization and control issues at the system interface level in parallel to context centric design. Towards this direction, we present Persona, a toolkit that provides support for extending context-aware applications with end-user personalization and control features. Specifically, Persona exposes a few application programming interfaces that abstract end-user customization and control mechanisms and enables developers to integrate these user-centric aspects with rest of the application seamlessly. There are two primary advantages of Persona. First, it can be used with various existing middlewares as a ready-to-use plug-in to build customizable and controllable context-aware applications. Second, existing context-aware applications can easily be augmented to provide end-user personalization and control support. In this paper, we discuss the design and implementation of Persona and demonstrate its usefulness through the development and augmentation of a range of common context-aware applications.