Context-Aware Dynamic Presentation Synthesis for Exploratory Multimodal Environments

Workflow model has been successfully applied to the traditional computing environment. Currently, there are many studies trying to apply workflow to ubiquitous computing environment. In ubiquitous computing environment, a service must be based on the user's context information to be executed. Now, however, there is no workflow system has a pervasive computing environment to support context-aware services. We intend to establish a pervasive computing environment which can be used in smart home workflow model. The system model based on the user's current context information to provide services for the user's current context, and use the Petri net model tools for workflow modeling. Thus parallel to the workflow model and to visualize formal verification correctness. Workflow using Petri net model which is a graphical and mathematical sets in one, is an ideal tool for formal modeling. We intend to apply the system model to a specific smart home, to validate the correctness of our proposed system.

With continuous increase of available online spatial data, requirements for the adaptation of spatial content to user's context becomes increasingly important. Location-based services (LBS) deliver to the user information specific to a given location preferably using mobile devices. Personalizing the information provided to the user to take into account her/his information preferences and current location, the problem of inundating the user with irrelevant information is avoided. The research presented in this paper introduces an approach which implicitly monitors the user's activity and generates a user profile reflecting her/his information preferences based on the interactions of the user with the system, and her/his physical location and movements. The system recognizes the user profile and adapts accordingly both to provide suitable information, and to prioritize the functionality appropriate to the user's current context.

In an open source cloud computing platform such as OpenStack, operators use Role-Based Access Control (RBAC) model to grant access to cloud resources. However, these user-level role-based access control techniques fail to include comprehensive user context. We believe a situational aware framework will improve security by bringing in user's context to such cloud systems. In this paper, we create a semantically rich context-sensitive access control system for OpenStack by incorporating the user's current context attributes like location, time, etc. In a proof-of-concept implementation, we integrate a knowledge graph with our own access control system to express and enforce the contextual-situation policies in OpenStack. The proposed system provides enhanced, flexible access control while minimizing the overhead of altering the existing access control framework. We also discuss various use cases, to highlight the benefits of our system and show enforcement results.

Despite the acknowledgment that the perception of explanations may vary considerably between end-users, explainable recommender systems (RS) have traditionally followed a one-size-fits-all model, whereby the same explanation level of detail is provided to each user, without taking into consideration individual user's context, i.e., goals and personal characteristics. To fill this research gap, we aim in this paper at a shift from a one-size-fits-all to a personalized approach to explainable recommendation by giving users agency in deciding which explanation they would like to see. We developed a transparent Recommendation and Interest Modeling Application (RIMA) that provides on-demand personalized explanations of the recommendations, with three levels of detail (basic, intermediate, advanced) to meet the demands of different types of end-users. We conducted a within-subject study (N=31) to investigate the relationship between user's personal characteristics and the explanation level of detail, and the effects of these two variables on the perception of the explainable RS with regard to different explanation goals. Our results show that the perception of explainable RS with different levels of detail is affected to different degrees by the explanation goal and user type. Consequently, we suggested some theoretical and design guidelines to support the systematic design of explanatory interfaces in RS tailored to the user's context.

This paper considers a context similarity algorithm based on ontology semantic which recommends commodities to users by the similarity between current user's context and source context recorded. First, we divide the context ontology tree into many subtrees with subtree cutting algorithm. According to calculating the similarity of subtrees with the weight sum, we obtain the similarity between the source context and target context. Meanwhile, during calculating the similarity of subtrees, this paper allows for ontology semantic similarity, and adds the structure similarity degree algorithm on the basis of the old ontology similarity degree algorithm, which makes the result more accord with actual, and finally the experiment is verified.

Error handling in multimodal voice-enabled interfaces of tour-guide robots using graphical models

With the increasing number of mobile devices and the development of all kinds of mobile technology, the volume of data is getting larger and larger. People have to face huge amounts of data. At the same time, as the continuous development of various mobile devices providing more data acquisition technology, the dimension of data have a bigger growth too. It's not enough for the existing technology in the treatment of huge amounts and high dimension data. User's interests in different time have been taken into equal consideration with the method being used, which leads to lack of effectiveness in the given period of time. In order to solve this problem, personalized recommendation is faced with great challenge. What's more, timeliness which is getting more and more urgent in people's need is very important. Towards the problem of recommendation based on context-aware, this paper propose a personalized recommendation algorithm based on user context clustering, with the consideration of timeliness. This algorithm uses the idea of contextual pre-filtering. A method of fuzzy clustering is used on the users' context in history data set first to construct the user set which is similar with current user context, and then combined with user-based collaborative filtering algorithm for personalized recommendation.

We propose NeuralWOZ, a novel dialogue collection framework that uses model-based dialogue simulation. NeuralWOZ has two pipelined models, Collector and Labeler. Collector generates dialogues from (1) user's goal instructions, which are the user context and task constraints in natural language, and (2) system's API call results, which is a list of possible query responses for user requests from the given knowledge base. Labeler annotates the generated dialogue by formulating the annotation as a multiple-choice problem, in which the candidate labels are extracted from goal instructions and API call results. We demonstrate the effectiveness of the proposed method in the zero-shot domain transfer learning for dialogue state tracking. In the evaluation, the synthetic dialogue corpus generated from NeuralWOZ achieves a new state-of-the-art with improvements of 4.4% point joint goal accuracy on average across domains, and improvements of 5.7% point of zero-shot coverage against the MultiWOZ 2.1 dataset.

Personalized Web search is an effective means of providing specific results to different users when they submit the same query. How to obtain user's real-time information need is a key issue in personalized search. Existing methods concentrate more on the building user profile based on Web pages/documents which affects the efficiency of search engine. In addition, dynamics of user profile is often ignored. To address this problem, we introduce an approach that captures the user context to accurately provide preferences of users for effective personalized search in this paper. First, short-term query context is generated from Web-snippets to play a role of semantic background of user's search behavior, identifying related concepts of the query. Second, user context snap is built based on query context according to user's interactive search behavior. Finally, evolution of user context is considered by introducing forgetting factor to merge the independent user context snap in a user session. The experimental results fully demonstrate that our approach can successfully build user context according to individual user information need.

In this demo we present a robust system for delivering real-time news recommendation to the user based on the user's history of the past visits to the site, current user's context and popularity of stories. Our system is running live providing real-time recommendations of news articles. The system handles overspecializing as we recommend categories as opposed to items, it implicitly uses collaboration by taking into account user context and popular items and, it can handle new users by using context information. A unique characteristic of our system is that it prefers freshness over relevance, which is important for recommending news articles in real-world setting as addressed here. We experimentally compare the proposed approach as implemented in our system against several state-of-the-art alternatives and show that it significantly outperforms them.

In recent years, numerous sensing devices and wireless networks are immersed into our living environments, creating the Internet of Things (IoT) integrating the cyber and physical objects. Searching for objects in IoT is a challenging problem because the context relationships among IoT objects are various and complex. The traditional web search approaches cannot work well in the IoT search domain because they miss the critical characteristics of the context relationships. In addition, a user's dynamic and changing context affects the user's information needs, and an IoT search system should exploit context relationship in IoT for retrieving relevant information suitable for the user's current context. In this paper, we present a context-aware search system for IoT, which aims to search objects and related information with more suitable results. We construct a hierarchical context model based on ontology to represent the IoT objects and their contextual relationships. Then, searches are executed with consideration of users' context that is recognized by a context-aware hidden Markov model. Experimental results confirmed that users could obtain more suitable and reasonable search results than with a typical web or map search system.

Traditional recommender systems have won great success on electronic commerce. However, when the user-item rating record matrix is sparse, traditional recommendation algorithms perform poor, which is known as the cold-start problem. Recently, more and more contextual features have been proven to be valuable information for improving the accuracy of recommendation, and newly formed context-aware recommendation systems (CARS) provide a way to solve the cold-start problem by using some certain features such as users location, mood and social relationship. In order to handle multidimensional context, this paper first extracts relevant contextual information by calculating the information entropy, then divides the contextual information into three categories — user context, item context and interaction context. Finally, we extend the matrix factorization (MF) model to integrate the context information. Experimental results on LDOS-CoMoDa dataset have shown that our approach provides improvement in terms of recommendation accuracy.

The SUM'20 workshop was held at the 13th ACM International WSDM Conference on Web Search and Data Mining (WSDM 2020) in Houston, Texas. The purpose of the workshop was to stimulate the research community to explore open challenges in building systems that can capture the user's state, context and goals, as well as effectively use these for leveraging intelligent user-centric systems in a wide range of applications. The workshop incorporated different plenary sessions and contributed talks. The workshop website and proceedings are available at https://www.k4all.org/event/wsdmsum20.

The aim of personalizing web information systems is to tailor content (media) to the user's personal preferences, goals and context, in turn increasing the reusability of that content. However, most developers are increasingly seeking to apply 'Web as a Platform' based approaches where web-based content is integrated with web services to provide the platform and environment features that were traditionally offered by desktop environments and applications. Therefore, next generation personalized web information systems need to be capable of dynamically personalizing, adapting and integrating web content and web services to create customized experiences for individual users. The goal of the research presented in this paper is to provide innovative techniques and technologies to achieve this. As part of this research, a novel architecture for the generation of Personalized Learning Activities, which highlights both the need for, and the power of combining and personalizing content and services has been developed. The system has been evaluated in the context of a Higher Education use case based on the user's perception of three key elements of the Personalized Learning Activity: the personalization, the usability and the educational benefits.

We analyze preferences and the reading flow of users of a popular Austrian online newspaper. Unlike traditional news filtering approaches, we postulate that a user's preference for particular articles depends not only on the topic and on propositional contents, but also on the user's current context and on more subtle attributes. Our assumption is motivated by the observation that many people read newspapers because they actually enjoy the process. Such sentiments depend on a complex variety of factors. The present study is part of an ongoing effort to bring more advanced personalization to online media. Towards this end, we present a systematic evaluation of the merit of contextual and non-propositional features based on real-life clickstream and postings data. Furthermore, we assess the impact of different recommendation strategies on the learning performance of our system.