Uncertainty handling in rule-based mobile context-aware systems

Uncertainty handling is one of the most important aspects of modelling of context-aware systems. It has direct impact on the adaptability, understood as an ability of the system to adjust to changing environmental conditions or hardware configuration (missing data), changing user habits (ambiguous concepts), or imperfect information (low quality sensors). In mobile context-aware systems, data is most often acquired from device’s hardware sensors (like GPS, accelerometer), virtual sensors (like activity recognition sensor provided by the Google API) or directly from the user. Uncertainty of such data is inevitable, and therefore it is obligatory to provide mechanisms for modelling and processing it. In this paper, we propose three complementary methods for dealing with most common uncertainty types present in mobile context-aware systems. We combine modified certainty factors algebra, probabilistic interpretation of rule-based model, and time-parametrised operators into a comprehensive toolkit for modelling and building robust mobile context-aware systems. Presented approach was implemented and evaluated on the practical use-case.     

HEARTDROID—Rule engine for mobile and context‐aware expert systems

Building mobile context‐aware systems is inherently complex and non‐trivial task. It consists of several phases starting from acquisition of context, through modeling to execution of contextual models. Today, such systems are mostly implemented on mobile platforms, that introduce specific requirements, such as intelligibility, robustness, privacy, and efficiency. Over the last decade, along with the rapid development of mobile industry, many approaches were developed that unevenly support these requirements. This is mainly caused by the fact that current modelling and reasoning methods are not crafted to operate in mobile environments. We argue that the use of rule‐based reasoning tailored to mobile environments is an optimal solution. Rules are based on symbolic knowledge representation, as such they meet the general tendency to enforce understandability, intelligibility, and controllability of artificial intelligence software, as stated in the recent European Union General Data Protection Regulation. To this goal, we introduce a lightweight rule engine dedicated for Android platform called HEARTDROID. It executes models in the HMR+ rule language that are capable of expressing uncertainty of knowledge, capturing dynamics of mobile environment and provide high level of intelligibility. We present a qualitative and quantitative comparison of HEARTDROID with the most popular rule engines available.     

Interactive Paper as a Mobile Client for a Multi-channel Web Information System

We describe how interactive paper can be used together with a multi-channel web information system to build a platform for experimenting with multi-modal context-aware mobile information services. As an application, we present a tourist guide for visitors to an international festival that was developed to investigate alternative modes of information delivery and interaction in mobile environments. The guide is based around a set of interactive paper documents—an event brochure, map and bookmark. The brochure and map are augmented with digital services by using a digital pen to activate links and a text-to-speech engine for information delivery. The digital pen is also used for data capture of event ratings and reviews. The bookmark provides access to advanced searches and ticket reservations. We describe the architecture and operation of the system, highlighting the challenges of extending a web information system to support both the generation of the paper documents and the interaction from these documents, alongside more traditional access channels. Finally, we discuss the range of context-aware interactions that is supported by our platform.     

Inferring contextual preferences using deep encoder-decoder learners

ABSTRACT

Context-aware systems enable the sensing and analysis of user context in order to provide personalised services. Our study is part of growing research efforts examining how high-dimensional data collected from mobile devices can be utilised to infer users’ dynamic preferences that are learned over time. We suggest novel methods for inferring the category of the item liked in a specific contextual situation, by applying encoder-decoder learners (long short-term memory networks and auto encoders) on mobile sensor data. In these approaches, the encoder-decoder learners reduce the dimensionality of the contextual features to a latent representation which is learned over time. Given new contextual sensor data from a user, the latent patterns discovered from each deep learner is used to predict the liked item’s category in the given context. This can greatly enhance a variety of services, such as mobile online advertising and context-aware recommender systems. We demonstrate our contribution with a point of interest (POI) recommender system in which we label contextual situations with the items’ categories. Empirical results utilising a real world data set of contextual situations derived from mobile phones sensors log show a significant improvement (up to 73% improvement) in prediction accuracy compared with state of the art classification methods.     

Supporting ubiquitous sensor-cloudlets and context-cloudlets: Programming compositions of context-aware systems for mobile users

Increasing widespread use of sensor and networking technologies are yielding ubiquitous sensors and applications that pervade daily life. At the same time, context-aware pervasive computing has experienced tremendous developments in terms of context modelling and reasoning, and applications. Such developments coupled with a cloud computing model are yielding sensor-cloudlets and context-cloudlets based on sensors and applications deployed as services that can be harnessed in applications on-demand, ad-hoc and on a pay-per-use model. Sensor-cloudlets and context-cloudlets depend on and adapt to the available resources at the time, and involve context-aware systems (including sensors) that need to be dynamically composed as needed. This paper first outlines current trends and key issues and challenges in sensor-cloudlets and context-cloudlets. We then present a key contribution of this paper, which is an application of an abstract model of context-aware systems for specifying compositions of context-aware systems used in sensor-cloudlets and context-cloudlets. We show how expressions in our formalism can be embedded into a programming language (which we show via an example extending the logic programming language Prolog). We then present numerous examples illustrating applications expressed in our extended Prolog language. We also show how compositions specified in our formalism supports estimating the reliability and cost of using such compositions of resources in computations, in a well-defined semantics. Finally, we describe meta-level control operators on evaluation of queries posed to compositions of resources and specify a service-based interface on context-aware systems. We conclude with issues to be tackled in the future.     

情境计算研究综述

作为一种新的计算模式,情境计算得到了学术界和产业界越来越多的关注.随着物联网、云计算、大数据、社会计算等相关技术的不断发展成熟,情境计算进入了快速发展阶段.情境计算是一种通过对获取到的情境信息进行处理、从而得出用户所需服务并主动向用户提供相应情境感知服务的计算模式.这一新的计算模式为使用者的工作、生活带来了舒适和便利.对情境计算的诞生背景进行阐述,介绍情境、情境计算、情境感知、情境感知系统和情境感知服务等关键概念,总结情境数据获取、情境模型与建模、情境推理、主动服务提供、情境感知中间件和安全与隐私等重要研究内容以及其中使用到的关键技术,最后依托情境计算的一般性架构分析得出情境计算的未来发展挑战.     

基于深度学习的情境感知推荐系统研究进展

传统的推荐系统存在数据高度稀疏、冷启动及用户偏好建模难等问题,而把情境信息融入推荐系统中能有效缓解此类问题.深度学习技术已经成为人工智能领域研究热点,把深度学习应用在情境感知推荐系统当中,为推荐领域的研究带来新的机遇与挑战.本文从情境感知推荐系统相关概念出发,综合整理国内外研究相关文献,介绍深度学习技术融入情境感知推荐系统相关应用模型,提出了基于深度学习的情境感知推荐系统研究的不足以及对未来的展望.     

Design and validation of a light inference system to support embedded context reasoning

Embedded context management in resource-constrained devices (e.g. mobile phones, autonomous sensors or smart objects) imposes special requirements in terms of lightness for data modelling and reasoning. In this paper, we explore the state-of-the-art on data representation and reasoning tools for embedded mobile reasoning and propose a light inference system (LIS) aiming at simplifying embedded inference processes offering a set of functionalities to avoid redundancy in context management operations. The system is part of a service-oriented mobile software framework, conceived to facilitate the creation of context-aware applications—it decouples sensor data acquisition and context processing from the application logic. LIS, composed of several modules, encapsulates existing lightweight tools for ontology data management and rule-based reasoning, and it is ready to run on Java-enabled handheld devices. Data management and reasoning processes are designed to handle a general ontology that enables communication among framework components. Both the applications running on top of the framework and the framework components themselves can configure the rule and query sets in order to retrieve the information they need from LIS. In order to test LIS features in a real application scenario, an ‘Activity Monitor’ has been designed and implemented: a personal health-persuasive application that provides feedback on the user’s lifestyle, combining data from physical and virtual sensors. In this case of use, LIS is used to timely evaluate the user’s activity level, to decide on the convenience of triggering notifications and to determine the best interface or channel to deliver these context-aware alerts.     

Context-aware decision making under uncertainty for voice-based control of smart home

This paper presents a framework to build home automation systems reactive to voice for improved comfort and autonomy at home. The focus of this paper is on the context-aware decision process which must reason from uncertain facts inferred from real sensor data. This framework for building context aware systems uses a hierarchical knowledge model so that different inference modules can communicate and reason with same concepts and relations. The context-aware decision module is based on a Markov Logic Network, a recent approach which make it possible to benefit from formal logical representation and to model uncertainty of this knowledge. In this work, uncertainty of the decision model has been learned from data. Although some expert systems are able to deal with uncertainty, the Markov Logic Network approach brings a unified theory for dealing with logical entailment, uncertainty and missing data. Moreover, the ability to use a priori knowledge and to learn weights and structure from data make this model appealing to address the challenge of adaptation of expert systems to new applications. Finally, the framework has been implemented in an on-line system which has been evaluated in a real smart home with real naive users. Results of the experiment show the interest of context-aware decision making and the advantages of a statistical relational model for the framework.     

Intelligent video surveillance system: 3-tier context-aware surveillance system with metadata

This paper presents an intelligent video surveillance system with the metadata rule for the exchange of analyzed information. We define the metadata rule for the exchange of analyzed information between intelligent video surveillance systems that automatically analyzes video data acquired from cameras. The metadata rule is to effectively index very large video surveillance databases and to unify searches and management between distributed or heterogeneous surveillance systems more efficiently. The system consists of low-level context-aware, high-level context-aware and intelligent services to generate metadata for the surveillance systems. Various contexts are acquired from physical sensors in monitoring areas for the low-level context-aware system. The situation is recognized in the high-level context-aware system by analyzing the context data collected in the low-level system. The system provides intelligent services to track moving objects in Fields Of View (FOVs) and to recognize human activities. Furthermore, the system supports real-time moving objects tracking with Panning, Tilting and Zooming (PTZ) cameras in overlapping and non-overlapping FOVs.     

A pluggable middleware architecture for developing context-aware mobile applications

The proliferation of powerful smartphone devices provides a great opportunity for context-aware mobile applications becoming mainstream. However, we argue that conventional software development techniques suffer because of the added complexity required for collecting and managing context information. This paper presents a component-based middleware architecture which facilitates the development and deployment of context-aware applications via reusable components. The main contribution of this approach is the combination of a development methodology with the middleware architecture, which together bring significant value to developers of context-aware applications. Further contributions include the following: The methodology utilizes separation of concerns, thus decreasing the developmental cost and improving the productivity. The design and implementation of context-aware applications are also eased via the use of reusable components, called context plug-ins. Finally, the middleware architecture facilitates the deployment and management of the context plug-ins in a resource-aware manner. The proposed methodology and middleware architecture are evaluated both quantitatively and qualitatively.     

情景感知的软件需求获取与建模技术综述

情境感知的移动应用能够适应用户当前状态,因此这类应用越来越受到青睐。但由于上下文情景的维度是无数的,这使得获取和建模情境感知系统的情景需求成为一大挑战。本文通过文献综述的方法,旨在:(1)发现有哪些情境感知的需求获取与建模方法;(2)评估这些方法的技术转移成熟度。通过对所选择的61篇相关文献,进行数据抽取和分析综合,本文总结并识别出11种需求获取的方法、10种需求建模的方法以及它们的技术转移现状。结果显示:(1)最受欢迎的情景感知需求获取方法是用例和场景,而最常用的情境感知需求建模方法则是面向目标的方法;(2)在大多数相关文献中的需求获取与建模技术的技术成熟度都不高,不利于其面向工业界进行技术转移。     

经验研究中情景感知需求获取与建模系统文献综述

情景感知（context aware）的应用是当前的一个研究热点,但由于情景的复杂性和不确定性,如何获取这些应用的需求面临着巨大挑战,需求工程领域出现了大量的研究来解决这个挑战.使用系统文献综述（systematic literature review）的方法首先分析了不同情景维度对于需求获取与建模的支持;统计并深入分析情景感知的需求获取与建模中常用的方法;评估了不同经验方法的技术转移成熟度.最后,基于上述结论,给出了情景感知的需求获取与建模下一步的研究方向.     

Recognizing multi-modal sensor signals using evolutionary learning of dynamic Bayesian networks

Multi-modal context-aware systems can provide user-adaptive services, but it requires complicated recognition models with larger resources. The limitations to build optimal models and infer the context efficiently make it difficult to develop practical context-aware systems. We developed a multi-modal context-aware system with various wearable sensors including accelerometers, gyroscopes, physiological sensors, and data gloves. The system used probabilistic models to handle the uncertain and noisy time-series sensor data. In order to construct the efficient probabilistic models, this paper uses an evolutionary algorithm to model structure and EM algorithm to determine parameters. The trained models are selectively inferred based on a semantic network which describes the semantic relations of the contexts and sensors. Experiments with the real data collected show the usefulness of the proposed method.     

A new model for context-aware transactions in mobile services

With the ubiquity of handheld devices (such as smart phones and PDAs) and the availability of a wide range of mobile services (such as mobile banking, road traffic updates, and weather forecast), people can nowadays access information and conduct online transactions virtually anywhere and anytime. In such flexible, dynamic but less reliable environment, transaction management technology is believed to provide service reliability and data consistency. Indeed, in mobile and ubiquitous environments where devices as well as services can seamlessly join and leave the ubiquitous network; transaction management can be very helpful during the recovery of services from failure. Current transaction models and commit protocols do not take into account context information. However, in mobile environments, it is imperative to consider context information in the commit of a transaction—i.e., a transaction can be successfully completed if it meets the required context. In this paper, we propose a new model for context-aware transactions and their performance management in mobile environments. Unlike conventional transactions, context-aware transactions adapt to the required context. By context, we mean the service’s context as well as the users’ context that includes users’ needs and preferences. This paper designs and develops the proposed transaction model and evaluates its performance in terms of time and message complexities as well as transaction’s throughput.     

Context data management: an architectural framework for context-aware services

Mobile devices are equipped with increasing processing power and sensing capabilities, and mobile services can benefit from these features to provide a more personalized and context-aware experience to final users. To efficiently collect and deliver context information, a proper architecture is required, where heterogeneous context information can be processed to provide higher-level context information, context data are represented uniformly, and applications can process context data with high-level queries. This paper fulfils this goal of interoperability and domain independence by defining a framework for context data management relying on open standards (XMPP and REST), acting as an enabler for third-party context-aware applications; other main novelties of our work are the definition of a ContextML for standard context data representation, and a Context Query Language (CQL) to access context information based on high-level data filtering.     

The ECORA framework: A hybrid architecture for context-oriented pervasive computing

An infrastructure approach to support context-aware pervasive computing is advantageous for rapid prototyping of context-aware distributed applications and beneficial for unifying modelling of context and reasoning in uncertain conditions. This paper presents the ECORA framework for context-aware computing, which is designed with a focus on reasoning about context under uncertainty and addressing issues of heterogeneity, scalability, communication and usability. The framework follows an agent-oriented hybrid approach, combining centralized reasoning services with context-aware, reasoning capable mobile software agents. The use of a centralized reasoning engine provides powerful reasoning capabilities and deploying context-aware mobile agents enables agility and robustness of components in the pervasive system. The design and implementation of the framework at different levels, as well as three case studies, are presented.     

Switched state feedback control for continuous-time uncertain systems

This paper is concerned to design a switched state feedback robust control for continuous-time systems subject to norm bounded uncertainty. As important features of the proposed design method, we mention that it can handle a general LFT structure for the uncertainty and it is based on stability conditions that can be numerically solved by means of LMIs and a line search. Moreover, the switching rule as well as the state feedback gains are determined from the minimization of a guaranteed cost function derived from a multi-objective criterion. The theoretical results are illustrated with an academic example.     

Sequential Event Pattern Based Design of Context-Aware Adaptive Application

Recent pervasive systems are designed to be context-aware so that they are able to adapt to continual changes of their environments. Rule-based adaptation, which is commonly adopted by these applications, introduces new challenges in software design and verification. Recent research results have identified some faulty or unwanted adaptations caused by factors such as asynchronous context updating, and missing or faulty context reading. In addition, adaptation rules based on simple event models and propositional logic are not expressive enough to address these factors and to satisfy users'' expectation in the design. We tackle these challenges at the design stage by introducing sequential event patterns in adaptation rules to eliminate faulty and unwanted adaptations with features provided in the event pattern query language. We illustrate our approach using the recent published examples of adaptive applications, and show that it is promising in designing more reliable context-aware adaptive applications. We also introduce adaptive rule specification patterns to guide the design of adaptation rules.