Design of context-aware middleware for mobile healthcare services

We design and develop a context-aware middleware for various mobile healthcare services, specifically those for preventive medicine. The middleware provides medical status information in a context form and then links such information with medical records. Information is collected by the middleware through the recognition of diverse environmental data that affect patients’ health. Information-to-information-related values are obtained as a measure for effectively categorizing and managing medical-related context information. High-frequency context values are determined using the Bayesian probability formula to manage frequently occurring risk situations. The middleware also allows for real-time analysis of information, as well as the calculation of risk frequency via a real-time sensor and recognition of radio frequency identification tag information. It is designed to transmit calculated and preventive care-related information to mobile devices. Using the unique target application program of the ubiquitous healthcare system, the general environment and preventive medicine environment are set as the primary paradigms for generating and managing practical medical context information. This research presents methods for providing automated preventive medical services under a ubiquitous healthcare system. The proposed middleware is expected to present new interactive concepts for preventive medicine-related environments, consequently satisfying the demands of user-oriented ubiquitous healthcare.     

基于本体的语境信息模型与推理

语境信息是用来刻画一个实体情形的信息,该文提出了基于本体的语境信息建模以及查询方法,利用本体极强的语义描述能力和有效的推理机制,更好地实现了语境信息的管理。介绍了关键技术、相关支持工具以及开发的原型系统。该模型采用2种推理机制：基于描述逻辑的推理与规则推理,能够更快速有效地管理语境信息。 普     

面向战场信息共享平台的个性化推荐研究

随着大数据技术的发展,信息化、智能化作战将成为现代战争的未来趋势,如何从浩瀚信息中获取有效信息是提高作战指挥效率的重要问题。面向战场信息共享平台,利用推荐系统可解决信息过载问题的优势,结合军事领域信息数据特点,构建军事平台的个性化推荐系统框架,然后基于该推荐系统,提出融合情景感知的推荐算法,以提高军事平台的推荐服务质量。     

一种面向主动服务的情境觉察计算方法

We focus on modeling and computing of aware con- text with uncertainty for making dynamic decision during seam- less mobile service.We re-examine formalism of random set, which is not finite-set statistics (FISST),argue the limitations of the direct numerical approaches,give new modeling mode based on random sets theory (RST) for aware context,and propose our computing approach of modeled aware context.In addition, we extend classic D-S evidence theory after considering relia- bility,time efficiency,relativity of context,and compare these two kinds of relative computing methods for uncertain context. By comparing,the validity of new context-aware computing ap- proach based on improved random set theory (IRST) or extended D-S evidence theory (EDS) for proactive service has been tested.     

基于属性上下文可知的Web服务访问控制

Web服务本身的特性和分布式网络环境的复杂性使得访问控制成为一个富有挑战性的问题.该文提出了一种新型访问控制模型,引入了上下文参数,使得模型是上下文可知的,并能根据当时的上下文情况进行控制决策;采用基于用户属性的Web服务访问授权和控制方式,用户通过提供相关的信任证证明其拥有的属性.该模型较好地解决了Web服务的访问控制的新问题,适合分布式的、动态变化的Web服务环境.     

情景感知的物流Web服务动态优化组合研究

第四方物流服务通过大规模的资源整合,可以将领域内优秀的物流服务组合起来,为用户提供技术、仓储、运输服务等最佳结合的物流服务方案,实现物流服务的低成本、高效率、实时运作.然而,如何高效、动态地构建满足用户服务质量需求的可靠物流服务组合,是第四方物流服务商亟需解决的关键问题.针对这一问题,提出了一种情景感知的物流Web服务动态组合方法,该方法首先基于改进的遗传算法,将用户提出的全局QoS约束分解成局部QoS约束,从而将QoS感知的物流Web服务组合这一全局优化问题转化成局部最优服务选择问题;然后,在物流服务流程执行的过程中,依据当前关键的情景信息,选出可用并且能够满足局部QoS约束的最优物流服务;最后,通过实验验证了所设计方法的可行性和有效性.     

基于上下文感知的移动学习系统设计

移动学习足了信息化时代人们随时随地进行学习的需求,是泛在学习的重要组成。然而用户个体的差异性、学习环境的复杂性、终端设备的局限性等因素阻碍了移动学习的个性化发展。在对比了现有移动学习实现模式的基础上,构建了一个基于上下文感知的移动学习系统,利用泛在计算中的上下文感知技术应对复杂的学习环境,提升人与移动设备之间的交互,实现系统的个性化及智能化。     

A framework for smart workflow services in agricultural environments

To improve work efficiency and productivity in agricultural environment, which may naturally be protean, unpredictable and laborious, many researchers have made attempts to apply information technology in the field of conventional agriculture. Especially, they have great concern toward a reasonable and reliable service control model or architecture to control agricultural works automatically and smartly. This article proposes a framework to support context-aware or smart services in agricultural environments, based on a context-aware workflow model and USN/RFID. The suggested framework is focused on supporting autonomous agricultural services in the fields of growth control, protection against disease and insects, and the output control of the agricultural computing environment using a workflow model which is one of the successful service automation models, using contexts from various sensors in agricultural fields. The proposed framework, based on a context-aware workflow, can be greatly helpful in the development of smart applications or work automation in the field of agriculture.     

Future Perspectives of the Unified Global Infrastructure

A novel approach towards the realisation of future communication systems is presented, highlighting some key research-areas, whose proper development will contribute to the development of the envisaged trends. The concept of a unified global infrastructure is the core of this vision approach. Key-elements that need to be analysed are identified together with the approach required for their effective investigation. This revised version was published online in August 2006 with corrections to the Cover Date.     

用户情境感知的流式移动应用推荐

在目前流式应用分发系统中,客户端的移动应用分发都是依靠系统后台管理员人工操作或者简单地依靠位置信息为用户分发应用,没有考虑到用户在不同的情境活动下对应用的需求差异问题。针对上述问题,提出一种基于用户情境感知的流式应用推荐机制。该机制通过采集流式应用场景下用户的情境信息数据,利用机器学习Xgboost算法识别用户情境活动,并根据识别的用户情境来为用户推荐应用。同时,利用用户的反馈信息进一步提高用户个性化应用推荐的准确度。实验结果表明,Xgboost算法在准确率和时间开销上性能优于传统算法,在流式应用分发系统中有很高的实际应用价值。