基于案例推理的鱼雷制导系统故障诊断方法

为了解决传统的基于规则推理（RBR）方法存在的不足,将基于案例推理（CBR）方法引入鱼雷制导故障诊断系统中。阐述了案例推理的诊断策略,重点描述了二级案例检索策略及其算法,进而从案例描述、系统结构和工作流程3个方面介绍了基于案例推理的鱼雷制导系统故障诊断方法设计,并在VB6.0平台上开发了故障诊断系统,最后通过具体的故障案例比较了RBR和CBR两种方法。案例分析结果表明,所开发的基于案例推理故障诊断系统能够提高鱼雷制导系统维修的准确性和高效性。     

基于本体和规则的扬弹机故障诊断研究

通过对OWL(Web Ontology Language,OWL)本体和SWRL规则语言进行研究,将基于本体和规则的知识表示和智能推理技术应用到舰船扬弹机的故障诊断中。构建了舰船扬弹机的OWL本体及相关的故障诊断SWRL(Semantic Web Rule Language,SWRC)规则,在此基础上开发出一个故障诊断的系统,并实现了诊断推理过程。该系统能帮助设备维护员快速定位故障发生原因,并提供可选用排除故障的基本措施。     

中心城区绿道智能选线规划研究——以宿迁为例

【目的】当前在绿道系统规划分析中较少应用自下而上的人本分析视角和时空间行为分析方法,缺乏对居民在绿道中行为方式的研究,在方法上对于机器学习的应用仍然处于探索阶段。【方法】以经典设计理论作为支撑,选取宿迁市中心城区作为案例地,整合手机信令数据、居民活动数据、街景数据等多源数据,借助人工智能、LSTM神经网络、时空行为分析等量化分析方法,分析居民真实出行的时空特征,提出绿道智能选线分析框架。【结果】结合LSTM神经网络、类A*算法等构建的轨迹模拟模型可有效开展绿道选线评估,模拟居民真实出行行为,提取潜在绿道网络。【结论】构建了中心城区绿道智能选线方法,将居民真实活动轨迹融入空间要素分析中,融合居民出行行为特征与街道环境要素,通过量化评估方法为绿道选线规划和建设提供指导。     

An adaptive clinical decision support system for serving the elderly with chronic diseases in healthcare industry

With the increasing ageing population worldwide, providing effective nursing care planning in nursing homes is important in meeting the expectations of elderly patients and in streamlining the healthcare information process, hence maintaining high‐quality services. Instead of the traditional manual nursing care planning formulation based on expert experience and subjective judgement, this paper describes an adaptive decision support system, namely, the cloud‐based nursing care planning system, to enable decision making in formulating nursing care strategies. By integrating cloud computing technology and the case‐based reasoning (CBR) technique, medical records and documents pertaining to the elderly can be captured in real time, whereas appropriate treatment plans based on past similar treatment records can be formulated. However, the current case adaptation processes in CBR rely on domain experts to modify retrieved cases, which may not satisfy the needs of the elderly. Therefore, text mining is integrated in the case adaptation process of CBR for extracting up‐to‐date medical information from the Internet so that its efficiency can be improved. By conducting a pilot study in a nursing home, it was shown that the time for formulating applicable treatment plans for elderly patients can be reduced, and the service satisfaction level can be enhanced.     

Spatio-temporal analysis of precipitable water vapour over northwest china utilizing MERSI/FY-3A products

Northwest China is considered as the arid and semi-arid temperate continental climate, where the precipitation is closely related to precipitable water vapour (PWV) content. In this paper, the Medium-Resolution Spectral Imager (MERSI) water vapour products were first used to study the spatial and temporal characteristics of water vapour over Northwest China, which were developed by the National Satellite Meteorological Center of China from the Chinese second-generation polar orbit Meteorological Satellite Fengyun 3A (FY-3A). In order to utilize the MERSI water vapour products, the MERSI 5 min water vapour product is compared respectively with global positioning system (GPS), Aerosol Robotic Network (AERONET) and Radiosonde water vapour data in situ datasets. The results show that the water vapour values of the MERSI product are a slightly lower than referenced data, and the accuracy of MERSI product compared with GPS water vapour is the most agreeable, with a mean absolute percentage error (MAPE) of 22.83%. The PWV content displays a typical spatial distribution pattern in Northwest China that it is the highest in the southeast, the second for the northwest and the lowest in the south-centre. The water vapour content over each province in a descending order is Shaanxi, Ningxia, west of Inner Mongolia, Xinjiang, Gansu and Qinghai. The seasonal variation of water vapour content over Northwest China appears to be lowest in winter, followed by spring, then for autumn, and highest in summer. The PWV content of each province in Northwest China shows the periodic inner-annual variation, that is, the PWV content is lowest in January, and gradually increases with time till it peaks in July, and then decreases monthly afterwards, which agrees with the quadratic polynomial model by months. The standard deviation of the water vapour content in summer is 0.533–1.027 mm, while that in winter is 0.262–0.527 mm.     

FUZZY REASONING USING POSITIONAL INFORMATION

Abstract

The paper argues in favour of reasoning methods that process positional information, i.e. information about the position of the input with respect to the class prototype, and thus achieve a better specification of the corresponding output class. It is shown that such an approach leads to reducing or cancelling unwanted nonlinearities (of input-output characteristic) imposed by reasoning methods, nonlinearities that alter the dependence expressed in the knowledge base. Two methods which use positional information are presented: (a) the mapping of o-cut borders (MACB) (Stoica, 1993, Proc. Fifth IFSA World Congress, pp. 1266-1269), inspired from a particular interpretation of the representation theorem and (b) the Left/Right Centre of Gravity (L/R COG) (Ghanayem, 1995, Proc. IEA/AIE, pp. 41 -45). The methods are tested in implementing a power system stabiliser (PSS) Simulation results show better performance of methods that use positional information, as compared with classic Mamdani (Mamdani, 1975, International Journal of Man-Machine Studies, 7, 1-13) reasoning. Reflections on a “best” reasoning method conclude the paper.     

Cartographic visualization of human trajectory data: overview and analysis

With the prevalence of mobile computing systems and location based services, large amounts of spatio-temporal data are nowadays being collected, representing the mobility of people performing various activities. However, despite the increasing interest in the exploration of these data, there are still open challenges in various application contexts, e.g. related to visualisation and human–computer interaction. In order to support the extraction of useful and relevant information from the spatio-temporal and the thematic properties associated with human trajectories, it is crucial to develop and study adequate interactive visualisation techniques. In addition to the properties of the visualisations themselves, it is important to take into consideration the types of information present within the data and, more importantly, the types of tasks that a user might need to consider in order to achieve a given goal. The understanding of these factors may, in turn, simplify the development and the assessment of a given interactive visualisation. In this paper, we present and analyse the most relevant concepts associated to these topics. In particular, our analysis addresses the main properties associated with (human) trajectory data, the main types of visualisation tasks/objectives that the users may require in order to analyse that data and the high-level classes of techniques for visualising trajectory data. In addition, this paper also presents an overview on a user study, conducted in function of this analysis, to compare two classes of visualisation techniques, namely static maps and space-time cubes, regarding their adequacy in helping users completing basic visualisation tasks.     

Detecting modes of transport from unlabelled positioning sensor data

Global positioning systems (GPS) logs recorded in personal devices contain rich information such as travel patterns, locations of frequent visits and place–event associations. There have been rather successful attempts in detecting the mode of transport from GPS logs such as walking, driving or taking a bus, which has found varied applications. However, the best-known schemes either require tedious manual labelling or pre-training process (or both). We present MoDetect (MD), a unsupervised scheme which eliminates the need of manual labelling and pre-training while attaining equal or greater accuracy compared with the best-known supervised methods. MD can also cater for differences in individual's behaviours, and hence may be more widely applicable than the existing schemes. To achieve this, MD relies on Kolmogorov–Smirnov test which offers a theoretical assurance when computing similarity between segments of records. Our analysis shows that the higher speed modes can be better differentiated through a weighted bootstrapping procedure. We also augment the decisions with reference to the transfer probabilities between different modes at locations identified from the GPS records.     

PRACTICAL INCONSISTENCY MANAGEMENT FOR CRITICAL-TASKS DECISION-SUPPORT SYSTEMS

Abstract

In this paper, the problem of logical consistency in critical-tasks decision systems is addressed. It is shown how local search techniques can be used to check the (in)consistency of very large propositional knowledge bases (KBs). Using new heuristic findings. we can now implement efficient forms of diagnostic reasoning in the context of very large ICBs modeling deep models of complex devices and including patterns of default reasoning.