Assessment of quality of life in equine patients

Reasons for performing study: Assessing patients' quality of life (QOL) is a core part of clinical decision making. Various methodologies for assessing patients' QOL have been developed in human medicine and small animal veterinary disciplines. In contrast, the lack of aids for QOL assessment in equine veterinary practice leaves practitioners reliant on subjective assessments of QOL, which may be prone to avoidable errors. Objectives: This paper suggests pragmatic ways in which QOL may be enhanced, while remaining appropriate for the time, financial and owner‐based constraints within equine practice. Methods: Through interdisciplinary research, this paper identifies, adapts and applies insights from several areas of research and practical experience in order to develop an overarching approach to making QOL‐based decisions in clinical cases. Results: The paper identifies 6 steps involved in QOL‐based decision making and provides examples of how these steps may be practically applied. These include deciding what each clinician feels is important; deciding how to evaluate it, including taking owners' views into consideration; making decisions about each case and achieving the desired clinical outcomes. Conclusions: Practitioners can draw their own conclusions on how they may improve QOL assessment in practice and may usefully share these with colleagues. Reporting cases and sharing practical examples of QOL tools used on the ground are vital to the development of this field and appropriate methodologies. Potential relevance: Improvements in QOL assessment are relevant to all areas of equine veterinary practice, and several areas of research. Further research may develop QOL assessment in practice, but more important are the personal improvements that each practitioner may achieve. See also correspondence by Grove     

Coping with imbalanced data problem in digital mapping of soil classes

An unsolved problem in the digital mapping of categorical soil variables and soil types is the imbalanced number of observations, which leads to reduced accuracy and the loss of the minority class (the class with a significantly lower number of observations compared to other classes) in the final map. So far, synthetic over- and under-sampling techniques have been explored in soil science; however, more efficient approaches that do not have the drawbacks of these techniques and guarantee retention of the minority classes in the produced map are essentially required. Such approaches suggested in the present study for digital mapping of soil classes include machine learning models of ensemble gradient boosting, cost-sensitive learning and one-class classification (OCC) of the minority class combined with multi-class classification. In this regard, extreme gradient boosting (XGB) as an ensemble gradient learner, a cost-sensitive decision tree (CSDT) within the C5.0 algorithm, and a one-class support vector machine combined with multi-class classification (OCCM) were investigated to map eight soil great groups with a naturally imbalanced frequency of observations in northwest Iran. A total of 453 profile data points were used for mapping the soil great groups of the study area. A data split was done manually for each class separately, which resulted in an overall 70% of the data for calibration and 30% for validation. The bootstrapping approach of calibration (with 10 runs) was performed to produce multiple maps for each model. The 10 bootstraps were evaluated against the hold-out validation dataset. The average values of accuracy measures, including Kappa (K), overall accuracy (OA), producer's accuracy (PA) and user's accuracy (UA), were explored. In addition, the results of this study were compared with a previous study in the same area, in which resampling techniques were used to deal with imbalanced data for digital soil class mapping. The findings show that all three suggested methods can deal well with the imbalanced classification problem, with OCCM showing the highest K (= 0.76) and OA (= 82) in the validation stage. Also, this model can guarantee the retention of the minority classes in the final map. Comparing the present approaches with the previous study approach demonstrates that the three newly suggested methods can remarkably increase both overall and individual class accuracy for mapping.     

模糊综合评判与灰色决策渗透糅合在旅游方案选择中的应用

从产量、产值、价值3个方面对旅游点选择进行了综合评判,从中得出最佳方案,进而又从群众、专家、领导3个层次,从不同角度对其投资进行了灰色层次决策,为科学选择旅游点、合理投资提供了依据.     

基于机器学习的高光谱湿地植被分类研究

为实现湿地植被的精细分类和高精度制图,为湿地管理部门提供准确的决策依据,以美国加州萨克拉门托—圣华金水域的典型湿地植被为研究对象,以高光谱影像为数据源,结合野外GPS采样点,对典型湿地植被的光谱反射率作一阶导数和二阶导数处理,基于均值置信区间原理筛选特征波段,基于单因素分析法筛选能够明显区分植被类型的植被指数。联合特征波段和植被指数构建特征集,利用机器学习C5.0决策树生成知识规则并提取湿地植被信息。结果表明,基于机器学习C5.0决策树的湿地植被提取总体精度为80.09%,Kappa系数为0.792,与最大似然法比较,总体精度提升10.79%,Kappa系数提升0.105,说明基于机器学习的C5.0决策树法能够实现植被的精细分类,方法切实可行。     

天空地数字农业管理系统框架设计与构建建议

数据正在成为基础性战略资源。构建以天空地大数据为关键要素的数字农业管理系统,对于建设数字中国、推进农业高质量发展、抢占全球农业制高点具有重要意义。本研究围绕农业农村部提出的天空地数字农业管理系统建设任务,从农业信息技术学科出发,首先给出了天空地数字农业的科学内涵,阐述了其与传统数字农业的异同点,理清了天空地数字农业管理系统在资源调查、生产调度、灾害监测、市场预警、决策服务的五大核心功能;其次,重点阐述了天空地数字农业管理系统的关键任务,即一个观测体系（天空地一体化的数字农业观测体系）、四个数字化（农业资源权属、生产过程、灾害监测和市场预警）、一个管理平台（农业生产、加工、经营、管理、服务等全产业链的天空地数字农业管理平台）;然后,明确提出了天空地数字农业管理系统在标准规范研制、关键技术与装备研发、系统集成与平台开发三方面的科技创新重点任务;最后,针对天空地数字农业管理系统建设的复杂性和系统性,从规划设计、科技创新、资源共享、多方参与、应用领域拓展等方面提出了发展建议。     

基于Web的煤矿废弃地土地复垦决策支持系统设计与实现

为了克服现有煤矿废弃地土地复垦与植被恢复试验法费时费力的缺陷,根据土壤基质和气候相似性原理,采用模糊综合评价一灰色关联优势分析、基于距离的相似算法、基于规则的推理等多种数学方法,分别从植被恢复潜力评价、适生植物品种选择、土地复垦方案选择3个方面建立了相关数学模型,解决了煤矿废弃地恢复潜力的分级、先锋植物选种和土地复垦方案的确定等问题,从而为煤矿废弃地的植被恢复提供了一系列的决策支持.并使用ASENET 等编程语言结合MS Access数据库设计并开发了基于web的煤矿废弃地植被恢复的决策支持系统,该系统能为煤矿废弃地植被恢复工作提供新的研究模式和手段,并已经在辽宁省阜新矿区得到应用,结果表明系统所采用的方法科学、合理、可行.     

Study on Decision Method in Choosing MIS Softwares for Manufacturing Enterprises

The decision objects and evaluation target architecture in choosing Management Information Systems (MIS) softwares for manufacturing enterprises are proposed. Fuzzy mathematics comprehensive evaluation method is used in decision analysis. The method in is applied practically.     

Fuzzy Decision Making in Cooperation Choosing the Objective of M&A

In order to socve the realistic problems happening in the process of M&A,the paper gives the fuzzy decision making method of cooperation choosing the best objective of M&A using the tool of fuzzy maths and applies the method to a case,which may be helpful to choose the best objective of M&A more scientifically.     

Application of the Fractal Theory in Modelling Decision Making Models for Manufacturing by Using the Experimental Data

Based on the fractal theory,the fractal dimension of the decision making mapping model for manufacturing by using the experimental data is studied.In modelling the decision making mapping of the intermittent cutting process,the approach for modelling mapping models by the fractal theory and the fractal dimension of the models are discussed.     

Social resilience as a controlling influence on desertification in Senegal

While ecological resilience may explain why apparent symptoms of desertification are often temporary, social resilience can prevent degradation resulting from overexploitation of land in response to drought and other constraints. This paper describes a Social Resilience Model in which actors switch from performance strategies to survival strategies when the perceived severity of constraints exceeds a critical performance–survival threshold (PST). This is determined in comparison with a reference mode that depends on a learning facility developed by repeated exposure to cycles of constraint, search and feedback. Actors select particular strategies by comparing welfare gains with their aspiration levels—a concept that allows more flexible decision making than profit maximizing or satisficing alone. The model is tested in the silvopastoral zone of Senegal, where desertification is not as widespread as commonly assumed, despite severe constraints. The two major ethnic groups, the Wolof (mainly croppers) and the Peul (mainly pastoralists) anticipate and respond to environmental and socio‐economic constraints differently, and have different performance and survival strategies. The Peul have the higher social resilience, with more flexible decision‐making objectives, greater mobility, a more extensive action space, a learning facility supporting efficient search and feedback processes, a reference mode attuned to high anticipation and recognition of stress, and a high PST. They also exhibit more continuous performance–survival switching than the Wolof, who make a radical change from cropping to labour migration and reliance on external support. Copyright © 2004 John Wiley & Sons, Ltd.