医疗事故辅助鉴定系统的设计与实现

本文以典型的医疗事故(事件)鉴定问题为应用背景，提出一类PRS案例的推理问题及其知识结构和表达方法，以及基于相似度的PRS案例检索算法和PRS案例的混合推理算法。根据医疗事故鉴定问题的特点．应用理论方法研究结果，设计实现了一个计算机辅助医疗鉴定系统(CAMCS)，并且对实际发生的几个医疗事故鉴定的典型案例进行分析，验证了基于案例混合推理方法的正确性，以及CAMCS系统的实际应用效果。     

玉米灰斑病菌致病性分化的寄主鉴定方法

玉米灰斑病现已严重威胁中国北方玉米生产的可持续发展。本研究采用苗期鉴定、成株期鉴定、温室鉴定和田间鉴定等方法，利用玉米自交系和品种对玉米灰斑病菌致病性分化鉴定方法进行了研究。结果表明：玉米苗期和成株期均可用于玉米灰斑病的抗性鉴定，两者鉴定结果有一定的相似性，但利用成株期进行鉴定比较好，因为接种比较容易；利用自交系或品种均可进行抗性鉴定，从效果上看，利用自交系较好，因为利用成株期自交系鉴定法，不同自交系一菌株组合间病级差异较明显，变异系数为47．32％，能有效地区分不同菌株间致病性分化的程度，但是由于成株期品种鉴定法与成株期白交系鉴定法比较。变异系数差异很小，所以成株期品种鉴定法可以作为抗性鉴定的辅助方法。     

欧洲星2000推进剂贮箱的设计和鉴定

原型欧洲星推进剂贮箱是１９８７年进行鉴定试验的。由于当时它也设计用于其他任务，用与基本设计类似的方法对中间柱体部分长度比基本设计长３．１８１ｉｎ到短６．９７ｉｎ的长度范围的贮箱进行了鉴定。这样，使用相同推进剂管理装置的同一基本设计的推进剂贮箱，其容积范围可在基本设计容量的７７．７％－１１０．１％之间变化。     

利用决策树方法对蛋白质鉴定结果二次评价

为了有效地利用蛋白质串联质谱数据,进一步提高蛋白质鉴定的准确性,提出一种基于决策树的蛋白质鉴定结果的二次评价算法.目前,串联质谱已经成为解决蛋白质鉴定问题的最为有效的技术手段.随着蛋白质串联质谱数据的大量聚集,蛋白质鉴定算法也日益增加.然而,现有的蛋白质鉴定算法通常返回数量庞大的结果列表,因此对列表中的鉴定结果进行二次评价是提高蛋白质鉴定准确性的一个重要环节.针对此问题,首先利用频繁模式挖掘方法获得了b离子的特征信息,进而基于决策树理论提出一种蛋白质鉴定结果的二次评价算法即ReCheck算法.实验结果表明,该算法有效的提高了蛋白质鉴定的准确性.     

职业技能鉴定集成管理系统设计与实现

随着计算机信息和技术的发展,国家对信息化的建设越来越重视,计算机在各个部门和商业领域已在普及．人们传统的手工处理信息的方式已被计算机所取代,“无纸”办公已占据了主流,各种相关信息综合管理已成为现代信息录入与管理的基本手段。对我院职业技能鉴定进行了研究,编程实现了职业技能鉴定系统的实现。     

安全级仪控系统设备鉴定样机代表性分析

安全级仪控系统是核电站的中枢神经,是核电厂安全运行必不可少的系统设备。为了确定安全级仪控系统的可靠性和安全性,设备鉴定成为其主要技术手段。受成本和时间等因素限制,设备鉴定通常使用具有一定代表性的鉴定样机来完成相关试验。因此,核电厂安全级仪控系统鉴定样机的代表性是鉴定结论能否适用于工程产品的关键。NB/T20344和IEEE标准提出了一些关于鉴定样机代表性方面的要求和分析方法。以相关法规、标准为基础,对鉴定样机的代表性分析进行了研究,详细描述了定性分析的要素,并在定性分析的基础上提出了一项全新的基于符合性系数的定量分析方法。该方法大大提高了鉴定样机代表性分析结果的可信性。     

核电站1E级仪表环境鉴定技术探析

为了保证核电厂的运行安全,必须对1E级仪表进行环境鉴定。本文论述了核电站1E级仪表环境的鉴定方法和主要内容,并通过三代核电站和二代改进型核电站环境鉴定要求的对比,分析了三代核电站在1E级仪表环境鉴定技术中的改进。     

细菌数值分类鉴定法的程序设计

细菌的数值分类鉴定集数学、电子、信息及自动化技术于一体,实现细菌鉴定过程的系统化、标准化、自动化,是目前自动化细菌鉴定系统中广泛应用的一种细菌鉴定方法。该方法以细菌的生化试验检测为基础,采用数理统计原理,计算并比较待检菌株与细菌数据库中已知细菌在生化特征上的符合概率,从而作出鉴定结论（包括鉴定菌名称、鉴定值、模拟机率值等）。本程序以临床上常见的肠杆菌科细菌的鉴定作为设计示例,肠杆菌科细菌名称及有关试验数据的资料参见《全国临床检验操作规程》（第二版）。程序通过输入的试验结果（＋／－）,可确定一个符…     

针对装表接电工技师鉴定考前培训的探讨

装表接电工技师鉴定是电力行业特有工种职业技能鉴定中的一种,是测量从事装表接电相关工作的劳动者职业技能水平的一种考试。该文从培训目的、培训对象、培训内容、培训教材、培训组织形式和培训评估等几个方面对装表接电工技师鉴定考前培训进行了探讨。     

“师带徒”与技能鉴定

技能鉴定培训目标的明确化、培训内容的标准化、培训结果的可追溯、可监控决定了它比传统的师带徒方式更有可控的学习效果,有助于那些优秀经验在组织中迅速传播。     

用于大豆品种识别的叶片深度特征学习方法

大豆有许多品种(cultivar),它们的叶片图像模式的差异非常细微,因此很难通过叶片特征将大豆品种区分开.虽然在使用叶片图像模式进行植物种类(species)识别方面的研究已经取得了巨大的进步,然而,作为一项非常细粒度的模式识别问题,大豆品种的识别与分类研究尚未引起足够的重视.传统的手工叶片图像分析方法一般无法刻画不同大豆品种的叶片特征的细微差异,因此识别率很低.本文尝试使用深度学习来提取具有强的辨识能力的叶片特征,以解决大豆的品种识别问题.我们提出了一种新颖的深度学习模型,称为目标转换注意力网络(Transformation Attention Network,TAN).该方法首先通过注意力机制提取细粒度的叶片图像特征,然后使用仿射变换纠正叶片姿势.我们构建了一个由240个大豆品种组成的大豆叶片品种图像数据库,每个品种有10个样本,以此数据集验证叶片图像模式中品种信息的可用性,并验证了所提出的深度学习模型对大豆品种识别的有效性.令人鼓舞的是实验结果证实了叶片图像模式在区分栽培大豆品种方面的有效性,并证明了所提出的方法优于流行的叶片手工特征提取方法和深度学习方法.     

RZWQM2 simulated management practices to mitigate climate change impacts on nitrogen losses and corn production

Gaseous and aqueous nitrogen (N) losses from corn (maize) production systems are concerns under projected climate change. In the present study, the Root Zone Water Quality Model (RZWQM2) was used to test the ability of agricultural management practices (N application rate, corn cultivar, planting date, tillage and controlled drainage) to mitigate future climate change effects on N losses and corn yield in a subsurface drained field in Iowa, USA. Under a future downscaled climate scenario, the simulated non-constant N₂O emission factor (EF), yield-scaled global warming potential and N loss through drainage increased with increasing fertilization above an optimal N rate of 120 kg N ha⁻¹. This rate represents the optimal tradeoff point between environmental issues and economic returns. While yields of the cultivar IB1068 DEKALB declined with climate change, yields of cultivar, IB 0090 GL 482 in the future climate were greater than historical yields of IB 1068 DEKALB.     

Grain Yield Prediction: Extending the Stress-Degree-Day Approach to Accommodate Climatic Variability

Combination of the stress-degree-day concept of plant water stress assessment with the growing degree-day concept of plant phenological development leads to a new approach to the prediction of grain crop yields that accounts for climatic effects of light, temperature, and water. The model requires knowledge of the dates of plant emergence and heading, maximum and minimum air temperatures through the growing season, and midafternoon canopy-air temperature differentials from the time of heading to physiological maturity. Its utility is illustrated by development of the predictive relationship for a specific cultivar of wheat grown at Phoenix, Arizona, and a test of its predictions for the same cultivar grown at Davis, California. Both final yield and the time of cessation of crop growth are adequately predicted.     

特异高产株型大豆—沈豆4号生育规律的研究

采有特异高产株型大豆沈豆4号进行了3年的研究，探讨了沈豆4号在不同年份，不同播种期条件下的生育规律，结果表明，浓豆4号的株高增长，单株生物产量积累和籽粒鼓粒过程均可以用Logistic曲线方程来描述。不同播期对沈豆4号植株形态和生育进程有很大影响。在5月10日前后播种最适宜，此时植株生物产量积累轨迹更合乎高速积累出现早，积累速度不偏高的高产积累轨迹，沈豆4号开花后期和植株上部形成的籽粒其灌浆速率最大。     

The effect of data augmentation and network simplification on the image‐based detection of broccoli heads with Mask R‐CNN

In current practice, broccoli heads are selectively harvested by hand. The goal of our work is to develop a robot that can selectively harvest broccoli heads, thereby reducing labor costs. An essential element of such a robot is an image‐processing algorithm that can detect broccoli heads. In this study, we developed a deep learning algorithm for this purpose, using the Mask Region‐based Convolutional Neural Network. To be applied on a robot, the algorithm must detect broccoli heads from any cultivar, meaning that it can generalize on the broccoli images. We hypothesized that our algorithm can be generalized through network simplification and data augmentation. We found that network simplification decreased the generalization performance, whereas data augmentation increased the generalization performance. In data augmentation, the geometric transformations (rotation, cropping, and scaling) led to a better image generalization than the photometric transformations (light, color, and texture). Furthermore, the algorithm was generalized on a broccoli cultivar when 5% of the training images were images of that cultivar. Our algorithm detected 229 of the 232 harvestable broccoli heads from three cultivars. We also tested our algorithm on an online broccoli data set, which our algorithm was not previously trained on. On this data set, our algorithm detected 175 of the 176 harvestable broccoli heads, proving that the algorithm was successfully generalized. Finally, we performed a cost‐benefit analysis for a robot equipped with our algorithm. We concluded that the robot was more profitable than the human harvest and that our algorithm provided a sufficient basis for robot commercialization.     

Development of a micrometeorological model for the estimation of methane flux from paddy fields: Validation with standard direct measurements

This work has focussed on the development of an indirect method for estimating methane fluxes from paddy fields and wetlands. A micrometeorological model, based on an analytical solution of the Eulerian advection–diffusion equation for vertical diffusion, has been used; model parameters include the location of the methane analyser and standard surface layer scaling factors. Flux chambers, which are commonly used for measuring methane fluxes from agricultural sources, are usually mechanically operated with a rated induced-draft fan and as such cannot replicate the real world atmospheric conditions. The results are not very reliable due to leakages along the piping and at fittings, especially when these chambers are used over a relatively rough surface like an agricultural field or a wetland. The results of the model have been compared with those from the direct method. The seasonal average methane flux calculated by the indirect method, for the cultivar type “Sundari”, is 7.13E+05 g/ha, while cultivar type “Shatabdi” gives a little lower value of 5.22E+05 g/ha. In case of the direct chamber method also, the seasonal average methane flux for the cultivar type “Sundari” (6.20E+05 g/ha) is more than cultivar type “Shatabdi” (4.84E+05 g/ha). When the two methods of assessment were compared, season September–December 2004 gave r² = 0.91, RMSE = 0.16 and MNB = 0.13 while we got r² = 0.94, RMSE = 1.22 and MNB = 0.06 for the season September–December 2005.In very few experiments we could cover a huge aerial plot instead of a huge number of experiments necessary for the direct chamber method.     

Discrimination of sugarcane varieties in Southeastern Brazil with EO-1 Hyperion data

Hyperspectral data acquired by the Hyperion instrument, on board the Earth Observing-1 (EO-1) satellite, were evaluated for the discrimination of five important Brazilian sugarcane varieties (RB72-454, SP80-1816, SP80-1842, SP81-3250, and SP87-365). The radiance values were converted into surface reflectance images by a MODTRAN4-based technique. To discriminate varieties with similar reflectance values, multiple discriminant analysis (MDA) was applied over the data. To obtain an adequate discriminant function, a stepwise method was used to select the best variables among surface reflectance values, ratios of reflectance, and several spectral indices potentially sensitive to changes in chlorophyll content, leaf water, and lignin-cellulose. Results showed that the five Brazilian sugarcane varieties were discriminated using EO-1 Hyperion data. Differences in canopy architecture affected sunlight penetration and reflectance, resulting in a higher reflectance for planophile (e.g., SP81-3250) than erectophile (e.g., SP80-1842) sugarcane plants. The variety SP80-1842 presented lower reflectance values, deeper lignin-cellulose absorption bands at 2103 nm and 2304 nm, shallower leaf liquid water absorption bands at 983 nm and 1205 nm, and lower leaf liquid water content than the other sugarcane varieties. To discriminate this cultivar, a single near-infrared (NIR) band threshold was used. To discriminate the other four sugarcane varieties with similar reflectance values, MDA was used producing a classification accuracy of 87.5% for a hold-out set of pixels. The comparison between the ground truth data and the MDA-derived classification image confirmed the model' capacity to differentiate the varieties accurately. The best results were obtained for the cultivar SP87-365 that presented the lowest spectral variability in the discriminant space. Some misclassified areas were associated with the cultivars SP80-1816 and SP81-3250 that showed the highest spectral variability.     

Reflectance assessment of mite effects on apple trees

Reflectance measurements were conducted in field plots of Golden Smoothee 2038 apple cultivar subjected to different levels of mite attack (from 0 to 500 cumulative mite days) over a 2-year period. Chlorophyll concentration decreased and carotenoid/chlorophyll a ratio increased with increasing level of attack. Classical reflectance indices such as red edge wavelength or the Normalized Difference Vegetation Index were unable to distinguish among treatments. On the other hand, spectral indices based on carotenoid/chlorophyll a (SRPI R430/R680) and chlorophyll degradation (Normalized Phaeophytinization Index calculated as (R415-R435)/(R435 +R415)) were correlated with the level of attack. These reflectance indices show potential uses of visible reflectance as non-invasive, non-destructive techniques for detection of mite effects.     

A GIS-based approach to evaluate biomass potential from energy crops at regional scale

The aim of the paper is to propose a method to maximize energy production from arboreous and herbaceous dedicated crops given the characteristics of the local environment: geo-morphology, climate, natural heritage, current land use. The best energy crops available in the Italian panorama are identified and the problem of maximizing the bioenergy production over an entire regional area is formulated. Each cultivar is thus assigned to the suitable land accounting for sensitive parameters that characterize it and taking into account current land use. The assumption made here is that marginal land and set-asides can be converted to energy crops without altering current practices and cash crops’ production. The method is based on the integration of GIS data (spatially continuous) with data derived from the agricultural census (spatially discrete). We carry out the analysis for Emilia-Romagna, in Northern Italy. The sustainable growth of energy crops, with an optimized network of conversion facilities distributed in the territory, may significantly contribute to the local energy supply and to climate change mitigation.     

Multiscale recognition of legume varieties based on leaf venation images

In this work we propose an automatic low cost procedure aimed at classifying legume species and varieties based exclusively on the characterization and analysis of the leaf venation network. The identification of leaf venation patterns which are characteristic for each species or variety is not an easy task since in some situations (specially for cultivars from the same species) the vein differences are visually indistinguishable for humans. The proposed procedure takes as input leaf images acquired using a standard scanner, processes the images in order to segment the veins at different scales, and measures different traits on them. We use these features in combination with modern automatic classifiers and feature selection techniques in order to perform recognition. The process was initially applied to recognize three different legumes in order to evaluate the improvements over previous works in the literature, and then it was employed to distinguish three diverse soybean cultivars. The results show the improvements achieved by the usage of the multiscale features. The cultivar recognition is a more challenging problem, since the experts cannot distinguish evident differences in plain sight. However, we achieve acceptable classification results. We also analyze the feature relevance and identify, for each classifier, a small set of distinctive traits to differentiate the species and varieties.