对预测集样品预测平均相对偏差为3.2％。
The average relative deviation of the predication set was 3.2%.
以预测集的预测相关系数(r)，预测标准偏差(RMSEP)作为模型评价指标。
The correlation coefficients (r) and root mean square error of prediction (RMSEP) were used as the model evaluation indices.
在承受了一周的损失之后美国市场在周五集合起来，但是昨天未来市场交易者预测今天澳洲市场开盘较低而不是跟随海外势头。
Us markets rallied on Friday after a week of losses, but yesterday futures market traders predicted the Australian market would open lower today rather than follow the lead from overseas.
预测值需要按照给定的测试集顺序排列。
The predictions should be arranged by the given test set order.
音译是解决多语言挑战的一个关键组件，提供一个公共基础来构建一个可预测的标准化规则集。
Transliteration will serve as a key component to solving multiple linguistic challenges, and provides a common ground for you to build a standardization rule set with predictability.
Track1和Track1，你需要上传一个包含了个字测试集预测结果的文件。
For both Track1 and Track2, you will be required to upload one file, which includes the predictions for the respective test set.
该方法的缺点在于离线实验只能评测一个很狭窄的数据集切面，主要是关于算法预测或者评估的准确性。
The downside is that off-line experiments can evaluate a narrow set of aspects, primarily about algorithms prediction or recommendation accuracy.
针对民用机场多因素气象预测问题的复杂性，该文构建出一种基于粗糙集的模糊神经网络模型。
For a multifactor weather prediction problem, this paper constructs a new model of fuzzy neural network based on rough set.
连续型储集层属性分布预测是油气储集层研究的重要内容。
Predicting the distribution of continuous reservoir attributes is an important task in the reservoir research.
本文把影响地下水位的因素集作为网络的输入向量，地下水位本身作为网络的输出向量，构成了预测地下水位的BP网络模型。
In the paper, a BP network in which the factors to effect groundwater levels are set as input neurons and the groundwater level is set as output neuron, was established to forecast groundwater level.
本文简述了跨膜蛋白预测算法的研究进展，并给出了基于欧洲生物信息中心测试集的各种算法的预测结果。
In this paper, we reviewed the development on the prediction algorithms and gave their prediction accuracy based on the datasets created by European Bioinfomatics Institute.
结果表明，在训练集样本数据较少时，广义回归神经网络的预测准确度仍然很高。
The results showed that the prediction accuracy is satisfied, even though there are a few data in training sets.
实际应用表明：该模型大大提高了网络的学习效率和预测评判的精度，可以作为油气集输管道腐蚀速率预测的良好工具。
The results show that the model has a great efficiency of network learning and a high accuracy of prediction and judgement.
根据异常时刻组成的灾变日期集用灰色灾变模型进行预测。
The prediction is conducted with the grey catastrophe model through the abrupt date set composed of abnormality times.
最后，使用分类器对测试数据集进行分类和预测。
Finally, test data sets and forecasts by using the classifier.
实例表明，集对分析方法能够较好地预测煤与瓦斯突出的可能性，是预测灰色系统的一种方便、合理的方法。
By a practical example, the set-pair method is good for forecasting coal-gas emerging, and it is a convenient and reasonable method of analyzing gray system.
这些不仅为燃煤发热量预测提供了一种新的方法，而且也拓宽了粗糙集理论的应用领域。
All these not only provides a new method to forecast the quantity of heat, but also develops the application fields of RS.
在关键井点测井资料研究基础上，结合岩石力学实验，用有限单元方法对迪那气田古近系储集层现今地应力分布做出预测。
Based on key well log data and rock mechanics experiment, the present ground stress distribution of Paleogene reservoir in Dina gas field is predicted with finite element method.
地震波阻抗反演技术已日益成为油气藏勘探、开发中储集层横向预测的重要手段。
The seismic wave impedance inversion technique is becoming an increasingly important tool in carrying out reservoir prediction for oil exploration and development.
地震储集层预测一般分为递推反演、测井约束反演和叠前反演三大类，应用时有条件限制。
Generally, reservoir predicting technologies can be classified as: recurrence inversion, logging restriction inversion and pre-stack inversion, which should be fit to some conditions in application.
由于地质条件和资料品质的限制，复杂断块区的三维地震资料反演和储集层预测有较大的难度。
The seismic inversion and reservoir prediction in complex fault-block areas are hard to make due to complicated geologic conditions and poor quality of seismic data.
本文基于储集层裂缝系统具有非线性特征，提出了裂缝非线性预测技术。
Based on non-linear character having in fractured system of reservoir, the paper presented non-linear prediction technique of fracture.
目的预测海拉尔盆地呼和湖凹陷下白垩统有利储集相带和复合圈闭。
AimInteresting Cretaceous reservoir belts and complex traps are predicted in Huhehu Depression of Hailar Basin, Notheast China.
通过模型正演、反射特征、地震波谱属性参数分析认为，以实际资料为基础的地震模型研究可用于集储层预测工作。
According to the analysis of forward modelling, reflector characteristics and spectral properties, it is considered that the seismic model based on actual data can be used in reservoir prediction.
地震储集层预测的基本内容可以归结为岩相预测、岩性预测、物性预测及含油气性预测。
The basic content of seismic reservoir prediction covers a large prediction range from petrofacies, lithology, petrophysics, to oil and gas distribution.
测井数据的统计指标可用于预测储集层参数的分布。
The statistical indicators of well log can be used to predict the distribution of reservoir parameters.
在合作风险预测方面，主要采用了粗集理论。
In the part of cooperation forecasting, Rough Set Theory is been used.
提出了一种综合运用高分辨率地震反演技术和地质模拟方法预测薄储集层的方法。
The method for prognoses of thin reservoirs by combining seismic high-resolution inversion technology and geological simulation was presented.
为了查明该区油气储层的形成条件和控制因素，预测有利储集带则成为该区迫切需要解决的问题。
It is exigent to understand the formation conditions and control factors for petroleum reservoir in order to fine out advantageous regions in the area.
为了查明该区油气储层的形成条件和控制因素，预测有利储集带则成为该区迫切需要解决的问题。
It is exigent to understand the formation conditions and control factors for petroleum reservoir in order to fine out advantageous regions in the area.
应用推荐