The use of infrared spectroscopy and machine learning tools for detection of Meloidogyne infestations

Plant parasitic nematodes are generally soilborne pathogens that attack plants and cause economic losses in many crops. The infested plants show nonspecific symptoms or, often, are symptomless; therefore, diagnosis is performed by taking soil and root tissue samples. Here, we show that a combination of different infrared spectra analysis and machine learning algorithms can be used to detect plant parasitic nematode infestations before symptoms become visible, using leaves instead of roots and soil as samples. We found that tomato and guava plants infested with Meloidogyne enterorlobii produced different spectral patterns compared to uninfested plants. Using partial spectra from 1,450 to 900/cm as the "fingerprint region", principal component analyses indicated that after 5 (tomatoes) or 8 weeks (guava), plants with no visible symptoms of infestations were positively diagnosed. To improve the early detection response, we used machine learning modelling. A support vector machine (SVM) was used to obtain more robust, accurate models. The SVM model contained 34 support vectors, 17 for each level. The overall performance of the model was >97% and the total accuracy was significantly higher, demonstrating the absence of chance prediction. The best prediction of infestation was obtained at the second and fourth weeks for tomatoes and guavas, respectively, reducing the diagnostic time by half. The combined application of these techniques reduces the processing time from field to laboratory and shows enormous advantages by avoiding root and soil sampling.     

Precipitation forecasting by large-scale climate indices and machine learning techniques

Global warming is one of the most complicated challenges of our time causing considerable tension on our societies and on the environment. The impacts of global warming are felt unprecedentedly in a wide variety of ways from shifting weather patterns that threatens food production, to rising sea levels that deteriorates the risk of catastrophic flooding. Among all aspects related to global warming, there is a growing concern on water resource management. This field is targeted at preventing future water crisis threatening human beings. The very first stage in such management is to recognize the prospective climate parameters influencing the future water resource conditions. Numerous prediction models, methods and tools, in this case, have been developed and applied so far. In line with trend, the current study intends to compare three optimization algorithms on the platform of a multilayer perceptron (MLP) network to explore any meaningful connection between large-scale climate indices (LSCIs) and precipitation in the capital of Iran, a country which is located in an arid and semi-arid region and suffers from severe water scarcity caused by mismanagement over years and intensified by global warming. This situation has propelled a great deal of population to immigrate towards more developed cities within the country especially towards Tehran. Therefore, the current and future environmental conditions of this city especially its water supply conditions are of great importance. To tackle this complication an outlook for the future precipitation should be provided and appropriate forecasting trajectories compatible with this region's characteristics should be developed. To this end, the present study investigates three training methods namely backpropagation (BP), genetic algorithms (GAs), and particle swarm optimization (PSO) algorithms on a MLP platform. Two frameworks distinguished by their input compositions are denoted in this study: Concurrent Model Framework (CMF) and Integrated Model Framework (IMF). Through these two frameworks, 13 cases are generated: 12 cases within CMF, each of which contains all selected LSCIs in the same lead-times, and one case within IMF that is constituted from the combination of the most correlated LSCIs with Tehran precipitation in each lead-time. Following the evaluation of all model performances through related statistical tests, Taylor diagram is implemented to make comparison among the final selected models in all three optimization algorithms, the best of which is found to be MLP-PSO in IMF.     

自动车床工序调整卡的计算机辅助设计

“经验式”和“创成式”是计算机辅助工艺过程设计的两种基本的技术方法.后一种技术方法虽然还不够成熟,但它在CAPP系统的设计与实现上具有很多的优势.描述了计算机辅助设计在自动车床加工中的一些应用,它涉及到工艺方案的制定和加工工序的安排.另外,它描述了一些特有的计算机算法和编程原理.     

基于MFO-LSTM的母猪发情行为识别

及时准确识别母猪的发情行为可以有效增加受胎率和产仔量,对提高养殖企业的繁育水平和经济效益具有重要意义。该研究针对生猪养殖过程中母猪发情行为识别存在主观性强、智能化水平低、假警报和错误率高、识别不及时等问题,提出了一种基于飞蛾扑火算法(Moth-Flame Optimization,MFO)优化长短时记忆网络(Long Short Term Memory,LSTM)的母猪发情行为识别方法。利用安装在母猪颈部的姿态传感器获得母猪姿态数据,然后使用姿态数据训练MFO-LSTM姿态分类模型,将母猪姿态分为立姿、卧姿和爬跨3类。通过对姿态分类结果进行分析,确定以爬跨行为和活动量2个特征作为发情行为识别依据,使用MFO-LSTM分类算法判断母猪是否发情。以山西省太原市杏花岭区五丰养殖场的试验数据对该方法进行验证,结果表明,该方法在以30 min为发情行为识别时间时的识别效果最好,发情行为识别的错误率为13.43%,召回率为90.63%,特效性为81.63%,与已有的母猪发情行为识别方法相比错误率降低了80%以上。该方法在保证识别准确率的情况下有效降低了错误率,可满足母猪养殖生产过程中发情行为自动识别要求。     

格网化小麦生长模拟预测系统设计与实现

利用作物生长模型模拟小麦区域生产力,分析气候变化对农业生产的影响是研究粮食安全的热点问题之一。拥有操作方便、计算快速特点的小麦区域生产力模拟系统,可有效提高作物生长模型区域应用能力。该研究在分解小麦生长模型WheatGrow算法基础上,利用Python语言构建了格网化小麦生长模型,实现了基于空间格网数据的小麦区域生产力模拟。验证试验结果表明:模拟产量的均方根误差为1 070 kg/hm~2,标准均方根误差小于20%,系统所集成的WheatGrow模型具有较好的预测性;同时,结合格网数据分块构建区域模拟的并行计算策略,优化了区域模拟的性能。在此基础上,采用GIS组件式开发模式,在.NET平台下开发格网化小麦生长模拟预测系统,实现作物生长模型与GIS耦合,为研究区域小麦产量潜力,评估气候变化对小麦生长影响,制定农业决策提供软件工具。     

基于改进BP神网络的离心泵性能预测

采用改进神经网络(贝叶斯正则化算法)对IB型单级离心泵水力模型的性能进行了预测,通过工程实践中得到的100组离心泵最优几何尺寸来训练网络,并用训练好的网络对需生产的水泵进行工况预测。结果显示,用改进神经网络来预测单级离心泵的性能,预测误差不超过6%。     

Determining crop-water production functions using yield–irrigation gradient algorithms

Crop-water production functions (CWPFs) are a useful tool for irrigation planning, but derivation of CWPFs by field experimentation is expensive, and traditional analytical techniques are not well suited to derivation of CWPFs. Physiologically based crop models provide a useful tool for simulation of agricultural experiments, but they have not been extensively applied to the task of CWPF determination. A new algorithm type based upon differential crop yield response to irrigation (“yield–irrigation gradients” [YIG]) is presented that uses these crop models to determine planning-level irrigation schedules and CWPFs. Three specific algorithms are developed within this type, varying in complexity, performance, and computational costs. Performance of the YIG methods is compared against a standard reference evapotranspiration method. In particular, the randomized iterative YIG (RIYIG) algorithm provides near-optimal results but at the highest computational costs of all the methods specified. All of the techniques presented have general applicability and are not limited to any one crop or location.     

Combining deliberative and computer-based methods for multi-objective land-use planning

This paper reports the outcomes of a deliberative workshop comparing land-use plans proposed by land-manager or domain experts with those derived using a computer-based decision support system (DSS). The DSS integrates four main components, a geographic information system, land-use systems simulation models, impact assessments and land-use planning tools. The land-use planning tools draw on the other components to generate and evaluate alternative patterns of land use and management. Since the land-use planning tools are based on multi-objective genetic algorithms (mGAs) it is possible to generate a range of alternative plans that define the structure of the trade-off between the objectives. The workshop tasked the delegates with specifying land-use plans that achieved the best compromise between two objectives known to be non-commensurable and conflicting. The nature of the best compromise was dependent on their individual perspectives. The delegates proposed allocations both as individuals and in researcher-facilitated sub-groups. The mGA allocations were then compared with those derived by delegates and were found to be broadly similar in performance. Differences in the range of allocations considered feasible were explained by the hard and soft constraints on allocations agreed between the delegates and articulated within the workshop process. The hypothesis that part of the difference in performance between the mGA and delegate allocations was due to the delegates blocking together fields with the same land use for convenience of management was proved. The analysis of the group allocations revealed that the decision-making process had failed to improve on the individual allocations. From these results it was concluded that there was a potential role for mGA based land-use planning tools in researching into, and deliberating on, the possible impacts of policy or other factors affecting land-use systems. It was further concluded that the tools should not be used in isolation since there was the need for stake-holder inputs to adequately define the range of feasible and practical land-use plans.     

基于二分法的微灌毛管水力设计

根据微灌毛管水力学特性,采用二分法搜索原理,并与逆递推法相结合,提出微灌毛管水力解析与设计方法。利用计算机编程从毛管末端向毛管进口逆序递推,可以快速、方便地求解出毛管各个孔口的压力和流量,设计毛管运行的水力参数,校核平均流量、流量偏差率等设计控制指标。实例验证结果表明,该设计方法具有直观、简便和快捷的特点,易为非专业人员理解与应用,具有较高的求解效率和计算精度。     

基于机器视觉的蒜头最大横切面直径分级方法

针对中国蒜头分选率和分选精度较低而影响其商品价值等现状,设计了一套基于机器视觉技术的大蒜蒜头分选系统,以蒜头最大横切面直径作为分级标准,利用VC6.0编程实现上述分级模型的算法。试验选择3 2 0个金乡蒜头样本对其进行测试,该装置对蒜头总体筛选精度达到9 0.9 3 7 5%。试验结果表明:利用机器视觉技术可以对大蒜蒜头进行分级。