关键词： 农业   大数据   分类   遗传算法   极限学习机  

摘要： 论文在分析的极限学习机和遗传算法的基础上,提出通过遗传算法选择最优染色体,获得优化的极限学习机输入权值和阈值,提高网络稳定性,降低数据分类误差的方法。算法测试结果表明,基于遗传算法的极限学习机对于特征点较多的农业类数据的分类性能有较大提高。

关键词： Logistic回归模型   机器学习   员工流失  

摘要： 通过建立Logistic回归模型和机器学习模型对IBM员工的基本特征进行分析。基于员工的年龄、部门、受教育程度等特征值,处理相关数据,设置虚拟变量,进一步构建Logistic回归模型及机器学习模型,实证分析各类特征值对员工流失率是否有显著影响,并找出最优拟合及预测效果。同时,从这些相关因素出发,针对不同属性的员工提出相应的解决方法,降低员工的流失率。最后,对不同方法的模型进行比较,为模型的可靠性提供参考标准。

关键词： 耦合   陆面水文模型   机器学习   径流量预报   物理模型   人工智能  

摘要： 采用智能网格预报等多种气象预报数据与陆面水文模型及机器学习方法进行耦合,以岩滩水库流域区间为例,将区间预报径流量与历史径流量数据输入长短期记忆网络模型(LSTM)进行水库入库径流量预报,通过对日径流量模拟试验和业务试用分析,探明该方法在短期水文预报中的适用性。结果表明,耦合气象-水文-机器学习的径流量预报模型在率定期和验证期纳什效率系数(NSE)在0.65左右,在强降水过程训练试验中,日径流量和洪峰预报合格率≥87.5%,达到甲级预报精度标准;在业务试用中,24h、48h、72h日径流量预报合格率分别为87.3%、70.4%、75.5%,达到甲级或乙级预报精度标准,满足发布正式预报的精度要求;3次较大降水过程径流量和峰现时间预报合格率均为100%,达到甲级预报精度标准;峰值预报为66.7%,达到丙级预报标准,可用于参考性预报。将物理模型与人工智能方法进行有机耦合,可提高水文预报产品精度和适用性。

关键词： Smoothing algorithm   Machine learning   Support vector machine   Continuity   Parametric curve  

摘要： Computer-aided manufacturing (CAM) software outputs machining data by encoding a tool-path into a series of G-codes which are composed of various lengths of line segments. The discontinuities of these line segments may cause inefficiency for computer numerical control (CNC) system. To achieve high-speed continuous motions, corner smoothing algorithms based on look-ahead methods are widely used. However, it is difficult to meet smoothing trajectories in real-time requirements. Based on machine learning method, in this paper, a support vector machine (SVM) system is presented for directly outputting classification results of the various geometric continuities at the transition corners. The feature values used for generating continuity classification model are extracted from sampling paths of the previous publication work: the machining parameters, length, fairness criteria, the root mean square (RMS) contour errors, and dominant stage type of movement of each sampling path are calculated. The acceleration/deceleration (ACC/DEC) feedrate planning scheme is used to determine the feedrate at the transition corners. Simulations and experiments show that the proposed algorithm can realize accurately and efficiently continuity classification in real-time requirements under the conditions of machining accuracy.

关键词： zeolites   MFI   prediction of properties   machine learning methods   gradient boosting   big data analytics   degree of crystallinity  

摘要： Predicting the degree of crystallinity of zeolites from the initial synthesis parameters is an extremely difficult-to-solve problem. One of the ways to find the corresponding relationships is processing of data on the zeolite synthesis by machine learning algorithms. In this study, we analyzed 650 research papers and created a database including the parameters of the synthesis of MFI type zeolites and data on the degree of crystallinity of the material obtained. Finding relationships between the initial synthesis parameters and degree of crystallinity of the zeolite formed is a regression problem. In this study, it was solved by three machine learning algorithms: decision tree, random forest, and gradient boosting. To enhance the algorithm operation accuracy, we added to the initial dataset polynomial features of degrees 2-5. The gradient boosting algorithm based on data with third-degree polynomial features showed the highest accuracy in combination with the database processing rate. The mean absolute error (MAE) of the values given by the model relative to the real degrees of crystallinity was 10.3%.

关键词： constraints-based models   data generation   generative adversarial networks   generative models   inverse frequent itemset mining   synthetic dataset   variational autoencoder  

摘要： The development of platforms and techniques for emerging Big Data and Machine Learning applications requires the availability of real-life datasets. A possible solution is to synthesize datasets that reflect patterns of real ones using a two-step approach: first, a real dataset X is analyzed to derive relevant patterns Z and, then, to use such patterns for reconstructing a new dataset X ' that preserves the main characteristics of X. This survey explores two possible approaches: (1) Constraint-based generation and (2) probabilistic generative modeling. The former is devised using inverse mining (IFM) techniques, and consists of generating a dataset satisfying given support constraints on the itemsets of an input set, that are typically the frequent ones. By contrast, for the latter approach, recent developments in probabilistic generative modeling (PGM) are explored that model the generation as a sampling process from a parametric distribution, typically encoded as neural network. The two approaches are compared by providing an overview of their instantiations for the case of discrete data and discussing their pros and cons. This article is categorized under: Fundamental Concepts of Data and Knowledge > Big Data Mining Technologies > Machine Learning Algorithmic Development > Structure Discovery

关键词： wildfire prediction   next day prediction   machine learning   feature extraction   imbalance  

摘要： Next day wildfire prediction is an open research problem with significant environmental, social, and economic impact since it can produce methods and tools directly exploitable by fire services, assisting, thus, in the prevention of fire occurrences or the mitigation of their effects. It consists in accurately predicting which areas of a territory are at higher risk of fire occurrence each next day, exploiting solely information obtained up until the previous day. The task's requirements in spatial granularity and scale of predictions, as well as the extreme imbalance of the data distribution render it a rather demanding and difficult to accurately solve the problem. This is reflected in the current literature, where most existing works handle a simplified or limited version of the problem. Taking into account the above problem specificities, in this paper, we present a machine learning methodology that effectively (sensitivity > 90%, specificity > 65%) and efficiently performs next day fire prediction, in rather high spatial granularity and in the scale of a country. The key points of the proposed approach are summarized in: (a) the utilization of an extended set of fire driving factors (features), including topography-related, meteorology-related and Earth Observation (EO)-related features, as well as historical information of areas' proneness to fire occurrence;(b) the deployment of a set of state-of-the-art classification algorithms that are properly tuned/optimized on the setting;(c) two alternative cross-validation schemes along with custom validation measures that allow the optimal and sound training of classification models, as well as the selection of different models, in relation to the desired trade-off between sensitivity (ratio of correctly identified fire areas) and specificity (ratio of correctly identified non-fire areas). In parallel, we discuss pitfalls, intuitions, best practices, and directions for further investigation derived from our analysis

关键词： Downscaling   Gradient boosting decision trees   Southern Africa   Karst   Remote and satellite sensing  

摘要： A novel approach using machine learning algorithms is used to predict high-resolution groundwater-level changes, both current and in the future. The Southern African Development Community (SADC) is dependent on groundwater resources to meet freshwater demand but knowledge of groundwater resources in the region is hampered by the lack of available data, especially at a local scale. Improving the ability to generate near-real-time and high-resolution groundwater data is imperative to support effective groundwater management in the SADC. In this study, an autoregressive approach is applied to develop a set of generalized gradient-boosting decision tree models that can predict 30-day groundwater-level changes, both current and 1 month ahead. The approach integrates numerous readily available satellite-based, land-surface-model, and hydrogeological datasets to train, calibrate and test the gradient-boosting decision tree models. The models achieve a mean absolute error of 15.27 and 12.78 cm, for the groundwater-level-change predictions that are current and 1 month ahead, respectively. The models were used to predict monthly groundwater-level changes, both current and 1 month ahead, at a 10-km resolution, in the Ramotswa/North West/Gauteng dolomite aquifers of Southern Africa. When compared to observed in-situ groundwater-level changes, the mean absolute error for the current and 1-month-ahead groundwater-level changes were 21.23 and 22.26 cm, respectively. While the results are largely satisfactory, challenges associated with limited target data, and extreme values associated with groundwater abstraction, reduce model performance. Nonetheless, the approach demonstrates the applicability of machine learning to generate local groundwater information to improve groundwater management.

关键词： UAV multispectral image   machine learning   field scale   winter wheat   yield prediction   vegetation index  

摘要： Accurate prediction of food crop yield is of great significance for global food security and regional trade stability. Since remote sensing data collected from unmanned aerial vehicle (UAV) platforms have the features of flexibility and high resolution, these data can be used as samples to develop regional regression models for accurate prediction of crop yield at a field scale. The primary objective of this study was to construct regional prediction models for winter wheat yield based on multi-spectral UAV data and machine learning methods. Six machine learning methods including Gaussian process regression (GPR), support vector machine regression (SVR) and random forest regression (RFR) were used for the construction of the yield prediction models. Ten vegetation indices (VIs) extracted from canopy spectral images of winter wheat acquired from a multi-spectral UAV at five key growth stages in Xuzhou City, Jiangsu Province, China in 2021 were selected as the variables of the models. In addition, in situ measurements of wheat yield were obtained in a destructive sampling manner for prediction algorithm modeling and validation. Prediction results of single growth stages showed that the optimal model was GPR constructed from extremely strong correlated VIs (ESCVIs) at the filling stage (R-2 = 0.87, RMSE = 49.22 g/m(2), MAE = 42.74 g/m(2)). The results of multiple stages showed GPR achieved the highest accuracy (R-2 = 0.88, RMSE = 49.18 g/m(2), MAE = 42.57 g/m(2)) when the ESCVIs of the flowering and filling stages were used. Larger sampling plots were adopted to verify the accuracy of yield prediction;the results indicated that the GPR model has strong adaptability at different scales. These findings suggest that using machine learning methods and multi-spectral UAV data can accurately predict crop yield at the field scale and deliver a valuable application reference for farm-scale field crop management.

关键词： intelligent transportation systems   sound mitigation   noise maps   traffic measurements   machine learning   YOLO   vehicle detection   noise exposure   annoyance   G(den)  

摘要： Noise maps and action plans represent the main tools in the fight against citizens' exposure to noise, especially that produced by road traffic. The present and the future in smart traffic control is represented by Intelligent Transportation Systems (ITS), which however have not yet been sufficiently studied as possible noise-mitigation tools. However, ITS dedicated to traffic control rely on models and input data that are like those required for road traffic noise mapping. The present work developed an instrumentation based on low-cost cameras and a vehicle recognition and counting methodology using modern machine learning techniques, compliant with the requirements of the CNOSSOS-EU noise assessment model. The instrumentation and methodology could be integrated with existing ITS for traffic control in order to design an integrated method, which could also provide updated data over time for noise maps and action plans. The test was carried out as a follow up of the L.I.S.T. Port project, where an ITS was installed for road traffic management in the Italian port city of Piombino. The acoustic efficacy of the installation is evaluated by looking at the difference in the acoustic impact on the population before and after the ITS installation by means of the distribution of noise exposure, the evaluation of G(den) and G(night), and the calculation of the number of highly annoyed and sleep-disturbed citizens. Finally, it is shown how the ITS system represents a valid solution to be integrated with targeted and more specific sound mitigation, such as the laying of low-emission asphalts.