关键词： day-ahead forecasting   extreme learning machines (ELMs)   feature selection   machine learning   support vector regression (SVR)   wind power market  

摘要： In liberalized markets, there usually exists a day-ahead session where energy is sold and acquired for the following production day. Owing to the high uncertainty of its production, renewable energy (wind in particular) can significantly influence the network imbalance of the following day. In this work, we consider the problem of predicting the sum of the bid volumes for wind energy of all the producers inside the day-ahead energy market. This is a valuable tool to be used by an energy provider in order to determine the imbalance of a market zone and, thus, properly size its bids. In particular, we focus on the estimation of the possible relationship between the meteorological forecasts and the wind power offered on the market by the companies for a market zone. We propose a machine learning model which is used to compute a 1-day-ahead forecast. The input-output mapping is obtained by support vector regression. The input feature vector is defined by a suitable feature extraction technique since the meteorological forecasts are given on a lattice of thousands of geographical points. The computational experiments are performed considering the Italian market as a case study (years 2012-2016). The results show that the proposed feature extraction technique, selecting only some geographical zones, manages to reduce the error attained using all the features. Moreover, classical statistical methods are shown to be outperformed by machine learning models. The analysis reveals also some weaknesses of the model, which may be due to other nonmeteorological factors at play.

关键词： Viruses  

摘要： Medicinal Wants are reported to possess antiviral activity, but finding the substances that are responsible for antiviral activity in the complex mixture of the plant extract is an extremely difficult task. In this paper a methodology related to the determination of the antiviral properties of medicinal plant extracts and based on phytochemical analysis, antiviral tests and machine [earning methods is described. 16 potentially antiviral medicinal Wants were selected, and their chemometric characteristics and antiviral properties were investigated. Three different analytical methods were used for chemical analysis: (i) spectrophotometry, (ii) capillary electrophoresis with contactess conductivity detection, and (iii) gas chromatography-mass spectrometry. 14 attributes were obtained describing the composition of the plant extracts. Viral growth inhibition properties were investigated and 8 candidate plant extracts were selected as being active against viruses. Infectious bronchitis virus was used as a mode[virus. Machine [earning techniques including deep neural network classification, classification and regression tree induction and hierarchical clusterization were used for mining the factors that are responsible for antiviral effects. It was determined that (i) phenolic compounds providing high radical scavenging activity and fractions containing high content of phenolic compounds are positively related to antiviral activity in plant extracts, (ii) hydrophilic compounds that are positively charged (pK(a) > 4.7) in acidic media and possess medium and Low electrophoretic mobility properties are negatively related to antiviral activity in medicinal Wants, (iii) phenolic acids with pK(a) Lower than 4.7 are not related to antiviral activity in the extracts, and (iv) volatile compounds in the extracts, including diversity, quantity and different volatility properties, do not affect the antiviral activity of plant extracts. Following the proposed methodological approach, i

关键词： Dengue   Modeling techniques   Weather   Relative humidity   Climate   Metropolitan Manila  

摘要： Background: Several studies have applied ecological factors such as meteorological variables to develop models and accurately predict the temporal pattern of dengue incidence or occurrence. With the vast amount of studies that investigated this premise, the modeling approaches differ from each study and only use a single statistical technique. It raises the question of whether which technique would be robust and reliable. Hence, our study aims to compare the predictive accuracy of the temporal pattern of Dengue incidence in Metropolitan Manila as influenced by meteorological factors from four modeling techniques, (a) General Additive Modeling, (b) Seasonal Autoregressive Integrated Moving Average with exogenous variables (c) Random Forest and (d) Gradient Boosting. Methods: Dengue incidence and meteorological data (flood, precipitation, temperature, southern oscillation index, relative humidity, wind speed and direction) of Metropolitan Manila from January 1, 2009 - December 31, 2013 were obtained from respective government agencies. Two types of datasets were used in the analysis;observed meteorological factors (MF) and its corresponding delayed or lagged effect (LG). After which, these datasets were subjected to the four modeling techniques. The predictive accuracy and variable importance of each modeling technique were calculated and evaluated. Results: Among the statistical modeling techniques, Random Forest showed the best predictive accuracy. Moreover, the delayed or lag effects of the meteorological variables was shown to be the best dataset to use for such purpose. Thus, the model of Random Forest with delayed meteorological effects (RF-LG) was deemed the best among all assessed models. Relative humidity was shown to be the top-most important meteorological factor in the best model. Conclusion: The study exhibited that there are indeed different predictive outcomes generated from each statistical modeling technique and it further revealed that the Random for

摘要： All models of evolution of human behaviour depend on the correct identification and interpretation of bone surface modifications (BSM) on archaeofaunal assemblages. Crucial evolutionary features, such as the origin of stone tool use, meat-eating, food-sharing, cooperation and sociality can only be addressed through confident identification and interpretation of BSM, and more specifically, cut marks. Recently, it has been argued that linear marks with the same properties as cut marks can be created by crocodiles, thereby questioning whether secure cut mark identifications can be made in the Early Pleistocene fossil record. Powerful classification methods based on multivariate statistics and machine learning (ML) algorithms have previously successfully discriminated cut marks from most other potentially confounding BSM. However, crocodile-made marks were marginal to or played no role in these comparative analyses. Here, for the first time, we apply state-of-the-art ML methods on crocodile linear BSM and experimental butchery cut marks, showing that the combination of multivariate taphonomy and ML methods provides accurate identification of BSM, including cut and crocodile bite marks. This enables empirically-supported hominin behavioural modelling, provided that these methods are applied to fossil assemblages.

关键词： 蛋白质组学   定位预测   亚线粒体   预测算法   线粒体蛋白质   机器学习方法   生命科学   位置信息  

摘要： 蛋白质亚线粒体定位预测是生命科学领域中蛋白质组学研究的重要内容，也是当前研究的热点，获得蛋白质的亚线粒体定位位置信息对进一步了解线粒体蛋白质的功能是非常必要的，急需更优秀的预测方法结合其他机器学习方法的基础上，提出更加合理的蛋白质亚线粒体定位理论预测算法。

关键词： 周期蛋白依赖性激酶4   机器学习方法   抑制剂   随机森林  

摘要： 最近的研究已经证实,以周期蛋白依赖性激酶4(cyclin-dependent kinase 4,CDK4)为靶点,通过CDK4的抑制剂重新建立细胞周期的调控在肿瘤靶向治疗的发展中已经成为有吸引力的方向。本文测试了三种机器学习方法,k最近邻、C4.5决策树和随机森林(random forest,RF),用于预测CDK4的抑制剂。所建这些模型都达到了令人满意的预测效果。其中,RF模型当参数Mtry=13、jbt=255时对应的总预测精度最大,为96.65%。同时,与CDK4抑制剂最相关的25个分子描述符也被最优的RF模型挑选了出来。本文的研究表明,机器学习方法特别是RF方法,对于发现潜在的CDK4抑制剂十分有效。

关键词： 机器学习   预测   臭氧浓度  

摘要： 臭氧(O_3)浓度变化与天然源、移动源和点源的排放量存在某些隐含的关联。根据臭氧浓度变化的特性,基于污染源在线排放数据、气象监测数据以及空气质量监测数据构造特征,运用机器学习方法进行逐小时臭氧浓度预测。该方法不仅充分利用了臭氧浓度变化时序数据,而且考虑了气象条件变化对污染物浓度变化的影响,最重要的是将点源排放氮氧化物这一臭氧生成的重要前体物纳入模型考虑。在金砖国家领导人厦门会晤前后(2017年8月31日至9月9日),运用该方法对厦门市溪东、洪文、鼓浪屿和湖里中学四个大气自动监测站的臭氧小时浓度平均值进行滚动预报,比较准确地模拟出臭氧浓度的日周期性变化,同时对峰值和低谷能够进行较为有效的捕捉和刻画。按照《环境空气质量标准》(GB3095—2012)臭氧日最大八小时浓度平均值进行评价,四个站点均取得了90%的预报等级准确率。

关键词： 神经网络   支持向量机   XGBoost   高频数据  

摘要： 机器学习在人工智能领域取得了巨大的成就,在学界和业界都掀起了机器学习的热潮.针对股指期货交易速度快、交易频率高和交易量巨大且交易数据具有高纬、时序的特征,构建了新的股指期货量化投资模型,采用沪深300股指期货1分钟高频数据作为研究对象.并对比分析了神经网络、支持向量机和XGBoost对股指期货下1分钟价格的变动方向的预测能力.研究结果表明,三种机器学习方法都具有较好的预测能力,但XGBoost的预测能力要优于传统的神经网络和支持向量机.

关键词： Predictive modeling   Spatial modeling   Time series   Tree-based methods   Uncertainty quantification   Urban water use  

摘要： Forecasts of water use are crucial to efficiently manage water utilities to meet growing demand in urban areas. Improved household-level forecasts may be useful to water managers in order to accurately identify, and potentially target for management and conservation, low-efficiency homes and relative high-demand customers. Advanced machine learning (ML) techniques are available for feature-based predictions, but many of these methods ignore multiscale spatiotemporal associations that may improve prediction accuracy. We use a large dataset collected by Tampa Bay Water, a regional water wholesaler in southwest Florida, to evaluate an array of spatiotemporal statistical models and ML algorithms using out-of-sample prediction accuracy and uncertainty quantification to find the best tools for forecasting household-level monthly water demand. Time series models appear to provide the best short-term forecasts, indicating that the temporal dynamics of water use are more important for prediction than any exogenous features. (c) 2018 Elsevier Ltd. All rights reserved.

关键词： Data Mining   Machine Learning   Microvascular Complications   Risk Predictions   Type 2 Diabetes  

摘要： One of the areas where Artificial Intelligence is having more impact is machine learning, which develops algorithms able to learn patterns and decision rules from data. Machine learning algorithms have been embedded into data mining pipelines, which can combine them with classical statistical strategies, to extract knowledge from data. Within the EU-funded MOSAIC project, a data mining pipeline has been used to derive a set of predictive models of type 2 diabetes mellitus (T2DM) complications based on electronic health record data of nearly one thousand patients. Such pipeline comprises clinical center profiling, predictive model targeting, predictive model construction and model validation. After having dealt with missing data by means of random forest (RF) and having applied suitable strategies to handle class imbalance, we have used Logistic Regression with stepwise feature selection to predict the onset of retinopathy, neuropathy, or nephropathy, at different time scenarios, at 3, 5, and 7 years from the first visit at the Hospital Center for Diabetes (not from the diagnosis). Considered variables are gender, age, time from diagnosis, body mass index (BMI), glycated hemoglobin (HbA1c), hypertension, and smoking habit. Final models, tailored in accordance with the complications, provided an accuracy up to 0.838. Different variables were selected for each complication and time scenario, leading to specialized models easy to translate to the clinical practice. © 2017, © 2017 Diabetes Technology Society.