关键词： Himawari-8 AOD   PM2   5 concentration   Machine learning method   Model combination  

摘要： The estimation of the PM2.5 concentration based on satellite remote sensing is currently a hot topic for research, with machine learning algorithms starting to be applied to the estimation model. However, there are few comparisons between different machine learning algorithms, and few scholars objectively evaluate the estimation performance of machine learning algorithms under different weather conditions. In this study, PM2.5 concentration was estimated by six commonly used machine learning algorithms, and their performances were compared in four different weather conditions in the Beijing-Tianjin-Hebei (BTH) region. The results showed that decision tree and random forest consistently performed well in different weather conditions, while SVM performed poorly. When the PM2.5 concentration was greater than 150 mu g/m(3), the R and RMSE values for decision tree were 0.854 and 31.53 mu g/m(3), respectively, while the evaluation coefficient of SVM algorithm was only 0.597 and 49.31 mu g/m(3), it was worth noting that all algorithms performed better in this interval than in others. This study also focused on the development of an optimal combination algorithm to estimate PM2.5 concentration under different weather conditions and got a good application effect. The results of this research may provide a theoretical basis and an important reference for the application of machine learning algorithms in the field of remote sensing.

关键词： Machine learning   MBA admission selection   Non-native language   Performance prediction  

摘要： Although the research on student selection criteria has been very rich up to now, the role of the level of foreign language played in the admission selection of a non-native spoken program is still receiving little attention. This study intends to explore the issue through three research methods: (1) two-sample test of a hypothesis;(2) multiple linear regression analysis;(3) machine learning algorithms (Ridge regression, SVM, Random forest, GBDT). The case about 549 students enrolled in the Shanghai International MBA Program in China from 2007 to 2014 was used as empirical research samples. Through three methods of analysis and comparison, it was found that Oral English fluency played a key role in the admission selection of the English spoken MBA program in China. It is confirmed that the criteria, such as Rank of the graduated university, Company Nature, Latest Highest Degree, Math Exam, Sponsor (Tuition provider) and Stress management, have very good effect in predicting the final grades of students when graduation. This study also shows that the methods based on machine learning algorithm modeling such as ridge regression and SVM are suitable for student selection decision modeling.

关键词： Radiation Oncology   DICOM   Machine Learning   Class imbalance   Random Forest   TG-263  

摘要： Purpose: To present a Machine Learning pipeline for automatically relabeling anatomical structure sets in the Digital Imaging and Communications in Medicine (DICOM) format to a standard nomenclature that will enable data abstraction for research and quality improvement. Methods: DICOM structure sets from approximately 1200 lung and prostate cancer patients across 40 treatment centers were used to build predictive models to automate the relabeling of clinically specified structure labels to standardized labels as defined by the American Association of Physics in Medicine's (AAPM) Task Group 263 (TG-263). Volumetric bitmaps were created based on the delineated volumes and were combined with associated bony anatomy data to build feature vectors. Feature reduction was performed with singular value decomposition and the resulting vectors were used for predicting the label of each structure using five different classifier algorithms on the Apache Spark platform with 5-fold cross-validation. Undersampling methods were used to deal with underlying class imbalance that hindered the performance of classifiers. Experiments were performed on both a curated version of the data, which included only annotated structures, and the non-curated data that included all structures from the original treatment plans. Results: Random Forest provided the highest accuracies with F, scores of 98.77 for lung and 95.06 for prostate on the curated data sets. Scores were lower with 95.67 for lung and 90.22 for prostate on the non-curated data sets, highlighting some of the challenges of classifying real clinical data. Including bony anatomy data and pooling information from all structures for the same patient both increased accuracies. In some cases, undersampling with k-Means clustering for class balancing improved classifier accuracy but in all experiments it significantly reduced run time compared to random undersampling. Conclusion: This work shows that structure sets can be relabeled using ou

关键词： Carbonate reservoirs   Shear wave velocity prediction   Petrophysical model   Wireline logs   LSTM  

摘要： Shear wave velocity (S-wave velocity or Vs) is one of the most critical issues for carbonate reservoirs characterization, because of its complexity of rock compositions and pore structures. The Xu-Payne petrophysical model is a commonly used method to predict S-wave velocity. However, the model excessively depends on the interpretation accuracy of rock compositions, pore structures, fluid properties and fluid saturation, which makes the prediction result potentially uncertain. With the development of intelligent algorithms, a machine learning method (Long-short Term Memory Neural Network, LSTM) is proposed to improve the traditional petrophysical workflow. With the capabilities of deep learning and data mining, the LSTM model can deeply mine the rich information in the wireline logs and then establish the relationships between S-wave velocity and wireline logs. In order to illustrate the prediction effect, the carbonate reservoir in the Majiagou Formation Member 5(Ma 5 Member) which belongs to the Ordovician system in the D area of Sulige gas field is taken as an example. Six kinds of sensitive wireline logs, including compensated acoustic log (AC), natural gamma ray log(GR), photoelectric absorption cross-section log (PE), density log (DEN), deep lateral resistivity log(RLLD), neutron log(CNL), are selected as the input data of the LSTM model. The results reveal that the accuracy of LSTM method is up to 98.9%, whereas the Xu-Payne model is only 73%. With the predicted result of all wells in the areas using LSTM, the sensitive elastic properties, including P-and S-wave velocity, P- and S-wave impendences, ratio of P- and S-wave velocity, Poisson's ratio, lame coefficient and fluid sensitivity factor, are also concluded. Compared with the Xu-Payne model, the newly proposed workflow is proved to be convenient and suitable for the prediction of S-wave velocity in carbonate reservoirs.

关键词： Sustainable smart cities   Security   Traffic   Classification   Data marling   Machine learning   A survey  

摘要： This survey paper describes the significant literature survey of Sustainable Smart Cities (SSC), Machine Learning (ML), Data Mining (DM), datasets, feature extraction and selection for network traffic classification. Considering relevance and most cited methods and datasets of features were identified, read and summarized. As data and data features are essential in Internet traffic classification using machine learning techniques, some well-known and most used datasets with details statistical features are described. Different classification techniques for SSC network traffic classification are presented with more information. The complexity of data set, features extraction and machine learning methods are addressed. In the end, challenges and recommendations for SSC network traffic classification with the dataset of features are presented.

关键词： machine learning   remote sensing   forest stand characteristics   Bayesian additive regression tree  

摘要： The estimation and mapping of forest stand characteristics are vital because this information is necessary for sustainable forest management. The present study considers the use of a Bayesian additive regression trees (BART) algorithm as a non-parametric classifier using Sentinel-2A data and topographic variables to estimate the forest stand characteristics, namely the basal area (m(2)/ha), stem volume (m(3)/ha), and stem density (number/ha). These results were compared with those of three other popular machine learning (ML) algorithms, such as generalised linear model (GLM), K-nearest neighbours (KNN), and support vector machine (SVM). A feature selection was done on 28 variables including the multi-spectral bands on Sentinel-2 satellite, related vegetation indices, and ancillary data (elevation, slope, and topographic solar-radiation index derived from digital elevation model (DEM)) and then the most insignificant variables were removed from the datasets by recursive feature elimination (RFE). The study area was a mountainous forest with high biodiversity and an elevation gradient from 26 to 1636 m. An inventory dataset of 1200 sample plots was provided for training and testing the algorithms, and the predictors were fed into the ML models to compute and predict the forest stand characteristics. The accuracies and certainties of the ML models were assessed by their root mean square error (RMSE), mean absolute error (MAE), and R-squared (R-2) values. The results demonstrated that BART generated the best basal area and stem volume predictions, followed by GLM, SVM, and KNN. The best RMSE values for both basal area (8.12 m(2)/ha) and stem volume (29.28 m(3)/ha) estimation were obtained by BART. Thus, the ability of the BART model for forestry application was established. On the other hand, KNN exhibited the highest RMSE values for all stand variable predictions, thereby exhibiting the least accuracy for this specific application. Moreover, the effectiveness of the na

关键词： Database systems  

摘要： Superhard materials are of great interest in various practical applications, and an increasing number of research efforts are focused on their development. In this article, we demonstrate that machine learning can be successfully applied to searching for such materials. We construct a machine learning model using neural networks on graphs together with a recently developed physical model of hardness and fracture toughness. The model is trained using available elastic data from the Materials Project database and has good accuracy for predictions. We use this model to screen all crystal structures in the database and systematize all the promising hard or superhard materials, and find that diamond (and its polytypes) are the hardest materials in the database. Our results can be further used for the investigation of interesting materials using more accurate ab initio calculations and/or experiments.

关键词： Hyperspectral image   Near infrared   Cannabis sativa Linnaeu   Sparse-Principal Component Analysis   Soft Independent Class Analogy model  

摘要： Remote identification of illegal plantations of Cannabis sativa Linnaeus is an important task for the Brazilian Federal Police. The current analytical methodology is expensive and strongly dependent on the expertise of the forensic investigator. A faster and cheaper methodology based on automatic methods can be useful for the detection and identification of Cannabis sativa L. in a reliable and objective manner. In this work, the high potential of Near Infrared Hyperspectral Imaging (HSI-NIR) combined with machine learning is demonstrated for supervised detection and classification of Cannabis sativa L. This plant, together with other plants commonly found in the surroundings of illegal plantations and soil, were directly collected from an illegal plantation. Due to the high correlation of the NIR spectra, sparse Principal Component Analysis (sPCA) was implemented to select the most important wavelengths for identifying Cannabis sativa L. One class Soft Independent Class Analogy model (SIMCA) was built, considering just the spectral variables selected by sPCA. Sensitivity and specificity values of 89.45% and 97.60% were, respectively, obtained for an external validation set subjected to the s-SIMCA. The results proved the reliability of a methodology based on NIR hyperspectral cameras to detect and identify Cannabis sativa L., with only four spectral bands, showing the potential of this methodology to be implemented in low-cost airborne devices. (C) 2020 Elsevier B.V. All rights reserved.

关键词： Agricultural systems   Change monitoring   Phenological metrics   NDVI time series   Machine learning   MODIS  

摘要： This study aims to provide accurate information about changes in agricultural systems (AS) using phenological metrics derived from the NDVI time series. Use of such information could help land managers optimize land use choices and monitor the status of agricultural lands, under a variety of environmental and socioeconomic conditions. For this purpose, the Moderate Resolution Imaging Spectroradiometer (MODIS) NDVI data were used to derive phenological metrics over the Oum Er-Rbia basin (central Morocco). Random forest (RF), support vector machine (SVM), and K-nearest neighbor (KNN) classifiers were explored and compared on their ability to classify AS classes over the study area. Four main AS classes have been considered: (1) irrigated annual crop (IAC), (2) irrigated perennial crop (IPC), (3) rainfed area (RA), and (4) fallow (FA). By comparing the accuracy of the three classifiers, the RF method showed the best performance with an overall accuracy of 0.97 and kappa coefficient of 0.96. The RF method was then chosen to examine time variations in AS over a 16-year period (2000-2016). The AS main variations were detected and evaluated for the four AS classes. These variations have been found to be linked well with other indicators of local agricultural land management, as well as the historical agricultural drought changes over the study area. Overall, the results present a tool for decision makers to improve agricultural management and provide a different perspective in understanding the spatiotemporal dynamics of agricultural systems.

关键词： Green ports   Energy consumption prediction of ships   Energy consumption reduction strategy   Machine learning  

摘要： Two main contributions of this paper are 1) the energy consumption of ships (ECS) in port is predicted, 2) reduction strategies for energy consumption of ships in port are discussed by the proposed prediction models considering green port. Firstly, 15 characteristics which have impact on the energy consumption of ships are collected by Jingtang Port in China and analysis is conducted. Then, five machine learning models including Gradient Boosting Regression (GBR), Random Forest Regression (RF), BP Network (BP), Liner Regression (LR) and K-Nearest Neighbor Regression (KNN) are developed and 15 features consisting of inherent property of ship and external features of ports are set as inputs. After then, k-folds cross validation is adopted to verify the effectiveness of models. Finally, the feature importance is calculated and the most important features are selected. Besides, experiments are conducted to find the effect of changing several features on energy consumption of ships, and two consumption reduction strategies are discussed. The results show that net tonnage, deadweight tonnage, actual weight and efficiency of facilities are the top 4 features for predicting the energy consumption of ships. In conclusion, when efficiency of facilities is doubled, the energy consumption of ships is reduced by 34.17% at berth and 8.41% in port. The finding of proposed methods and discussed strategies can give references to green port construction. (C) 2020 Elsevier Ltd. All rights reserved.