Search

Copyright of Fly Ash Comprehensive Utilization is the property of Hebei Fly Ash Comprehensive Utilization Magazine Co., Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Bulletin of Soil & Water Conservation is the property of Bulletin of Soil & Water Conservation Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

This study aims to understand and enhance the indicative significance of convective initiation (CI) products from Fengyun-4A (FY-4A) satellite for summer precipitation over the Qinghai-Tibet Plateau. Using the convective initiation (CI) products of FY-4A and precipitation data from the Global Precipitation Measurement Program (GPM), and based on the correspondence between the CI samples identified by the FY-4A CI product and the actual observed precipitation one hour after identifying the CI in the Qinghai-Tibet Plateau region from June to August 2022, three categories of the CI samples, including no precipitation CI, weak precipitation CI, and strong precipitation CI, were divided. Then a CI class recognition model was established and the model performance testing was conducted by combining atmospheric convective parameters and geographic location information, two machine learning methods, decision tree and random forest. The results show that there are significant regional differences in the precipitation situation within one hour after the occurrence of CI in the Qinghai Tibet Plateau region, with a higher proportion of no precipitation in the northwest region and a higher proportion of precipitation in the southeast region. By utilizing atmospheric convective parameters such as lift index, total cloud water, wind shear, middle and low level humidity, cloud bottom height, zero degree layer height and so on, it is possible to better distinguish whether there is precipitation and the strength of precipitation after the appearance of CI in the Qinghai Tibet Plateau. The random forests identify model have better performance for CI classification than decision tree, and the use of random forests identify model can more effectively classify summer CI on the Qinghai Tibet Plateau according to precipitation intensity.

Copyright of Journal of Food Safety & Quality is the property of Journal of Food Safety & Quality Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Irrigation & Drainage is the property of Journal of Irrigation & Drainage Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Arid Land Geography is the property of Chinese Academy of Sciences, Xinjiang Institute of Ecology & Geography and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Acta Agronomica Sinica is the property of Crop Science Society of China and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The traditional method of loading and unloading time prediction of freight transport, which directly utilizes the standard time specified in the Detailed Instructions Governing Train Operation at Station, cannot properly characterize the time change under the impacts of complex factors, and achieves low prediction accuracy. This paper utilizes the data mining method to gather the relevant data on the loading and unloading time of freight transport from the railway integrated dispatching information system. It also utilizes the boosted decision tree model Xgboost to predict the loading and unloading time of freight transport. Compared with the reference model, the proposed model can achieve substantial improvement in prediction accuracy, and provide more effective support for traffic flow prediction and automatic drawing of train operation charts. [ABSTRACT FROM AUTHOR]

Copyright of West China Journal of Stomatology is the property of Sichuan University, West China College of Stomatology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In order to solve the problem of the attitude estimation accuracy decline of the inertial sensor in the environment of magnetic field interference and large acceleration interference, a complementary filter attitude estimation method based on decision tree adaptive was proposed. Aiming at the zero-degree offset characteristic of the gyroscope, it performed zero-degree offset processing. The processed angular velocity data and acceleration data constituted a static detection unit, which realized accurate classification of static and dynamic situations. In the dynamic situation, the decision tree composed of acceleration data and magnetic field data can automatically adjust the system error gain by analyzing the degree of external interference, so as to achieved the purpose of anti-interference and effectively improve the accuracy of attitude estimation. The experimental results show that the attitude estimation is not affected by the magnetic field in the static state, and can effectively avoid the magnetic field interference and the large acceleration interference in the dynamic state. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Computer Engineering & Applications is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of East China University of Science & Technology is the property of Journal of East China University of Science & Technology Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Beijing University of Technology is the property of Journal of Beijing University of Technology, Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Computer Measurement & Control is the property of Magazine Agency of Computer Measurement & Control and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Objective To investigate the prevalence of depression in blood donors and analyze the related factors, so as to develop a rapid depression screening model for blood donors. Methods A total of 13 015 street whole blood donors in Guangzhou Blood Center during May to August, 2020 filled in an anonymous e-questionnaire, including social demography information and the Patient Health Questionnaire-9 before donation. The cut-off value for detecting depression was 10. Logistic regression by SPSS 26.0 was used to analyze depression related factors. 2-level decision tree with 30/10 as the minimum number of cases in parent/child node, 10-fold cross validation was used to cut items of PHQ-9 to form the depression screening model. Results 364 out of 13 015 (2.80%) street whole blood donors reported a score ≥ 10. Donors with 18-29 years old (P

The deep decision tree transfer learning Boosting method (DTrBoost) can only adapt to the training data of one source domain and one target domain, and can not adapt to the samples of several different distribution source domains. In addition, the DTrBoost method synchronously learns data from the source domain to the target domain model, and does not quantify the weight of the learned knowledge according to the degree of importance. In practice, the distribution of data divided according to one or some characteristics of a certain dataset is often inconsistent, the importance of these different distributions to the final model is also inconsistent, and the weight of knowledge transfer is therefore not equal. To solve this problem, a transfer learning method of multi-source domain weight optimization is proposed. The main idea is to calculate the KL divergence distance to the target domain according to the source domain space of different distributions, and calculate the learning weight proportion parameters of the source domain samples of different distributions by using the ratio of KL divergence, so as to optimize the overall gradient function and make the learning direction towards the direction of the fastest gradient decline. The gradient descent algorithm can make the model converge quickly, and ensure the learning speed as well as the transfer learning effect. Experimental results show that the algorithm proposed in this paper adaptively achieves better average performance on the whole. The average classification error rate on all the adopted datasets decreases by 0.013 and even 0.030 on OCR dataset.

Sonic boom suppression is a key technology that must be broken through in the development of a new generation of supersonic civil aircraft. The reasonable design of configuration parameters can make the aircraft have good sonic boom characteristics. In order to break through the bottleneck of evolutionary algorithm in optimizing large-scale design variables, a hierarchical optimization method based on data mining is proposed, and the decision tree (DT) algorithm based data mining is used to extract the design knowledge, obtain the hierarchical information of design variables, and guide the configuration optimization of low sonic boom aircraft. For a low boom supersonic aircraft, five configuration parameters, including sweep angle, aspect ratio, taper ratio, dihedral angle and fuselage slenderness ratio, are selected as design variables to carry out the numerical experiments of hierarchical optimization, and the method is performed with comparison verification with the integrated optimization method. The results show that the hierarchical optimization method can obtain the optimal solution consistent with the integrated optimization method, and the convergence speed of hierarchical optimization method is significantly faster than that of integrated optimization method, and the performance of different optimization processes is more robust.

With the rapid development of deep neural networks, the advantages of knowledge tracing models based on deep learning are gradually emerging. Deep-IRT combines item response theory with dynamic key-value memory networks (DKVMN), which increases the connection between students and exercises but ignores the influence of learning features. DKVMN-DT adds behavior feature preprocessing based on CART decision tree to DKVMN, but the decision tree is still a greedy algorithm. To optimize the local optimum problem caused by CART and strengthen the connection between student ability and exercise difficulty, a model combining CART based on genetic algorithm and Deep-IRT is proposed. Firstly, CART is optimized twice based on genetic algorithm, and the learning behavior characteristics of learners are preprocessed. Then, the cross characteristics are calculated and integrated into the underlying model of DKVMN. Finally, item response theory is introduced to predict the completion probability according to students' ability and exercise difficulty. The experimental results show that DKVMNGACART- IRT model has better AUC values than the original model, and have better prediction performance. [ABSTRACT FROM AUTHOR]

Due to the influence of many factors such as reservoir lithology and pore structure, it is difficult to identify oil and water layers with traditional complex fluid identification methods, and the identification efficiency is low. Based on the traditional identification methods such as map method, overlap method and logging method, the logging response characteristics can be integrated, and the basic geological data, logging data and oil-water relationship can be fully used to identify the fluid properties. However, the unstable properties and strong heterogeneity of tight sandstone reservoirs, coupled with the complex relationship between pore structure and oil and water, lead to low identification efficiency and strong subjectivity, which limits the identification effect. Taking the Chang 8 tight reservoir in Yanchi area as the research object, this paper proposes a method for fluid identification of tight reservoir based on decision tree. In this method, parameters such as porosity, permeability and oil saturation are calculated as the characteristic values of the decision tree through logging response characteristics and reservoir fluid characteristics of the study area, combined with logging data such as resistivity, sonic time difference, neutron and density, etc. Finally, the Gini index is calculated according to the principle of decision tree. The smaller the Gini index is, the higher the accuracy is, the decision tree model is established. The characteristics of reservoir flow are predicted. The test results show that the accuracy of the decision tree prediction results is 90%, which is basically consistent with the oil test results, which verifies the effectiveness and reliability of this method for tight reservoir prediction. [ABSTRACT FROM AUTHOR]

Copyright of Tunnel Construction / Suidao Jianshe (Zhong-Yingwen Ban) is the property of Tunnel Construction Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Journal of Jilin University (Science Edition) / Jilin Daxue Xuebao (Lixue Ban) is the property of Zhongguo Xue shu qi Kan (Guang Pan Ban) Dian zi Za zhi She and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Modern Food Science & Technology is the property of Editorial Office of Modern Food Science & Technology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

SMP Negeri 1 Soreang is one of the favorite public junior high schools in the Soreang area, Bandung Regency. To improve the quality of schools, it is done through the distribution of scholarships. Determination of scholarships is determined by using an assessment that has certain criteria. By utilizing classification techniques, one of which is the Decision Tree algorithm model, which is chosen to be able to assist in making decisions about who is eligible to get a scholarship so that it is right on target. Decision Tree Algorithm is a classification method to utilize data in order to find the relationship between the target variable and the input variable. The data contains student scores of 237 people. From the modeling process, the accuracy value is 92%. So it can be concluded that this algorithm can assist in providing selection decisions for junior high school (SMP) scholarship recipients. The Decision Tree algorithm was chosen because it has a high level of accuracy compared to other classification algorithms. In addition, the Decision Tree algorithm is used to make a decision from the information obtained. [ABSTRACT FROM AUTHOR]

As a critical part of desision tree (DT） growth, its nodes can be split to grow by either axis- or nonaxis-aligned way based on such splitting criteria as purity and misclassification error. However, these have nothing to do with the geometric structure of data, e. g. multicentric data or single-center data. In order to compensate for this, two splitting criteria are proposed by combining the between-class margin in the same inner node (BCM） and the between-node margin within the same class (BNM） respectively with the purity measure in weighting and the two-step method. Unlike traditional greedy growth of DT which only finds the current locally optimal splitting point, the proposed method first selects the top-k purity splitting nodes, then determines the optimal one by maximizing BCM and minimizing BNM. Since not only alleviating purity-based local optimality but also considering global structures of the data, our method greatly improves the division of descendant nodes and generalization of the formed trees, while enhancing the interpretability. In addition, two aforementioned splitting criteria can be combined to further boost the performance. The comparison results on 21 benchmark datasets show an improvement in predictive performance of new trees with reduction in complexity, while also are competitive with many other DTs using hybrid splitting criteria. [ABSTRACT FROM AUTHOR]

Copyright of Journal of Frontiers of Computer Science & Technology is the property of Beijing Journal of Computer Engineering & Applications Journal Co Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In view of the drastic changes in the ocean - atmosphere environment, the accurate and efficient identification of coral reef substrate information is essential for the dynamic monitoring of coral reefs. Based on the Landsat8 satellite data of the Yongle Atoll in the Xisha Islands of four periods during 2013-2021, this study proposed a decision tree classification model using spectral and texture indices according to the spectral and texture differences between different substrates. Then, the coral information was extracted using object-oriented and pixel-based classification methods. In addition, the changes in the substrate of the Yongle Atoll were quantitatively analyzed. The results are as follows: (1) The results of the object - oriented classification are superior to those of pixel - based classification overall. Moreover, the decision tree classification results yielded Kappa coefficients of 0.63 ?? 0.68, with classification accuracy about 7 ~ 10 percentage points higher than that of conventional supervised classification; (2) Coral thickets are mostly distributed in the central, weakly - hydrodynamic parts of islands and reefs. The corals in the Yinyu Reef and the Jinyin Island exhibit a planar distribution pattern, while those in other islands and reefs mostly show a zonal distribution pattern; (3) The areas of coral thickets and sandbanks in the Yongle Atoll changed significantly overall. Although the total area of coral thickets increased by 1.689 km², the coral thickets in the Shiyu, Jinqing, Quanfu, and Shanhu islands and the Lingyang reef were severely degraded, with areas decreasing by 0.107 ~ 0.892 km². This study verified that the substrate index established using medium spatial resolution images is reliable and can be applied to remote sensing information extraction of corals. Therefore, this study will provide technical support for the investigation and scientific management of coral reef resources. [ABSTRACT FROM AUTHOR]

Copyright of Ordnance Industry Automation is the property of Editorial Board for Ordnance Industry Automation and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of China Forest Products Industry is the property of China Forest Products Industry Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

[Objective] Understanding planting structure and crop growth in a region is important to assess its food supply and security. The objective of this paper is to investigate the feasibility of a decision-tree model derived from the Sentinel-2 remote sensing imagery to map cropping structure in fragmented irrigation regions. [Method] The study site was Alagou irrigation area in Xinjiang. The planting areas of major crops in 2021 were estimated using the Sentinel-2 remote sensing imagery. We then compared these with both field investigation and visual interpretation from the Google HD images. Critical growth stage for identifying each crop was determined based on the phenological information and the NDVI time series, from which we derived a decision tree classification model. Accuracy of the model was verified against ground-truth data. [Result] The planting structure mapped from the Sentinel-2 remote sensing imagery had sharp textures, meeting the requirements for agricultural water management. The decision tree classification model can accurately classify crops at the scale required for irrigation management. The model is simple and feasible. Compared with ground-truth data, its average accuracy is 81.56% and the Kappa coefficient is 0.716 6. [Conclusion] The Sentinel-2 remote sensing imagery and the decision tree classification method derived form it can be used to accurately identify planting structure in fragmented lands. They can provide support information for decision-making in water management, and improve agricultural water usage in irrigation districts. [ABSTRACT FROM AUTHOR]

Currently, network traffic scheduling strategy cannot be intelligent and on-demand, especially in the congestion caused by sudden network failures and escort scenarios of high-value services. They cannot guarantee latency-sensitive service experience on demand. The delay-sensitive attribute requirements of different network traffic were analyzed and studied, and the internal correlation between the behavior characteristics of varying network traffic and its delay sensitivity requirements was explored. Then, AI technology was used to learn this inherent relationship and construct its mapping relationship, realizing a traffic scheduling technical solution based on the intelligent awareness of delay-sensitive traffic. At the same time, considering the practical issues of interpretability and deploy-ability of AI models, reinforcement learning (RL) technology was used to prune and optimize the interpretable decision tree model, which improved the robustness of the model and made model lighter and easier to implement in equipment deployment. Through experiments by the collected real network traffic, the decision tree model optimized by reinforcement learning could improve the awareness accuracy by 1.75% in a single inference case, and the inference performance was improved by about 30%. The experiment also proved that using micro-statistical features for multiple inferences could help improve the model accuracy; in all experiments, the scale of the decision tree model optimized by RL was reduced by about 60.0%~87.2%, and the Saras had better optimization performance than Q-learning. [ABSTRACT FROM AUTHOR]

There are many landslide disasters in southern Jiangxi, with a wide area and a small scale, and are characterized by mass and suddenness. More than 90% of landslides are caused by artificial slope cutting. In order to study the applicability of the susceptibility evaluation model for cutting slope landslides caused by cutting slopes in southern Jiangxi, taking Yinkeng Town, Yudu County, Ganzhou City as an example, based on the results of field geological surveys, and using GeoDetectors, the slope, the slope structure, rock formation, fault, road, and vegetation, were selected to carry out landslide susceptibility assessment by using the information value model (I), artificial neural network model (ANN), decision tree model (DT) and Logic regression model respectively. The results show that the AUC values obtained from information value model, artificial neural network model, decision tree model and logistic regression model are 0.800, 0.708, 0.672 and 0.586, respectively. The susceptibility results obtained by the information value model are in good agreement with the actual distribution of landslides in the study area. The specific value of the proportion of landslides in high-prone areas and medium-prone areas exceeds 80%. The information model is more suitable for the landslide susceptibility assessment under cutting slope in southern Jiangxi than the other three models. The assessment results provide a reference for the selection of the assessment model for the geohazard susceptibility in this region.

Application programming interface(API) benefits to effectively improve software development efficiency by reusing existing software frameworks or libraries.However,many constraints must be satisfied to correctly use APIs,such as call order,exception handling.Violation of these constraints will cause API misuse,which may result in software crashes,errors,or vulnerabilities.Although many API misuse detection techniques have been proposed,these techniques still face two challenges:1) the acquisition of API usage specification is difficult,and 2) the detection of many different types of API misuse at the same time is difficult.To address the above challenges,a decision tree algorithm-based API misuse detection method is proposed.First,the API usage source code is converted into an API usage graph,and the API usage specification is mined from the graph to effectively solve the first challenge.Second,an API usage decision tree is constructed based on the obtained API specification information,and the generalization ability of the API usage decision tree is improved by incorporating pruning strategies.Finally,a combination of coarse-grained and fine-grained detection is proposed in the detection phase to improve the detection capability of the API usage decision tree,which effectively solves the second challenge.Experimental results show that the proposed approach can rea-lize detection of API misuse defects to a certain extent.

Clinical practice guidelines can facilitate the standardization of the diagnosis and treatment and improve health care quality. However, there are barriers to guideline dissemination and implementation, thus impeding the standardization of clinical practice and improvement of patient outcomes. One major barrier is that it is difficult for doctors to read and understand the unstructured text-based guidelines, and apply them in real clinical practice. This paper introduces the design of decision trees based on clinical practice guidelines, and the advantages, challenges and solutions of this approach, with the hope of providing references for promoting the transformation of textual clinical practice guidelines.

The deep decision tree migration learning boosting method ( DtrBoost) can effectively realize the migration learning from a single source domain to a target domain under supervision, but can not realize the unsupervised migration scenario under multiple source domains. To solve this problem, this paper proposed an unsupervised transfer learning boosting method for optimizing the weight under multi-source domain distribution. The main idea was to calculate the corresponding KL value according to the distribution of different source domains and target domains, selected an appropriate number of samples from different source domains to train the classifier and pseudo label the samples from the target domain. Finally, the algorithm assigned different learning weights according to the KL distance of each different source domain, and the labeled source domain samples integrated to the pseudo labeled target domain to obtain the final result. Comparative experiments show that the proposed algorithm achieves better classification accuracy and adaptive effect on different data sets. The average classification error rate decreases by 2. 4% and more than 6% on the best marketing data set. [ABSTRACT FROM AUTHOR]

Aiming at the problems that the features extracted by the traditional deep forest algorithm are not complete, and the equal-power decision mechanism is easy to produce differences in the classification results, an improved DeepForest (IDF) model applied to inexact graph matching is proposed. Firstly, in the process of mining feature subsets, the methods of fusing moving windows and random moving windows are adopted. While the moving window scans the sample, a same size feature subset of the moving scanning window is randomly captured, and these form a new feature subset, which is used as the input of the cascade module. Secondly, in the iterative process of the cascading forest, the weight of decision result in the current forest is calculated. Compared with the upper level forest, the weight value is assigned to the current forest by the strategy rule of Min, and iteration is continued until the result meets the given threshold value by the model. Finally, training and testing are conducted on datasets such as MUTAG, PTC and COX2. The experimental results show that, compared with traditional deep forest algorithm, IDF fully considers the structural characteristics of the graph, and can effectively enhance the diversity of samples and the goodness of fit, and reduce the decision-making difference and the complexity of the model. It efectively improves the classification and recognition rate of the model.

Aiming at the problem of aerosapce time-sensitive target recognition, a new sequential feature extraction method for radar high resolution range profile (HRRP) is proposed, and a multi classifier based on decision tree and support vector description (SVDD) method is designed. Firstly, the method estimates the radial size of the target based on time-series HRRP, uses sequential pulse accumulation to perform sliding window processing on the size estimation results, and obtains the four statistical characteristics of mean, range, median, and end mean of the radial size in each window. Then, The four types of features are spliced to obtain more robust high-dimensional features. Finally, the proposed multi classification SVDD method based on decision tree (Multi-SVDD-DT) is used to classify the obtained high-dimensional features. The simulation data experiments of four types of aircraft show that the proposed method can extract the robust features of the target, and can effectively complete the recognition task of aerospace time-sensitive targets.

Copyright of Telecommunication Engineering is the property of Telecommunication Engineering and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Objectives: We used the Indoor Air Pollution Health Literacy (IAPHL) model to determine the characteristics of Taiwanese adults with inadequate health literacy regarding indoor pollution. Methods: This cross-sectional study collected data on the characteristics of Taiwanese participants aged ≥20 years through online questionnaires based on the IAPHL model. The responses were analyzed and categorized by region, gender, and age group of the interviewees as of April 2020. The characteristics of the participants with inadequate IAPHL (i.e., less than the median score) were described by using decision tree. Results: In total, 616 out of 647 questionnaires were included in the analysis after weighting. The decision tree model revealed that 67.5% (158/234) of Taiwanese citizens had inadequate IAPHL. Furthermore, 36% of the participants lacked information on indoor air pollution at their workplace or home. Conclusions: This study found occupation type and a lack of knowledge regarding indoor air pollution at the workplace are key predictors of inadequate IAPHL. These findings suggest that IAPHL can be better improved through the use of occupation specific educational materials for adults in Taiwan. [ABSTRACT FROM AUTHOR]

(Background and objective) Global warming and anthropogenic activities will change ecological functions of lakes, resulting in eutrophication and algal blooms, for example. Monitoring the change in aquatic vegetation and algae is important to improve lake management but difficult, especially at large scale. Remot sensing can plug this gap and in this paper, we study the feasibility of using it to acquire vegetation dynamics in lakes. (Method) The studied site is Ulansuhai lake in the upper reach of the Yellow River basin. Emergent and submerged vegetation as well as floating algae were calculated based on spectral feature analysis of the spectral data acquired from the Landsat8 imageries. A decision tree classification model was constructed to analyze the aquatic vegetation and algal blooms. A MNDSI spectral index was proposed to identify the aquatic vegetation and yellow moss algal blooms; a NDWI spectral water index was used to extract water bodies that were free of vegetation and algae. An improved enhanced vegetation index (AEVI) was used to extract the emergent vegetation; a modified macroalgal index (MFAI) was used to distinguish the submerged vegetation from the yellow moss algal blooms. The accuracy of the method was tested against ground-truth data. (Result) The spectral index combined with the decision tree classification model is effective to distinguish the aquatic vegetation from the yellow moss algal blooms. Using the Landsat8 imageries acquired from 1986 to 2018 revealed that the emergent vegetation taxa grew slowly, and the coverage area of the submerged vegetation showed periodic changes, decreasing 1986 to 2013 and increasing after 2013. The yellow moss algal bloom did not show identifiable trends, with their outbreaks occurring irregularly from 1986 to 2018. [ABSTRACT FROM AUTHOR]

Vegetation has obvious interannual variation, and its succession plays an important role in climate regulation and soil and water conservation. Remote sensing technology is an effective means to study the distribution and coverage changes of surface vegetation at regional and global scales, which can provide long-term and continuous observation of the ground surface and has the advantages of macroscopic, extensive, diversity and adaptability. Therefore, the research status of vegetation phenology and spatio-temporal dynamic changes of vegetation coverage based on remote sensing monitoring technology at home and abroad, the application of different satellite remote sensing data in vegetation classification, and the methods of remote sensing vegetation identification and classification are reviewed and summarized. The advantages and disadvantages of decision tree and other methods in remote sensing vegetation classification are analyzed; several issues that still need further research for future remote sensing vegetation identification and classification are proposed. [ABSTRACT FROM AUTHOR]

Copyright of Journal of China Medical University is the property of Journal of China Medical University Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of Chinese Journal of Geological Hazard & Control is the property of China Institute of Geological Environmental Monitoring (CIGEM) Editorial Department and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Hydraulic system is one of the important airborne systems of aircraft. It outputs energy to drive the aircraft, and its performance, stability and reliability directly affect the safety of the aircraft. Flow rate is an important criterion to measure the stability of hydraulic system. Real-time monitoring of pipeline flow rate of hydraulic system can provide powerful support for system characteristic analysis and fault diagnosis. However, the flow resistance caused by the flow sensor has a significant influence on the system characteristics, so it is not widely used in the aviation hydraulic system. Aiming at the problem of flow resistance caused by sensors, the flow-related parameters were analyzed in depth, and a flow prediction model of aviation hydraulic system based on gradient lifting regression tree was proposed to predict the flow of hydraulic system through key parameters. Finally, the experimental results show that the GBRT model has better performance in prediction accuracy, training time, test time and other indicators than the least square linear regression model, decision tree regression model and extreme gradient lifting tree XGBoost model, which verifies the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

There are many factors that affect autonomous vehicles' behavioral decision-making in the traffic environment. It is very important for the safety of autonomous vehicles to handle uncertainty factors accurately and timely. To this end, we design a behavioral decision-making model of Bayesian network (BN) based on classification of human driving behaviors. The decision tree classification algorithm is used to classify the driving behaviors of human driving vehicles, The BN is used to model the driving scene and create the best driving behavior. It not only analyzes the human driving behavioral style timely, but also takes into account the uncertain factors in the driving scene. We design the PreScan simulation experiments, the simulation results show that the behavioral decision model can provide safe and reasonable behavior of autonomous vehicles. [ABSTRACT FROM AUTHOR]

Copyright of Telecommunications Science is the property of Beijing Xintong Media Co., Ltd. and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Copyright of West China Journal of Stomatology is the property of Sichuan University, West China College of Stomatology and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

BackgroundCommunity-based elderly care may effectively contribute to the handling of serious elderly care challenges brought by an increasingly aging population in China.ObjectiveTo explore the factors associated with older adults' intention to choose community-based elderly care using the decision tree and Logistic regression models.MethodsThis questionnaire survey was conducted in three communities selected from Daqing by convenient sampling from August to December 2020. 500 eligible community-dwelling older adults (≥60 years old) were selected as the research objects. The decision tree and Logistic regression models were used to explore factors associated with these older adults' intention to choose community-based elderly care via analyzing their demographics, self-rated physical and mental health, and family and social support collected by the survey.ResultsAltogether, 489 cases (97.8%) who effectively responded to the survey were included for analysis. The prevalence of intending to choose community-based elderly care in the respondents was 32.5% (159/489) . Logistic regression analysis revealed that the older adults' understanding level of community-based elderly care, views of elderly care, sense of loneliness, and intergenerational relationship had varying degrees of influence on their intention to choose community-based elderly care (P

Background and purpose: The biological risk of gastrointestinal stromal tumor (GIST) can be divided into very low-risk, low-risk, moderate-risk and high-risk. Accurate preoperative prediction of risk is very important for clinical diagnosis and treatment. This study explored the application value of decision tree model based on ultrasonic signs in predicting the risk grade of GIST. Methods: A total of 206 GIST patients treated in Union Hospital Affiliated to Fujian Medical University from December 2016 to December 2020 were collected. The decision tree model was established, and the prediction accuracy of the model was calculated. Results: There were statistically significant differences in long diameter, short diameter/long diameter (S/L), location, internal echo, echo uniformity, boundary, shape, cystic necrosis and blood flow signals among low-risk, moderate-risk and high-risk groups (all P

Random forest (RF) is one of the most classic machine learning methods, which has been widely used. However, although there are many two-view data in reality and extensive analytical research has been carried out, the RF construction for two-view scenarios is little. The only RF method for two-view learning first generates RF for each view respectively, and then merges the view information when making decisions. Therefore, it turns out an obvious disadvantage that the correlation between views is not utilized effectively during the RF construction stage, which undoubtedly wastes information resources. In order to make up for this disadvantage, an improved two-view RF (ITVRF) is proposed in this paper. Specifically, canonical correlation analysis (CCA) is used for view fusion in the process of generating decision trees, and the information interaction between views is embedded into the tree construction stage, realizing the utilization of complementary information between views in the entire RF generation process. In addition, ITVRF also generates discriminant decision boundaries for decision trees through discriminant analysis and thus makes it more suitable for classification. Experimental results show that ITVRF achieves better accuracy than existing two-view RF (TVRF).