Search

Copyright of Water Conservancy Science & Techonlogy & Economy is the property of Water Conservancy Science & Technology & Economy 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.)

Automatic Target Recognition (ATR) is an interdisciplinary technological field related to pattern recognition, artificial intelligence, and information processing. ATR evaluation focuses on accessing ATR algorithms and systems. Due to the noncooperative targets, complex operating conditions, and multiple subjective preferences of the decision maker, ATR evaluation is performed for the entire ATR research process and shows its importance in guiding ATR development. This paper presents the connotation of ATR evaluation and briefly reviews ATR development. Furthermore, the conventional methods, applications, and latest developments in ATR evaluation are presented and discussed from the perspective of performance measures, test condition, inference and decision. Finally, several ATR evaluation research directions are summarized. This paper serves as a valuable reference for a better understanding of ATR evaluation and the effective adoption of various ATR evaluation methods.

In order to solve the problems that decision process is not closely integrated with on-site data, and it lacks quantitative indicators and fails to grasp the key points of management and control of rail transit engineering, the method for safety decision analysis and on-site information standardization is proposed based on IFC and AHP. In combination with the information characteristics of safety management and control, the IFC standard of on-site data is derived from IFC standard, and the standardization of project safety information is realized. The calculation method of analysis and decision-making on safety management and control information is proposed based on AHP, and standard process is formulated. Combined with the comprehensive monitoring system for construction projects, automatic data analysis, early warning and visual display are fulfilled. The data collection, analysis, early warning and follow-up response are analyzed in detail based on a safety risk event of shield machine passing through a residential building of Guangzhou Metro Line 11. The practice shows that the extended data structure based on IFC can fully express various on-site data, and solve its data standardization problem; the decision-making system based on AHP can quantitatively calculate the amount of security risk at the target layer and evaluate the risk level, and provide an effective theoretical basis for scientific and accurate decision-making of security management and control. [ABSTRACT FROM AUTHOR]

In coal industry, there are problems of serious information island, insufficient business interconnection and interoperability, and poor data value mining and utilization under the existing single system and single business application mode. And there are problems of single application point and insufficient intelligent empowerment of new generation information technology such as Internet of Things, cloud computing, big data, artificial intelligence, intelligent control, etc. In order to solve the above problems, the new generation information technology is deeply integrated with coal mine safety, production and operation management and control business. The construction concept of intelligent mine integrated management and control platform is proposed. The platform is based on the basic information platform of intelligent mine, which aggregates, manages, stores and analyzes massive heterogeneous data through the coal industry big data center. The data platform, technology platform and application platform is applied to realize data fusion, collaborative control, business linkage and decision analysis in the same platform. By adopting unified portal, unified data and unified style, a centralized and unified intelligent control and business application center is built for production scheduling collaborative management and control, comprehensive risk prevention and control management, comprehensive management and control for decision analysis, and precise operation and maintenance detection. The production scheduling collaborative management and control application center applies coal mine safety production collaborative technology to realize business interconnection and hierarchical scheduling among mine leaders, scheduling command centers, departments, district teams and work groups, and integrated scheduling and collaborative control in fixed sites. The comprehensive risk prevention and control management application center takes coal mine safety risk prevention and control as the core, and realizes all-round perception, real-time monitoring, dynamic evaluation, and abnormal linkage treatment of risk and hazard elements in the whole mine to ensure efficient and orderly operation of coal mine safety production. The comprehensive management and control for decision analysis application center applies time-series data mining and analysis technology to realize the analysis and prediction of indicators such as safety, production and operation. Through the safety production big data board and personal workbench, the comprehensive display of safety, production and operation conditions is carried out. The precise operation and maintenance detection application center uses running probes to realizes the fault monitoring and abnormality tracking and processing during the operation of the platform.

Copyright of Journal of Mine Automation is the property of Industry & Mine Automation 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 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 Journal of Harbin Institute of Technology. Social Sciences Edition / Haerbin Gongye Daxue Xuebao. Shehui Kexue Ban is the property of Harbin Institute of 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.)

Interdependent-decision analysis is an important research stream in the area of decision sciences in recent years. Particularly, the development of studies on interdependent-decision analysis with cross-organizations, cross-processes, cross-tasks and cross-stages is promoted by supply chain integration and the management of collaboration innovation. Systematic review on the newest trends in this area will contribute to clear the research streams, improve the effectiveness of method application and promote state-of-the-art research development. Firstly, an in-depth analysis of interdependent-decision elements is conducted to clarify the changes of research trends as well as the differences and features of different decision elements in terms of types, structures and information. Then, interdependent-decision analysis methods in the existing literature are classified according to the applicative scenarios. Furthermore, to know the applicable and theoretical values, these methods are compared from the perspectives of principles, innovation and contribution, information processing capabilities and application complexities. Finally, new research opportunities of interdependent-decision analysis methods are discussed. [ABSTRACT FROM AUTHOR]

Due to the difficulty of estimating probability function and the high space complexity of the existing probabilistic neural network (PNN), an improved PNN model is presented by introducing the mechanism of back-propagation (BP). The improved model inherits the principle and structure of PNN, and meanwhile applies the BP algorithm of multilayer perceptron (MLP) to train probability function and parameters. The above two aspects help overcome the PNN's shortcomings. Three numerical experiments have been designed to verify the improved model, and their results indicate that the new model has strong capacity to identify the importance of input indicators and own high accuracy of classification. In conclusion, the BP-PNN model is a new pattern classification method with widespread applicability and can support management decision. [ABSTRACT FROM AUTHOR]

A decision analysis algorithm based on manifold learning (DAML) is proposed for high-dimensional decision information system. Firstly, the dimension of the original data is reduced by using isometric mapping (ISOMAP) in the algorithm. Some decision rules are extracted from the low-dimensional embedding of manifold learning. The principal component of the original data is computed by the relationship of kernel principal component analysis and ISOMAP. Then, a support subset significant algorithm is proposed for decision analysis. The support subset significant algorithm is used to computing the at-tribution significant, discrimination power and support subset. The decision rules are extracted by the support subset. Finally, the Iris, Breast cancer, Wine, Spectf heart and Ionosphere on UCI benchmark are selected for simulation. The classification accuracy among C4.5, k-nearest neighbor (KNN) and DAML are compared on the 5 data sets to validate the effectiveness of the DAML. [ABSTRACT FROM AUTHOR]