Aiming at the problem that the traditional deep reinforcement learning algorithm has poor generalization ability of generating strategies when solving complex game problems such as real-time strategy games, an agent s...
详细信息
In this study, we present a middleware-based approach for detecting anomalies in distributed systems. Our method facilitates the dynamic collection of logs at various levels of detail and incorporates an a priori dict...
详细信息
In complex terrain regions, it is very challenging to obtain high accuracy and resolution precipitation data that are required in land hydrological studies. In this study, an adaptive precipitation downscaling method ...
详细信息
In complex terrain regions, it is very challenging to obtain high accuracy and resolution precipitation data that are required in land hydrological studies. In this study, an adaptive precipitation downscaling method is proposed based on the statistical downscaling model MicroMet. A key input parameter in the MicroMet is the precipitation adjustment factor(PAF) that shows the elevation dependence of precipitation. Its value is estimated conventionally based on station observations and suffers sparse stations in high altitudes. This study proposes to estimate the PAF value and its spatial variability with precipitation data from high-resolution atmospheric simulations and tests the idea in Nepal of South Himalayas, where rainfall stations are relatively dense. The result shows that MicroMet performs the best with the PAF value estimated from the simulation data at the scale of approximately 1.5 degrees. Not only the value at this scale is qualitatively consistent with early knowledge obtained from intensive observations, but also the downscaling performance with this value is better than or comparable to that with the PAF estimated from dense station data. Finally, it is shown that the PAF estimation, although critical, cannot replace the importance of increasing input station density for downscaling.
The complexity of business and information systems(IS)alignment is a growing concern for researchers and practitioners *** extant research on alignment architecture fails to consider the human viewpoint,which makes it...
详细信息
The complexity of business and information systems(IS)alignment is a growing concern for researchers and practitioners *** extant research on alignment architecture fails to consider the human viewpoint,which makes it difficult to embrace emergent *** paper contributes to the extant literature in the following ***,we combine an enterprise architecture(EA)framework with a human viewpoint to address alignment issues in the architecture design phase;second,we describe a dynamic alignment model by developing a humancentered meta-model that explains first-and second-order changes and their effects on alignment *** paper provides better support for the theoretical research and the practical application of dynamic alignment.
This paper addresses the consistency issue of multi-robot distributed cooperative localization. We introduce a consistent distributed cooperative localization algorithm conducting state estimation in a transformed coo...
详细信息
ISBN:
(数字)9798350377705
ISBN:
(纸本)9798350377712
This paper addresses the consistency issue of multi-robot distributed cooperative localization. We introduce a consistent distributed cooperative localization algorithm conducting state estimation in a transformed coordinate. The core idea involves a linear time-varying coordinated transformation to render the propagation Jacobian independent of the state and make it suitable for a distributed manner. This transformation is seamlessly integrated into a server-based distributed cooperative localization framework, in which each robot estimates its own state while the server maintains the cross-correlations. The transformation ensures the correct observability property of the entire framework. Moreover, the algorithm accommodates various types of robot-to-robot relative measurements, broadening its applicability. Through simulations and real-world dataset experiments, the proposed algorithm has demonstrated better performance in terms of both consistency and accuracy compared to existing algorithms.
The central and western Tibetan Plateau(CWTP)is characterized by harsh environment and strong interactions among the spheres of earth as well as significant changes in climate and water cycles over the past four *** l...
详细信息
The central and western Tibetan Plateau(CWTP)is characterized by harsh environment and strong interactions among the spheres of earth as well as significant changes in climate and water cycles over the past four *** lack of precipitation observations is a bottleneck for the study of land surface processes in this *** the past six years,we have designed and established two observation transects across the south-north and the west-east in this region to obtain hourly rainfall data during the warm season(May-September).The south-north transect extends from Yadong Valley on the southern slope of the Himalayas to Shuanghu County in the hinterland of the plateau,with a total of 31stations;the west-east transect extends from Shiquanhe in the west to Naqu in the central TP,with a total of 22 *** observation dataset has been applied to clarify the spatiotemporal characteristics of precipitation in the CWTP,to evaluate the quality of typical gridded precipitation products,to support the development of regional climate models,and to reveal the processes of summertime lake-air *** observation dataset has been released in the national Tibetan Plateau Data Center.
In this work, we develop an analytical framework that integrates opinion dynamics with a recommendation system. By incorporating elements such as collaborative filtering, we provide a precise characterization of how r...
详细信息
Nitrogen oxides(NOx),significant contributors to air pollution and climate change,form aerosols and ozone in the ***,timely,and transparent information on NOx emissions is essential for decision-making to mitigate bot...
详细信息
Nitrogen oxides(NOx),significant contributors to air pollution and climate change,form aerosols and ozone in the ***,timely,and transparent information on NOx emissions is essential for decision-making to mitigate both haze and ozone ***,a comprehensive understanding of the trends and drivers behind anthropogenic NOx emissions from Chinadthe world's largest emitterdhas been lacking since 2020 due to delays in emissions *** we show a consistent decline in China's NOx emissions from 2020 to 2022,despite increased fossil fuel consumption,utilizing satellite observations as constraints for NOx emission estimates through atmospheric *** reduction is corroborated by data from two independent spaceborne instruments:the TROPOspheric Monitoring Instrument(TROPOMI)and the Ozone Monitoring Instrument(OMI).Notably,a reduction in transport emissions,largely due to the COVID-19 lockdowns,slightly decreased China's NOx emissions in *** subsequent years,2021 and 2022,reductions in NOx emissions were driven by the industry and transport sectors,influenced by stringent air pollution *** satellite-based inversion system developed in this study represents a significant advancement in the real-time monitoring of regional air pollution emissions from space.
To offer the military personnel a good service of assisting them to get information about enemy's equipment outside Internet, we build a system named MilChat which includes a large language model that has the abil...
详细信息
ISBN:
(数字)9798350354973
ISBN:
(纸本)9798350354980
To offer the military personnel a good service of assisting them to get information about enemy's equipment outside Internet, we build a system named MilChat which includes a large language model that has the ability to generate texts and an application which is easy to use. The model of MilChat is fine-tuned by the method of LoRA with military datasets from the basic model, Qwen-7B-Chat which is opensource and has good performance. After fine-tuning, the new model has higher scores than the basic one. Besides, we use the method of Prompt Learning to limit the answers into a standard format. Therefore, it is more accurate and professional than the basic model. This study has also a value of industrial application.
Target detection technology is vital in modern social management and urban security, with small target detection—accurately identifying tiny objects in large scenes—posing a key challenge for improving surveillance ...
详细信息
ISBN:
(纸本)9798331541699
Target detection technology is vital in modern social management and urban security, with small target detection—accurately identifying tiny objects in large scenes—posing a key challenge for improving surveillance system accuracy and real-time performance. The YOLO series is still the mainstream target detection model, for the YOLOv5 model, as the IoU metric it adopts still uses the geometrical overlap of the detection frame as the basis of the loss calculation, while the experiments have proved that this metric is unable to effectively utilize the small-scale characteristics of small targets. Therefore, improving the loss metric in the existing framework can help the model to pay more attention to the spatial semantic features of small targets in the image in the training phase of the network, respectively, and thus improve the detection effect. In this paper, we propose the NWDYOLOv5 model, i.e., we introduce the NWD loss that measures the difference in the distribution of the detection frames for the existing target detection framework YOLOv5, which ensures that the loss of the small targets is not neglected in the calculation of the forward propagation loss of the model, and we purposefully modify the structure of the feature extraction network in the original framework by adding a feature extraction layer for the detection of the small targets, which enhances the ability of the model to capture the subtle features thus improving the accuracy of small target detection. Through comparative experiments, we evaluated the detection performance of the original YOLOv5 model, the YOLOv5 model using only the NWD loss, the YOLOv5 model with only the additional small-target detection layer, and the full NWD-YOLOv5 model for small-targeted human bodies on the screened COCO2017 public dataset, respectively. The experimental results show that compared to the original YOLOv5 model, the model with only the NWD loss improves the mAP@.5 metrics on small-target detection by 16.5
暂无评论