The paper presents, two-novel current control converter topologies for 4-phase Switched Reluctance Motors (SRMs). The first converter is based on a reduced switch model, significantly decreasing the number of switchin...
详细信息
This keynote speech is to all intents and purposes introducing a new process mining approach and its implemented system, which are named as eXplainable process mining (XPM) approach and system, respectively. Through t...
详细信息
Reinforcement Learning from Human Feedback (RLHF) technology provides a method for agents to learn human preferences and perform actions that satisfy human desires. This technology was originally used to complete robo...
详细信息
In end-to-end data sharing, data are directly distributed to data receivers and stored on their terminals, making it hard to ensure forward security because receivers whose permissions have been revoked may still acce...
详细信息
Traditional mining exploration techniques require significant effort, including drilling and sample collection, making the process highly challenging and costly. The application of machine learning (ML) in mineral exp...
详细信息
In conventional exponentially weighted moving average (EWMA) control charts, a basic premise is that the data are independent of each other. However, in the era of big data, with the popularization and application of ...
详细信息
ISBN:
(纸本)9798400711831
In conventional exponentially weighted moving average (EWMA) control charts, a basic premise is that the data are independent of each other. However, in the era of big data, with the popularization and application of automatic data collection technology, there are often correlations between data, making conventional EWMA control chart monitoring ineffective. To solve this problem, an AEWMA control chart for autocorrelation processes (adaptive EWMA control chart) is proposed in this study, that is, the AEWMA control chart is constructed by fitting the residual of the time series model, and the optimal parameters of the control chart under autocorrelation conditions are found by combining the three principles with the search algorithm, so that the control limits can be set more accurately for monitoring. Then, by comparing the performance of conventional control chart and AEWMA control chart in terms of average running length, it is concluded that AEWMA control chart is better than conventional EWMA control chart in the case of non-strong correlation regardless of the size of the mean offset. Finally, the application effect of AEWMA control chart in the process of monitoring autocorrelation is demonstrated by an example, which fully proves its superiority in solving the quality control problem under the condition of autocorrelation.
There is an increasing demand for the accurate documentation of architectural main colors in the urban color design field. Drone-based photography has emerged as a pivotal tool, due to its capability for high-altitude...
详细信息
There is an increasing demand for the accurate documentation of architectural main colors in the urban color design field. Drone-based photography has emerged as a pivotal tool, due to its capability for high-altitude visual field and convenient data collection. However, a significant challenge remains in ensuring recorded color consistency across varying environmental conditions and timeframes, which requires accurate calibration method. Current calibration methods tend to apply end-to-end neural networks directly on the images, ignoring the difference between the calibration targets of architectural subjects and their surrounding backgrounds. This will lead to significant color deviations in the background areas, resulting in inaccurate calibrated results. Besides, large models are hard to be deployed on computational resource-limited drones. With respect to the above challenges, we propose a novel method called two-stage generative color calibration (TGCC) network for drone photography with cloud-edge collaboration. TGCC tackles the above issues via a two-stage calibration process. The initial stage is conducted at the drone edge side, employing a lightweight neural network for coarse color calibration. Then, the coarsely calibrated images are sent to the cloud server for the subsequent stage, which first extract calibration masks from the target architectural subjects, and then utilizes these masks as guidances for the large generative model to refine color calibration results. Experimental results demonstrate that our approach contributes to higher accuracy and better consistency of color calibration results than prior methods.
In this study, we assess the performance of various regression models for predicting the theoretical power generated by a wind turbine using supervisory control and data acquisition. The tested models include linear r...
详细信息
The following achievements have been made: in the research of the operation image model of the large power grid, a real-time operation image model of the large power grid has been proposed. Corresponding solutions or ...
详细信息
In recent years, global climate change has increased the occurrence of extreme rainfall events, frequently triggering large-scale flooding disasters, which have severe impact on the economic security and social stabil...
详细信息
暂无评论