A novel hierarchical hyper-parameter search algorithm based on greedy strategy for wind turbine fault diagnosis

Zhang, Yan; Liu, Wenyi; Wang, Xin; Shaheer, Mirza Ali

doi:10.1016/j.eswa.2022.117473

Cited by 24 publications

(10 citation statements)

References 27 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The machine learning models involve the adjustment of hyperparameters, but the selection of hyperparameters is subjective and time-consuming [42]. Grid search (GS) solves the problems faced in tuning hyperparameters and is a common hyperparameter-optimized method that improves the objectivity of hyperparameter selection [49].…”

Section: Model Development 231 Grid Search Methodsmentioning

confidence: 99%

“…RF is a machine regression model that combines decision trees with bagging algorithms, and this model calculation strategy can both improve prediction accuracy and avoid overfitting [41]. At the same time, the training process of using machine learning methods to build models requires the configuration of a large number of hyperparameters, and the selection of these hyperparameters greatly depends on experience [42], which is computationally intensive and subjective. In response to this problem, it is recommended to use the grid search (GS) method [43] to optimize the machine learning method and improve the modeling and estimation results.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of Soil Organic Carbon Content in Coastal Wetlands with Measured VIS-NIR Spectroscopy Using Optimized Support Vector Machines and Random Forests

et al. 2022

View full text Add to dashboard Cite

Coastal wetland soil organic carbon (CW-SOC) is crucial for both “blue carbon” and carbon sequestration. It is of great significance to understand the content of soil organic carbon (SOC) in soil resource management. A total of 133 soil samples were evaluated using an indoor spectral curve and were categorized into silty soil and sandy soil. The prediction model of CW-SOC was established using optimized support vector machine regression (OSVR) and optimized random forest regression (ORFR). The Leave-One-Out Cross-Validation (LOO-CV) method was used to verify the model, and the performance of the two prediction models, as well as the models’ stability and uncertainty, was examined. The results show that (1) The SOC content of different coastal wetlands is significantly different, and the SOC content of silty soils is about 1.8 times that of sandy soils. Moreover, the characteristic wavelengths associated with SOC in silty soils are mainly concentrated in the spectral range of 500–1000 nm and 1900–2400 nm, while the spectral range of sandy soils is concentrated in the spectral range of 600–1400 nm and 1700–2400 nm. (2) The organic carbon prediction model of silty soil based on the OSVR method under the first-order differential of reflectance (R′) is the best, with the Adjusted-R2 value as high as 0.78, the RPD value is much greater than 2.0 and 5.07, and the RMSE value as low as 0.07. (3) The performance of the OSVR model is about 15~30% higher than that of the support vector machine regression (SVR) model, and the performance of the ORFR model is about 3~5% higher than that of the random forest regression (RFR) model. OSVR and ORFR are better methods of accurately predicting the CW-SOC content and provide data support for the carbon cycle, soil conservation, plant growth, and environmental protection of coastal wetlands.

show abstract

Section: Model Development 231 Grid Search Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Estimation of Soil Organic Carbon Content in Coastal Wetlands with Measured VIS-NIR Spectroscopy Using Optimized Support Vector Machines and Random Forests

et al. 2022

View full text Add to dashboard Cite

show abstract

“…Compared with a single greedy strategy, the calculation conversion algorithm based on pre-learning proposed in this paper will not greatly increase the complexity of the calculation. Moreover, the goal of the greedy calculation transfer strategy is to minimize the system cost in the current calculation conversion cycle [15]. From the perspective of the long-term operation of the system, the optimal value cannot be obtained in many cases.…”

Section: System Performance Analysismentioning

confidence: 99%

Campus IoT system and students’ Employment Education Innovation based on mobile edge computing

Xie

2023

Preprint

View full text Add to dashboard Cite

With the rapid development of Internet of things, more and more computing intensive applications are running on the Internet of things terminals. These computing intensive applications usually need strong computing power. It requires high energy consumption to process these applications locally through Internet of things terminals. At the same time, the computing capacity and battery capacity of the Internet of things terminals are limited. To solve this problem, computing tasks can be transferred from single Internet (IOT) terminals to cloud computing with powerful computing functions. However, cloud computing has inherent limitations. That is, the distance from user terminal to remote cloud center server is very long, and the application delay time is too long. Mobile edge computing, as a new computing technology, is introduced to the network edge, which provides computing services that can generate enough capacity by obtaining a large number of free computing capacity and scattered storage space on the edge. This is a task that is used in mobile terminal or Internet of things terminal to perform computationally intensive and wait time important tasks. Unlike traditional cloud computing, mobile edge computing can be extended to wireless access points. This paper uses mobile edge computing Internet of things technology to study campus system innovation and student employment education. The high quality employment guidance education for college students is not only an important way to promote the external output of talents, but also an important link to realize the connection between universities and enterprises, and also an important means for universities to provide services to the society.

show abstract

“…Parameter search is the most common method to find the optimal parameter combinations in machine learning [27], fault diagnosis [28], activity recognition [29] and software testing [30]. For the non-uniform random variate generation methods, the design of the proposal distribution can be regarded as a kind of parameter search process, and the goal is to find an optimal proposal distribution, so as to improve the sampling efficiency while ensuring the sampling performance.…”

Section: Introductionmentioning

confidence: 99%

An Efficient Self-Tuning Proposal Distribution for Random Variate Generation With Complex Density Representation

et al. 2023

View full text Add to dashboard Cite

Random variate generation has been widely used in various engineering applications and model frameworks. The introduction of the proposal distribution makes this kind of methods can deal with more general sampling problems with complex probability density representation. However, the design of proposal distribution is usually difficult, especially when the target distribution is so complex that it contains asymmetric, multimodal and skewed, or even unsmooth, heavy tailed and illegal density, the sampling performance and efficiency will be greatly affected. In this paper, a novel parameter optimization method with efficient self-tuning strategy is proposed in order to automatically construct the optimal proposal distribution for any complex target density, which treats the design of proposal distribution as a parameter search process and search the optimal solution in an infeasible region by evaluating the loss of solution. The significant advantage of the proposed method is that the search based on infeasible region can converge to a good solution with only a few iterations, making our method far superior to other existing methods in efficiency, which is very suitable for the complex target distribution model with time-consuming density calculation process. Experimental results show the advantages of the proposed method in terms of search strategy, optimal solution performance, search efficiency and robustness.INDEX TERMS Monte Carlo methods, generative model, parameter optimization, rejection sampling, machine learning.

show abstract

A novel hierarchical hyper-parameter search algorithm based on greedy strategy for wind turbine fault diagnosis

Cited by 24 publications

References 27 publications

Estimation of Soil Organic Carbon Content in Coastal Wetlands with Measured VIS-NIR Spectroscopy Using Optimized Support Vector Machines and Random Forests

Estimation of Soil Organic Carbon Content in Coastal Wetlands with Measured VIS-NIR Spectroscopy Using Optimized Support Vector Machines and Random Forests

Campus IoT system and students’ Employment Education Innovation based on mobile edge computing

An Efficient Self-Tuning Proposal Distribution for Random Variate Generation With Complex Density Representation

Contact Info

Product

Resources

About