Article
Engineering, Electrical & Electronic
Yajun Wang, Jidong Wang, Man Cao, Weixun Li, Long Yuan, Ning Wang
Summary: This paper introduces a short-term wind power forecasting method that utilizes feature clustering, correlation analysis, and modeling to improve accuracy, with results confirming its effectiveness and superiority.
ELECTRIC POWER SYSTEMS RESEARCH
(2022)
Article
Energy & Fuels
Zhiqiang Li, Yuemin Zhao, Zhaolin Lu, Wei Dai, Jinzhan Huang, Sen Cui, Biao Chen, Shenghong Wu, Liang Dong
Summary: This paper presents a novel hybrid analysis method to predict the calorific value (CV) of coal. By eliminating correlations between variables and finding the optimal combination of input variables, the RF model proposed in this study achieves better regression, fit and robustness on the testing set. Sensitivity analysis reveals the relative importance of input variables and how each variable affects the output variable.
INTERNATIONAL JOURNAL OF COAL PREPARATION AND UTILIZATION
(2023)
Review
Urology & Nephrology
Roemer J. Janse, Tiny Hoekstra, Kitty J. Jager, Carmine Zoccali, Giovanni Tripepi, Friedo W. Dekker, Merel van Diepen
Summary: This paper discusses the basics, limitations, and alternatives of the correlation coefficient, with examples from nephrology literature to support the concepts discussed.
CLINICAL KIDNEY JOURNAL
(2021)
Review
Geology
Behnam Sadeghi
Summary: This article introduces commonly used correlation coefficient (CC) methods in geochemical studies and discusses their advantages and limitations when dealing with different types of data. It then introduces a new correlation method, Chatterjee CC (CCC), which is simple, computationally efficient, and robust to various types of data. A Python package called TripleCpy was developed to apply CCC to datasets and its efficiency was demonstrated compared to traditional methods.
ORE GEOLOGY REVIEWS
(2022)
Article
Computer Science, Artificial Intelligence
Hao Liang, Rui Cai
Summary: This study introduces an evidence correlation coefficient based on generalized information quality to accurately describe the relationship between evidence and calculate evidence conflicts. The results show that this method effectively reflects the differences between evidence and improves the rationality and accuracy of evidence combination.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2021)
Article
Computer Science, Artificial Intelligence
Ankit Thakkar, Dhaval Patel, Preet Shah
Summary: This article introduces a method of weight initialization using Pearson correlation coefficient and absolute PCC to enhance the performance of neural network models in predicting stock trends. Empirical studies show that these two methods yield better or comparable results compared to random initialization.
NEURAL COMPUTING & APPLICATIONS
(2021)
Article
Computer Science, Interdisciplinary Applications
Yuxin Dong, Linlin Wang, Mingai Li
Summary: In brain computer interface-based neurorehabilitation system, it is challenging to acquire signals and decode motor imagery EEG (MI-EEG) due to a large number of electrodes. Traditional electrode optimization methods are limited by low spatial resolution of scalp EEG. In this paper, a new electrode optimization method called ECCEO is proposed based on EEG source imaging (ESI) and correlation analysis, which significantly reduces computational cost and achieves high decoding accuracy.
MEDICAL & BIOLOGICAL ENGINEERING & COMPUTING
(2023)
Article
Physics, Applied
M. Vukovic, K. H. Liland, U. G. Indahl, M. Jakovljevic, A. S. Flo, E. Olsen, I. Burud
Summary: Photoluminescence imaging is a promising technique for high-throughput on-site inspection of photovoltaic modules. A noninvasive photoluminescence imaging method has been proposed recently, which acquires images during a current-voltage curve sweep to detect continuously changing photoluminescence signals. An alternative algorithm based on the Pearson correlation coefficient is employed to process the images efficiently and unsupervised, enabling real-time surveillance and detection of functional anomalies. This algorithm is robust to varying solar irradiance and can process photoluminescence signals from multiple asynchronized strings.
JOURNAL OF APPLIED PHYSICS
(2023)
Article
Engineering, Multidisciplinary
Limu Qin, Gang Yang, Qi Sun
Summary: This paper presents a new blind deconvolution (BD) method, named maximum correlation Pearson correlation coefficient deconvolution (MCPCCD), which improves the recovery of periodic impulses. The method constructs a new objective function that combines correlation Pearson correlation coefficient (CPC) and signal fidelity term (SFT), and maximizes the function to obtain the optimal FIR filter. A preprocessing step is also introduced to reduce the requirement for periodic prior.
Article
Biochemical Research Methods
Mei Zhao, Zhenqi Yuan, Longtao Wu, Shenghu Zhou, Yu Deng
Summary: By constructing and characterizing a mutant library of Trc promoters, a synthetic promoter library was established with a wide range of intensities. Using this library, machine learning models were built and optimized, with the XgBoost model exhibiting optimal performance in predicting the strength of artificially designed promoter sequences. This work provides a powerful platform for predictably tuning promoters to achieve optimal transcriptional strength.
ACS SYNTHETIC BIOLOGY
(2022)
Article
Green & Sustainable Science & Technology
Siyeon Kim, Jiwan Lee, Seol Jeon, Moonyoung Lee, Heejin An, Kichul Jung, Seongjoon Kim, Daeryong Park
Summary: This study aimed to explore the correlation between ecological indices and flow metrics in aquatic ecosystems, in order to understand the characteristics of flow and its relationship with ecosystem health. The research found a negative correlation between flow metrics and ecological indices in watersheds with high imperviousness, providing valuable insights for quantitative evaluation of river ecosystems.
Article
Energy & Fuels
Hongling Liu, Chuanyu Bie, Fan Luo, Jianqiang Kang, Yuping Zhang
Summary: A fast and reliable capacity prediction method for retired Ni-MH batteries is proposed in this paper. Several parameters are obtained through short-time measurement and pulse rapid nondestructive testing, and SVR is used for capacity prediction. The results show that several characteristic parameters are strongly negatively correlated with the battery's discharge capacity and can effectively reflect the internal structural characteristics of the battery.
Article
Energy & Fuels
Zongxiang Li, Yan Yang, Liwei Li, Dongqing Wang
Summary: In this paper, a multi-fault online diagnosis approach combining a non-redundant measurement topology and weighted Pearson correlation coefficient (WPCC) is proposed to detect various circuit faults. The approach uses weighted measured data with different forgetting factors and can accurately distinguish and locate battery abuse faults, connection faults, sensor faults, adjacent homogeneous faults, and adjacent hybrid faults.
JOURNAL OF ENERGY STORAGE
(2023)
Article
Engineering, Multidisciplinary
Yaping Wang, Jiajun Zhao, Chaonan Yang, Di Xu, Jianghua Ge
Summary: An effective feature fusion method was proposed for predicting the remaining useful life (RUL) of rolling bearings based on Pearson correlation coefficient and kernel principal component analysis (KPCA). This method extracts multi-domain features, obtains correlations between features before fusion, and establishes a RUL prediction model using LSTM neural network and Cox proportional-hazards model.
Article
Computer Science, Artificial Intelligence
Jixiang Deng, Yong Deng, Kang Hao Cheong
Summary: A novel evidence combination method based on the Pearson correlation coefficient and weighted graph is proposed in the article, which can accurately identify conflicting evidence and exhibit better convergence performance. The weighted graph generated by the method can directly represent the relationship between different evidence, aiding researchers in estimating evidence reliability.
INTERNATIONAL JOURNAL OF INTELLIGENT SYSTEMS
(2021)