Yafeng Wu

Yafeng Wu


Research Focus & Metrics

Academic Career Length

11Years (2016-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
1 April 2019 in Medical Image Analysis
Verified
Journal Article
Closed access
Geng ChenGeng Chen
Geng Chen
YWYafeng Wu
Yafeng Wu
DSDinggang Shen
Dinggang Shen
PYPew-Thian Yap
Pew-Thian Yap

20 September 2024 in Expert Systems with Applications
Verified
Journal Article
Closed access
SLSijie Liu
Sijie Liu
LJLi Jin
Li Jin
NZNan Zhou
Nan Zhou
Geng ChenGeng Chen
Geng Chen
KLKuan Lu
Kuan Lu
YWYafeng Wu
Yafeng Wu

5 February 2024 in Aerospace
Verified
Journal Article
Open access
PDF file
SLSijie Liu
Sijie Liu
NZNan Zhou
Nan Zhou
CSChenchen Song
Chenchen Song
Geng ChenGeng Chen
Geng Chen
YWYafeng Wu
Yafeng Wu
This research introduces the Enhanced Scale-Aware efficient Transformer (ESAE-Transformer), a novel and advanced model dedicated to predicting Exhaust Gas Temperature (EGT). The ESAE-Transformer merges the Multi-Head ProbSparse Attention mechanism with the established Transformer architecture, significantly optimizing computational efficiency and effectively discerning key temporal patterns. The incorporation of the Multi-Scale Feature Aggregation Module (MSFAM) further refines 2 s input and output timeframe. A detailed investigation into the feature dimensionality was undertaken, leading to an optimized configuration of the model, thereby improving its overall performance. The efficacy of the ESAE-Transformer was rigorously evaluated through an exhaustive ablation study, focusing on the contribution of each constituent module. The findings showcase a mean absolute prediction error of 3.47∘R, demonstrating strong alignment with real-world environmental scenarios and confirming the model’s accuracy and relevance. The ESAE-Transformer not only excels in predictive accuracy but also sheds light on the underlying physical processes, thus enhancing its practical application in real-world settings. The model stands out as a robust tool for critical parameter prediction in aero-engine systems, paving the way for future advancements in engine prognostics and diagnostics.

27 November 2016 in Scientific Reports
Verified
Journal Article
Open access
PDF file
GCGeng Chen
Geng Chen
PZPei Zhang
Pei Zhang
KLKe Li
Ke Li
CWChong-Yaw Wee
Chong-Yaw Wee
YWYafeng Wu
Yafeng Wu
PYPew-Thian Yap
Pew-Thian Yap
Diffusion magnetic resonance imaging is widely used to investigate diffusion patterns of water molecules in the human brain. It provides information that is useful for tracing axonal bundles and inferring brain connectivity. Diffusion axonal tracing, namely tractography, relies on local directional information provided by the orientation distribution functions (ODFs) estimated at each voxel. To accurately estimate ODFs, data of good signal-to-noise ratio and sufficient angular samples are desired. This is however not always available in practice. In this paper, we propose to improve ODF estimation by using inter-subject image correlation. Specifically, we demonstrate that diffusion-weighted images acquired from different subjects can be transformed to the space of a target subject to drastically increase the number of angular samples to improve ODF estimation. This is largely due to the incoherence of the angular samples generated when the diffusion signals are reoriented and warped to the target space. To reorient the diffusion signals, we propose a new spatial normalization method that directly acts on diffusion signals using local affine transforms. Experiments on both synthetic data and real data show that our method can reduce noise-induced artifacts, such as spurious ODF peaks, and yield more coherent orientations.

8 October 2023 in Sensors
Verified
Journal Article
Open access
PDF file
MTMIngyang Tang
MIngyang Tang
YWYafeng Wu
Yafeng Wu
Currently, the widely used blind source separation algorithm is typically associated with issues such as a sluggish rate of convergence and unstable accuracy, and it is mostly suitable for the separation of independent source signals. Nevertheless, source signals are not always independent of one another in practical applications. This paper suggests a blind source separation algorithm based on the bounded component analysis of the enhanced Beetle Antennae Search algorithm (BAS). Firstly, the restrictive assumptions of the bounded component analysis method are more relaxed and do not require the signal sources to be independent of each other, broadening the applicability of this blind source separation algorithm. Second, the objective function of bounded component analysis is optimized using the improved Beetle Antennae Search optimization algorithm. A step decay factor is introduced to ensure that the beetle does not miss the optimal point when approaching the target, improving the optimization accuracy. At the same time, since only one beetle is required, the optimization speed is also improved. Finally, simulation experiments show that the algorithm can effectively separate independent and dependent source signals and can be applied to blind source separation of images. Compared to traditional blind source separation algorithms, it has stronger universality and has faster convergence speed and higher accuracy compared to the original independent component analysis algorithm.

24 May 2023 in Aerospace
Verified
Journal Article
Open access
PDF file
SMShuai Ma
Shuai Ma
YWYafeng Wu
Yafeng Wu
HZHua Zheng
Hua Zheng
LGLinfeng Gou
Linfeng Gou
Aiming at engine health management, a novel hybrid prediction method is proposed for exhaust gas temperature (EGT) prediction of gas turbine engines. This hybrid model combines a nonlinear autoregressive with exogenous input (NARX) model and a moving average (MA) model. A feature attention mechanism-enhanced long short-term memory network (FAE-LSTM) is first developed to construct the NARX model, which is used for identifying the aircraft engine using condition parameters and gas path measurement parameters that correlate to the EGT. A vanilla LSTM is then used for constructing the MA model, which is used for improving the difference between the actual EGT and the predicted EGT given by the NARX model. The proposed method is evaluated using real flight process data and compared to several dynamic prediction techniques. The results show that our hybrid model reduces the predicted RMSE and MAE by at least 13.23% and 18.47%, respectively. The developed FAE-LSTM network can effectively deal with dynamic data. Overall, the present work demonstrates a promising performance and provides a positive guide for predicting engine parameters.