Improving penalized semi supervised nonnegative matrix factorization result’s confidence using deep residual learning approach in spectrum analysis
Improving penalized semi supervised nonnegative matrix factorization result’s confidence using deep residual learning approach in spectrum analysis
复制标题
DOI：
10.1109/icecet55527.2022.9873493
复制
发表时间：
2022-07
期刊：
影响因子：
--
通讯作者：
Nathaniel Saura;Koh Mastumoto;S. Benkadda;K. Ibano;Heun Tae Lee;Yoshio Ueda;Satoshi Hamaguchi
中科院分区：
文献类型：
--
作者：
Nathaniel Saura;Koh Mastumoto;S. Benkadda;K. Ibano;Heun Tae Lee;Yoshio Ueda;Satoshi Hamaguchi
Signa1去噪是当今在边缘托卡马克等离子体原子光谱和天体物理数据分析等主要问题上取得进展的最关键任务之一。在辐射光谱的研究中，噪声减去是显著提高识别光谱显著组成元素的方法的关键。其中一种方法是惩罚半监督非负矩阵分解(PSNMF)：它成功地提取了光谱的显著元素，但其结果的置信度对噪声敏感，最终会影响该方法的性能。另一方面，人工智能(AI)表现出很好的解开复杂输入的能力，并允许图像去模糊、模式识别等。本文的目的是在残差学习方法中使用特定的一维卷积神经网络来识别和减去噪声频谱中的噪声。该框架在不损害PSNMF已经很好的识别性能的情况下，提高了PSNMF输出的置信度。对于所考虑的最有噪声的数据，我们可以在接近于无噪声的情况下以置信度推断出好的元素集。
Signa1 denoising is one of the most crucial tasks to progress in today’s main issues including edge Tokamak plasmas’ atomic spectra and astrophysical data analyses. In the study of radiative spectra, noise subtraction is the key to significantly enhance methods developed to identify spectra’s prominent constituent elements. One of these methods is the penalized semi supervised nonnegative matrix factorization (PSNMF): it extracts the spectra’s prominent elements successfully, but its results’ confidence are sensitive to noise and can ultimately hurt the method’s performance. On the other hand, artificial intelligence (AI) shows very good ability to disentangle complex inputs and allows image unblurring, pattern recognition and so on. The work presented here aims to use a specific 1D convolutional neural network in the residual learning approach to identify and subtract the noise from noisy spectra. This framework improves the confidence of the PSNMF output without hurting its already good recognition performance. For the most noisy data considered, we can infer the good element set with a confidence close to the noiseless case.