Matrix completion models have been receiving keen attention due to their wide applications in science and engineering. However, the majority of these models assumes a symmetric noise distribution in their completion p...
详细信息
Matrix completion models have been receiving keen attention due to their wide applications in science and engineering. However, the majority of these models assumes a symmetric noise distribution in their completion processes and uses conditional mean to characterize data distribution in a data set, the assumption of which incurs noticeable bias toward outliers. Recognizing the fact that noise distribution tends to be asymmetric in the real-world, this paper proposes a novel deep Quantile Matrix Completion model, abbreviated as DQMC, which aims to accurately capture noise distribution in a data set by modeling conditional quantile of the data set instead of its conditional mean as traditionally handled by many state-of-the-art methods. Implemented via a deep computing paradigm, the newly proposed model maps a data set from its input space to the latent spaces through a two branched deep autoencoder network. Such a mapping can effectively capture complex information latent in the data set. The proposed model is empowered by two key designed elements, including: (1) its two-branched deep autoencoder network that provides a flexible computing pathway to attain completion results with a high quality;(2) the introduction of a quantile loss function in combination with the proposed deepnetwork, leading to a new unsupervised learning algorithm for tackling the matrix completion tasks with a superior capability. Comparative experimental results consistently demonstrate the superiority of the proposed DQMC model in conducting the top-N recommendation tasks involving both explicit and implicit rating data sets with respect to a series of state-of-the-art recommendation algorithms. (C) 2021 Elsevier B.V. All rights reserved.
We present a spatial-spectral autoencoder (SSAE) for hyperspectral unmixing, including a net for endmember extraction (EENet) and a net for abundance estimation (AENet). The EENet exploits the spatial information in h...
详细信息
ISBN:
(纸本)9781728163741
We present a spatial-spectral autoencoder (SSAE) for hyperspectral unmixing, including a net for endmember extraction (EENet) and a net for abundance estimation (AENet). The EENet exploits the spatial information in hyperspectral image by a "many to one" strategy, i.e., the abundance of a pixel is combined by the abundances of its adjacent pixels. The idea is based on the assumption: once an endmember is mixed in a pixel, it is mixed in the surrounding pixels with high probability. The strategy promotes a continuous and smooth spatial distribution of abundances, and it is more effective than the other methods for endmember extraction. Besides, to make full use of the rich spectral information and obtain more accurate abundances, we design an AENet, which applies the deep convolutional neural network to estimate the abundances with the endmembers acquired from the EENet. The experiments are conducted on two real datasets, which show the SSAE outperforms the state-of-the-art methods.
In order to find the optimal method for identifying geochemical anomalies in geochemical exploration,the Gaussian mixture model and the deep autoencoder network were compared in this *** on the determination of the op...
详细信息
In order to find the optimal method for identifying geochemical anomalies in geochemical exploration,the Gaussian mixture model and the deep autoencoder network were compared in this *** on the determination of the optimal L value of the Gaussian mixture model and the structure of the deep autoencoder network,geochemical anomaly detection was carried out in the Yawan-Daqiao area,Gansu Province,*** experimental results show that the geochemical data modeling results of the Gaussian mixture model and the deep autoencoder network are highly consistent with the mineralization characteristics of the study area,and the separated geochemical anomalies have a highly consistent spatial relationship with the known deposit positions in the study area.
Automated Modulation Classification (AMC) shows great significance for any receiver that has little knowledge of the modulation scheme of the received signal. A useful digital signal modulation recognition scheme insp...
详细信息
ISBN:
(纸本)9781538620724
Automated Modulation Classification (AMC) shows great significance for any receiver that has little knowledge of the modulation scheme of the received signal. A useful digital signal modulation recognition scheme inspired by the deep auto-encoder network is proposed in this investigation. In our proposed method, there are two deep auto-encoder networks. The system extracts the original features of the signal one by one to complete the recognition of unknown modulation signals, according to different modulation signals has different cyclic spectrum characteristics and wavelet characteristics. Finally, the effectiveness of the system is verified by simulation. The system can identify nine typical signals, which are 2FSK, 4FSK, 8FSK, BPSK, QPSK, 16QAM, 64QAM, 2ASK, MSK. The recognition accuracy can achieve 85% when signal to noise ratio is higher than 0 dB. The results indicate that digital signal modulation recognition based on deep auto-encoder network is feasible and accuracy rate.
暂无评论